Merge pull request #40 from Lioscro/update

sort transcripts in transcript_infos, make split-seq fwd strand, update CI
Lioscro · Nov 22, 2023 · 63e15ec · 63e15ec
2 parents 2b12a21 + c7f2410
commit 63e15ec
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 4 deletions.
diff --git a/.gitignore b/.gitignore
@@ -127,4 +127,6 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
-.vscode
+.vscode
+ngs_tools/.DS_Store
+.DS_Store
diff --git a/ngs_tools/chemistry/SingleCellChemistry.py b/ngs_tools/chemistry/SingleCellChemistry.py
@@ -324,7 +324,7 @@ def whitelist_path(self) -> str:
     name='SPLiT-seq',
     description='Rosenberg et al. 2018',
     n=2,
-    strand=SequencingStrand.UNSTRANDED,
+    strand=SequencingStrand.FORWARD,
     cdna_parser=SubSequenceParser(SubSequenceDefinition(0)),
     cell_barcode_parser=SubSequenceParser(
         SubSequenceDefinition(1, 10, 8),

diff --git a/ngs_tools/fasta/__init__.py b/ngs_tools/fasta/__init__.py
@@ -35,9 +35,10 @@ def split_genomic_fasta_to_cdna(
             for gene_id, gene_attributes in gene_infos.items():
                 if gene_attributes['chromosome'] == entry.name:
                     _gene_infos[gene_id] = gene_attributes
+                    all_transcripts = sorted(gene_attributes['transcripts'])
                     _transcript_infos.update({
                         transcript_id: transcript_infos[transcript_id]
-                        for transcript_id in gene_attributes['transcripts']
+                        for transcript_id in all_transcripts
                     })
 
             # Write all transcripts as separate FASTA entries.
@@ -107,9 +108,10 @@ def split_genomic_fasta_to_intron(
             for gene_id, gene_attributes in gene_infos.items():
                 if gene_attributes['chromosome'] == entry.name:
                     _gene_infos[gene_id] = gene_attributes
+                    all_transcripts = sorted(gene_attributes['transcripts'])
                     _transcript_infos.update({
                         transcript_id: transcript_infos[transcript_id]
-                        for transcript_id in gene_attributes['transcripts']
+                        for transcript_id in all_transcripts
                     })
 
             # Write all transcripts as separate FASTA entries.