Skip to content

Commit

Permalink
Seqcount support (#159)
Browse files Browse the repository at this point in the history 
* Updates based on testing

* Tellseq support added to GenPrepFileJob

* update ref

* Update uri

* Update

* Updated test data, Reverted metapool url to master
  • Loading branch information
@charles-cowart
charles-cowart authored Jan 9, 2025
1 parent 1937477 commit 4d55b55
Show file tree
Hide file tree
Showing 19 changed files with 205 additions and 155 deletions.
2 changes: 0 additions & 2 deletions sequence_processing_pipeline/Commands.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,15 +14,13 @@ def split_similar_size_bins(data_location_path, max_file_list_size_in_gb,
:param batch_prefix: Path + file-name prefix for output-files.
:return: The number of output-files created, size of largest bin.
'''

# to prevent issues w/filenames like the ones below from being mistaken
# for R1 or R2 files, use determine_orientation().
# LS_8_22_2014_R2_SRE_S2_L007_I1_001.fastq.gz
# LS_8_22_2014_R1_SRE_S3_L007_I1_001.fastq.gz

# since the names of all fastq files are being scanned for orientation,
# collect all of them instead of mistakenly pre-filtering some files.
# fastq_paths = glob.glob(data_location_path + '/*/*_R?_*.fastq.gz')
fastq_paths = glob.glob(data_location_path + '/*/*.fastq.gz')
fastq_paths = [x for x in fastq_paths
if determine_orientation(x) in ['R1', 'R2']]
Expand Down
4 changes: 2 additions & 2 deletions sequence_processing_pipeline/tests/data/SeqCounts.csv
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
Sample_ID,raw_reads_r1r2,Lane
LS_8_22_2014_R1_SRE,140798056,1
LS_8_22_2014_R2_SRE,128928324,1
Test_8_22_2014_R1_example,140798056,4
Test_8_22_2014_R2_example,128928324,4
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_1.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_R1_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_R1_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_1.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_R1_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_R1_001.fastq.gz
64464162 8345327641
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_2.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_R1_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_R1_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_2.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_R1_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_R1_001.fastq.gz
70399028 9293296513
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_4.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_R2_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_R2_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_4.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_R2_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_R2_001.fastq.gz
70399028 9317943166
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_5.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_I1_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_I1_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_5.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_I1_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_I1_001.fastq.gz
70399028 1267182504
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_6.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_R2_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_R2_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_6.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R2_SRE_S2_L007_R2_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R2_example_S2_L007_R2_001.fastq.gz
64464162 8370238082
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_7.err
View file
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
This is an example .err file produced by seq_counts.sbatch.
Additional details removed.
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_I1_001.fastq.gz
+ seqtk size REMOVED/working_dir/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_I1_001.fastq.gz
2 changes: 1 addition & 1 deletion sequence_processing_pipeline/tests/data/seq_counts_logs/seq_count_2679966_7.out
View file
Original file line number Diff line number Diff line change
@@ -1,2 +1,2 @@
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/LS_8_22_2014_R1_SRE_S3_L007_I1_001.fastq.gz
REMOVED/8edbdee2-da52-4278-af40-267185bbcd7e/TRIntegrateJob/integrated/Test_8_22_2014_R1_example_S3_L007_I1_001.fastq.gz
64464162 1160354916
Loading

0 comments on commit 4d55b55

Please sign in to comment.