From 775caaae46150e23e0b24906b835688fbae1eafd Mon Sep 17 00:00:00 2001
From: Rapsssito <contact@rodrigomartin.dev>
Date: Wed, 6 Sep 2023 13:59:41 +0200
Subject: [PATCH] feat: Complete pipeline designer

---
 modules/oncoliner_assesment/README.md         |  11 +-
 modules/oncoliner_harmonization/README.md     |   8 +
 modules/oncoliner_improvement/README.md       |   7 +
 tools/pipeline_designer/.gitignore            |   1 -
 tools/pipeline_designer/README.md             | 158 +++++++++++++++-
 tools/pipeline_designer/TODO                  |   0
 tools/pipeline_designer/example.sh            |   9 -
 tools/pipeline_designer/example/.gitignore    |   1 +
 tools/pipeline_designer/example/example.sh    |   9 +
 tools/pipeline_designer/example/fake_ref.fa   |   1 +
 .../pipeline_designer/example/fake_ref.fa.fai |   1 +
 .../sample_1/variant_caller_1_sample_1.vcf    | 169 ++++++++++++++++++
 .../sample_2/variant_caller_1_sample_2.vcf    | 168 +++++++++++++++++
 .../sample_1/variant_caller_2_sample_1.vcf    | 168 +++++++++++++++++
 .../sample_2/variant_caller_2_sample_2.vcf    | 167 +++++++++++++++++
 .../input/truth/sample_1/truth_sample_1.vcf   | 169 ++++++++++++++++++
 .../input/truth/sample_2/truth_sample_2.vcf   | 168 +++++++++++++++++
 tools/pipeline_designer/src/main.py           |  77 ++++----
 18 files changed, 1238 insertions(+), 54 deletions(-)
 delete mode 100644 tools/pipeline_designer/TODO
 delete mode 100644 tools/pipeline_designer/example.sh
 create mode 100644 tools/pipeline_designer/example/.gitignore
 create mode 100644 tools/pipeline_designer/example/example.sh
 create mode 120000 tools/pipeline_designer/example/fake_ref.fa
 create mode 120000 tools/pipeline_designer/example/fake_ref.fa.fai
 create mode 100644 tools/pipeline_designer/example/input/test/variant_caller_1/sample_1/variant_caller_1_sample_1.vcf
 create mode 100644 tools/pipeline_designer/example/input/test/variant_caller_1/sample_2/variant_caller_1_sample_2.vcf
 create mode 100644 tools/pipeline_designer/example/input/test/variant_caller_2/sample_1/variant_caller_2_sample_1.vcf
 create mode 100644 tools/pipeline_designer/example/input/test/variant_caller_2/sample_2/variant_caller_2_sample_2.vcf
 create mode 100644 tools/pipeline_designer/example/input/truth/sample_1/truth_sample_1.vcf
 create mode 100644 tools/pipeline_designer/example/input/truth/sample_2/truth_sample_2.vcf

diff --git a/modules/oncoliner_assesment/README.md b/modules/oncoliner_assesment/README.md
index 9039e03..c24d36b 100644
--- a/modules/oncoliner_assesment/README.md
+++ b/modules/oncoliner_assesment/README.md
@@ -20,12 +20,15 @@ It is written in Python 3 (**requires Python version 3.6 or higher**).
 Oncoliner's assesment module makes use of the following Python modules:
 * [`pandas`](https://pandas.pydata.org/)
 * [`pysam`](https://github.com/pysam-developers/pysam)
+* [`variant-extractor`](https://github.com/EUCANCan/variant-extractor)
 
 You may install them using pip:
 ```
-pip3 install pandas pysam
+pip3 install pandas pysam variant-extractor
 ```
 
+However, we recommend using the provided [Dockerfile](../../Dockerfile)/[Singularity recipe](../../singularity.def) for building the whole Oncoliner suite to avoid dependency issues.
+
 ## Functional analysis
 
 The module will try to obtain the genes affected by the variants from the `INFO` field in the truth files. **WARNING: Oncoliner does not compute genes linked to false positives.** Oncoliner's assesment module is compatible with the following functional analysis tools annotations:
@@ -88,8 +91,8 @@ options:
  * `{OUTPUT_PREFIX}fp.[snv|indel|sv].vcf.gz`: VCF files with the false positives (FP) variants. One file per variant type (SNV, indel and SV).
  * `{OUTPUT_PREFIX}fn.[snv|indel|sv].vcf.gz`: VCF files with the false negatives (FN) variants. One file per variant type (SNV, indel and SV).
  * `{OUTPUT_PREFIX}metrics.csv`: CSV file containing the metrics for the comparison of the test and truth VCF files. It contains the following columns:
-   * `variant_type`: variant type (SNV, indel or SV), as outputted by [VariantExtractor](https://github.com/EUCANCan/variant-extractor).
-   * `variant_size`: range of variant sizes for that particular row.
+   * `variant_type`: variant type, as outputted by [VariantExtractor](https://github.com/EUCANCan/variant-extractor).
+   * `variant_size`: range of variant sizes analyzed for that particular row.
    * `window_radius`: window radius used for the assessment.
    * `recall`: Recall. TP / (TP + FN).
    * `precision`: Precision. TP / (TP + FP).
@@ -104,7 +107,7 @@ options:
 
 ### `assesment_bulk.py`
 
-Wrapper for `assesment_main.py`. It allows to compare a series of (VCF/BCF/VCF.GZ) files generated by any variant callers against a series of (VCF/BCF/VCF.GZ) truth files for **multiple samples**. It takes advantage of multiple processors. It is provided as a standalone command line tool. Example of usage:
+Wrapper for `assesment_main.py`. It allows to compare a series of (VCF/BCF/VCF.GZ) files generated by any variant callers against a series of (VCF/BCF/VCF.GZ) truth files for **multiple samples**. It takes advantage of multiple processors and is also able to recover from a previous execution (if the execution was interrupted). It is provided as a standalone command line tool. Example of usage:
 
 ```
 python3 -O src/assesment_main.py -c config.tsv -o output_
diff --git a/modules/oncoliner_harmonization/README.md b/modules/oncoliner_harmonization/README.md
index 493df95..88979c2 100644
--- a/modules/oncoliner_harmonization/README.md
+++ b/modules/oncoliner_harmonization/README.md
@@ -8,3 +8,11 @@ WIP
 Oncoliner's harmonization module makes use of the following Python modules:
 * [`pandas`](https://pandas.pydata.org/)
 * [`pysam`](https://github.com/pysam-developers/pysam)
+* [`variant-extractor`](https://github.com/EUCANCan/variant-extractor)
+
+You may install them using pip:
+```
+pip3 install pandas pysam variant-extractor
+```
+
+However, we recommend using the provided [Dockerfile](../../Dockerfile)/[Singularity recipe](../../singularity.def) for building the whole Oncoliner suite to avoid dependency issues.
diff --git a/modules/oncoliner_improvement/README.md b/modules/oncoliner_improvement/README.md
index e04b8cd..6a0bd02 100644
--- a/modules/oncoliner_improvement/README.md
+++ b/modules/oncoliner_improvement/README.md
@@ -14,7 +14,14 @@ WIP
 Oncoliner's improvement module makes use of the following Python modules:
 * [`pandas`](https://pandas.pydata.org/)
 * [`pysam`](https://github.com/pysam-developers/pysam)
+* [`variant-extractor`](https://github.com/EUCANCan/variant-extractor)
 
+You may install them using pip:
+```
+pip3 install pandas pysam variant-extractor
+```
+
+However, we recommend using the provided [Dockerfile](../../Dockerfile)/[Singularity recipe](../../singularity.def) for building the whole Oncoliner suite to avoid dependency issues.
 
 
 ## Usage
diff --git a/tools/pipeline_designer/.gitignore b/tools/pipeline_designer/.gitignore
index a4ff7ff..68bc17f 100644
--- a/tools/pipeline_designer/.gitignore
+++ b/tools/pipeline_designer/.gitignore
@@ -158,4 +158,3 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
-example
\ No newline at end of file
diff --git a/tools/pipeline_designer/README.md b/tools/pipeline_designer/README.md
index 3bcf116..3340973 100644
--- a/tools/pipeline_designer/README.md
+++ b/tools/pipeline_designer/README.md
@@ -1 +1,157 @@
-# pipeline-designer
\ No newline at end of file
+# Pipeline Designer<!-- omit in toc -->
+
+## Table of contents<!-- omit in toc -->
+- [Dependencies](#dependencies)
+- [Usage](#usage)
+  - [Interface](#interface)
+  - [Output](#output)
+- [Use case example](#use-case-example)
+
+
+## Dependencies
+Oncoliner's pipeline designer makes use of the following Python modules:
+* [`pandas`](https://pandas.pydata.org/)
+* [`pysam`](https://github.com/pysam-developers/pysam)
+* [`pysam`](https://github.com/pysam-developers/pysam)
+
+You may install them using pip:
+```
+pip3 install pandas pysam variant-extractor
+```
+
+However, we recommend using the provided [Dockerfile](../../Dockerfile)/[Singularity recipe](../../singularity.def) for building the whole Oncoliner suite to avoid dependency issues.
+
+## Usage
+
+**WARNING**: It is recommended to normalize indels and SNVs for each variant caller before executing the pipeline designer. For this purpose, we recommend using pre.py from [Illumina's Haplotype Comparison Tools (hap.py)](https://github.com/Illumina/hap.py). We provide an standalone and containerized **[EUCANCan's pre.py wrapper](https://github.com/EUCANCan/prepy-wrapper)** for this purpose.
+
+The main executable code is in the [`src/`](/src/) folder. There is one executable file: [`main.py`](/src/main.py). It is provided as a standalone command line tool. Example of usage:
+
+```bash
+python3 src/main.py -t ./input/truth -v ./input/test -o ./output
+    -f  ./fake_ref.fa \
+    -rs sample_1 \
+    -ps sample_2 \
+    -p 32 \
+    --max-combinations 5
+```
+
+Check the example of usage in the [example](./example/) folder for more information.
+
+### Interface
+```
+usage: main.py [-h] -t TRUTH -v TEST -o OUTPUT -f FASTA_REF -rs RECALL_SAMPLES [RECALL_SAMPLES ...] -ps PRECISION_SAMPLES [PRECISION_SAMPLES ...] [-it INDEL_THRESHOLD] [-wr WINDOW_RADIUS]
+               [--sv-size-bins SV_SIZE_BINS [SV_SIZE_BINS ...]] [--contigs CONTIGS [CONTIGS ...]] [-p PROCESSES] [--max-combinations MAX_COMBINATIONS]
+
+Pipeline designer
+
+options:
+  -h, --help            show this help message and exit
+  -t TRUTH, --truth TRUTH
+                        Path to the VCF truth folder
+  -v TEST, --test TEST  Path to the VCF test folder
+  -o OUTPUT, --output OUTPUT
+                        Path to the output folder
+  -f FASTA_REF, --fasta-ref FASTA_REF
+                        Path to reference FASTA file
+  -rs RECALL_SAMPLES [RECALL_SAMPLES ...], --recall-samples RECALL_SAMPLES [RECALL_SAMPLES ...]
+                        Recall samples names
+  -ps PRECISION_SAMPLES [PRECISION_SAMPLES ...], --precision-samples PRECISION_SAMPLES [PRECISION_SAMPLES ...]
+                        Precision samples names
+  -it INDEL_THRESHOLD, --indel-threshold INDEL_THRESHOLD
+                        Indel threshold, inclusive (default=100)
+  -wr WINDOW_RADIUS, --window-radius WINDOW_RADIUS
+                        Window ratio (default=100)
+  --sv-size-bins SV_SIZE_BINS [SV_SIZE_BINS ...]
+                        SV size bins for the output_prefix metrics (default=[500])
+  --contigs CONTIGS [CONTIGS ...]
+                        Contigs to process (default=['1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14', '15', '16', '17', '18', '19', '20', '21', '22', 'X', 'Y'])
+  -p PROCESSES, --processes PROCESSES
+                        Number of processes to use
+  --max-combinations MAX_COMBINATIONS
+                        Maximum number of combinations to perform (-1) for all
+```
+
+### Output
+
+The pipeline designer will generate a series of files in the output folder. Most of them are intermediate files that are used by the pipeline designer to generate the final output files and recover in case of failure. The most important ones are the `.csv` files in `$OUTPUT_FOLDER/improvement_list`.
+
+Each output `.csv` file is named after the variant type and the variant size (e.g `SNV_1.csv` contains the callers combinations results for SNVs of size 1). Each file contains the following columns:
+
+* `operation`: The combination performed (e.g. `variant_caller_1$or$variant_caller_2`, which means that the combination is the union of the results of `variant_caller_1` and `variant_caller_2`).
+* `variant_type`: variant type, as outputted by [VariantExtractor](https://github.com/EUCANCan/variant-extractor).
+* `variant_size`: range of variant sizes analyzed for that particular file.
+* `window_radius`: window radius used for the assessment.
+* `recall`: Recall. TP / (TP + FN). Calculated **only** from the recall samples.
+* `precision`: Precision. TP / (TP + FP). Calculated **only** from the precision samples.
+* `f1_score`: F1 score. 2 * (precision * recall) / (precision + recall).
+* `tp`: Number of true positives. Calculated **only** from the recall samples.
+* `fp`: Number of false positives. Calculated **only** from the precision samples.
+* `fn`: Number of false negatives. Calculated **only** from the recall samples.
+* `protein_affected_genes_count`: Number of genes affected by the variants.
+* `protein_affected_driver_genes_count`: Number of cancer driver genes affected by the variants.
+* `protein_affected_genes`: List of genes affected by the variants (separated by `;`).
+* `protein_affected_driver_genes`: List of cancer driver genes affected by the variants (separated by `;`).
+
+## Use case example
+
+Assume that we have the following input variant callers: `variant_caller_1` and `variant_caller_2`. Both are SV callers. We want to combine them to improve the results of our pipeline. We have the following samples: `sample_1` and `sample_2`. We will use `sample_1` as a recall sample and `sample_2` as a precision sample.
+
+First of all, we need to run the variant callers and obtain the VCF files for each sample. Assume we obtain the following VCF files: `variant_caller_1.vcf` and `variant_caller_2.vcf` for each sample. **Make sure the names of the VCF files are the same across all the samples**.
+
+**Optional**. We recommend normalizing the VCF files before running the pipeline designer (see [Usage](#usage) for more information). However, in this case it is not necessary because we are only working with SVs.
+
+Now, we can run the pipeline designer. We will use the following command:
+
+```bash
+python3 src/main.py -t ./input/truth -v ./input/test -o ./output
+    -f  ./genome.fa \
+    -rs sample_1 \
+    -ps sample_2 \
+    -p 32 \
+    --max-combinations 5
+```
+
+The `input` folder must have the following structure:
+```
+input
+├── truth
+│   ├── sample_1
+│   │   └── truth_sample_1.vcf
+│   └── sample_2
+│       └── truth_sample_2.vcf
+└── test
+    ├── variant_caller_1
+    │   ├── sample_1
+    │   │   └── variant_caller_1_sample_1.vcf
+    │   └── sample_2
+    │       └── variant_caller_1_sample_2.vcf
+    └── variant_caller_2
+        ├── sample_1
+        │   └── variant_caller_2_sample_1.vcf
+        └── sample_2
+            └── variant_caller_2_sample_2.vcf
+```
+
+After running the pipeline designer, we will obtain the following output folder structure:
+```
+output
+├── ...
+└── improvement_list
+    ├── SNV_1.csv
+    ├── INDEL_1__100.csv
+    ├── ...
+    └── SV_ALL.csv
+```
+
+We are looking for the `SV_ALL.csv` file. This file contains the results of the combinations of all the SVs. The file may look like this:
+
+| operation                               | variant_type | variant_size | recall | precision | f1_score | ... | num_callers |
+| --------------------------------------- | ------------ | ------------ | ------ | --------- | -------- | --- | ----------- |
+| `variant_caller_1$or$variant_caller_2`  | SV           | ALL          | 1.00   | 0.50      | 0.67     | ... | 2           |
+| `variant_caller_2`                      | SV           | ALL          | 0.67   | 0.50      | 0.57     | ... | 1           |
+| `variant_caller_1$and$variant_caller_2` | SV           | ALL          | 0.33   | 1.00      | 0.5      | ... | 2           |
+| `variant_caller_1`                      | SV           | ALL          | 0.67   | 1.00      | 0.8      | ... | 1           |
+
+
+In our case, the best option for maximizing the F1 score is to use `variant_caller_1` alone. However, we can see that the union of `variant_caller_1` and `variant_caller_2` has a higher recall and that `variant_caller_1` alone has a higher precision. Selecting one option or another will depend on the use case.
diff --git a/tools/pipeline_designer/TODO b/tools/pipeline_designer/TODO
deleted file mode 100644
index e69de29..0000000
diff --git a/tools/pipeline_designer/example.sh b/tools/pipeline_designer/example.sh
deleted file mode 100644
index bf3fe9d..0000000
--- a/tools/pipeline_designer/example.sh
+++ /dev/null
@@ -1,9 +0,0 @@
-
-export EVALUATOR_COMMAND='python3 ./example/variant-evaluator/src/variant_evaluator/main.py'
-python3 src/main.py -t ./example/input/truth -v ./example/input/test -o ./example/output \
-    -f  ./example/input/genome.fa \
-    -rs PCAWG_pilot_1 PCAWG_pilot_2 \
-    -ps PCAWG_pilot_2 \
-    -p 32 \
-    --max-combinations 5
-
diff --git a/tools/pipeline_designer/example/.gitignore b/tools/pipeline_designer/example/.gitignore
new file mode 100644
index 0000000..6caf68a
--- /dev/null
+++ b/tools/pipeline_designer/example/.gitignore
@@ -0,0 +1 @@
+output
\ No newline at end of file
diff --git a/tools/pipeline_designer/example/example.sh b/tools/pipeline_designer/example/example.sh
new file mode 100644
index 0000000..8bbd4a8
--- /dev/null
+++ b/tools/pipeline_designer/example/example.sh
@@ -0,0 +1,9 @@
+
+export ASSESMENT_COMMAND='python3 ../../../modules/oncoliner_assesment/src/assesment_main.py'
+python3 ../src/main.py -t ./input/truth -v ./input/test -o ./output \
+    -f  ./fake_ref.fa \
+    -rs sample_1 \
+    -ps sample_2 \
+    -p 32 \
+    --max-combinations 5
+
diff --git a/tools/pipeline_designer/example/fake_ref.fa b/tools/pipeline_designer/example/fake_ref.fa
new file mode 120000
index 0000000..a4394f0
--- /dev/null
+++ b/tools/pipeline_designer/example/fake_ref.fa
@@ -0,0 +1 @@
+../../../modules/oncoliner_assesment/examples/fake_ref.fa
\ No newline at end of file
diff --git a/tools/pipeline_designer/example/fake_ref.fa.fai b/tools/pipeline_designer/example/fake_ref.fa.fai
new file mode 120000
index 0000000..12fcfb7
--- /dev/null
+++ b/tools/pipeline_designer/example/fake_ref.fa.fai
@@ -0,0 +1 @@
+../../../modules/oncoliner_assesment/examples/fake_ref.fa.fai
\ No newline at end of file
diff --git a/tools/pipeline_designer/example/input/test/variant_caller_1/sample_1/variant_caller_1_sample_1.vcf b/tools/pipeline_designer/example/input/test/variant_caller_1/sample_1/variant_caller_1_sample_1.vcf
new file mode 100644
index 0000000..3a39e2f
--- /dev/null
+++ b/tools/pipeline_designer/example/input/test/variant_caller_1/sample_1/variant_caller_1_sample_1.vcf
@@ -0,0 +1,169 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+1	900	.	T	T]1:3000]	.	PASS	FP;TEST_VARIANT;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+1	1100	.	T	T]1:2100]	.	PASS	TP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	2000	.	T	T]2:3000]	.	PASS	FP;TEST_VARIANT;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+1	2000	.	T	T]2:3000]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/example/input/test/variant_caller_1/sample_2/variant_caller_1_sample_2.vcf b/tools/pipeline_designer/example/input/test/variant_caller_1/sample_2/variant_caller_1_sample_2.vcf
new file mode 100644
index 0000000..41e7a29
--- /dev/null
+++ b/tools/pipeline_designer/example/input/test/variant_caller_1/sample_2/variant_caller_1_sample_2.vcf
@@ -0,0 +1,168 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+1	63	.	A	C	.	PASS	FP;TEST_VARIANT;AS_SB_TABLE=88,80|4,3;DP=176;ECNT=1;GERMQ=93;MBQ=36,35;MFRL=542,675;MMQ=40,34;MPOS=15;NALOD=1.63;NLOD=12.59;POPAF=0.903;TLOD=10.11	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:42,0:0.023:42:17,0:24,0:19,23,0,0	0/1:126,7:0.06:133:69,3:56,4:69,57,4,3
+2	1000	.	T	T]2:3000]	.	PASS	FP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	900	.	T	T]2:3000]	.	PASS	TP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/example/input/test/variant_caller_2/sample_1/variant_caller_2_sample_1.vcf b/tools/pipeline_designer/example/input/test/variant_caller_2/sample_1/variant_caller_2_sample_1.vcf
new file mode 100644
index 0000000..99fbcd9
--- /dev/null
+++ b/tools/pipeline_designer/example/input/test/variant_caller_2/sample_1/variant_caller_2_sample_1.vcf
@@ -0,0 +1,168 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+1	3000	.	T	T]1:6000]	.	PASS	FP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+1	1100	.	T	T]1:2100]	.	PASS	TP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	1000	.	T	T]2:3000]	.	PASS	TP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/example/input/test/variant_caller_2/sample_2/variant_caller_2_sample_2.vcf b/tools/pipeline_designer/example/input/test/variant_caller_2/sample_2/variant_caller_2_sample_2.vcf
new file mode 100644
index 0000000..3e25a52
--- /dev/null
+++ b/tools/pipeline_designer/example/input/test/variant_caller_2/sample_2/variant_caller_2_sample_2.vcf
@@ -0,0 +1,167 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+2	900	.	T	T]2:3000]	.	PASS	TP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	2102	.	T	T]2:2200]	.	PASS	FP;AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/example/input/truth/sample_1/truth_sample_1.vcf b/tools/pipeline_designer/example/input/truth/sample_1/truth_sample_1.vcf
new file mode 100644
index 0000000..4f60627
--- /dev/null
+++ b/tools/pipeline_designer/example/input/truth/sample_1/truth_sample_1.vcf
@@ -0,0 +1,169 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+1	63	.	A	C	.	PASS	AS_FilterStatus=SITE;CSQ=ENSG00000142611|ZSWIM7|protein_altering_variant,ENSG00000142611|PRDM16|protein_altering_variant;AS_SB_TABLE=88,80|4,3;DP=176;ECNT=1;GERMQ=93;MBQ=36,35;MFRL=542,675;MMQ=40,34;MPOS=15;NALOD=1.63;NLOD=12.59;POPAF=0.903;TLOD=10.11	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:42,0:0.023:42:17,0:24,0:19,23,0,0	0/1:126,7:0.06:133:69,3:56,4:69,57,4,3
+1	1100	.	T	T]1:2100]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	1000	.	T	T]2:3000]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+1	2000	.	T	T]2:3000]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/example/input/truth/sample_2/truth_sample_2.vcf b/tools/pipeline_designer/example/input/truth/sample_2/truth_sample_2.vcf
new file mode 100644
index 0000000..93eedd6
--- /dev/null
+++ b/tools/pipeline_designer/example/input/truth/sample_2/truth_sample_2.vcf
@@ -0,0 +1,168 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##FILTER=<ID=FAIL,Description="Fail the site if all alleles fail but for different reasons.">
+##FILTER=<ID=base_qual,Description="alt median base quality">
+##FILTER=<ID=clustered_events,Description="Clustered events observed in the tumor">
+##FILTER=<ID=contamination,Description="contamination">
+##FILTER=<ID=duplicate,Description="evidence for alt allele is overrepresented by apparent duplicates">
+##FILTER=<ID=fragment,Description="abs(ref - alt) median fragment length">
+##FILTER=<ID=germline,Description="Evidence indicates this site is germline, not somatic">
+##FILTER=<ID=haplotype,Description="Variant near filtered variant on same haplotype.">
+##FILTER=<ID=low_allele_frac,Description="Allele fraction is below specified threshold">
+##FILTER=<ID=map_qual,Description="ref - alt median mapping quality">
+##FILTER=<ID=multiallelic,Description="Site filtered because too many alt alleles pass tumor LOD">
+##FILTER=<ID=n_ratio,Description="Ratio of N to alt exceeds specified ratio">
+##FILTER=<ID=normal_artifact,Description="artifact_in_normal">
+##FILTER=<ID=orientation,Description="orientation bias detected by the orientation bias mixture model">
+##FILTER=<ID=panel_of_normals,Description="Blacklisted site in panel of normals">
+##FILTER=<ID=position,Description="median distance of alt variants from end of reads">
+##FILTER=<ID=possible_numt,Description="Allele depth is below expected coverage of NuMT in autosome">
+##FILTER=<ID=slippage,Description="Site filtered due to contraction of short tandem repeat region">
+##FILTER=<ID=strand_bias,Description="Evidence for alt allele comes from one read direction only">
+##FILTER=<ID=strict_strand,Description="Evidence for alt allele is not represented in both directions">
+##FILTER=<ID=weak_evidence,Description="Mutation does not meet likelihood threshold">
+##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
+##FORMAT=<ID=AF,Number=A,Type=Float,Description="Allele fractions of alternate alleles in the tumor">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">
+##FORMAT=<ID=F1R2,Number=R,Type=Integer,Description="Count of reads in F1R2 pair orientation supporting each allele">
+##FORMAT=<ID=F2R1,Number=R,Type=Integer,Description="Count of reads in F2R1 pair orientation supporting each allele">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another; will always be heterozygous and is not intended to describe called alleles">
+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">
+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">
+##FORMAT=<ID=PS,Number=1,Type=Integer,Description="Phasing set (typically the position of the first variant in the set)">
+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher's Exact Test to detect strand bias.">
+##GATKCommandLine=<ID=FilterMutectCalls,CommandLine="FilterMutectCalls --output COLO829T_vs_COLO829N_Mutect2_filtered.vcf.gz --stats COLO829T_vs_COLO829N.vcf.gz.stats --contamination-table COLO829T_contamination.table.tsv --variant COLO829T_vs_COLO829N_Mutect2_unfiltered.vcf.gz --reference hg19.fa --threshold-strategy OPTIMAL_F_SCORE --f-score-beta 1.0 --false-discovery-rate 0.05 --initial-threshold 0.1 --mitochondria-mode false --max-events-in-region 2 --max-alt-allele-count 1 --unique-alt-read-count 0 --min-median-mapping-quality 30 --min-median-base-quality 20 --max-median-fragment-length-difference 10000 --min-median-read-position 1 --max-n-ratio Infinity --min-reads-per-strand 0 --min-allele-fraction 0.0 --contamination-estimate 0.0 --log-snv-prior -13.815510557964275 --log-indel-prior -16.11809565095832 --log-artifact-prior -2.302585092994046 --normal-p-value-threshold 0.001 --min-slippage-length 8 --pcr-slippage-rate 0.1 --distance-on-haplotype 100 --long-indel-length 5 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays  --disable-tool-default-read-filters false",Version="4.1.9.0",Date="8 juillet 2021 16:09:27 CEST">
+##GATKCommandLine=<ID=Mutect2,CommandLine="Mutect2 --tumor-sample COLO829T --normal-sample COLO829N --germline-resource /mnt/beegfs/home/tgutman/eucancan/colo829/work/c0/6c82bf4687b64df35ad12193f8e3cd/af-only-gnomad_modified.raw.sites.vcf.gz --dont-use-soft-clipped-bases true --min-base-quality-score 13 --output 10_1-135534747_COLO829T_vs_COLO829N.vcf --intervals 10_1-135534747.bed --input COLO829T_recal.bam --input COLO829N_recal.bam --reference hg19.fa --minimum-mapping-quality 20 --f1r2-median-mq 50 --f1r2-min-bq 20 --f1r2-max-depth 200 --genotype-pon-sites false --genotype-germline-sites false --af-of-alleles-not-in-resource -1.0 --mitochondria-mode false --tumor-lod-to-emit 3.0 --initial-tumor-lod 2.0 --pcr-snv-qual 40 --pcr-indel-qual 40 --max-population-af 0.01 --downsampling-stride 1 --callable-depth 10 --max-suspicious-reads-per-alignment-start 0 --normal-lod 2.2 --ignore-itr-artifacts false --gvcf-lod-band -2.5 --gvcf-lod-band -2.0 --gvcf-lod-band -1.5 --gvcf-lod-band -1.0 --gvcf-lod-band -0.5 --gvcf-lod-band 0.0 --gvcf-lod-band 0.5 --gvcf-lod-band 1.0 --minimum-allele-fraction 0.0 --independent-mates false --disable-adaptive-pruning false --kmer-size 10 --kmer-size 25 --dont-increase-kmer-sizes-for-cycles false --allow-non-unique-kmers-in-ref false --num-pruning-samples 1 --min-dangling-branch-length 4 --recover-all-dangling-branches false --max-num-haplotypes-in-population 128 --min-pruning 2 --adaptive-pruning-initial-error-rate 0.001 --pruning-lod-threshold 2.302585092994046 --pruning-seeding-lod-threshold 9.210340371976184 --max-unpruned-variants 100 --linked-de-bruijn-graph false --disable-artificial-haplotype-recovery false --debug-assembly false --debug-graph-transformations false --capture-assembly-failure-bam false --error-correction-log-odds -Infinity --error-correct-reads false --kmer-length-for-read-error-correction 25 --min-observations-for-kmer-to-be-solid 20 --base-quality-score-threshold 18 --pair-hmm-gap-continuation-penalty 10 --pair-hmm-implementation FASTEST_AVAILABLE --pcr-indel-model CONSERVATIVE --phred-scaled-global-read-mismapping-rate 45 --native-pair-hmm-threads 4 --native-pair-hmm-use-double-precision false --bam-writer-type CALLED_HAPLOTYPES --smith-waterman JAVA --emit-ref-confidence NONE --max-mnp-distance 1 --force-call-filtered-alleles false --allele-informative-reads-overlap-margin 2 --min-assembly-region-size 50 --max-assembly-region-size 300 --active-probability-threshold 0.002 --max-prob-propagation-distance 50 --force-active false --assembly-region-padding 100 --padding-around-indels 75 --padding-around-snps 20 --padding-around-strs 75 --max-reads-per-alignment-start 50 --interval-set-rule UNION --interval-padding 0 --interval-exclusion-padding 0 --interval-merging-rule ALL --read-validation-stringency SILENT --seconds-between-progress-updates 10.0 --disable-sequence-dictionary-validation false --create-output-bam-index true --create-output-bam-md5 false --create-output-variant-index true --create-output-variant-md5 false --lenient false --add-output-sam-program-record true --add-output-vcf-command-line true --cloud-prefetch-buffer 40 --cloud-index-prefetch-buffer -1 --disable-bam-index-caching false --sites-only-vcf-output false --help false --version false --showHidden false --verbosity INFO --QUIET false --use-jdk-deflater false --use-jdk-inflater false --gcs-max-retries 20 --gcs-project-for-requester-pays --disable-tool-default-read-filters false --max-read-length 2147483647 --min-read-length 30 --disable-tool-default-annotations false --enable-all-annotations false",Version="4.1.9.0",Date="8 juillet 2021 12:41:08 CEST">
+##INFO=<ID=AS_FilterStatus,Number=A,Type=String,Description="Filter status for each allele, as assessed by ApplyRecalibration. Note that the VCF filter field will reflect the most lenient/sensitive status across all alleles.">
+##INFO=<ID=AS_SB_TABLE,Number=1,Type=String,Description="Allele-specific forward/reverse read counts for strand bias tests. Includes the reference and alleles separated by |.">
+##INFO=<ID=AS_UNIQ_ALT_READ_COUNT,Number=A,Type=Integer,Description="Number of reads with unique start and mate end positions for each alt at a variant site">
+##INFO=<ID=CONTQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to contamination">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">
+##INFO=<ID=ECNT,Number=1,Type=Integer,Description="Number of events in this haplotype">
+##INFO=<ID=GERMQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not germline variants">
+##INFO=<ID=MBQ,Number=R,Type=Integer,Description="median base quality">
+##INFO=<ID=MFRL,Number=R,Type=Integer,Description="median fragment length">
+##INFO=<ID=MMQ,Number=R,Type=Integer,Description="median mapping quality">
+##INFO=<ID=MPOS,Number=A,Type=Integer,Description="median distance from end of read">
+##INFO=<ID=NALOD,Number=A,Type=Float,Description="Negative log 10 odds of artifact in normal with same allele fraction as tumor">
+##INFO=<ID=NCount,Number=1,Type=Integer,Description="Count of N bases in the pileup">
+##INFO=<ID=NLOD,Number=A,Type=Float,Description="Normal log 10 likelihood ratio of diploid het or hom alt genotypes">
+##INFO=<ID=OCM,Number=1,Type=Integer,Description="Number of alt reads whose original alignment doesn't match the current contig.">
+##INFO=<ID=PON,Number=0,Type=Flag,Description="site found in panel of normals">
+##INFO=<ID=POPAF,Number=A,Type=Float,Description="negative log 10 population allele frequencies of alt alleles">
+##INFO=<ID=ROQ,Number=1,Type=Float,Description="Phred-scaled qualities that alt allele are not due to read orientation artifact">
+##INFO=<ID=RPA,Number=R,Type=Integer,Description="Number of times tandem repeat unit is repeated, for each allele (including reference)">
+##INFO=<ID=RU,Number=1,Type=String,Description="Tandem repeat unit (bases)">
+##INFO=<ID=SEQQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles are not sequencing errors">
+##INFO=<ID=STR,Number=0,Type=Flag,Description="Variant is a short tandem repeat">
+##INFO=<ID=STRANDQ,Number=1,Type=Integer,Description="Phred-scaled quality of strand bias artifact">
+##INFO=<ID=STRQ,Number=1,Type=Integer,Description="Phred-scaled quality that alt alleles in STRs are not polymerase slippage errors">
+##INFO=<ID=TLOD,Number=A,Type=Float,Description="Log 10 likelihood ratio score of variant existing versus not existing">
+##INFO=<ID=END,Number=1,Type=Integer,Description="End position of the variant described in this record">
+##MutectVersion=2.2
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=Un_gl000211,length=166566>
+##contig=<ID=Un_gl000212,length=186858>
+##contig=<ID=Un_gl000213,length=164239>
+##contig=<ID=Un_gl000214,length=137718>
+##contig=<ID=Un_gl000215,length=172545>
+##contig=<ID=Un_gl000216,length=172294>
+##contig=<ID=Un_gl000217,length=172149>
+##contig=<ID=Un_gl000218,length=161147>
+##contig=<ID=Un_gl000219,length=179198>
+##contig=<ID=Un_gl000220,length=161802>
+##contig=<ID=Un_gl000221,length=155397>
+##contig=<ID=Un_gl000222,length=186861>
+##contig=<ID=Un_gl000223,length=180455>
+##contig=<ID=Un_gl000224,length=179693>
+##contig=<ID=Un_gl000225,length=211173>
+##contig=<ID=Un_gl000226,length=15008>
+##contig=<ID=Un_gl000227,length=128374>
+##contig=<ID=Un_gl000228,length=129120>
+##contig=<ID=Un_gl000229,length=19913>
+##contig=<ID=Un_gl000230,length=43691>
+##contig=<ID=Un_gl000231,length=27386>
+##contig=<ID=Un_gl000232,length=40652>
+##contig=<ID=Un_gl000233,length=45941>
+##contig=<ID=Un_gl000234,length=40531>
+##contig=<ID=Un_gl000235,length=34474>
+##contig=<ID=Un_gl000236,length=41934>
+##contig=<ID=Un_gl000237,length=45867>
+##contig=<ID=Un_gl000238,length=39939>
+##contig=<ID=Un_gl000239,length=33824>
+##contig=<ID=Un_gl000240,length=41933>
+##contig=<ID=Un_gl000241,length=42152>
+##contig=<ID=Un_gl000242,length=43523>
+##contig=<ID=Un_gl000243,length=43341>
+##contig=<ID=Un_gl000244,length=39929>
+##contig=<ID=Un_gl000245,length=36651>
+##contig=<ID=Un_gl000246,length=38154>
+##contig=<ID=Un_gl000247,length=36422>
+##contig=<ID=Un_gl000248,length=39786>
+##contig=<ID=Un_gl000249,length=38502>
+##contig=<ID=1_gl000191_random,length=106433>
+##contig=<ID=1_gl000192_random,length=547496>
+##contig=<ID=4_ctg9_hap1,length=590426>
+##contig=<ID=4_gl000193_random,length=189789>
+##contig=<ID=4_gl000194_random,length=191469>
+##contig=<ID=6_apd_hap1,length=4622290>
+##contig=<ID=6_cox_hap2,length=4795371>
+##contig=<ID=6_dbb_hap3,length=4610396>
+##contig=<ID=6_mann_hap4,length=4683263>
+##contig=<ID=6_mcf_hap5,length=4833398>
+##contig=<ID=6_qbl_hap6,length=4611984>
+##contig=<ID=6_ssto_hap7,length=4928567>
+##contig=<ID=7_gl000195_random,length=182896>
+##contig=<ID=8_gl000196_random,length=38914>
+##contig=<ID=8_gl000197_random,length=37175>
+##contig=<ID=9_gl000198_random,length=90085>
+##contig=<ID=9_gl000199_random,length=169874>
+##contig=<ID=9_gl000200_random,length=187035>
+##contig=<ID=9_gl000201_random,length=36148>
+##contig=<ID=11_gl000202_random,length=40103>
+##contig=<ID=17_ctg5_hap1,length=1680828>
+##contig=<ID=17_gl000203_random,length=37498>
+##contig=<ID=17_gl000204_random,length=81310>
+##contig=<ID=17_gl000205_random,length=174588>
+##contig=<ID=17_gl000206_random,length=41001>
+##contig=<ID=18_gl000207_random,length=4262>
+##contig=<ID=19_gl000208_random,length=92689>
+##contig=<ID=19_gl000209_random,length=159169>
+##contig=<ID=21_gl000210_random,length=27682>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##contig=<ID=M,length=16571>
+##filtering_status=These calls have been filtered by FilterMutectCalls to label false positives with a list of failed filters and true positives with PASS.
+##normal_sample=COLO829N
+##source=FilterMutectCalls
+##source=Mutect2
+##tumor_sample=COLO829T
+##bcftools_normVersion=1.10.2+htslib-1.10.2
+##bcftools_normCommand=norm -Oz -m -both -f hg19.fa --threads 8 -o COLO829T_vs_COLO829N_Mutect2_filtered_pass_norm.vcf.gz COLO829T_vs_COLO829N_Mutect2_filtered_pass.vcf.gz; Date=Thu Jul  8 16:14:34 2021
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	COLO829N	COLO829T
+1	74	.	T	G	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+1	900	.	T	T]1:3000]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
+2	900	.	T	T]2:3000]	.	PASS	AS_FilterStatus=SITE;AS_SB_TABLE=16,23|7,7;DP=55;ECNT=1;GERMQ=6;MBQ=38,34;MFRL=531,532;MMQ=60,38;MPOS=14;NALOD=1.23;NLOD=4.77;POPAF=1.54;TLOD=33.58	GT:AD:AF:DP:F1R2:F2R1:SB	0/0:16,0:0.056:16:4,0:11,0:7,9,0,0	0/1:23,14:0.38:37:13,5:10,7:9,14,7,7
diff --git a/tools/pipeline_designer/src/main.py b/tools/pipeline_designer/src/main.py
index 76d5a93..635a417 100644
--- a/tools/pipeline_designer/src/main.py
+++ b/tools/pipeline_designer/src/main.py
@@ -10,10 +10,10 @@
 from concurrent.futures import ProcessPoolExecutor, as_completed, ThreadPoolExecutor
 
 # Add vcf-ops to the path
-sys.path.insert(0, os.path.join(os.path.abspath(os.path.dirname(__file__)), '..', '..', 'shared', 'vcf-ops','src'))
+sys.path.insert(0, os.path.join(os.path.abspath(os.path.dirname(__file__)), '..', '..', '..', 'shared', 'vcf_ops', 'src'))
 
 from vcf_ops.constants import DEFAULT_INDEL_THRESHOLD, DEFAULT_WINDOW_RADIUS, DEFAULT_SV_BINS, DEFAULT_CONTIGS  # noqa
-from vcf_ops.metrics import aggregate_metrics  # noqa
+from vcf_ops.metrics import aggregate_metrics, combine_precision_recall_metrics  # noqa
 from vcf_ops.intersect import intersect  # noqa
 from vcf_ops.union import union  # noqa
 from vcf_ops.i_o import read_vcfs, write_masked_vcfs  # noqa
@@ -38,27 +38,26 @@ def extract_vcfs(path_prefix: str) -> pd.DataFrame:
     return read_vcfs(files)
 
 
-def evaluate_sample(truth_sample_folder, test_sample_folder, output_prefix, fasta_ref, indel_threshold, window_ratio, window_limit, sv_size_bins, contigs):
+def evaluate_sample(truth_sample_folder, test_sample_folder, output_prefix, fasta_ref, indel_threshold, window_radius, sv_size_bins, contigs):
     # If output_prefix*metrics.csv exists and is not empty, skip
     output_metrics = glob.glob(output_prefix + '*metrics.csv')
     if len(output_metrics) > 0 and os.path.getsize(output_metrics[0]) > 0:
         return
     # Get evaluator path from the environment
-    evaluator_command = os.environ.get('EVALUATOR_COMMAND')
-    if evaluator_command is None:
-        raise Exception('EVALUATOR_COMMAND environment variable not defined')
+    assesment_command = os.environ.get('ASSESMENT_COMMAND')
+    if assesment_command is None:
+        raise Exception('ASSESMENT_COMMAND environment variable not defined')
     # Get files
     truth_sample_vcfs = get_vcf_files(truth_sample_folder + '/')
     test_sample_vcfs = get_vcf_files(test_sample_folder + '/')
     subprocess.check_call(
-        evaluator_command.split() + [
+        assesment_command.split() + [
             '-t'] + truth_sample_vcfs + [
             '-v'] + test_sample_vcfs + [
             '-o', output_prefix,
             '-f', fasta_ref,
             '-it', str(indel_threshold),
-            '-wr', str(window_ratio),
-            '-wl', str(window_limit),
+            '-wr', str(window_radius),
             '--sv-size-bins'] + [str(bin) for bin in sv_size_bins] + [
             '--contigs'] + contigs
     )
@@ -127,7 +126,7 @@ def union_callers(caller_1_prefix: str, caller_2_prefix: str, output_prefix: str
     # Union
     df_union, _ = union(df_1, df_2, indel_threshold, window_radius)
     # Write VCF files
-    if len(df_union) != len(df_1):
+    if len(df_union) > len(df_1):
         write_masked_vcfs(df_union, output_prefix, indel_threshold, fasta_ref)
         return True
     return False
@@ -200,14 +199,7 @@ def calculate_aggregated_metrics_caller(caller_folder: str, recall_samples: List
     recall_aggregated_metrics = aggregate_metrics([pd.read_csv(metrics_file) for metrics_file in recall_metrics_files])
     precision_metrics_files = [glob.glob(os.path.join(caller_folder, sample, '*metrics.csv'))[0] for sample in precision_samples]
     precision_aggregated_metrics = aggregate_metrics([pd.read_csv(metrics_file) for metrics_file in precision_metrics_files])
-    final_metrics = recall_aggregated_metrics
-    final_metrics['precision'] = precision_aggregated_metrics['precision']
-    final_metrics['f1_score'] = 2 * final_metrics['recall'] * \
-        final_metrics['precision'] / (final_metrics['recall'] + final_metrics['precision'])
-    final_metrics['f1_score'].fillna(0, inplace=True)
-    final_metrics['fp'] = precision_aggregated_metrics['fp']
-    # Set columns
-    final_metrics = final_metrics[['variant_type', 'variant_size', 'window_size', 'tp', 'fp', 'fn', 'recall', 'precision', 'f1_score']]
+    final_metrics = combine_precision_recall_metrics(recall_aggregated_metrics, precision_aggregated_metrics)
     final_metrics.to_csv(output_file, index=False)
 
 
@@ -257,19 +249,19 @@ def main(args):
     args.truth = os.path.abspath(args.truth)
     args.test = os.path.abspath(args.test)
 
-    # All subfolders (samples) in truth must be in test
-    if set(os.listdir(args.truth)) != set(os.listdir(args.test)):
-        raise ValueError('The samples in the truth and test folders are not the same')
-
-    # All test subfolders (samples) must contain the same subfolders (callers)
-    callers_names = set(os.listdir(os.path.join(args.test, os.listdir(args.test)[0])))
-    for folder in os.listdir(args.test):
-        if set(os.listdir(os.path.join(args.test, folder))) != callers_names:
-            raise ValueError(f'The samples in the test folder do not contain the same files: {folder}')
-    # Remove the extension from the callers names
-    callers_names = [caller.replace('.vcf.gz', '').replace('.bcf', '').replace('.vcf', '') for caller in callers_names]
+    # Get callers names
+    callers_names = os.listdir(args.test)
     callers_names.sort()
 
+    # All test folders (callers) must contain the same subfolders (samples)
+    for caller_folder in callers_names:
+        missing_truth_samples = set(os.listdir(args.truth)) - set(os.listdir(os.path.join(args.test, caller_folder)))
+        missing_test_samples = set(os.listdir(os.path.join(args.test, caller_folder))) - set(os.listdir(args.truth))
+        if len(missing_truth_samples) > 0:
+            raise Exception(f'Caller {caller_folder} is missing samples from the truth folder: {missing_truth_samples}')
+        if len(missing_test_samples) > 0:
+            raise Exception(f'Caller {caller_folder} has more samples than the truth folder: {missing_test_samples}')
+
     # Create output folder
     os.makedirs(args.output, exist_ok=True)
     # Create output folder for evaluations
@@ -278,21 +270,26 @@ def main(args):
     # Create output folder for combinations
     output_combinations = os.path.join(args.output, 'combinations')
     os.makedirs(output_combinations, exist_ok=True)
-    # Copy each variant caller files to the output_combinations folder
+    # Evaluate the callers
+    original_caller_folders = [os.path.join(args.test, caller_name) for caller_name in callers_names]
+    evaluate_callers(original_caller_folders, args.truth, output_evaluations, args.processes, fasta_ref=args.fasta_ref,
+                     indel_threshold=args.indel_threshold, window_radius=args.window_radius,
+                     sv_size_bins=args.sv_size_bins, contigs=args.contigs)
+
+    # Copy each variant caller TP+FP files to its corresponding output_combinations folder
     for caller_name in callers_names:
         caller_combination_folder = os.path.join(output_combinations, caller_name)
         os.makedirs(caller_combination_folder, exist_ok=True)
-        for sample in os.listdir(args.test):
+        for sample in os.listdir(os.path.join(args.test, caller_name)):
             caller_combination_sample_folder = os.path.join(caller_combination_folder, sample)
             os.makedirs(caller_combination_sample_folder, exist_ok=True)
-            for file in get_vcf_files(os.path.join(args.test, sample, caller_name)):
+            for file in get_vcf_files(os.path.join(output_evaluations, caller_name, sample, '')):
+                # Filter TP+FP files
+                if 'tp.' not in file and 'fp.' not in file:
+                    continue
                 shutil.copy(file, caller_combination_sample_folder)
     # Get callers prefixes
     callers_folders = [os.path.join(output_combinations, caller_name) for caller_name in os.listdir(output_combinations)]
-    # Evaluate the callers
-    evaluate_callers(callers_folders, args.truth, output_evaluations, args.processes, fasta_ref=args.fasta_ref,
-                     indel_threshold=args.indel_threshold, window_radius=args.window_radius,
-                     sv_size_bins=args.sv_size_bins, contigs=args.contigs)
     # Get the variant types for each caller
     # Create a dict variant_type -> callers
     callers_variant_types = {
@@ -309,13 +306,15 @@ def main(args):
         callers_operations_by_variant_type[variant_type] = generate_combinations(callers, args.max_combinations)
     # Perform the operations
     for operations in callers_operations_by_variant_type.values():
+        if len(operations) == 0:
+            continue
         execute_operations(operations, output_combinations, args.processes, fasta_ref=args.fasta_ref,
-                           indel_threshold=args.indel_threshold, window_ratio=args.window_ratio, window_limit=args.window_limit)
+                           indel_threshold=args.indel_threshold, window_radius=args.window_radius)
     # Evaluate the combinations
     combinations_prefixes = list(set(os.listdir(output_combinations)) - set(callers_folders))
     combinations_folders = [os.path.join(output_combinations, combination_prefix) for combination_prefix in combinations_prefixes]
     evaluate_callers(combinations_folders, args.truth, output_evaluations, args.processes, fasta_ref=args.fasta_ref,
-                     indel_threshold=args.indel_threshold, window_ratio=args.window_ratio, window_limit=args.window_limit,
+                     indel_threshold=args.indel_threshold, window_radius=args.window_radius,
                      sv_size_bins=args.sv_size_bins, contigs=args.contigs)
 
     # Calculate aggregated metrics
@@ -328,7 +327,7 @@ def main(args):
 
 
 if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
+    parser = argparse.ArgumentParser(description='Pipeline designer')
     parser.add_argument('-t', '--truth', help='Path to the VCF truth folder', required=True, type=str)
     parser.add_argument('-v', '--test', help='Path to the VCF test folder', required=True, type=str)
     parser.add_argument('-o', '--output', help='Path to the output folder', required=True, type=str)