mgnify-pipelines-toolkit 0.1.6__tar.gz → 0.1.8__tar.gz

{mgnify_pipelines_toolkit-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mgnify_pipelines_toolkit
-Version: 0.1.6
+Version: 0.1.8
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0

{mgnify_pipelines_toolkit-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py

@@ -277,6 +277,8 @@ def main():
     taxa_df = taxa_df.fillna("0")
     taxa_df = order_df(taxa_df)
 
+    asv_list = taxa_df.ASV.to_list()
+
     amp_reads = [read.strip() for read in list(open(amp, "r"))]
     headers = [read.split(" ")[0][1:] for read in list(open(headers, "r"))]
     amp_region = ".".join(amp.split(".")[1:3])
@@ -288,7 +290,7 @@ def main():
         counter += 1
         line_fwd = line_fwd.strip()
 
-        if line_fwd == "0":
+        if line_fwd == "0" or f"seq_{line_fwd}" not in asv_list:
             continue
 
         if headers[counter] in amp_reads:

{mgnify_pipelines_toolkit-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/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-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/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:

{mgnify_pipelines_toolkit-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mgnify_pipelines_toolkit
-Version: 0.1.6
+Version: 0.1.8
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0

{mgnify_pipelines_toolkit-0.1.6 → mgnify_pipelines_toolkit-0.1.8}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "0.1.6"
+version = "0.1.8"
 readme = "README.md"
 license = {text = "Apache Software License 2.0"}
 authors = [