Integration of RF model to predict efficacy of immune checkpoint blockade (BioModels) #1355
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
bgruening
reviewed
Nov 7, 2023
tools/biomodelsML/bio_ml_tool.xml
Outdated
| <container type="docker">docker.io/anupkumar/immune-checkpoint:latest</container> | ||
| </requirements> | ||
| <command><
There was a problem hiding this comment.
Suggested change
| cp /home/\$NB_USER/forest16.onnx `pwd` && python '$biom_script' | |
| cp /home/\$NB_USER/forest16.onnx ./ && | |
| python '$biom_script' |
There was a problem hiding this comment.
I fixed the permissions in the container, let's see. Not sure if we need to create a new user just like the GPU based container.
tools/biomodelsML/bio_ml_tool.xml
Outdated
| </test> | ||
| <test> | ||
| <param name="input_file" value="test_data.csv" ftype="csv" /> | ||
| <output name="output_file" file="pred_data.tabular" compare="sim_size" delta="5" /> |
There was a problem hiding this comment.
sim_size is not recommendade, can we use assert_contents here, number of columns, number of rows https://docs.galaxyproject.org/en/latest/dev/schema.html#id112
tools/biomodelsML/bio_ml_tool.xml
Outdated
| @@ -0,0 +1,89 @@ | |||
| <tool id="bio_ml_tool" name="Random Forest model" version="0.0.1" profile="22.05"> | |||
There was a problem hiding this comment.
Suggested change
| <tool id="bio_ml_tool" name="Random Forest model" version="0.0.1" profile="22.05"> | |
| <tool id="biomodel_BIOMD0000001066" name="Random Forest model" version="1" profile="22.05"> |
I have taken those from https://www.ebi.ac.uk/biomodels/BIOMD0000001066#History
There was a problem hiding this comment.
sounds good, fixed it.
tools/biomodelsML/bio_ml_tool.xml
Outdated
| <tool id="bio_ml_tool" name="Random Forest model" version="0.0.1" profile="22.05"> | ||
| <description>to predict efficacy of immune checkpoint blockade across multiple cancer patient cohorts</description> | ||
| <requirements> | ||
| <container type="docker">docker.io/anupkumar/immune-checkpoint:latest</container> |
There was a problem hiding this comment.
maybe also rename the container to fit the tool_id?
bgruening
approved these changes
Nov 7, 2023
bgruening
approved these changes
Nov 7, 2023
7 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The PR adds a tool that uses an RF model, downloaded via a Docker container, to predict the efficacy of immune checkpoint blockage on the provided test data. The RF model is available via BioModels (https://www.ebi.ac.uk/biomodels/BIOMD0000001066). The Docker container available in BioModels (https://www.ebi.ac.uk/biomodels/BIOMD0000001066#Files) for prediction has been customised to reduce its uncompressed size (by half, from over 4 GBs to less than 2). The newly developed container is linked in the tool (docker.io/anupkumar/immune-checkpoint:latest) and also stored on Docker Hub (https://hub.docker.com/repository/docker/anupkumar/biomd0000001066/general). The script used to create this customised container is available on GitHub (https://github.com/anuprulez/biomodelsml-docker/tree/master/rf_immune_checkpoints_blockage).
test file(s):
test_data.xlsx
test_data.csv
Use one of these files to test the tool on Galaxy server.
Tool's UI (on a local Galaxy instance):
ping @bgruening