mgnify-pipelines-toolkit 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py

@@ -46,18 +46,11 @@ def get_read_count(read_path, type='fastq'):
         ]
         zcat_proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
-        cmd = [
-            'sed',
-            '-n',
-            '1~4p',
-        ]
-        sed_proc = subprocess.Popen(cmd, stdin=zcat_proc.stdout, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-
         cmd = [
             'wc',
             '-l'
         ]
-        wc_proc = subprocess.Popen(cmd, stdin=sed_proc.stdout, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        wc_proc = subprocess.Popen(cmd, stdin=zcat_proc.stdout, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         stdout, stderr = wc_proc.communicate()
 
     elif type == 'fasta':
@@ -78,6 +71,9 @@ def get_read_count(read_path, type='fastq'):
 
     read_count = int(read_count)
 
+    if type == 'fastq':
+        read_count /= 4
+
     return read_count
 
 def build_cons_seq(cons_list, read_count, cons_threshold=0.80, do_not_include=None, counter=1, max_line_count=None):

mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py

@@ -25,13 +25,14 @@ from mgnify_pipelines_toolkit.constants.tax_ranks import _SILVA_TAX_RANKS, _PR2_
 logging.basicConfig(level=logging.DEBUG)
 
 def parse_args():
-
     parser = argparse.ArgumentParser()
 
     parser.add_argument("-t", "--taxa", required=True, type=str, help="Path to taxa file")
     parser.add_argument("-f", "--fwd", required=True, type=str, help="Path to DADA2 forward map file")
     parser.add_argument("-r", "--rev", required=False, type=str, help="Path to DADA2 reverse map file")
-    parser.add_argument("-a", "--amp", required=True, type=str, help="Path to extracted amp_region reads from inference subworkflow")
+    parser.add_argument(
+        "-a", "--amp", required=True, type=str, help="Path to extracted amp_region reads from inference subworkflow"
+    )
     parser.add_argument("-hd", "--headers", required=True, type=str, help="Path to fastq headers")
     parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
 
@@ -48,7 +49,6 @@ def parse_args():
 
 
 def order_df(taxa_df):
-
     if len(taxa_df.columns) == 9:
         taxa_df = taxa_df.sort_values(_SILVA_TAX_RANKS, ascending=True)
     elif len(taxa_df.columns) == 10:
@@ -60,11 +60,9 @@ def order_df(taxa_df):
     return taxa_df
 
 def make_tax_assignment_dict_silva(taxa_df, asv_dict):
-
     tax_assignment_dict = defaultdict(int)
 
     for i in range(len(taxa_df)):
-        
         sorted_index = taxa_df.index[i]
         asv_num = taxa_df.iloc[i, 0]
         asv_count = asv_dict[asv_num]
@@ -78,7 +76,7 @@ def make_tax_assignment_dict_silva(taxa_df, asv_dict):
         c = taxa_df.loc[sorted_index, "Class"]
         o = taxa_df.loc[sorted_index, "Order"]
         f = taxa_df.loc[sorted_index, "Family"]
-        g = taxa_df.loc[sorted_index, "Genus"]        
+        g = taxa_df.loc[sorted_index, "Genus"]
         s = taxa_df.loc[sorted_index, "Species"]
 
         tax_assignment = ""
@@ -142,11 +140,9 @@ def make_tax_assignment_dict_silva(taxa_df, asv_dict):
     return tax_assignment_dict
 
 def make_tax_assignment_dict_pr2(taxa_df, asv_dict):
-
     tax_assignment_dict = defaultdict(int)
 
     for i in range(len(taxa_df)):
-        
         sorted_index = taxa_df.index[i]
         asv_num = taxa_df.iloc[i, 0]
         asv_count = asv_dict[asv_num]
@@ -162,12 +158,11 @@ def make_tax_assignment_dict_pr2(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"]         
+        s = taxa_df.loc[sorted_index, "Species"]
 
         tax_assignment = ""
 
         while True:
-
             if d != "0":
                 d = "_".join(d.split(" "))
                 tax_assignment += d
@@ -228,10 +223,28 @@ def make_tax_assignment_dict_pr2(taxa_df, asv_dict):
 
     return tax_assignment_dict
 
-def main():
+def generate_asv_count_dict(asv_dict):
+
+    res_dict = defaultdict(list)
+
+    for asv_id, count in asv_dict.items():
+
+        if count == 0:
+            continue
+
+        res_dict['asv'].append(asv_id)
+        res_dict['count'].append(count)
+
+    res_df = pd.DataFrame.from_dict(res_dict)
+    res_df = res_df.sort_values(by='asv', ascending=True)
+    res_df = res_df.sort_values(by='count', ascending=False)
 
+    return res_df
+
+
+def main():
     _TAXA, _FWD, _REV, _AMP, _HEADERS, _SAMPLE = parse_args()
-    
+
     fwd_fr = open(_FWD, "r")
     paired_end = True
 
@@ -244,36 +257,25 @@ def main():
     taxa_df = pd.read_csv(_TAXA, sep="\t", dtype=str)
     taxa_df = taxa_df.fillna("0")
     taxa_df = order_df(taxa_df)
-    
-    amp_reads = [ read.strip() for read in list(open(_AMP, "r")) ]
-    headers = [ read.split(" ")[0][1:] for read in list(open(_HEADERS, "r")) ]
+
+    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])
 
     asv_dict = defaultdict(int)
 
     counter = -1
     for line_fwd in fwd_fr:
-
         counter += 1
         line_fwd = line_fwd.strip()
-        fwd_asvs = line_fwd.split(",")
-
-        if paired_end:
-            line_rev = next(rev_fr).strip()
-            rev_asvs = line_rev.split(",")        
-            asv_intersection = list(set(fwd_asvs).intersection(rev_asvs))
-            
-            if len(asv_intersection) == 0:
-                continue
-            
-            if len(asv_intersection) == 1 and asv_intersection[0] == "0":
-                continue
-        else:
-            asv_intersection = fwd_asvs
+
+        if line_fwd == '0':
+            continue
 
         if headers[counter] in amp_reads:
-            asv_dict[f"seq_{int(asv_intersection[0]) - 1}"] += 1
-    
+            asv_dict[f"seq_{line_fwd}"] += 1
+
     fwd_fr.close()
     if paired_end:
         rev_fr.close()
@@ -290,7 +292,9 @@ def main():
     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")
-    
+
+    asv_count_df = generate_asv_count_dict(asv_dict)
+    asv_count_df.to_csv(f'./{_SAMPLE}_{amp_region}_asv_read_counts.tsv', sep='\t', index=False)
 
 if __name__ == "__main__":
-    main()
+    main()

mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py

@@ -23,10 +23,16 @@ import pandas as pd
 logging.basicConfig(level=logging.DEBUG)
 
 def parse_args():
-
     parser = argparse.ArgumentParser()
     parser.add_argument("-i", "--input", required=True, type=str, help="Input from MAPseq output")
-    parser.add_argument("-l", "--label", choices=['DADA2-SILVA', 'DADA2-PR2'], required=True, type=str, help="Database label - either DADA2-SILVA or DADA2-PR2")
+    parser.add_argument(
+        "-l",
+        "--label",
+        choices=["DADA2-SILVA", "DADA2-PR2"],
+        required=True,
+        type=str,
+        help="Database label - either DADA2-SILVA or DADA2-PR2",
+    )
     parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
 
     args = parser.parse_args()
@@ -38,20 +44,19 @@ def parse_args():
     return _INPUT, _LABEL, _SAMPLE
 
 def parse_label(label):
-
     silva_short_ranks = ["sk__", "k__", "p__", "c__", "o__", "f__", "g__", "s__"]
     pr2_short_ranks = ["d__", "sg__", "dv__", "sdv__", "c__", "o__", "f__", "g__", "s__"]
 
     silva_long_ranks = ["Superkingdom", "Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
     pr2_long_ranks = ["Domain", "Supergroup", "Division", "Subdivision", "Class", "Order", "Family", "Genus", "Species"]
 
-    chosen_short_ranks = ''
-    chosen_long_ranks = ''
+    chosen_short_ranks = ""
+    chosen_long_ranks = ""
 
-    if label == 'DADA2-SILVA':
+    if label == "DADA2-SILVA":
         chosen_short_ranks = silva_short_ranks
         chosen_long_ranks = silva_long_ranks
-    elif label == 'DADA2-PR2':
+    elif label == "DADA2-PR2":
         chosen_short_ranks = pr2_short_ranks
         chosen_long_ranks = pr2_long_ranks
     else:
@@ -61,26 +66,28 @@ def parse_label(label):
     return chosen_short_ranks, chosen_long_ranks
 
 def parse_mapseq(mseq_df, short_ranks, long_ranks):
-
     res_dict = defaultdict(list)
 
     for i in range(len(mseq_df)):
         asv_id = mseq_df.iloc[i, 0]
-        tax_ass = mseq_df.iloc[i, 1].split(';')
 
-        res_dict['ASV'].append(asv_id)
-        
-        for j in range(len(short_ranks)):
+        if pd.isna(mseq_df.iloc[i, 1]):
+            tax_ass = [short_ranks[0]]
+        else:
+            tax_ass = mseq_df.iloc[i, 1].split(";")
+
+        res_dict["ASV"].append(asv_id)
 
+        for j in range(len(short_ranks)):
             curr_rank = long_ranks[j]
-            
+
             if j >= len(tax_ass):
                 # This would only be true if the assigned taxonomy is shorter than the total reference database taxononmy
                 # so fill each remaining rank with its respective short rank blank
                 curr_tax = short_ranks[j]
             else:
                 curr_tax = tax_ass[j]
-            
+
             res_dict[curr_rank].append(curr_tax)
     res_df = pd.DataFrame.from_dict(res_dict)
 
@@ -91,27 +98,33 @@ def process_blank_tax_ends(res_df, ranks):
     # while avoiding making blanks in the middle as NAs
 
     for i in range(len(res_df)):
-        last_empty_rank = ''
+        last_empty_rank = ""
         currently_empty = False
-        for j in reversed(range(len(ranks))): # Parse an assignment backwards, from Species all the way to Superkingdom/Domain
-            curr_rank = res_df.iloc[i, j+1]
+        for j in reversed(
+            range(len(ranks))
+        ):  # Parse an assignment backwards, from Species all the way to Superkingdom/Domain
+            curr_rank = res_df.iloc[i, j + 1]
             if curr_rank in ranks:
-                if last_empty_rank == '': # Last rank is empty, start window of consecutive blanks 
-                    last_empty_rank = j+1
+                if last_empty_rank == "":  # Last rank is empty, start window of consecutive blanks
+                    last_empty_rank = j + 1
                     currently_empty = True
-                elif currently_empty: # If we're in a window of consecutive blank assignments that started at the beginning
-                    last_empty_rank = j+1
+                elif (
+                    currently_empty
+                ):  # If we're in a window of consecutive blank assignments that started at the beginning
+                    last_empty_rank = j + 1
                 else:
                     break
             else:
                 break
-        if last_empty_rank != '':
-            res_df.iloc[i, last_empty_rank:] = 'NA'
+        if last_empty_rank != "":
+            res_df.iloc[i, last_empty_rank:] = "NA"
+        if last_empty_rank == 1:
+            res_df.iloc[i, 1] = ranks[0]
 
     return res_df
 
-def main():
-    
+
+def main():    
     _INPUT, _LABEL, _SAMPLE = parse_args()
 
     mseq_df = pd.read_csv(_INPUT, header=1, delim_whitespace=True, usecols=[0, 12])
@@ -123,4 +136,4 @@ def main():
     final_res_df.to_csv(f"./{_SAMPLE}_{_LABEL}_asv_taxa.tsv", sep="\t", index=False)
 
 if __name__ == "__main__":
-    main()
+    main()

mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py

@@ -0,0 +1,116 @@
+#!/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.
+
+import argparse
+from collections import defaultdict
+import re
+
+from Bio import SeqIO
+import pandas as pd
+
+from mgnify_pipelines_toolkit.constants.var_region_coordinates import REGIONS_16S_BACTERIA, REGIONS_16S_ARCHAEA, REGIONS_18S
+
+STRAND_FWD = "fwd"
+STRAND_REV = "rev"
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("-i", "--input", required=True, type=str, help="Path to cmsearch_deoverlap_tblout file")
+    parser.add_argument("-f", "--fasta", required=True, type=str, help="Path to concatenated primers fasta file")
+    parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
+    args = parser.parse_args()
+
+    _INPUT = args.input
+    _FASTA = args.fasta
+    _SAMPLE = args.sample
+
+    return _INPUT, _FASTA, _SAMPLE
+
+
+def get_amp_region(beg, strand, model):
+    prev_region = ""
+
+    for region, region_coords in model.items():
+
+        region_beg = region_coords[0]
+        beg_diff = region_beg - beg
+
+        if strand == STRAND_FWD:
+            if beg_diff > 0:
+                return region
+        else:
+            if beg_diff > 0:
+                return prev_region
+
+        prev_region = region
+
+    return prev_region
+
+
+def main():
+    _INPUT, _FASTA, _SAMPLE = parse_args()    
+    res_dict = defaultdict(list)
+    fasta_dict = SeqIO.to_dict(SeqIO.parse(_FASTA, "fasta"))
+
+    with open(_INPUT, "r") as fr:
+        for line in fr:
+            line = line.strip()
+            line = re.sub("[ \t]+", "\t", line)
+            line_lst = line.split("\t")
+
+            primer_name = line_lst[0]
+            rfam = line_lst[3]
+            beg = float(line_lst[5])
+
+            if rfam == "RF00177":
+                gene = "16S"
+                model = REGIONS_16S_BACTERIA
+            elif rfam == "RF01959":
+                gene = "16S"
+                model = REGIONS_16S_ARCHAEA
+            elif rfam == "RF01960":
+                gene = "18S"
+                model = REGIONS_18S
+            else:
+                continue
+
+            res_dict["Run"].append(_SAMPLE)
+            res_dict["AssertionEvidence"].append("ECO_0000363")
+            res_dict["AssertionMethod"].append("automatic assertion")
+
+            strand = ""
+
+            if "F" in primer_name:
+                strand = STRAND_FWD
+            elif "R" in primer_name:
+                strand = STRAND_REV
+
+            amp_region = get_amp_region(beg, strand, model)
+            primer_seq = str(fasta_dict[primer_name].seq)
+
+            res_dict["Gene"].append(gene)
+            res_dict["VariableRegion"].append(amp_region)
+            res_dict["PrimerName"].append(primer_name)
+            res_dict["PrimerStrand"].append(strand)
+            res_dict["PrimerSeq"].append(primer_seq)
+
+    res_df = pd.DataFrame.from_dict(res_dict)
+    res_df.to_csv(f"./{_SAMPLE}_primer_validation.tsv", sep="\t", index=False)
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/constants/var_region_coordinates.py

@@ -15,36 +15,36 @@
 # limitations under the License.
 
 REGIONS_16S_BACTERIA = {
-    'V1': [69, 92],
-    'V2': [131, 239],
-    'V3': [430, 487],
-    'V4': [566, 672],
-    'V5': [812, 869],
-    'V6': [976, 1033],
-    'V7': [1107, 1164],
-    'V8': [1234, 1285],
-    'V9': [1426, 1456]
+    "V1": [69, 92],
+    "V2": [131, 239],
+    "V3": [430, 487],
+    "V4": [566, 672],
+    "V5": [812, 869],
+    "V6": [976, 1033],
+    "V7": [1107, 1164],
+    "V8": [1234, 1285],
+    "V9": [1426, 1456]
 }
 
 REGIONS_16S_ARCHAEA = {
-    'V1': [61, 79],
-    'V2': [114, 223],
-    'V3': [397, 436],
-    'V4': [516, 623],
-    'V5': [763, 824],
-    'V6': [932, 982],
-    'V7': [1056, 1119],
-    'V8': [1189, 1240],
-    'V9': [1372, 1410]
+    "V1": [61, 79],
+    "V2": [114, 223],
+    "V3": [397, 436],
+    "V4": [516, 623],
+    "V5": [763, 824],
+    "V6": [932, 982],
+    "V7": [1056, 1119],
+    "V8": [1189, 1240],
+    "V9": [1372, 1410]
 }
 
 REGIONS_18S = {
-    'V1': [69, 109],
-    'V2': [136, 298],
-    'V3': [474, 545],
-    'V4': [627, 873],
-    'V5': [1059, 1102],
-    'V7': [1366, 1454],
-    'V8': [1526, 1608],
-    'V9': [1728, 1795]
+    "V1": [69, 109],
+    "V2": [136, 298],
+    "V3": [474, 545],
+    "V4": [627, 873],
+    "V5": [1059, 1102],
+    "V7": [1366, 1454],
+    "V8": [1526, 1608],
+    "V9": [1728, 1795]
 }

{mgnify_pipelines_toolkit-0.1.2.dist-info → mgnify_pipelines_toolkit-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mgnify_pipelines_toolkit
-Version: 0.1.2
+Version: 0.1.4
 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-0.1.2.dist-info → mgnify_pipelines_toolkit-0.1.4.dist-info}/RECORD

@@ -1,13 +1,14 @@
 mgnify_pipelines_toolkit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=OkQsiVTh6Y-bYPZMHOnD9xn0dd9bENySFwgibK6x6CU,6549
+mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py,sha256=EvWTFV4gGn0SkrjwC2hzvNGSXFLeyFDmVj2QDa5DmtE,6402
 mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=fNjzWpXjqpQNRyWG6CoROyHAvA4lZsvPh8sxDpjyMkY,5141
 mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py,sha256=pBNpqHFb0zzWgTD1mY3Q5MslQ5nmT99-pSHpyngVEuo,7159
 mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=BCzLlfvRqiPC-YwzET901f_d0anYt1zpf5y0iOCQnvs,5191
 mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=89LKH4rvqRydAEGvfaWqIClcitJ1Vbu7b5d4FApzGp4,18392
 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=F0dGxsr7r_6Ogjtildwz2xiPboqHVpZyz_9EHRA7BVE,8507
-mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=xTEs_6KSP8WT4GSi0SAoShqRuXyGTz5fWaV4QJj0WcQ,4503
+mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=-Kh9KlEuWWFAWUaNjkCxl-L3IdEMURLM3UKb2Tf81CM,8605
+mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=lWVIhDxfsTuDzWjjUlMGx3RL7iD_Yy8m9Ppc9wjfCFg,4765
+mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=F4ALSuH8N-0hHUqPCFwHgoAnteb2Ft3tUN9j6DaD5h8,3539
 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
@@ -18,10 +19,10 @@ mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=glvql2Y-BTyA1hTIZ
 mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=oVeeCy33bY1WJ-rffOULZ3ogi48Jz0FfTS73MPTur-A,1095
 mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=fP97JvlUdxJBakJ694VresIY8-N3pcU99m7kZ9buKys,867
 mgnify_pipelines_toolkit/constants/thresholds.py,sha256=7J3caCikkEcLdKF4zSR0z8qMQw4-h9aSkSbFbS0LNg4,873
-mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=GAW1DdQ9IM3dCBMVMS6ZNtxVFEGwEGdJaDNorVAzR1g,1303
-mgnify_pipelines_toolkit-0.1.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-0.1.2.dist-info/METADATA,sha256=5P593pTSm6ZscTlb-cRvSX7U_T9dgFv2rPGlPCmkcZc,4950
-mgnify_pipelines_toolkit-0.1.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-mgnify_pipelines_toolkit-0.1.2.dist-info/entry_points.txt,sha256=H-wTSCg9M2719od6FW4w4nr6MMV00KnA4UgWXafRyNc,1204
-mgnify_pipelines_toolkit-0.1.2.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-0.1.2.dist-info/RECORD,,
+mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=E8Cd3A1Hj9M95zw9Ut-2x8sE6_PlH6RJJEoikyZUMaQ,1303
+mgnify_pipelines_toolkit-0.1.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-0.1.4.dist-info/METADATA,sha256=1s--DpsRsfAyM2HomRYTAfLF3shjuZ5o0CF-FoceZmw,4950
+mgnify_pipelines_toolkit-0.1.4.dist-info/WHEEL,sha256=Z4pYXqR_rTB7OWNDYFOm1qRk0RX6GFP2o8LgvP453Hk,91
+mgnify_pipelines_toolkit-0.1.4.dist-info/entry_points.txt,sha256=K8nqnyAQG9jqHGgIfMIaCIe20u5a0FFCCqJWi4DoD2U,1306
+mgnify_pipelines_toolkit-0.1.4.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-0.1.4.dist-info/RECORD,,

{mgnify_pipelines_toolkit-0.1.2.dist-info → mgnify_pipelines_toolkit-0.1.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (70.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.1.2.dist-info → mgnify_pipelines_toolkit-0.1.4.dist-info}/entry_points.txt

@@ -9,6 +9,7 @@ get_subunits_coords = mgnify_pipelines_toolkit.analysis.shared.get_subunits_coor
 make_asv_count_table = mgnify_pipelines_toolkit.analysis.amplicon.make_asv_count_table:main
 mapseq2biom = mgnify_pipelines_toolkit.analysis.shared.mapseq2biom:main
 mapseq_to_asv_table = mgnify_pipelines_toolkit.analysis.amplicon.mapseq_to_asv_table:main
+primer_val_classification = mgnify_pipelines_toolkit.analysis.amplicon.primer_val_classification:main
 remove_ambiguous_reads = mgnify_pipelines_toolkit.analysis.amplicon.remove_ambiguous_reads:main
 rev_comp_se_primers = mgnify_pipelines_toolkit.analysis.amplicon.rev_comp_se_primers:main
 standard_primer_matching = mgnify_pipelines_toolkit.analysis.amplicon.standard_primer_matching:main