mgnify-pipelines-toolkit 0.0.7__py3-none-any.whl → 0.0.9__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py

@@ -449,7 +449,7 @@ def parse_args(argv):
     return parser.parse_args(argv)
 
 
-def main(argv):
+def main(argv=None):
     t_start = time.perf_counter()  # time the run
     args = parse_args(argv)
     if not os.path.isdir(args.output_dir):
@@ -481,7 +481,7 @@ def main(argv):
 
 
 if __name__ == '__main__':
-    main(sys.argv[1:])
+    main()
 
 # don't print json
 # name the tsv file better

mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py

@@ -16,8 +16,14 @@
 
 import argparse
 from collections import defaultdict
+import logging
+
 import pandas as pd
 
+from mgnify_pipelines_toolkit.constants.tax_ranks import _SILVA_TAX_RANKS, _PR2_TAX_RANKS
+
+logging.basicConfig(level=logging.DEBUG)
+
 def parse_args():
 
     parser = argparse.ArgumentParser()
@@ -43,10 +49,13 @@ def parse_args():
 
 def order_df(taxa_df):
 
-    if len(taxa_df.columns) == 7:
-        taxa_df = taxa_df.sort_values(["Kingdom", "Phylum", "Class", "Order", "Family", "Genus"], ascending=True)
+    if len(taxa_df.columns) == 8:
+        taxa_df = taxa_df.sort_values(_SILVA_TAX_RANKS, ascending=True)
     elif len(taxa_df.columns) == 10:
-        taxa_df = taxa_df.sort_values(["Domain", "Supergroup", "Division", "Subdivision", "Class", "Order", "Family", "Genus", "Species"], ascending=True)
+        taxa_df = taxa_df.sort_values(_PR2_TAX_RANKS, ascending=True)
+    else:
+        logging.error("Data frame not the right size, something wrong.")
+        exit(1)
 
     return taxa_df
 
@@ -68,6 +77,7 @@ def make_tax_assignment_dict_silva(taxa_df, asv_dict):
         o = taxa_df.loc[sorted_index, "Order"]
         f = taxa_df.loc[sorted_index, "Family"]
         g = taxa_df.loc[sorted_index, "Genus"]        
+        s = taxa_df.loc[sorted_index, "Species"]
 
         tax_assignment = ""
 
@@ -109,6 +119,11 @@ def make_tax_assignment_dict_silva(taxa_df, asv_dict):
             if g != "0":
                 g = "_".join(g.split(" "))
                 tax_assignment += f"\tg__{g}"
+            else:
+                break
+            if s != "0":
+                s = "_".join(s.split(" "))
+                tax_assignment += f"\ts__{s}"
             break
 
         if tax_assignment == "":
@@ -147,10 +162,6 @@ def make_tax_assignment_dict_pr2(taxa_df, asv_dict):
             if d != "0":
                 d = "_".join(d.split(" "))
                 tax_assignment += f"d__{d}"
-                # if d == "Archaea" or d == "Bacteria":
-                #     tax_assignment += f"d__{d}"
-                # elif d == "Eukaryota":
-                #     tax_assignment += f"d__Eukaryota"
             else:
                 break
 
@@ -159,7 +170,6 @@ def make_tax_assignment_dict_pr2(taxa_df, asv_dict):
                 tax_assignment += f"\tsg__{sg}"
             else:
                 break
-
             if dv != "0":
                 dv = "_".join(dv.split(" "))
                 tax_assignment += f"\tdv__{dv}"
@@ -167,7 +177,6 @@ def make_tax_assignment_dict_pr2(taxa_df, asv_dict):
             if sdv != "0":
                 sdv = "_".join(sdv.split(" "))
                 tax_assignment += f"\tsdv__{sdv}"
-
             if c != "0":
                 c = "_".join(c.split(" "))
                 tax_assignment += f"\tc__{c}"
@@ -250,12 +259,16 @@ def main():
     if paired_end:
         rev_fr.close()
 
-    if len(taxa_df.columns) == 7:
+    ref_db = ""
+
+    if len(taxa_df.columns) == 8:
         tax_assignment_dict = make_tax_assignment_dict_silva(taxa_df, asv_dict)
+        ref_db = "silva"
     elif len(taxa_df.columns) == 10:
         tax_assignment_dict = make_tax_assignment_dict_pr2(taxa_df, asv_dict)
+        ref_db = "pr2"
 
-    with open(f"./{_SAMPLE}_{amp_region}_asv_krona_counts.txt", "w") as fw:
+    with open(f"./{_SAMPLE}_{amp_region}_{ref_db}_asv_krona_counts.txt", "w") as fw:
         for tax_assignment, count in tax_assignment_dict.items():
             fw.write(f"{count}\t{tax_assignment}\n")
     

mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py

@@ -21,14 +21,14 @@ import gzip
 
 from Bio import SeqIO, bgzf
 
-def parse_args(argv=None):
+def parse_args():
 
     parser = argparse.ArgumentParser()
 
     parser.add_argument("-f", "--fwd", required=True, type=str, help="Path to forward (or single-end) fastq file")
     parser.add_argument("-r", "--rev", required=False, type=str, help="Path to reverse fastq file")
     parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
-    args = parser.parse_args(argv)
+    args = parser.parse_args()
     
     _FWD = args.fwd
     _REV = args.rev
@@ -37,9 +37,9 @@ def parse_args(argv=None):
     return _FWD, _REV, _SAMPLE
 
 
-def main(argv=None):
+def main():
 
-    _FWD, _REV, _SAMPLE = parse_args(argv)
+    _FWD, _REV, _SAMPLE = parse_args()
 
     fwd_handle = gzip.open(_FWD, "rt")
     fwd_reads = SeqIO.to_dict(SeqIO.parse(fwd_handle, "fastq"))
@@ -54,25 +54,35 @@ def main(argv=None):
         rev_reads = SeqIO.to_dict(SeqIO.parse(rev_handle, "fastq"))
         rev_handle.close()
     
-    remove_lst = []
+    remove_set = set()
 
     for read_id in fwd_reads.keys():
 
-        if "N" in str(fwd_reads[read_id].seq):
-            print(read_id)
-            remove_lst.append(read_id)
+        fwd_read_seq = str(fwd_reads[read_id].seq)
+        if len(fwd_read_seq) < 100:
+            remove_set.add(read_id)
             continue
-        elif paired_end and "N" in str(rev_reads[read_id].seq):
+        elif "N" in fwd_read_seq:
             print(read_id)
-            remove_lst.append(read_id)
+            remove_set.add(read_id)
             continue
 
-    [ fwd_reads.pop(read_id) for read_id in remove_lst ]
+        if paired_end:
+            rev_read_seq = str(rev_reads[read_id].seq)
+            if len(rev_read_seq) < 100:
+                print(read_id)
+                remove_set.add(read_id)
+                continue
+            elif "N" in rev_read_seq:
+                print(read_id)
+                remove_set.add(read_id)
+                continue
+
+    [ fwd_reads.pop(read_id) for read_id in remove_set ]
     if paired_end:
-        [ rev_reads.pop(read_id) for read_id in remove_lst ]
+        [ rev_reads.pop(read_id) for read_id in remove_set ]
 
     if paired_end:
-        
         fwd_handle = bgzf.BgzfWriter(f"./{_SAMPLE}_noambig_1.fastq.gz", "wb")
         rev_handle = bgzf.BgzfWriter(f"./{_SAMPLE}_noambig_2.fastq.gz", "wb")
         

mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py

@@ -15,18 +15,17 @@
 # limitations under the License.
 
 import argparse
-import sys
 
 from Bio import Seq, SeqIO
 
-def parse_args(argv=None):
+def parse_args():
 
     parser = argparse.ArgumentParser()
 
     parser.add_argument("-i", "--input", required=True, type=str, help="Path to finalised primer list fasta file")
     parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
     parser.add_argument("-o", "--output", required=True, type=str, help="Output path")
-    args = parser.parse_args(argv)
+    args = parser.parse_args()
   
     _INPUT = args.input
     _SAMPLE = args.sample
@@ -34,9 +33,9 @@ def parse_args(argv=None):
 
     return _INPUT, _SAMPLE, _OUTPUT
 
-def main(argv=None):
+def main():
     
-    _INPUT, _SAMPLE, _OUTPUT = parse_args(argv)
+    _INPUT, _SAMPLE, _OUTPUT = parse_args()
 
     primers_dict = SeqIO.to_dict(SeqIO.parse(_INPUT, "fasta"))
     

mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py

@@ -101,7 +101,7 @@ def main():
     notaxidfile_header = []
 
     if args.taxid:
-        if args.label.startswith("UNITE"):
+        if args.label.startswith("UNITE") or args.label.startswith("PR2"):
             output_header = [
                 "# OTU ID",
                 args.label,

mgnify_pipelines_toolkit/constants/tax_ranks.py

@@ -0,0 +1,18 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 2024 EMBL - European Bioinformatics Institute
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+_SILVA_TAX_RANKS = ["Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
+_PR2_TAX_RANKS = ["Domain", "Supergroup", "Division", "Subdivision", "Class", "Order", "Family", "Genus", "Species"]

{mgnify_pipelines_toolkit-0.0.7.dist-info → mgnify_pipelines_toolkit-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mgnify_pipelines_toolkit
-Version: 0.0.7
+Version: 0.0.9
 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-0.0.7.dist-info → mgnify_pipelines_toolkit-0.0.9.dist-info}/RECORD

@@ -4,20 +4,21 @@ mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=cF_7zsdJTzIC
 mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=fNjzWpXjqpQNRyWG6CoROyHAvA4lZsvPh8sxDpjyMkY,5141
 mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py,sha256=leUjaD59EXA39HaMSDm909DGgNDuHVi-2EnUyBSNIWE,6847
 mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=AUGeYWWpJ8sP5wpPbTq32G3Iai3NV5JQTZz6MQ0CUU4,4935
-mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=kmS5-2SSldXyGElQ11eC4IqwfvwtZXhDWgZQvbPCAgo,18904
+mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=htoZyGuDV_64-4PRGpE2qjxw4VihmY4b-2ktuR03Pgg,18897
 mgnify_pipelines_toolkit/analysis/amplicon/find_mcp_inflection_points.py,sha256=5emeZjk8891IgyL5ygVcr8wMP-hGEJoEs2rcBbseWj0,3536
-mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=CMkD4Uyw1PUJg7npVORtDG7lRYM-MyW45qaQ2gpyEwc,8275
-mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=WsvqAQ_lL_L_XC4vb2lWe0AsYmf1TIsRF6ROfpMz8wU,2845
-mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=v5dgOmaj1FuAoZb9iOhbO_jTeLkfhurqtTlDfHw-7gI,1717
+mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=3ODVM7YxYrPiM95UnbYiKmtN93PdlF_JmjZYTEyoCL8,8468
+mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=yhDJFGD3t3TMfUlBCJGwzlK4IjFwm7Bporwp-aIM8uU,3139
+mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=VoSbou3BAZL4bJes4FsYJvmd45_PjKj8F2sQDIyLDoI,1680
 mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=odGVde7Ct9dS2aqsySWgdgVLCOqfr_ZGeHFcXcuukxs,10846
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=vvhn8O9t1zzD8rIvQ5bDLLgdzogBGKqgKXuMybnHEXA,4551
 mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=hFXUTZb-etmJS7Si3mCCVCXV5ZYN0tP6FSbeiVxG1jo,1879
-mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=65nvJMEQAPaJnpWdFXeYSZkbi0xD6auWe9kdTA4OUaY,5533
+mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=glvql2Y-BTyA1hTIZz2nlmST3SE6LJbep9sKdMH-vaI,5565
 mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=oVeeCy33bY1WJ-rffOULZ3ogi48Jz0FfTS73MPTur-A,1095
-mgnify_pipelines_toolkit-0.0.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-0.0.7.dist-info/METADATA,sha256=NKCi11tTiURD10pfskuBC5LPV_N526ou60E3J73obpM,4779
-mgnify_pipelines_toolkit-0.0.7.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-mgnify_pipelines_toolkit-0.0.7.dist-info/entry_points.txt,sha256=UqG2YtR6sMIwrJHV3Zx9r-hEwkLt8j59ah6Xfs88YDQ,1014
-mgnify_pipelines_toolkit-0.0.7.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-0.0.7.dist-info/RECORD,,
+mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=QOVkxZjMTYwIxCN7L4CLYFQjWoxsuZ4WKlKiTblD4tM,851
+mgnify_pipelines_toolkit-0.0.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-0.0.9.dist-info/METADATA,sha256=ZnCa-e-9xYNpGuhm9E4-rGK1GiCdmqQgdQkWRurvteA,4779
+mgnify_pipelines_toolkit-0.0.9.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+mgnify_pipelines_toolkit-0.0.9.dist-info/entry_points.txt,sha256=UqG2YtR6sMIwrJHV3Zx9r-hEwkLt8j59ah6Xfs88YDQ,1014
+mgnify_pipelines_toolkit-0.0.9.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-0.0.9.dist-info/RECORD,,