Dev (#22)

* update large file hook to increase size from 500KB to 20MB

* add antismash_gff_builder unit test

* add script that prints out current version of the package

* add simple unit test that just checks success

* add regex check in unit test for get_mpt_version

* remove failing exit codes for sanity check scripts - they should exit peacefully

* make pytest and lint workflows trigger on dev as well as main

* update pyproject.toml for versoin 0.1.6

* no need to run pytest on push to dev

* add output file from antismash_gff_builder unit test to repo

* fix get_subunits bug, add end_region check to primver_val_classification

* bump version

mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py

@@ -58,19 +58,20 @@ def parse_args():
     return input, fasta, sample
 
 
-def get_amp_region(beg, strand, model):
+def get_amp_region(beg, end, strand, model):
     prev_region = ""
 
     for region, region_coords in model.items():
 
         region_beg = region_coords[0]
         beg_diff = region_beg - beg
+        end_diff = region_beg - end
 
         if strand == STRAND_FWD:
-            if beg_diff > 0:
+            if beg_diff > 0 and end_diff > 0:
                 return region
         else:
-            if beg_diff > 0:
+            if beg_diff > 0 and end_diff > 0:
                 return prev_region
 
         prev_region = region
@@ -92,6 +93,7 @@ def main():
             primer_name = line_lst[0]
             rfam = line_lst[3]
             beg = float(line_lst[5])
+            end = float(line_lst[6])
 
             if rfam == "RF00177":
                 gene = "16S"
@@ -116,7 +118,7 @@ def main():
             elif "R" in primer_name:
                 strand = STRAND_REV
 
-            amp_region = get_amp_region(beg, strand, model)
+            amp_region = get_amp_region(beg, end, strand, model)
             primer_seq = str(fasta_dict[primer_name].seq)
 
             res_dict["Gene"].append(gene)

mgnify_pipelines_toolkit/analysis/shared/get_subunits.py

@@ -102,7 +102,7 @@ def main():
     ]
     open_files = {}
     for record in SeqIO.parse(args.input, "fasta"):
-        model = "-".join(record.id.split("/")[0].split("-")[1:])
+        model = "-".join(record.id.split("/")[0].split("-")[-1:])
         if model in coding_rna:
             filename = pattern_dict[model]
         else:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "0.1.6"
+version = "0.1.7"
 readme = "README.md"
 license = {text = "Apache Software License 2.0"}
 authors = [