mgnify-pipelines-toolkit 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py

@@ -0,0 +1,66 @@
+#!/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
+
+import pandas as pd
+import numpy as np
+
+from mgnify_pipelines_toolkit.constants.thresholds import MIN_AMPLICON_STRATEGY_CHECK
+
+
+def parse_args():
+
+    parser = argparse.ArgumentParser(
+        description="Script that checks the output of assess_mcp_proportions.py to guess whether a FASTQ file is AMPLICON or NOT AMPLICON."
+    )
+    parser.add_argument("-i", "--input", required=True, type=str, help="Input")
+    parser.add_argument("-s", "--sample", required=True, type=str, help="Sample ID")
+    parser.add_argument("-o", "--output", required=True, type=str, help="Output")
+
+    args = parser.parse_args()
+
+    input = args.input
+    sample = args.sample
+    output = args.output
+
+    return input, sample, output
+
+
+def main():
+
+    input, sample, output = parse_args()
+
+    cons_df = pd.read_csv(input, sep="\t")
+
+    cons_values = cons_df.values[0][1:]
+    mean_cons = np.mean(cons_values)
+
+    fw = open(f"{output}/{sample}_library_check_out.txt", "w")
+
+    if mean_cons >= MIN_AMPLICON_STRATEGY_CHECK:
+        print("This data is likely to be AMPLICON.")
+        fw.write("AMPLICON")  # File with "AMPLICON" written as a result.
+
+    else:
+        print("This data is unlikely to be AMPLICON.")
+        # If unlikely to be AMPLICON, the output file will be empty.
+
+    fw.close()
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py

@@ -61,7 +61,7 @@ def main():
             # Pull out the fields that we need
             line = line.strip()
             fields = line.split("\t")
-            
+
             if len(fields) < 14:
                 tax = "Unclassified"
             else:
@@ -168,4 +168,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py

@@ -15,7 +15,6 @@
 # limitations under the License.
 
 _AMBIGUOUS_BASES_DICT = {
-    
     "R": "[AG]",
     "Y": "[CT]",
     "S": "[GC]",
@@ -26,11 +25,10 @@ _AMBIGUOUS_BASES_DICT = {
     "D": "[AGT]",
     "H": "[ACT]",
     "V": "[ACG]",
-    "N": "[ACTG]"
+    "N": "[ACTG]",
 }
 
 _AMBIGUOUS_BASES_DICT_REV = {
-    
     "A,G": "R",
     "C,T": "Y",
     "C,G": "S",
@@ -41,5 +39,5 @@ _AMBIGUOUS_BASES_DICT_REV = {
     "A,G,T": "D",
     "A,C,T": "H",
     "A,C,G": "V",
-    "A,C,G,T": "N"
-}
+    "A,C,G,T": "N",
+}

mgnify_pipelines_toolkit/constants/regex_fasta_header.py

@@ -0,0 +1,20 @@
+#!/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.
+
+FORMAT_REGEX_MAP = {
+    "uniprotkb": r"^(?P<db>\w+)\|(?P<unique_identifier>\w+)\|(?P<entry_name>\w+)\s(?P<protein_name>.+)\sOS=(?P<organism_name>.+)\sOX=(?P<organism_identifier>\d+)(\sGN=(?P<gene_name>.+))?\sPE=(?P<protein_existence>\d+)\sSV=(?P<sequence_version>\d+)",  # noqa: E501
+    "rpxx": r"^(?P<unique_identifier>\S+)\s(?P<entry_name>\S+)\^\|\^.*\^\|\^(?P<protein_name>.+)\^\|\^.*\^\|\^.*\^\|\^(?P<organism_name>.+)\^\|\^(?P<organism_identifier>\d+)\^\|\^(?P<common_tax_name>.+)\^\|\^(?P<common_tax_identifier>\d+)",  # noqa: E501
+}

mgnify_pipelines_toolkit/constants/tax_ranks.py

@@ -14,5 +14,24 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-_SILVA_TAX_RANKS = ["Superkingdom", "Kingdom", "Phylum", "Class", "Order", "Family", "Genus", "Species"]
-_PR2_TAX_RANKS = ["Domain", "Supergroup", "Division", "Subdivision", "Class", "Order", "Family", "Genus", "Species"]
+_SILVA_TAX_RANKS = [
+    "Superkingdom",
+    "Kingdom",
+    "Phylum",
+    "Class",
+    "Order",
+    "Family",
+    "Genus",
+    "Species",
+]
+_PR2_TAX_RANKS = [
+    "Domain",
+    "Supergroup",
+    "Division",
+    "Subdivision",
+    "Class",
+    "Order",
+    "Family",
+    "Genus",
+    "Species",
+]

mgnify_pipelines_toolkit/constants/thresholds.py

@@ -21,4 +21,7 @@ MCP_MAX_LINE_COUNT = 300_000
 MIN_OVERLAP = 0.95
 MIN_SEQ_COUNT = 5000
 MAX_ERROR_PROPORTION = 0.01
-MAX_INTERNAL_PRIMER_PROPORTION = 0.2
+MAX_INTERNAL_PRIMER_PROPORTION = 0.2
+
+# used by library_strategy_checker in analysis.shared
+MIN_AMPLICON_STRATEGY_CHECK = 0.30

mgnify_pipelines_toolkit/constants/var_region_coordinates.py

@@ -23,7 +23,7 @@ REGIONS_16S_BACTERIA = {
     "V6": [976, 1033],
     "V7": [1107, 1164],
     "V8": [1234, 1285],
-    "V9": [1426, 1456]
+    "V9": [1426, 1456],
 }
 
 REGIONS_16S_ARCHAEA = {
@@ -35,7 +35,7 @@ REGIONS_16S_ARCHAEA = {
     "V6": [932, 982],
     "V7": [1056, 1119],
     "V8": [1189, 1240],
-    "V9": [1372, 1410]
+    "V9": [1372, 1410],
 }
 
 REGIONS_18S = {
@@ -46,5 +46,5 @@ REGIONS_18S = {
     "V5": [1059, 1102],
     "V7": [1366, 1454],
     "V8": [1526, 1608],
-    "V9": [1728, 1795]
-}
+    "V9": [1728, 1795],
+}

mgnify_pipelines_toolkit/utils/fasta_to_delimited.py

@@ -0,0 +1,144 @@
+#!/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
+import sys
+import re
+import csv
+import hashlib
+import gzip
+from Bio import SeqIO
+from mgnify_pipelines_toolkit.constants.regex_fasta_header import FORMAT_REGEX_MAP
+
+
+def is_gzipped(filepath):
+    with open(filepath, "rb") as test_f:
+        return test_f.read(2) == b"\x1f\x8b"
+
+
+def guess_header_format(header):
+    matches = [
+        (format, re.search(regex, header)) for format, regex in FORMAT_REGEX_MAP.items()
+    ]
+    guesses = [
+        (format, match.groups()) for format, match in matches if match is not None
+    ]
+
+    if not guesses:
+        raise ValueError("Header format could not be determined")
+
+    guessed_format, _ = max(guesses, key=lambda g: g[1])
+
+    return guessed_format
+
+
+def md5_hash(s):
+    md5 = hashlib.md5()
+    md5.update(s.encode("utf-8"))
+
+    return md5.hexdigest()
+
+
+def parse_args():
+
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument("input", type=str, help="Path to (gzipped) Fasta file")
+    parser.add_argument("-o", "--output", type=str, help="Output path")
+    parser.add_argument(
+        "-f",
+        "--format",
+        type=str,
+        choices=["auto", "uniprotkb", "rpxx"],
+        default="auto",
+        help="Format of the input Fasta header",
+    )
+    parser.add_argument(
+        "-d", "--delimiter", type=str, default="\t", help="Output column delimiter"
+    )
+    parser.add_argument(
+        "--with-hash",
+        action="store_true",
+        help="Add a MD5 hash of the sequence to the output",
+    )
+    parser.add_argument(
+        "--no-header", action="store_true", help="Do not add header to output file"
+    )
+
+    args = parser.parse_args()
+
+    path = args.input
+    output = args.output
+    format = args.format
+    delimiter = args.delimiter
+    with_hash = args.with_hash
+    no_header = args.no_header
+
+    return path, output, format, delimiter, with_hash, no_header
+
+
+def main():
+    path, output, format, delimiter, with_hash, no_header = parse_args()
+
+    if is_gzipped(path):
+        input_fh = gzip.open(path, mode="rt")
+    else:
+        input_fh = open(path, mode="rt")
+
+    if output is None:
+        output_fh = sys.stdout
+    else:
+        output_fh = open(output, mode="w", newline="")
+
+    with input_fh, output_fh:
+        if format != "auto":
+            header_regex = re.compile(FORMAT_REGEX_MAP[format])
+        else:
+            header, _ = next(SeqIO.FastaIO.SimpleFastaParser(input_fh))
+            format = guess_header_format(header)
+            header_regex = re.compile(FORMAT_REGEX_MAP[format])
+            input_fh.seek(0)
+
+        fieldnames = list(header_regex.groupindex.keys())
+
+        if with_hash:
+            fieldnames.append("sequence_hash")
+
+        fieldnames.append("sequence")
+
+        csv_writer = csv.DictWriter(
+            output_fh, fieldnames=fieldnames, delimiter=delimiter, extrasaction="ignore"
+        )
+
+        if not no_header:
+            csv_writer.writeheader()
+
+        for header, sequence in SeqIO.FastaIO.SimpleFastaParser(input_fh):
+            header_match = header_regex.match(header)
+
+            row = {"sequence": sequence}
+
+            if header_match:
+                row.update(header_match.groupdict())
+
+            if with_hash:
+                row["sequence_hash"] = md5_hash(sequence)
+
+            csv_writer.writerow(row)
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/utils/get_mpt_version.py

@@ -0,0 +1,26 @@
+#!/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 importlib.metadata
+
+
+def main():
+
+    print(importlib.metadata.version("mgnify-pipelines-toolkit"))
+
+
+if __name__ == "__main__":
+    main()

{mgnify_pipelines_toolkit-0.1.4.dist-info → mgnify_pipelines_toolkit-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mgnify_pipelines_toolkit
-Version: 0.1.4
+Version: 0.1.6
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -15,6 +15,12 @@ Requires-Dist: biopython ==1.82
 Requires-Dist: numpy ==1.26.0
 Requires-Dist: pandas ==2.0.2
 Requires-Dist: regex ==2023.12.25
+Provides-Extra: dev
+Requires-Dist: mgnify-pipelines-toolkit[tests] ; extra == 'dev'
+Requires-Dist: pre-commit ==3.8.0 ; extra == 'dev'
+Requires-Dist: black ==24.8.0 ; extra == 'dev'
+Requires-Dist: flake8 ==7.1.1 ; extra == 'dev'
+Requires-Dist: pep8-naming ==0.14.1 ; extra == 'dev'
 Provides-Extra: tests
 Requires-Dist: pytest ==7.4.0 ; extra == 'tests'
 Requires-Dist: pytest-md ==0.2.0 ; extra == 'tests'
@@ -22,6 +28,7 @@ Requires-Dist: pytest-workflow ==2.0.1 ; extra == 'tests'
 Requires-Dist: biopython ==1.82 ; extra == 'tests'
 Requires-Dist: pandas ==2.0.2 ; extra == 'tests'
 Requires-Dist: numpy ==1.26.0 ; extra == 'tests'
+Requires-Dist: regex ==2023.12.25 ; extra == 'tests'
 
 # mgnify-pipelines-toolkit
 
@@ -52,6 +59,16 @@ You should then be able to run the packages from the command-line. For example t
 
 ## Adding a new script to the package
 
+### Local development requirements
+Before starting any development, you should do these few steps:
+- Clone the repo if you haven't already and create a feature branch from the `dev` branch (NOT `main`).
+- Create a virtual environment with the tool of your choice (i.e. `conda create --name my_new_env`)
+- Activate you new environment (i.e. `conda activate my_new_env`)
+- Install dev dependencies `pip install -e '.[dev]'`
+- Install pre-commit hooks `pre-commit install`
+
+When doing these steps above, you ensure that the code you add will be linted and formatted properly.
+
 ### New script requirements
 
 There are a few requirements for your script:

mgnify_pipelines_toolkit-0.1.6.dist-info/RECORD

@@ -0,0 +1,34 @@
+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=ySMZkgRSg-dnh6HMAE_1Vx8_EvJj7AiHJ2FcCaXKI-s,6448
+mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py,sha256=P_BM3GTB1KKKDb5chDK7-6cP6KORJef7i8ub-XLDtM0,5289
+mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py,sha256=hVkg8-tdLLf1Ewy9hor-H9zsyi-n8dnuj_shTQ5_rrM,7548
+mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py,sha256=aNucaUnYejl2Not4YLMBSzyYWGYJvYwLPZcFE94TIDc,5355
+mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=kIuE2wo3FaFZw2-HRGxstKz29FyGuhqVDRhf_vPZgsA,19921
+mgnify_pipelines_toolkit/analysis/amplicon/find_mcp_inflection_points.py,sha256=EnsIrPGigsy8jVnjYgSECihhuquSJTgCi-k6fhusKYM,3547
+mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=pvMDfq-KA9LrD359fvM1uXbXa2Mow5Fja-1iUoVdSEg,8676
+mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=9QI6o85T4JPFq4EdKmnYzI6sxPLJG6t9W0xKiu24aqw,5035
+mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=Zyo2Fb8ZFi8a5vNhLb-XpboNGWd2qyfMRaaGrXuFIgw,3634
+mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=8vwH6PY-XwMZhaUo08tOwdFsoREfNumvvDawTb9Y98U,3168
+mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=19NgCYE12bEvRBVibhZtZywwRiMdiBUBJjzL4by3_qo,1717
+mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py,sha256=RDPsaWKf0wIDwvCHXyRCh2zSJf3y9E7uOhHjaAeX8bY,11099
+mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=H5ccd1e_e5dk8vhVOvHLK1lknYbRPbnqPjULCYnU0FQ,4021
+mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=xT-66JaeVA-jVh6l7PkvKSmMjnU6RsHz7sTiCehG_wk,4771
+mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=DTX7S1P_BkGPEeDkbmUn1YoB247hpdNIe5rdFdRYDdA,1929
+mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=XV1vjkjIHhzouM1k5hu_51XK_mgC_EOOGDN3mx4LOvc,1991
+mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=exzWyuK0YxDiVSu4WX2H7g-uT5Y00w_EmrFqSHjRObU,5554
+mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=dCP3u_Qo-JMk3aqVapkqEbVUGE06jBQmUH6bB3bT8k0,1088
+mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=_2UTWfHKJyyFkIRQIPM2wDf-QkRTdLJ4xsA6gAkY9f4,1188
+mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=VaHL4mbof_9Gl7Ca3b2UkqjRqjAAvBYqprfbchae480,942
+mgnify_pipelines_toolkit/constants/thresholds.py,sha256=zz8paGQfZAU8tT-RbSGpzZ1Aopf77yEs97BAblHH5fk,964
+mgnify_pipelines_toolkit/constants/var_region_coordinates.py,sha256=jbOB_bTnW2TRjmdF7IS1A7nNOLt-lGnGyVXUHu0TmvQ,1307
+mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=GbNT7clHso21w_1PbPpWKVRd5bNs_MDbGXt8XVIGl2o,3991
+mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=zsQ4TuR4vpqYa67MgIdopdscsS0DVJdy4enRe1nCjSs,793
+mgnify_pipelines_toolkit-0.1.6.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-0.1.6.dist-info/METADATA,sha256=eG7O-AjUoEx1OpdksKj9cfadbRUdzJ0TxT6ZRo2ANQ4,5859
+mgnify_pipelines_toolkit-0.1.6.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
+mgnify_pipelines_toolkit-0.1.6.dist-info/entry_points.txt,sha256=tCZ7ijAgfIn47xXGxNtoZbHTDyUfHjUzjXg-NBRlj6g,1646
+mgnify_pipelines_toolkit-0.1.6.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-0.1.6.dist-info/RECORD,,

{mgnify_pipelines_toolkit-0.1.4.dist-info → mgnify_pipelines_toolkit-0.1.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.3.0)
+Generator: setuptools (74.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-0.1.4.dist-info → mgnify_pipelines_toolkit-0.1.6.dist-info}/entry_points.txt

@@ -3,9 +3,13 @@ are_there_primers = mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers
 assess_inflection_point_mcp = mgnify_pipelines_toolkit.analysis.amplicon.assess_inflection_point_mcp:main
 assess_mcp_proportions = mgnify_pipelines_toolkit.analysis.amplicon.assess_mcp_proportions:main
 classify_var_regions = mgnify_pipelines_toolkit.analysis.amplicon.classify_var_regions:main
+fasta_to_delimited = mgnify_pipelines_toolkit.utils.fasta_to_delimited:main
+fastq_suffix_header_check = mgnify_pipelines_toolkit.analysis.shared.fastq_suffix_header_check:main
 find_mcp_inflection_points = mgnify_pipelines_toolkit.analysis.amplicon.find_mcp_inflection_points:main
+get_mpt_version = mgnify_pipelines_toolkit.utils.get_mpt_version:main
 get_subunits = mgnify_pipelines_toolkit.analysis.shared.get_subunits:main
 get_subunits_coords = mgnify_pipelines_toolkit.analysis.shared.get_subunits_coords:main
+library_strategy_check = mgnify_pipelines_toolkit.analysis.shared.library_strategy_check:main
 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

mgnify_pipelines_toolkit-0.1.4.dist-info/RECORD

@@ -1,28 +0,0 @@
-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=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=-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
-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=glvql2Y-BTyA1hTIZz2nlmST3SE6LJbep9sKdMH-vaI,5565
-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=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,,