Merge remote-tracking branch 'origin/hotfix'

griffithlab · Sep 8, 2023 · c78667b · c78667b
2 parents 3317d2c + 8ac2846
commit c78667b
Show file tree

Hide file tree

Showing 8 changed files with 30 additions and 22 deletions.
diff --git a/docs/conf.py b/docs/conf.py
@@ -70,7 +70,7 @@
 # The short X.Y version.
 version = '4.0'
 # The full version, including alpha/beta/rc tags.
-release = '4.0.3'
+release = '4.0.4'
 
 
 # The language for content autogenerated by Sphinx. Refer to documentation

diff --git a/docs/index.rst b/docs/index.rst
@@ -56,8 +56,8 @@ New in Release |release|
 
 This is a bugfix release. It fixes the following problem(s):
 
-- The fixes in issue in the reference proteome similarity step in pVACseq
-  where running with non-human data would cause an error.
+- This release makes various fixes to allow pVACtools to run with non-human
+  data.
 
 New in Version |version|
 ------------------------

diff --git a/docs/releases/4_0.rst b/docs/releases/4_0.rst
@@ -106,3 +106,11 @@ This is a bugfix release. It fixes the following problem(s):
 
 - The fixes in issue in the reference proteome similarity step in pVACseq
   where running with non-human data would cause an error.
+
+New in Version 4.0.4
+--------------------
+
+This is a bugfix release. It fixes the following problem(s):
+
+- This release makes various fixes to allow pVACtools to run with non-human
+  data.
diff --git a/pvactools/lib/calculate_reference_proteome_similarity.py b/pvactools/lib/calculate_reference_proteome_similarity.py
@@ -269,13 +269,7 @@ def _input_tsv_type(self, line):
     def _get_full_peptide(self, line, mt_records_dict, wt_records_dict):
         for record_id in mt_records_dict.keys():
             (rest_record_id, variant_type, aa_change) = record_id.rsplit(".", 2)
-            transcript_regex = '^.*(ENS[0-9|A-Z|.]+)$'
-            transcript_p = re.compile(transcript_regex)
-            m = transcript_p.match(rest_record_id)
-            if m:
-                transcript = m.group(1)
-            else:
-                raise Exception("Unexpected record_id format: {}".format(record_id))
+            (count, gene, transcript) = rest_record_id.split(".", 2)
             (parsed_aa_change, pos, wt_aa, mt_aa) = index_to_aggregate_report_aa_change(aa_change, variant_type)
             if line['Best Transcript'] == transcript and line['AA Change'] == parsed_aa_change:
                 return (mt_records_dict[record_id], wt_records_dict[record_id], variant_type, mt_aa, wt_aa)

diff --git a/pvactools/tools/pvacseq/generate_protein_fasta.py b/pvactools/tools/pvacseq/generate_protein_fasta.py
@@ -166,13 +166,7 @@ def parse_files(output_file, temp_dir, mutant_only, input_tsv, aggregate_report_
                         continue
                 else:
                     (rest_record_id, variant_type, aa_change) = record_id.rsplit(".", 2)
-                    transcript_regex = '^.*(ENST[0-9|.]+)$'
-                    transcript_p = re.compile(transcript_regex)
-                    m = transcript_p.match(rest_record_id)
-                    if m:
-                        transcript = m.group(1)
-                    else:
-                        raise Exception("Unexpected record_id format: {}".format(record_id))
+                    (peptide_type, count, gene, transcript) = rest_record_id.split(".", 3)
                     (parsed_aa_change, _, _, _) = index_to_aggregate_report_aa_change(aa_change, variant_type)
                     matches = [i for i in tsv_indexes if i['Best Transcript'] == transcript and i['AA Change'] == parsed_aa_change and i['Evaluation'] in aggregate_report_evaluation]
                     if len(matches) == 0:

diff --git a/pvactools/tools/pvacview/server.R b/pvactools/tools/pvacview/server.R
@@ -96,7 +96,13 @@ server <- shinyServer(function(input, output, session) {
     df$allele_specific_anchors <- df$metricsData$`allele_specific_anchors`
     df$anchor_contribution <- df$metricsData$`anchor_contribution_threshold`
     hla <- df$metricsData$alleles
-    converted_hla_names <- unlist(lapply(hla, function(x) {strsplit(x, "HLA-")[[1]][2]}))
+    converted_hla_names <- unlist(lapply(hla, function(x) {
+      if (grepl("HLA-", x)) {
+        strsplit(x, "HLA-")[[1]][2]
+      } else {
+        x
+      }
+    }))
     if (!("Ref Match" %in% colnames(df$mainTable))) {
       df$mainTable$`Ref Match` <- "Not Run"
     }
@@ -172,7 +178,13 @@ server <- shinyServer(function(input, output, session) {
      df$allele_specific_anchors <- df$metricsData$`allele_specific_anchors`
      df$anchor_contribution <- df$metricsData$`anchor_contribution_threshold`
      hla <- df$metricsData$alleles
-     converted_hla_names <- unlist(lapply(hla, function(x) {strsplit(x, "HLA-")[[1]][2]}))
+     converted_hla_names <- unlist(lapply(hla, function(x) {
+       if (grepl("HLA-", x)) {
+         strsplit(x, "HLA-")[[1]][2]
+       } else {
+         x
+       }
+     }))
      if (!("Ref Match" %in% colnames(df$mainTable))) {
        df$mainTable$`Ref Match` <- "Not Run"
      }

diff --git a/setup.py b/setup.py
@@ -51,7 +51,7 @@
 
 setup(
     name="pvactools",
-    version="4.0.3",
+    version="4.0.4",
     packages=[
         "pvactools.tools",
         "pvactools.tools.pvacbind",

diff --git a/tests/test_data/calculate_reference_proteome_similarity/Test.mouse.fasta b/tests/test_data/calculate_reference_proteome_similarity/Test.mouse.fasta
@@ -1,4 +1,4 @@
->WT.Rp1.ENSMUST00000027032.missense.1453N/S
+>WT.1.Rp1.ENSMUST00000027032.missense.1453N/S
 IAGTLKFNPETDYLTGTDG
->MT.Rp1.ENSMUST00000027032.missense.1453N/S
+>MT.1.Rp1.ENSMUST00000027032.missense.1453N/S
 IAGTLKFNPQTDYLTGTDG