mgnify-pipelines-toolkit 1.1.2__tar.gz → 1.2.1__tar.gz

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.2
+Version: 1.2.1
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -8,22 +8,21 @@ Keywords: bioinformatics,pipelines,metagenomics
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: biopython>=1.85
 Requires-Dist: numpy<3,>=2.2.4
 Requires-Dist: pandas<3,>=2.2.3
-Requires-Dist: regex>=2024.11.6
 Requires-Dist: requests<3,>=2.32.3
 Requires-Dist: click<9,>=8.1.8
 Requires-Dist: pandera<0.24,>=0.23.1
 Requires-Dist: pyfastx<3,>=2.2.0
 Requires-Dist: intervaltree<4,>=3.1.0
-Provides-Extra: tests
-Requires-Dist: pytest<9,>=8.3.5; extra == "tests"
-Requires-Dist: pytest-md>=0.2.0; extra == "tests"
-Requires-Dist: pytest-workflow==2.1.0; extra == "tests"
+Provides-Extra: test
+Requires-Dist: pytest<9,>=8.3.5; extra == "test"
+Requires-Dist: pytest-md>=0.2.0; extra == "test"
+Requires-Dist: pytest-workflow==2.1.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: black>=25.1.0; extra == "dev"

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py

@@ -22,7 +22,6 @@ import pandas as pd
 
 
 def parse_args():
-
     parser = argparse.ArgumentParser()
     parser.add_argument(
         "-i", "--input", required=True, type=str, help="Input JSON from antiSMASH"
@@ -64,7 +63,6 @@ def main():
         region_name = None
 
         for feature in record["features"]:
-
             if feature["type"] == "region":
                 # Annotate region features
                 region_name = (
@@ -129,35 +127,34 @@ def main():
             cds_by_protocluster = record["modules"][
                 "antismash.detection.hmm_detection"
             ]["rule_results"]["cds_by_protocluster"]
-            if len(cds_by_protocluster) > 0:
-                for feature in cds_by_protocluster[0][1]:
-                    if "cds_name" in feature.keys():
-                        locus_tag = feature["cds_name"]
-                        as_clusters = ",".join(
-                            list(feature["definition_domains"].keys())
+
+            if not cds_by_protocluster:
+                continue
+
+            for feature in cds_by_protocluster[0][1]:
+                if locus_tag := feature.get("cds_name"):
+                    as_clusters = ",".join(list(feature["definition_domains"].keys()))
+                    if locus_tag in attributes_dict:
+                        attributes_dict[locus_tag].update(
+                            {"as_gene_clusters": as_clusters}
                         )
-                        if locus_tag in attributes_dict.keys():
-                            attributes_dict[locus_tag].update(
-                                {"as_gene_clusters": as_clusters}
-                            )
 
         if "antismash.detection.genefunctions" in record["modules"].keys():
-            for tool in record["modules"]["antismash.detection.genefunctions"]["tools"]:
-                if tool["tool"] == "smcogs":
-                    for locus_tag in tool["best_hits"]:
-                        hit_id = tool["best_hits"][locus_tag]["hit_id"].split(":")[0]
-                        hit_desc = (
-                            tool["best_hits"][locus_tag]["hit_id"]
-                            .split(":")[1]
-                            .replace(" ", "_")
-                        )
-                        score = tool["best_hits"][locus_tag]["bitscore"]
-                        e_value = tool["best_hits"][locus_tag]["evalue"]
+            gene_function_tools = record["modules"][
+                "antismash.detection.genefunctions"
+            ]["tools"]
+            if tool_data := gene_function_tools.get("smcogs"):
+
+                for locus_tag in tool_data["best_hits"]:
+                    smcog_id = tool_data["best_hits"][locus_tag]["reference_id"]
+                    smcog_description = tool_data["best_hits"][locus_tag]["description"]
+
+                    score = tool_data["best_hits"][locus_tag]["bitscore"]
+                    e_value = tool_data["best_hits"][locus_tag]["evalue"]
 
-                        smcog_note = f"smCOG:{hit_id}:{hit_desc.replace(' ', '_')}(Score:{score}%3BE-value:{e_value})"
-                        if locus_tag in attributes_dict.keys():
-                            attributes_dict[locus_tag].update({"as_notes": smcog_note})
-                        break
+                    smcog_note = f"smCOG:{smcog_id}:{smcog_description.replace(' ', '_')}(Score:{score}%3BE-value:{e_value})"
+                    if locus_tag in attributes_dict.keys():
+                        attributes_dict[locus_tag].update({"as_notes": smcog_note})
 
     attributes = [
         ";".join(f"{k}={v}" for k, v in attrib_data.items() if v)

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit/constants/thresholds.py

@@ -14,9 +14,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# used by fetch_mcp in analysis.amplicon
-MCP_MAX_LINE_COUNT = 300_000
-
 # used by classify_var_regions in analysis.amplicon
 MIN_OVERLAP = 0.95
 MIN_SEQ_COUNT = 5000
@@ -26,7 +23,6 @@ MAX_INTERNAL_PRIMER_PROPORTION = 0.2
 # used by library_strategy_checker in analysis.shared
 MIN_AMPLICON_STRATEGY_CHECK = 0.30
 
-
 # used by markergene_study_summary in analysis.shared
 MAJORITY_MARKER_PROPORTION = 0.45
 # used by gff_toolkit in analysis.assembly

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.1.2
+Version: 1.2.1
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -8,22 +8,21 @@ Keywords: bioinformatics,pipelines,metagenomics
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: biopython>=1.85
 Requires-Dist: numpy<3,>=2.2.4
 Requires-Dist: pandas<3,>=2.2.3
-Requires-Dist: regex>=2024.11.6
 Requires-Dist: requests<3,>=2.32.3
 Requires-Dist: click<9,>=8.1.8
 Requires-Dist: pandera<0.24,>=0.23.1
 Requires-Dist: pyfastx<3,>=2.2.0
 Requires-Dist: intervaltree<4,>=3.1.0
-Provides-Extra: tests
-Requires-Dist: pytest<9,>=8.3.5; extra == "tests"
-Requires-Dist: pytest-md>=0.2.0; extra == "tests"
-Requires-Dist: pytest-workflow==2.1.0; extra == "tests"
+Provides-Extra: test
+Requires-Dist: pytest<9,>=8.3.5; extra == "test"
+Requires-Dist: pytest-md>=0.2.0; extra == "test"
+Requires-Dist: pytest-workflow==2.1.0; extra == "test"
 Provides-Extra: dev
 Requires-Dist: pre-commit>=4.2.0; extra == "dev"
 Requires-Dist: black>=25.1.0; extra == "dev"

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit.egg-info/SOURCES.txt

@@ -9,18 +9,12 @@ mgnify_pipelines_toolkit.egg-info/entry_points.txt
 mgnify_pipelines_toolkit.egg-info/requires.txt
 mgnify_pipelines_toolkit.egg-info/top_level.txt
 mgnify_pipelines_toolkit/analysis/__init__.py
-mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py
-mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py
-mgnify_pipelines_toolkit/analysis/amplicon/assess_inflection_point_mcp.py
-mgnify_pipelines_toolkit/analysis/amplicon/assess_mcp_proportions.py
 mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py
-mgnify_pipelines_toolkit/analysis/amplicon/find_mcp_inflection_points.py
 mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py
 mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py
 mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py
 mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py
 mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py
-mgnify_pipelines_toolkit/analysis/amplicon/standard_primer_matching.py
 mgnify_pipelines_toolkit/analysis/amplicon/study_summary_generator.py
 mgnify_pipelines_toolkit/analysis/assembly/add_rhea_chebi_annotation.py
 mgnify_pipelines_toolkit/analysis/assembly/antismash_gff_builder.py
@@ -49,7 +43,6 @@ mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py
 mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py
 mgnify_pipelines_toolkit/constants/db_labels.py
 mgnify_pipelines_toolkit/constants/ncrna.py
-mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py
 mgnify_pipelines_toolkit/constants/regex_fasta_header.py
 mgnify_pipelines_toolkit/constants/tax_ranks.py
 mgnify_pipelines_toolkit/constants/thresholds.py

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit.egg-info/entry_points.txt

@@ -2,17 +2,13 @@
 add_rhea_chebi_annotation = mgnify_pipelines_toolkit.analysis.assembly.add_rhea_chebi_annotation:main
 amplicon_study_summary_generator = mgnify_pipelines_toolkit.analysis.amplicon.study_summary_generator:cli
 antismash_gff_builder = mgnify_pipelines_toolkit.analysis.assembly.antismash_gff_builder:main
-are_there_primers = mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers:main
 assembly_study_summary_generator = mgnify_pipelines_toolkit.analysis.assembly.study_summary_generator:cli
-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
 combined_gene_caller_merge = mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:main
 convert_cmscan_to_cmsearch_tblout = mgnify_pipelines_toolkit.analysis.shared.convert_cmscan_to_cmsearch_tblout:main
 dwc_summary_generator = mgnify_pipelines_toolkit.analysis.shared.dwc_summary_generator: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
 generate_gaf = mgnify_pipelines_toolkit.analysis.assembly.generate_gaf:main
 genomes_extract_bacterial_rrnas_as_tsv = mgnify_pipelines_toolkit.analysis.genomes.rna.extract_bacterial_rrnas_as_tsv:main
 genomes_extract_rrnas_as_fasta = mgnify_pipelines_toolkit.analysis.genomes.rna.extract_rrnas_as_fasta:main
@@ -32,7 +28,6 @@ process_dbcan_cazys = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_r
 process_dbcan_clusters = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_result_clusters: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
 summarise_antismash_bgcs = mgnify_pipelines_toolkit.analysis.assembly.summarise_antismash_bgcs:main
 summarise_goslims = mgnify_pipelines_toolkit.analysis.assembly.summarise_goslims:main
 summarise_sanntis_bgcs = mgnify_pipelines_toolkit.analysis.assembly.summarise_sanntis_bgcs:main

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/mgnify_pipelines_toolkit.egg-info/requires.txt

@@ -1,7 +1,6 @@
 biopython>=1.85
 numpy<3,>=2.2.4
 pandas<3,>=2.2.3
-regex>=2024.11.6
 requests<3,>=2.32.3
 click<9,>=8.1.8
 pandera<0.24,>=0.23.1
@@ -14,7 +13,7 @@ black>=25.1.0
 flake8>=7.1.2
 pep8-naming>=0.14.1
 
-[tests]
+[test]
 pytest<9,>=8.3.5
 pytest-md>=0.2.0
 pytest-workflow==2.1.0

{mgnify_pipelines_toolkit-1.1.2 → mgnify_pipelines_toolkit-1.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "1.1.2"
+version = "1.2.1"
 readme = "README.md"
 license = { text = "Apache Software License 2.0" }
 authors = [
@@ -8,7 +8,7 @@ authors = [
 ]
 keywords = ["bioinformatics", "pipelines", "metagenomics"]
 description = "Collection of scripts and tools for MGnify pipelines"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: Apache Software License",
@@ -19,7 +19,6 @@ dependencies = [
     "biopython>=1.85",
     "numpy>=2.2.4,<3",
     "pandas>=2.2.3,<3",
-    "regex>=2024.11.6",
     "requests>=2.32.3,<3",
     "click>=8.1.8,<9",
     "pandera>=0.23.1,<0.24",
@@ -54,15 +53,10 @@ markergene_study_summary = "mgnify_pipelines_toolkit.analysis.shared.markergene_
 convert_cmscan_to_cmsearch_tblout = "mgnify_pipelines_toolkit.analysis.shared.convert_cmscan_to_cmsearch_tblout:main"
 dwc_summary_generator = "mgnify_pipelines_toolkit.analysis.shared.dwc_summary_generator:main"
 # analysis.amplicon #
-are_there_primers = "mgnify_pipelines_toolkit.analysis.amplicon.are_there_primers:main"
-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"
-find_mcp_inflection_points = "mgnify_pipelines_toolkit.analysis.amplicon.find_mcp_inflection_points:main"
 make_asv_count_table = "mgnify_pipelines_toolkit.analysis.amplicon.make_asv_count_table: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"
 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"
 amplicon_study_summary_generator = "mgnify_pipelines_toolkit.analysis.amplicon.study_summary_generator:cli"
@@ -89,7 +83,7 @@ fasta_to_delimited = "mgnify_pipelines_toolkit.utils.fasta_to_delimited:main"
 get_mpt_version = "mgnify_pipelines_toolkit.utils.get_mpt_version:main"
 
 [project.optional-dependencies]
-tests = [
+test = [
     "pytest>=8.3.5,<9",
     "pytest-md>=0.2.0",
     "pytest-workflow==2.1.0",

mgnify_pipelines_toolkit-1.1.2/mgnify_pipelines_toolkit/analysis/amplicon/amplicon_utils.py

@@ -1,221 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-# Copyright 2024-2025 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.
-
-from collections import defaultdict, Counter
-import logging
-import gzip
-import os
-import pyfastx
-
-from mgnify_pipelines_toolkit.constants.regex_ambiguous_bases import (
-    _AMBIGUOUS_BASES_DICT,
-    _AMBIGUOUS_BASES_DICT_REV,
-)
-
-logging.basicConfig(level=logging.DEBUG)
-
-
-def split_dir_into_sample_paths(dir):
-    file_list = os.listdir(dir)
-    file_list = [
-        file
-        for file in file_list
-        if ".fastq" in file and ("_1" in file or "_2" in file)
-    ]
-    sample_set = set()
-    [sample_set.add(f"{dir}/{file.split('_')[0]}") for file in file_list]
-    sample_list = sorted(list(sample_set))
-
-    return sample_list
-
-
-def get_read_count(read_path: str, file_type: str = "fastq") -> int:
-    """
-    Get the read count of a FASTQ or FASTA file.
-
-    :param read_path: The path to the FASTQ or FASTA file.
-    :type read_path: str
-    :param fasta_type: The type of the file, either "fastq" or "fasta". Defaults to "fastq".
-    :type fasta_type: str
-    :return: The number of reads in the file.
-    :rtype: int
-    :raises ValueError: If the file type is not supported or the read count is not a positive integer.
-    """
-    read_count = 0
-
-    if file_type == "fasta":
-        fasta = pyfastx.Fasta(read_path, build_index=False)
-        read_count = sum(1 for _ in fasta)
-    elif file_type == "fastq":
-        fastq = pyfastx.Fastq(read_path, build_index=False)
-        read_count = sum(1 for _ in fastq)
-    else:
-        raise ValueError(
-            f"Invalid file_type {file_type}, it needs to be either 'fasta' or 'fastq'"
-        )
-
-    if read_count <= 0:
-        raise ValueError(f"Read count is not a positive integer: {read_count}")
-
-    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,
-):
-    """
-    Generate consensus sequence using a list of base conservation dictionaries most likely
-    generated by the `build_mcp_cons_dict_list()` function.
-    Also returns a list containing the conservation value of the most conserved base at every
-    position in the list of base conservation dictionaries.
-    """
-
-    cons_seq = ""
-    cons_confs = []
-
-    if do_not_include is None:
-        do_not_include = []
-
-    for count_dict in cons_list:
-        max_count = 0
-        cons_dict = defaultdict(float)
-
-        if counter in do_not_include:
-            counter += 1
-            cons_seq += "N"
-            continue
-
-        for base, count in count_dict.items():
-            if base not in ("A", "T", "C", "G"):
-                continue
-
-            if max_line_count is None:
-                cons_dict[base] = count / read_count
-            else:
-                cons_dict[base] = count / max_line_count
-
-            if count > max_count:
-                max_count = count
-
-        counter += 1
-
-        try:
-            if max_line_count is None:
-                max_prop = max_count / read_count
-            else:
-                max_prop = max_count / max_line_count
-
-            cons_bases = []
-            curr_prop = 0.0
-            sorted_cons_dict = dict(
-                sorted(cons_dict.items(), key=lambda x: x[1], reverse=True)
-            )
-
-            for base, prop in sorted_cons_dict.items():
-                cons_bases.append(base)
-                curr_prop += prop
-                if curr_prop >= cons_threshold:
-                    break
-
-            cons_bases = sorted(cons_bases)
-
-            if len(cons_bases) == 1:
-                cons_seq += cons_bases[0]
-            else:
-                amb_string = ",".join(cons_bases)
-                amb_base = _AMBIGUOUS_BASES_DICT_REV[amb_string]
-                cons_seq += amb_base
-
-        except ZeroDivisionError:
-            max_prop = 0.0
-
-        cons_confs.append(max_prop)
-
-    return cons_seq, cons_confs
-
-
-def primer_regex_query_builder(primer):
-    """
-    Takes an input nucleotide sequence that can contain IUPAC ambiguous codes
-    Returns a string formatted as a regex query that considers the different
-    potential bases valid at a position with am abiguity code.
-    """
-
-    query = ""
-
-    for char in primer:
-        if char in ("A", "C", "T", "G"):
-            query += char
-        else:
-            query += str(_AMBIGUOUS_BASES_DICT[char])
-
-    query = f"(.*{query}){{e<=1}}"
-
-    return query
-
-
-def build_mcp_cons_dict_list(mcp_count_dict, mcp_len):
-    """
-    Generate list of dictionaries of base conservation for mcp output (mcp_cons_list)
-    e.g. [{'A':0.9, 'C':0.1}, {'T':1.0}, ....] for every base position
-    """
-
-    mcp_cons_list = []
-
-    for i in range(mcp_len):
-        index_base_dict = defaultdict(int)
-        for mcp in mcp_count_dict.keys():
-            if len(mcp) < mcp_len:
-                continue
-            base = mcp[i]
-            index_base_dict[base] += mcp_count_dict[mcp]
-        mcp_cons_list.append(index_base_dict)
-
-    return mcp_cons_list
-
-
-def fetch_mcp(fastq, prefix_len, start=1, rev=False, max_line_count=None):
-    """
-    Generates the most common prefix sequences along with their counts in a fastq file.
-    Outputs dictionary containing counts for each generated MCP in the fastq.
-    """
-
-    selected_lines = []
-
-    with gzip.open(fastq, "rt") as file:
-        for i, line in enumerate(file):
-            line = line.strip()
-            if i % 4 == 1:
-                if not rev:
-                    selected_lines.append(line[start - 1 : start + prefix_len - 1])
-                else:
-                    rev_line = line[::-1]
-                    selected_lines.append(rev_line[start - 1 : start + prefix_len - 1])
-            if max_line_count is not None:
-                if len(selected_lines) > max_line_count:
-                    break
-
-    sequence_counts = Counter(selected_lines)
-    mcp_count_dict = dict(
-        sorted(sequence_counts.items(), key=lambda x: x[1], reverse=True)
-    )
-
-    return mcp_count_dict

mgnify_pipelines_toolkit-1.1.2/mgnify_pipelines_toolkit/analysis/amplicon/are_there_primers.py

@@ -1,164 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-# Copyright 2024-2025 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 numpy as np
-
-from mgnify_pipelines_toolkit.analysis.amplicon.amplicon_utils import (
-    get_read_count,
-    build_cons_seq,
-    build_mcp_cons_dict_list,
-    fetch_mcp,
-)
-
-
-def parse_args(argv=None):
-    parser = argparse.ArgumentParser()
-
-    parser.add_argument(
-        "-i",
-        "--input",
-        required=True,
-        type=str,
-        help="Path to fastq file to check for primers",
-    )
-    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)
-
-    path = args.input
-    sample = args.sample
-    output = args.output
-
-    return path, sample, output
-
-
-def are_there_primers_in_this_sample(path, rev=False):
-    """
-    Predict the presence of primers based on windows of base conservation.
-
-    Takes a fastq file as input. Extracts proportion of most common base for the first 100 bases.
-    Computes the a threshold (Q3 - 0.15) based on this proportion and counts the number of bases below
-    it in windows of 10 bases.
-    If at least one of the first two windows contains at most one such a base, then the presence of a primer is flagged as true.
-    A primer is also flagged as true if the combined count of bases below Q3 is at most 4.
-
-    The output of this function is a boolean flag:
-        True if a primer was identified
-        False if a primer was not identified
-    """
-
-    read_count = get_read_count(
-        path, file_type="fastq"
-    )  # Get read count for fastq file
-    mcp_len = 100  # Script will look at first 100 base mcps (for rev=True, it will look at first 100 from 3' to 5')
-
-    mcp_count_dict = fetch_mcp(
-        path, mcp_len, rev=rev
-    )  # mcp dict where key is the mcp and value is the count
-    mcp_cons_list = build_mcp_cons_dict_list(
-        mcp_count_dict, mcp_len
-    )  # list of base conservation dicts for mcps
-    cons_seq, cons_confs = build_cons_seq(
-        mcp_cons_list, read_count
-    )  # get list of max base conservations for each index
-
-    window_size = 10
-    # Counter that will reset to 0 every 10 bases
-    window_count = 0
-    # Will append the window count to this list every 10 bases
-    window_count_list = []
-    # Compute Q3-based threshold
-    max_cons = np.quantile(cons_confs, 0.75)
-    threshold = max_cons - 0.15
-
-    if max_cons < 0.75:
-        threshold = 0.75
-    # Immediately return false (no primer) if the max conservation is less than 0.6
-    if max_cons < 0.6:
-        return False
-
-    # Loop through every base
-    for i, val in enumerate(cons_confs):
-        if i % window_size == 0 and i != 0:  # After looping through a window..
-            window_count_list.append(window_count)  # ..append window count
-            window_count = 0  # ..reset window count
-
-        if (
-            val < threshold
-        ):  # If the conservation at i is less than threshold, increment count for the window
-            window_count += 1
-
-    primer_flag = False  # Initialise primer flag as false
-
-    if (
-        1 in window_count_list[:2] or 0 in window_count_list[:2]
-    ):  # If window count is at most 1 of first two windows...
-        primer_flag = True  # ..primer flag is true
-    elif (
-        sum(window_count_list[:2]) <= 4
-    ):  # If sum of window counts of the first two windows is at most 4..
-        primer_flag = True  # ..primer flag is true
-
-    return primer_flag
-
-
-def save_out(results, sample_id, output):
-    """
-    Save primer presence flags into output .txt file.
-
-    1: primer exists
-    0: primer doesn't exist
-
-    First line will be the forward strand
-    Second line will be the reverse strand
-    """
-
-    with open(f"{output}/{sample_id}_general_primer_out.txt", "w") as fw:
-        fw.write(f"{results[0]}\n")
-        fw.write(f"{results[1]}\n")
-
-
-def main(argv=None):
-    path, sample, output = parse_args(argv)
-
-    fwd_primer_flag = are_there_primers_in_this_sample(
-        path
-    )  # Check for general primers in fwd
-    rev_primer_flag = are_there_primers_in_this_sample(
-        path, rev=True
-    )  # Check for general primers in rev
-
-    fwd_status = "0"
-    rev_status = "0"
-    # Flag for primer presence: 1 for yes 0 for no
-    if fwd_primer_flag:
-        print("Forward primer detected!")
-        fwd_status = 1
-    else:
-        print("No forward primer detected")
-    if rev_primer_flag:
-        print("Reverse primer detected!")
-        rev_status = 1
-    else:
-        print("No reverse primer detected")
-
-    save_out((fwd_status, rev_status), sample, output)  # Save primer flags to .txt file
-
-
-if __name__ == "__main__":
-    main()