mgnify-pipelines-toolkit 1.0.1__tar.gz → 1.0.3__tar.gz

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.1
+Version: 1.0.3
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -38,6 +38,7 @@ 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"
+Dynamic: license-file
 
 # mgnify-pipelines-toolkit
 

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/mgnify_pipelines_toolkit/analysis/assembly/go_utils.py

@@ -84,52 +84,51 @@ def parse_interproscan_tsv(ips_file: Path, mapped_go_terms: dict = None) -> dict
     previous_protein_acc = None
     go_annotations_single_protein = set()
 
-    fr = open(ips_file, "r")
     go_pattern = re.compile("GO:\\d+")
 
-    for line in fr:
-        # IPS files are parsed line by line - the same protein accession will appear multiple lines in a row with different annotation
-        line_counter += 1
-        line = line.strip()
-        chunks = line.split("\t")
-        # Get protein accession
-        current_protein_acc = chunks[0]
-
-        # TODO: not sure if this line is needed - do we ever have more than one protein in a single line of IPS?
-        # Will keep just in case
-        num_of_proteins = len(current_protein_acc.split("|"))
-
-        # If we're at a new protein accession in the IPS file then we finally increment
-        # the go2protein_count dictionary for each term that was found in that protein
-        if current_protein_acc != previous_protein_acc:
-            total_num_of_proteins += 1
-            if len(go_annotations_single_protein) > 0:
-                num_of_proteins_with_go += 1
-                go2protein_count = count_and_assign_go_annotations(
-                    go2protein_count,
-                    go_annotations_single_protein,
-                    num_of_proteins,
-                    mapped_go_terms,
-                )
-            # reset GO id set because we hit a new protein accession
-            go_annotations_single_protein = set()
-            previous_protein_acc = current_protein_acc
-
-        # Parse out GO annotations
-        # GO annotations are associated to InterPro entries (InterPro entries start with 'IPR')
-        # Than use the regex to extract the GO Ids (e.g. GO:0009842)
-        if len(chunks) >= 13 and chunks[11].startswith("IPR"):
-            for go_annotation in go_pattern.findall(line):
-                go_annotations_single_protein.add(go_annotation)
-
-    # Do final counting for the last protein
-    go2protein_count = count_and_assign_go_annotations(
-        go2protein_count,
-        go_annotations_single_protein,
-        num_of_proteins,
-        mapped_go_terms,
-    )
-
-    fr.close()
+    with open(ips_file, "r") as fr:
+
+        for line in fr:
+            # IPS files are parsed line by line - the same protein accession will appear multiple lines in a row with different annotation
+            line_counter += 1
+            line = line.strip()
+            chunks = line.split("\t")
+            # Get protein accession
+            current_protein_acc = chunks[0]
+
+            # TODO: not sure if this line is needed - do we ever have more than one protein in a single line of IPS?
+            # Will keep just in case
+            num_of_proteins = len(current_protein_acc.split("|"))
+
+            # If we're at a new protein accession in the IPS file then we finally increment
+            # the go2protein_count dictionary for each term that was found in that protein
+            if current_protein_acc != previous_protein_acc:
+                total_num_of_proteins += 1
+                if len(go_annotations_single_protein) > 0:
+                    num_of_proteins_with_go += 1
+                    go2protein_count = count_and_assign_go_annotations(
+                        go2protein_count,
+                        go_annotations_single_protein,
+                        num_of_proteins,
+                        mapped_go_terms,
+                    )
+                # reset GO id set because we hit a new protein accession
+                go_annotations_single_protein = set()
+                previous_protein_acc = current_protein_acc
+
+            # Parse out GO annotations
+            # GO annotations are associated to InterPro entries (InterPro entries start with 'IPR')
+            # Than use the regex to extract the GO Ids (e.g. GO:0009842)
+            if len(chunks) >= 13 and chunks[11].startswith("IPR"):
+                for go_annotation in go_pattern.findall(line):
+                    go_annotations_single_protein.add(go_annotation)
+
+        # Do final counting for the last protein
+        go2protein_count = count_and_assign_go_annotations(
+            go2protein_count,
+            go_annotations_single_protein,
+            num_of_proteins,
+            mapped_go_terms,
+        )
 
     return go2protein_count

mgnify_pipelines_toolkit-1.0.3/mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Copyright 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
+from collections import Counter
+import csv
+import logging
+
+RANK_PREFIXES = {
+    "superkingdom": "sk__",
+    "kingdom": "k__",
+    "phylum": "p__",
+    "class": "c__",
+    "order": "o__",
+    "family": "f__",
+    "genus": "g__",
+    "species": "s__",
+}
+
+logging.basicConfig(
+    level=logging.INFO, format="[%(asctime)s] - %(levelname)s - %(message)s"
+)
+
+
+def import_nodes(nodes_dmp):
+    logging.info(f"Loading file {nodes_dmp}")
+    taxid2rank = {}
+
+    with open(nodes_dmp) as f1:
+        reader = csv.reader(f1, delimiter="\t")
+        for line in reader:
+            taxid = line[0]
+            rank = line[4]
+            taxid2rank[taxid] = rank
+
+    return taxid2rank
+
+
+def import_names(names_dmp):
+    logging.info(f"Loading file {names_dmp}")
+    taxid2name = {}
+
+    with open(names_dmp, newline="") as f1:
+        reader = csv.reader(f1, delimiter="\t")
+        for line in reader:
+            if line[6] == "scientific name":
+                taxid = line[0]
+                name = line[2]
+                taxid2name[taxid] = name
+
+    return taxid2name
+
+
+def convert_to_official_names(lineage, taxid2rank, taxid2name):
+    lineage_ranks = [taxid2rank[taxid.rstrip("*")] for taxid in lineage]
+    official_names = list(RANK_PREFIXES.values())
+    lowest_classification_index = -1
+
+    for i, rank in enumerate(RANK_PREFIXES):
+        if rank in lineage_ranks:
+            index = lineage_ranks.index(rank)
+            taxid = lineage[index].rstrip("*")
+            name = taxid2name[taxid]
+            official_names[i] = official_names[i] + name
+            lowest_classification_index = i
+
+    return official_names[: lowest_classification_index + 1]
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Process TSV classification generated by CAT_pack contigs and write input file for Krona ktImportText"
+    )
+    parser.add_argument(
+        "-i", "--input", help="Path to the input TSV file from CAT_pack contigs"
+    )
+    parser.add_argument("-o", "--output", help="Name of the output Krona TXT file")
+    parser.add_argument(
+        "-n", "--names_dmp", help="Path to the nodes.dmp file from NCBI taxonomy"
+    )
+    parser.add_argument(
+        "-r", "--nodes_dmp", help="Path to the names.dmp file from NCBI taxonomy"
+    )
+    args = parser.parse_args()
+
+    taxid2rank = import_nodes(args.nodes_dmp)
+    taxid2name = import_names(args.names_dmp)
+
+    logging.info(f"Begin parsing of CAT_pack classiffication file {args.input}")
+    lineage_counter = Counter()
+    with open(args.input) as infile:
+        reader = csv.reader(infile, delimiter="\t")
+        next(reader)  # Skip the header row
+        for row in reader:
+            if row[1] == "no taxid assigned":
+                lineage = "unclassified"
+            else:
+                taxid_lineage = row[3].split(";")
+                names_lineage = convert_to_official_names(
+                    taxid_lineage, taxid2rank, taxid2name
+                )
+                lineage = "\t".join(names_lineage) if names_lineage else "unclassified"
+            lineage_counter[lineage] += 1
+
+    logging.info(f"Writting output to {args.output}")
+    with open(args.output, "w") as outfile:
+        for lineage, count in lineage_counter.most_common():
+            outfile.write(f"{count}\t{lineage}\n")
+
+    logging.info("Done")
+
+
+if __name__ == "__main__":
+    main()

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py

@@ -15,9 +15,10 @@
 # limitations under the License.
 
 import argparse
-from collections import defaultdict
+import csv
 import logging
 import os
+from collections import defaultdict
 from pathlib import Path
 
 from mgnify_pipelines_toolkit.analysis.assembly.go_utils import parse_interproscan_tsv
@@ -28,7 +29,6 @@ logging.basicConfig(
 
 
 def parse_args():
-
     description = "Go slim pipeline."
     parser = argparse.ArgumentParser(description=description)
     parser.add_argument(
@@ -59,46 +59,56 @@ def parse_args():
 
 
 def parse_mapped_gaf_file(gaf_file: Path) -> defaultdict[set]:
-
     mapped_go_dict = defaultdict(set)
     if os.path.exists(gaf_file):
-        handle = open(gaf_file, "r")
-        for line in handle:
-            if not line.startswith("!"):
-                line = line.strip()
-                splitted_line = line.split("\t")
-                go_id = splitted_line[1]
-                mapped_go_id = splitted_line[4]
-                mapped_go_dict[go_id].add(mapped_go_id)
-
+        with open(gaf_file, "r") as handle:
+            for line in handle:
+                if not line.startswith("!"):
+                    line = line.strip()
+                    splitted_line = line.split("\t")
+                    go_id = splitted_line[1]
+                    mapped_go_id = splitted_line[4]
+                    mapped_go_dict[go_id].add(mapped_go_id)
     return mapped_go_dict
 
 
 def get_go_slim_summary(go_slim_banding_file, goslims2_protein_count):
     summary = []
 
-    fr = open(go_slim_banding_file, "r")
-
-    for line in fr:
-        if line.startswith("GO"):
-            line = line.strip()
-            line_chunks = line.split("\t")
-            go_id = line_chunks[0]
-            term = line_chunks[1]
-            category = line_chunks[2]
-            # Default value for the count
-            count = 0
-            if go_id in goslims2_protein_count:
-                count = goslims2_protein_count[go_id]
-            summary.append((go_id, term, category, count))
+    with open(go_slim_banding_file, "r") as fr:
+        for line in fr:
+            if line.startswith("GO"):
+                line = line.strip()
+                line_chunks = line.split("\t")
+                go_id = line_chunks[0]
+                term = line_chunks[1]
+                category = line_chunks[2]
+                # Default value for the count
+                count = 0
+                if go_id in goslims2_protein_count:
+                    count = goslims2_protein_count[go_id]
+                summary.append((go_id, term, category, count))
     return summary
 
 
 def write_go_summary_to_file(go_summary, output_file):
-    fw = open(output_file, "w")
-    for go, term, category, count in go_summary:
-        fw.write('","'.join(['"' + go, term, category, str(count) + '"']) + "\n")
-    fw.close()
+    """
+    Write a sorted GO summary to a TSV file.
+
+    :param go_summary: A list of tuples, where each tuple contains the following
+                       elements:
+                       - go (str): The GO identifier.
+                       - term (str): The GO term description.
+                       - category (str): The category of the GO term.
+                       - count (int): The count associated with the GO term.
+    :param output_file: The path to the output TSV file where the sorted GO
+    """
+    sorted_go_summary = sorted(go_summary, key=lambda x: x[3], reverse=True)
+    with open(output_file, "w", newline="") as fw:
+        tsv_writer = csv.writer(fw, delimiter="\t")
+        tsv_writer.writerow(["go", "term", "category", "count"])
+        for go, term, category, count in sorted_go_summary:
+            tsv_writer.writerow([go, term, category, count])
 
 
 def parse_gene_ontology(obo_file):
@@ -108,23 +118,22 @@ def parse_gene_ontology(obo_file):
     :return:
     """
     go_term_tuples = []
-    fr = open(obo_file, "r")
-    id, term, category = "", "", ""
-    for line in fr:
-        line = line.strip()
-        split_line = line.split(": ")
-        if line.startswith("id:"):
-            id = split_line[1]
-        elif line.startswith("name:"):
-            term = split_line[1]
-        elif line.startswith("namespace"):
-            category = split_line[1]
-        else:
-            if id.startswith("GO:") and id and term and category:
-                item = (id, term, category)
-                go_term_tuples.append(item)
-                id, term, category = "", "", ""
-    fr.close()
+    with open(obo_file, "r") as fr:
+        id, term, category = "", "", ""
+        for line in fr:
+            line = line.strip()
+            split_line = line.split(": ")
+            if line.startswith("id:"):
+                id = split_line[1]
+            elif line.startswith("name:"):
+                term = split_line[1]
+            elif line.startswith("namespace"):
+                category = split_line[1]
+            else:
+                if id.startswith("GO:") and id and term and category:
+                    item = (id, term, category)
+                    go_term_tuples.append(item)
+                    id, term, category = "", "", ""
     return go_term_tuples
 
 
@@ -132,7 +141,6 @@ def get_full_go_summary(core_gene_ontology, go2protein_count_dict, top_level_go_
     summary = []
 
     for go_id, term, category in core_gene_ontology:
-
         if (go_id in go2protein_count_dict) and (
             go_id not in top_level_go_ids
         ):  # make sure that top level terms are not included (they tell you nothing!)
@@ -143,7 +151,6 @@ def get_full_go_summary(core_gene_ontology, go2protein_count_dict, top_level_go_
 
 
 def main():
-
     go_obo, go_banding, gaf_input, ips_input, output = parse_args()
 
     logging.info("Parsing the InterProScan input: " + ips_input)

mgnify_pipelines_toolkit-1.0.3/mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# Copyright 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.
+
+"""
+    Script to convert cmscan-table to cmsearch-table (swap columns 1 and 2 with 3 and 4)
+
+    input example:
+    #target name         accession query name           accession mdl mdl from   mdl to seq from   seq to strand ..
+    #------------------- --------- -------------------- --------- --- -------- -------- -------- -------- ------ ..
+    SSU_rRNA_eukarya     RF01960   SRR17062740.1        -          cm      582     1025        1      452      + ..
+
+    expected output:
+    #------------------- --------- -------------------- --------- --- -------- -------- -------- -------- ------ ..
+    #target name         accession query name           accession mdl mdl from   mdl to seq from   seq to strand ..
+    SRR17062740.1        -         SSU_rRNA_eukarya     RF01960    cm      582     1025        1      452      + ..
+
+"""
+
+import sys
+import argparse
+import fileinput
+from itertools import accumulate
+
+
+def parse_args(argv):
+    parser = argparse.ArgumentParser(
+        description="Convert cmscan table to cmsearch table"
+    )
+    parser.add_argument(
+        "-i", "--input", dest="input", help="Input cmscan file", required=True
+    )
+    parser.add_argument(
+        "-o", "--output", dest="output", help="Output filename", required=True
+    )
+    return parser.parse_args(argv)
+
+
+class TableModifier:
+    def __init__(
+        self,
+        input_file: str,
+        output_file: str,
+    ):
+        """
+        Output of cmsearch-table has columns separated with different number of spaces (to keep humanreadable format)
+        :param input_file: output of cmscan-table
+        :param output_file: name of cmsearch table
+        """
+        self.input_file = input_file
+        self.output_file = output_file
+
+    def modify_table(self):
+        with fileinput.hook_compressed(self.input_file, "rt") as file_in, open(
+            self.output_file, "w"
+        ) as file_out:
+            header_written = False
+            separator_line, header = "", ""
+            for line in file_in:
+                if line.startswith("#"):
+                    if "--" in line:
+                        separator_line = line.split(" ")
+                        separator_line[0] = separator_line[0].replace("#", "-")
+                        lengths = [0] + list(
+                            accumulate(len(s) + 1 for s in separator_line)
+                        )
+                    else:
+                        header = line
+                else:
+                    coord_to_keep = len(" ".join(separator_line[0:4]))
+                    if not header_written:
+                        file_out.write(header)
+                        file_out.write(
+                            " ".join(
+                                [
+                                    "#" + separator_line[2][1:],
+                                    separator_line[3],
+                                    separator_line[0].replace("#", ""),
+                                    separator_line[1],
+                                ]
+                                + separator_line[4:]
+                            )
+                        )
+                        header_written = True
+                    new_line = (
+                        line[lengths[2] : lengths[3]]
+                        + line[lengths[3] : lengths[4]]
+                        + line[lengths[0] : lengths[1]]
+                        + line[lengths[1] : lengths[2]]
+                        + line[coord_to_keep + 1 :]
+                    )
+                    file_out.write(new_line)
+
+
+def main():
+    args = parse_args(sys.argv[1:])
+    table_modifier = TableModifier(
+        input_file=args.input,
+        output_file=args.output,
+    )
+    table_modifier.modify_table()
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit-1.0.3/mgnify_pipelines_toolkit/analysis/shared/get_subunits.py

@@ -0,0 +1,141 @@
+#!/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 os
+from Bio import SeqIO
+from mgnify_pipelines_toolkit.constants.ncrna import (
+    DIRECTORY_SEQ_CAT,
+    SSU,
+    LSU,
+    Seq5S,
+    Seq5_8S,
+    SSU_rRNA_archaea,
+    SSU_rRNA_bacteria,
+    SSU_rRNA_eukarya,
+    SSU_rRNA_microsporidia,
+    LSU_rRNA_archaea,
+    LSU_rRNA_bacteria,
+    LSU_rRNA_eukarya,
+    NON_CODING_RNA,
+    SSU_MODELS,
+    LSU_MODELS,
+    RFAM_MODELS,
+)
+
+
+def set_model_names(prefix, name, directory, separate_subunits):
+    pattern_dict = {}
+    pattern_dict[SSU] = os.path.join(directory, f"{name}_SSU.fasta")
+    pattern_dict[LSU] = os.path.join(directory, f"{name}_LSU.fasta")
+    pattern_dict[Seq5S] = os.path.join(directory, f"{name}_5S.fasta")
+    pattern_dict[Seq5_8S] = os.path.join(directory, f"{name}_5_8S.fasta")
+    if separate_subunits:
+        pattern_dict[SSU_rRNA_archaea] = os.path.join(
+            directory,
+            f"{prefix}{name}_{SSU_rRNA_archaea}.{RFAM_MODELS[SSU_rRNA_archaea]}.fasta",
+        )
+        pattern_dict[SSU_rRNA_bacteria] = os.path.join(
+            directory,
+            f"{prefix}{name}_{SSU_rRNA_bacteria}.{RFAM_MODELS[SSU_rRNA_bacteria]}.fasta",
+        )
+        pattern_dict[SSU_rRNA_eukarya] = os.path.join(
+            directory,
+            f"{prefix}{name}_{SSU_rRNA_eukarya}.{RFAM_MODELS[SSU_rRNA_eukarya]}.fasta",
+        )
+        pattern_dict[SSU_rRNA_microsporidia] = os.path.join(
+            directory,
+            f"{prefix}{name}_{SSU_rRNA_microsporidia}.{RFAM_MODELS[SSU_rRNA_microsporidia]}.fasta",
+        )
+        pattern_dict[LSU_rRNA_archaea] = os.path.join(
+            directory,
+            f"{prefix}{name}_{LSU_rRNA_archaea}.{RFAM_MODELS[LSU_rRNA_archaea]}.fasta",
+        )
+        pattern_dict[LSU_rRNA_bacteria] = os.path.join(
+            directory,
+            f"{prefix}{name}_{LSU_rRNA_bacteria}.{RFAM_MODELS[LSU_rRNA_bacteria]}.fasta",
+        )
+        pattern_dict[LSU_rRNA_eukarya] = os.path.join(
+            directory,
+            f"{prefix}{name}_{LSU_rRNA_eukarya}.{RFAM_MODELS[LSU_rRNA_eukarya]}.fasta",
+        )
+    return pattern_dict
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Extract lsu, ssu and 5s and other models"
+    )
+    parser.add_argument(
+        "-i", "--input", dest="input", help="Input fasta file", required=True
+    )
+    parser.add_argument(
+        "-p", "--prefix", dest="prefix", help="prefix for models", required=False
+    )
+    parser.add_argument("-n", "--name", dest="name", help="Accession", required=True)
+    parser.add_argument(
+        "--separate-subunits-by-models",
+        action="store_true",
+        help="Create separate files for each kingdon example: sample_SSU_rRNA_eukarya.RF01960.fasta",
+    )
+
+    args = parser.parse_args()
+    prefix = args.prefix if args.prefix else ""
+    name = args.name if args.name else "accession"
+
+    directory = DIRECTORY_SEQ_CAT
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+    print("Start fasta mode")
+    pattern_dict = set_model_names(
+        prefix, name, directory, args.separate_subunits_by_models
+    )
+
+    open_files = {}
+    for record in SeqIO.parse(args.input, "fasta"):
+        model = "-".join(record.id.split("/")[0].split("-")[-1:])
+        if model in SSU_MODELS:
+            if SSU not in open_files:
+                file_out = open(pattern_dict[SSU], "w")
+                open_files[SSU] = file_out
+            SeqIO.write(record, open_files[SSU], "fasta")
+        elif model in LSU_MODELS:
+            if LSU not in open_files:
+                file_out = open(pattern_dict[LSU], "w")
+                open_files[LSU] = file_out
+            SeqIO.write(record, open_files[LSU], "fasta")
+
+        if model in NON_CODING_RNA:
+            if model in pattern_dict:
+                filename = pattern_dict[model]
+            else:
+                filename = None
+        else:
+            filename = os.path.join(directory, f"{name}_other_ncRNA.fasta")
+        if filename:
+            if model not in open_files:
+                file_out = open(filename, "w")
+                open_files[model] = file_out
+            SeqIO.write(record, open_files[model], "fasta")
+
+    for item in open_files:
+        open_files[item].close()
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit-1.0.3/mgnify_pipelines_toolkit/constants/ncrna.py

@@ -0,0 +1,84 @@
+#!/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.
+
+DIRECTORY_SEQ_CAT = "sequence-categorisation"
+
+SSU = "SSU_rRNA"
+LSU = "LSU_rRNA"
+Seq5S = "mtPerm-5S"
+Seq5_8S = "5_8S_rRNA"
+
+SSU_rRNA_archaea = "SSU_rRNA_archaea"
+SSU_rRNA_bacteria = "SSU_rRNA_bacteria"
+SSU_rRNA_eukarya = "SSU_rRNA_eukarya"
+SSU_rRNA_microsporidia = "SSU_rRNA_microsporidia"
+
+LSU_rRNA_archaea = "LSU_rRNA_archaea"
+LSU_rRNA_bacteria = "LSU_rRNA_bacteria"
+LSU_rRNA_eukarya = "LSU_rRNA_eukarya"
+
+NON_CODING_RNA = [
+    SSU_rRNA_archaea,
+    SSU_rRNA_bacteria,
+    SSU_rRNA_eukarya,
+    SSU_rRNA_microsporidia,
+    LSU_rRNA_archaea,
+    LSU_rRNA_bacteria,
+    LSU_rRNA_eukarya,
+    Seq5S,
+    Seq5_8S,
+]
+
+SSU_MODELS = [
+    SSU_rRNA_archaea,
+    SSU_rRNA_bacteria,
+    SSU_rRNA_eukarya,
+    SSU_rRNA_microsporidia,
+]
+
+LSU_MODELS = [LSU_rRNA_archaea, LSU_rRNA_bacteria, LSU_rRNA_eukarya]
+
+RFAM_MODELS = {
+    SSU_rRNA_archaea: "RF01959",
+    SSU_rRNA_bacteria: "RF00177",
+    SSU_rRNA_eukarya: "RF01960",
+    SSU_rRNA_microsporidia: "RF02542",
+    LSU_rRNA_archaea: "RF02540",
+    LSU_rRNA_bacteria: "RF02541",
+    LSU_rRNA_eukarya: "RF02543",
+}
+
+TRNA = [
+    "Ala",
+    "Gly",
+    "Pro",
+    "Thr",
+    "Val",
+    "Ser",
+    "Arg",
+    "Leu",
+    "Phe",
+    "Asn",
+    "Lys",
+    "Asp",
+    "Glu",
+    "His",
+    "Gln",
+    "Ile",
+    "Tyr",
+    "Cys",
+    "Trp",
+]

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.1
+Version: 1.0.3
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0
@@ -38,6 +38,7 @@ 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"
+Dynamic: license-file
 
 # mgnify-pipelines-toolkit
 

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/mgnify_pipelines_toolkit.egg-info/SOURCES.txt

@@ -29,8 +29,11 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_annotation_utils.py
 mgnify_pipelines_toolkit/analysis/assembly/gff_file_utils.py
 mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py
+mgnify_pipelines_toolkit/analysis/assembly/krona_txt_from_cat_classification.py
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py
+mgnify_pipelines_toolkit/analysis/genomes/__init__.py
 mgnify_pipelines_toolkit/analysis/shared/__init__.py
+mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py
 mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py
 mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py
 mgnify_pipelines_toolkit/analysis/shared/get_subunits.py
@@ -40,6 +43,7 @@ mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py
 mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py
 mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.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-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/mgnify_pipelines_toolkit.egg-info/entry_points.txt

@@ -1,18 +1,24 @@
 [console_scripts]
 add_rhea_chebi_annotation = mgnify_pipelines_toolkit.analysis.assembly.add_rhea_chebi_annotation:main
+antismash_gff_builder = mgnify_pipelines_toolkit.analysis.assembly.antismash_gff_builder:main
 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
 combined_gene_caller_merge = mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:main
-dwc_summary_generator = mgnify_pipelines_toolkit.analysis.assembly.dwc_summary_generator: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
+genomes_extract_trnas = mgnify_pipelines_toolkit.analysis.genomes.rna.extract_trnas: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
+krona_txt_from_cat_classification = mgnify_pipelines_toolkit.analysis.assembly.krona_txt_from_cat_classification: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

{mgnify_pipelines_toolkit-1.0.1 → mgnify_pipelines_toolkit-1.0.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "1.0.1"
+version = "1.0.3"
 readme = "README.md"
 license = {text = "Apache Software License 2.0"}
 authors = [
@@ -40,10 +40,11 @@ packages = ["mgnify_pipelines_toolkit",
             "mgnify_pipelines_toolkit.analysis.shared",
             "mgnify_pipelines_toolkit.analysis.amplicon",
             "mgnify_pipelines_toolkit.analysis.assembly",
-            ]
+            "mgnify_pipelines_toolkit.analysis.genomes"
+]
 
 [project.scripts]
-# analysis.shared
+# analysis.shared #
 get_subunits = "mgnify_pipelines_toolkit.analysis.shared.get_subunits:main"
 get_subunits_coords = "mgnify_pipelines_toolkit.analysis.shared.get_subunits_coords:main"
 mapseq2biom = "mgnify_pipelines_toolkit.analysis.shared.mapseq2biom:main"
@@ -51,7 +52,9 @@ fastq_suffix_header_check = "mgnify_pipelines_toolkit.analysis.shared.fastq_suff
 library_strategy_check = "mgnify_pipelines_toolkit.analysis.shared.library_strategy_check:main"
 study_summary_generator = "mgnify_pipelines_toolkit.analysis.shared.study_summary_generator:cli"
 markergene_study_summary = "mgnify_pipelines_toolkit.analysis.shared.markergene_study_summary:main"
-# analysis.amplicon
+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"
@@ -63,12 +66,18 @@ rev_comp_se_primers = "mgnify_pipelines_toolkit.analysis.amplicon.rev_comp_se_pr
 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"
-# analysis.assembly
+# analysis.assembly #
+krona_txt_from_cat_classification = "mgnify_pipelines_toolkit.analysis.assembly.krona_txt_from_cat_classification:main"
 add_rhea_chebi_annotation = "mgnify_pipelines_toolkit.analysis.assembly.add_rhea_chebi_annotation:main"
 combined_gene_caller_merge = "mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:main"
 generate_gaf = "mgnify_pipelines_toolkit.analysis.assembly.generate_gaf:main"
 summarise_goslims = "mgnify_pipelines_toolkit.analysis.assembly.summarise_goslims:main"
-dwc_summary_generator = "mgnify_pipelines_toolkit.analysis.assembly.dwc_summary_generator:main"
+antismash_gff_builder = "mgnify_pipelines_toolkit.analysis.assembly.antismash_gff_builder:main"
+# genomes #
+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"
+genomes_extract_trnas = "mgnify_pipelines_toolkit.analysis.genomes.rna.extract_trnas:main"
+
 # utils
 fasta_to_delimited = "mgnify_pipelines_toolkit.utils.fasta_to_delimited:main"
 get_mpt_version = "mgnify_pipelines_toolkit.utils.get_mpt_version:main"

mgnify_pipelines_toolkit-1.0.1/mgnify_pipelines_toolkit/analysis/shared/get_subunits.py

@@ -1,139 +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 os
-from Bio import SeqIO
-
-
-SSU = "SSU_rRNA"
-LSU = "LSU_rRNA"
-Seq5S = "mtPerm-5S"
-Seq5_8S = "5_8S_rRNA"
-
-SSU_rRNA_archaea = "SSU_rRNA_archaea"
-SSU_rRNA_bacteria = "SSU_rRNA_bacteria"
-SSU_rRNA_eukarya = "SSU_rRNA_eukarya"
-SSU_rRNA_microsporidia = "SSU_rRNA_microsporidia"
-
-LSU_rRNA_archaea = "LSU_rRNA_archaea"
-LSU_rRNA_bacteria = "LSU_rRNA_bacteria"
-LSU_rRNA_eukarya = "LSU_rRNA_eukarya"
-
-
-def set_model_names(prefix, name, directory):
-    pattern_dict = {}
-    pattern_dict[SSU] = os.path.join(directory, f"{name}_SSU.fasta")
-    pattern_dict[SSU_rRNA_archaea] = os.path.join(
-        directory, f"{prefix}{name}_{SSU_rRNA_archaea}.RF01959.fa"
-    )
-    pattern_dict[SSU_rRNA_bacteria] = os.path.join(
-        directory, f"{prefix}{name}_{SSU_rRNA_bacteria}.RF00177.fa"
-    )
-    pattern_dict[SSU_rRNA_eukarya] = os.path.join(
-        directory, f"{prefix}{name}_{SSU_rRNA_eukarya}.RF01960.fa"
-    )
-    pattern_dict[SSU_rRNA_microsporidia] = os.path.join(
-        directory, f"{prefix}{name}_{SSU_rRNA_microsporidia}.RF02542.fa"
-    )
-    pattern_dict[LSU] = os.path.join(directory, f"{name}_LSU.fasta")
-    pattern_dict[LSU_rRNA_archaea] = os.path.join(
-        directory, f"{prefix}{name}_{LSU_rRNA_archaea}.RF02540.fa"
-    )
-    pattern_dict[LSU_rRNA_bacteria] = os.path.join(
-        directory, f"{prefix}{name}_{LSU_rRNA_bacteria}.RF02541.fa"
-    )
-    pattern_dict[LSU_rRNA_eukarya] = os.path.join(
-        directory, f"{prefix}{name}_{LSU_rRNA_eukarya}.RF02543.fa"
-    )
-    pattern_dict[Seq5S] = os.path.join(directory, f"{name}_5S.fa")
-    pattern_dict[Seq5_8S] = os.path.join(directory, f"{name}_5_8S.fa")
-    return pattern_dict
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Extract lsu, ssu and 5s and other models"
-    )
-    parser.add_argument(
-        "-i", "--input", dest="input", help="Input fasta file", required=True
-    )
-    parser.add_argument(
-        "-p", "--prefix", dest="prefix", help="prefix for models", required=False
-    )
-    parser.add_argument("-n", "--name", dest="name", help="Accession", required=True)
-
-    args = parser.parse_args()
-    prefix = args.prefix if args.prefix else ""
-    name = args.name if args.name else "accession"
-
-    directory = "sequence-categorisation"
-    if not os.path.exists(directory):
-        os.makedirs(directory)
-    directory_ncrna = os.path.join("sequence-categorisation", "ncRNA")
-    if not os.path.exists(directory_ncrna):
-        os.makedirs(directory_ncrna)
-
-    print("Start fasta mode")
-    pattern_dict = set_model_names(prefix, name, directory)
-    coding_rna = [
-        SSU_rRNA_archaea,
-        SSU_rRNA_bacteria,
-        SSU_rRNA_eukarya,
-        SSU_rRNA_microsporidia,
-        LSU_rRNA_archaea,
-        LSU_rRNA_bacteria,
-        LSU_rRNA_eukarya,
-        Seq5S,
-        Seq5_8S,
-    ]
-    open_files = {}
-    for record in SeqIO.parse(args.input, "fasta"):
-        model = "-".join(record.id.split("/")[0].split("-")[-1:])
-        if model in coding_rna:
-            filename = pattern_dict[model]
-        else:
-            filename = os.path.join(directory_ncrna, f"{prefix}{name}_{model}.fasta")
-        if model not in open_files:
-            file_out = open(filename, "w")
-            open_files[model] = file_out
-        SeqIO.write(record, open_files[model], "fasta")
-
-        if model in (
-            SSU_rRNA_archaea,
-            SSU_rRNA_bacteria,
-            SSU_rRNA_eukarya,
-            SSU_rRNA_microsporidia,
-        ):
-            if SSU not in open_files:
-                file_out = open(pattern_dict[SSU], "w")
-                open_files[SSU] = file_out
-            SeqIO.write(record, open_files[SSU], "fasta")
-        if model in (LSU_rRNA_archaea, LSU_rRNA_bacteria, LSU_rRNA_eukarya):
-            if LSU not in open_files:
-                file_out = open(pattern_dict[LSU], "w")
-                open_files[LSU] = file_out
-            SeqIO.write(record, open_files[LSU], "fasta")
-
-    for item in open_files:
-        open_files[item].close()
-
-    if len(os.listdir(directory_ncrna)) == 0:
-        os.rmdir(directory_ncrna)
-
-
-if __name__ == "__main__":
-    main()