account for the case when FASTQ is missing on one side; introduce the…

… "XX" corrupt pair type
open2c · Apr 23, 2019 · 1579c6f · 1579c6f
1 parent cb4b3db
commit 1579c6f
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 6 deletions.
diff --git a/doc/formats.rst b/doc/formats.rst
@@ -81,22 +81,26 @@ and which side has a "better" alignment and find the corresponding row in the ta
  >2 alignments   Mapped    Unique             Mapped    Unique             Pair type                Code   Sidedness                           
  |check|         |cross|   |cross|            |cross|   |cross|            walk-walk                WW     0 [1]_
  |cross|         |cross|                      |cross|                      null                     NN     0     
+ |cross|         |cross|                      |cross|                      corrupt                  XX     0 [2]_    
  |cross|         |cross|                      |check|   |cross|            null-multi               NM     0     
- |check|         |cross|                      |check|   |check|            null-rescued             NR     1 [2]_
+ |check|         |cross|                      |check|   |check|            null-rescued             NR     1 [3]_
  |cross|         |cross|                      |check|   |check|            null-unique              NU     1     
  |cross|         |check|   |cross|            |check|   |cross|            multi-multi              MM     0     
- |check|         |check|   |cross|            |check|   |check|            multi-rescued            MR     1 [2]_
+ |check|         |check|   |cross|            |check|   |check|            multi-rescued            MR     1 [3]_
  |cross|         |check|   |cross|            |check|   |check|            multi-unique             MU     1     
- |check|         |check|   |check|            |check|   |check|            rescued-unique           RU     2 [2]_
- |check|         |check|   |check|            |check|   |check|            unique-rescued           UR     2 [2]_
+ |check|         |check|   |check|            |check|   |check|            rescued-unique           RU     2 [3]_
+ |check|         |check|   |check|            |check|   |check|            unique-rescued           UR     2 [3]_
  |cross|         |check|   |check|            |check|   |check|            unique-unique            UU     2     
- |cross|         |check|   |check|            |check|   |check|            duplicate                DD     2 [3]_
+ |cross|         |check|   |check|            |check|   |check|            duplicate                DD     2 [4]_
 =============== ========= ================== ========= ================== ======================== ====== ===========
 
 .. [1] "walks", or, `C-walks <https://www.nature.com/articles/nature20158>`_ are
    Hi-C molecules formed via multiple ligation events which cannot be reported 
    as a single pair.  
 
+.. [2] "corrupt" pairs are those with technical issues - e.g. missing a 
+   FASTQ sequence/SAM entry from one side of the molecule.
+
 .. [2] "rescued" pairs have two non-overlapping alignments on one of the sides
    (referred below as the chimeric side/read), but the inner (3'-) one extends the 
    only alignment on the other side (referred as the non-chimeric side/read).

diff --git a/pairtools/pairtools_parse.py b/pairtools/pairtools_parse.py
@@ -298,7 +298,6 @@ def empty_alignment():
         'clip5_ref': 0, 
         'read_len': 0,
         'type':'N'
-
     }
 
 
@@ -549,6 +548,14 @@ def parse_sams_into_pair(sams1,
 
     """
 
+    # Check if there is at least one SAM entry per side: 
+    if (len(sams1) == 0) or (len(sams2) == 0):
+        algns1 = [empty_alignment()]
+        algns2 = [empty_alignment()]
+        algns1[0]['type'] = 'X'
+        algns2[0]['type'] = 'X'
+        return algns1[0], algns2[0], algns1, algns2
+
     # Generate a sorted, gap-filled list of all alignments
     algns1 = [parse_algn(sam.rstrip().split('\t'), min_mapq, 
                          report_3_alignment_end, sam_tags, store_seq)

diff --git a/tests/data/mock.sam b/tests/data/mock.sam
@@ -53,3 +53,4 @@ readid21	141	*	0	0	*	chr1	10	0	SEQ	PHRED	FLAG1	FLAG2	SIMULATED:!,0,!,0,-,-,WW
 readid22	65	chr1	10	60	25M25S	chr1	200	0	SEQ	PHRED	FLAG1	SA:Z:chr1,5300,-,25M25H,60,0;	SIMULATED:!,0,!,0,-,-,WW
 readid22	2129	chr1	5300	60	25M25H	chr1	200	0	SEQ	PHRED	FLAG1	SA:Z:chr1,10,+,25M25S,60,0;	SIMULATED:!,0,!,0,-,-,WW
 readid22	129	chr1	200	0	50M	chr1	10	0	SEQ	PHRED	FLAG1	FLAG2	SIMULATED:!,0,!,0,-,-,WW
+readid23	129	chr1	200	0	50M	chr1	10	0	SEQ	PHRED	FLAG1	FLAG2	SIMULATED:!,0,!,0,-,-,XX