mgnify-pipelines-toolkit 1.0.0__tar.gz → 1.0.2__tar.gz

{mgnify_pipelines_toolkit-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.0
+Version: 1.0.2
 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-1.0.2/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-1.0.2/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-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
+import shutil
+from shutil import SameFileError
 
 # Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
@@ -33,6 +35,7 @@ from mgnify_pipelines_toolkit.schemas.schemas import (
     AmpliconNonINSDCPassedRunsSchema,
     TaxonSchema,
     PR2TaxonSchema,
+    validate_dataframe,
 )
 
 logging.basicConfig(level=logging.DEBUG)
@@ -127,9 +130,9 @@ def parse_one_tax_file(
     # Two different schemas used for validation depending on the database
     # because PR2 schema has different taxonomic ranks than the standard
     if len(long_tax_ranks) == 8:
-        TaxonSchema(res_df)
+        validate_dataframe(res_df, TaxonSchema, str(tax_file))
     elif len(long_tax_ranks) == 9:
-        PR2TaxonSchema(res_df)
+        validate_dataframe(res_df, PR2TaxonSchema, str(tax_file))
 
     res_df["full_taxon"] = res_df.iloc[:, 1:].apply(
         lambda x: ";".join(x).strip(";"), axis=1
@@ -205,9 +208,7 @@ def generate_db_summary(
                 amp_region_dict[amp_region].append(amp_region_df)
 
         for amp_region, amp_region_dfs in amp_region_dict.items():
-            if (
-                len(amp_region_dfs) > 1
-            ):  # Need at least two analyses with this amp_region to bother with the summary
+            if amp_region_dfs:
                 amp_res_df = amp_region_dfs[0]
                 for amp_df in amp_region_dfs[1:]:
                     amp_res_df = amp_res_df.join(amp_df, how="outer")
@@ -319,9 +320,7 @@ def summarise_analyses(
             if tax_file:
                 tax_files[run_acc] = tax_file
 
-        if (
-            len(tax_files) > 1
-        ):  # If at least two analyses have results from the current DB, generate a study-level summary for it
+        if tax_files:
             generate_db_summary(db_label, tax_files, output_prefix)
 
 
@@ -356,12 +355,12 @@ def merge_summaries(analyses_dir: str, output_prefix: str) -> None:
     :type output_prefix: str
     """
 
-    # TODO: The way we grab all the summaries might change depending on how the prefect side does things
     all_study_summaries = glob.glob(f"{analyses_dir}/*_study_summary.tsv")
 
     summaries_dict = organise_study_summaries(all_study_summaries)
 
     for db_label, summaries in summaries_dict.items():
+        merged_summary_name = f"{output_prefix}_{db_label}_study_summary.tsv"
         if len(summaries) > 1:
             res_df = pd.read_csv(summaries[0], sep="\t", index_col=0)
             for summary in summaries[1:]:
@@ -372,10 +371,18 @@ def merge_summaries(analyses_dir: str, output_prefix: str) -> None:
 
             res_df = res_df.reindex(sorted(res_df.columns), axis=1)
             res_df.to_csv(
-                f"{output_prefix}_{db_label}_study_summary.tsv",
+                merged_summary_name,
                 sep="\t",
                 index_label="taxonomy",
             )
+        elif len(summaries) == 1:
+            logging.info(
+                f"Only one summary ({summaries[0]}) so will use that as {merged_summary_name}"
+            )
+            try:
+                shutil.copyfile(summaries[0], merged_summary_name)
+            except SameFileError:
+                pass
 
 
 if __name__ == "__main__":

mgnify_pipelines_toolkit-1.0.2/mgnify_pipelines_toolkit/constants/ncrna.py

@@ -0,0 +1,62 @@
+#!/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",
+}

{mgnify_pipelines_toolkit-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/mgnify_pipelines_toolkit/schemas/schemas.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-
 # Copyright 2024-2025 EMBL - European Bioinformatics Institute
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -14,11 +13,15 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import logging
 import re
 
 from enum import Enum
-from typing import ClassVar, Optional
+from typing import ClassVar, Optional, Type
+
+import pandas as pd
 import pandera as pa
+from pandera.typing.common import DataFrameBase
 
 from pydantic import (
     Field,
@@ -215,3 +218,18 @@ class PR2TaxonSchema(pa.DataFrameModel):
 
         dtype = PydanticModel(PR2TaxonRecord)
         coerce = True
+
+
+def validate_dataframe(
+    df: pd.DataFrame, schema: Type[pa.DataFrameModel], df_metadata: str
+) -> DataFrameBase:
+    """
+    Validate a pandas dataframe using a pandera schema.
+    df_metadata will be shown in logs on failure: example, the TSV filename from which the df was read.
+    """
+    try:
+        dfs = schema.validate(df, lazy=True)
+    except pa.errors.SchemaErrors as e:
+        logging.error(f"{schema.__name__} validation failure for {df_metadata}")
+        raise e
+    return dfs

{mgnify_pipelines_toolkit-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/mgnify_pipelines_toolkit.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.0
+Version: 1.0.2
 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-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/mgnify_pipelines_toolkit.egg-info/SOURCES.txt

@@ -31,6 +31,7 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.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 +41,7 @@ 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-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/mgnify_pipelines_toolkit.egg-info/entry_points.txt

@@ -4,7 +4,8 @@ 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
-combined_gene_caller_merge = mgnify_pipelines_toolkit.analysis.assembly.combined_gene_caller_merge:combine_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.assembly.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

{mgnify_pipelines_toolkit-1.0.0 → mgnify_pipelines_toolkit-1.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mgnify_pipelines_toolkit"
-version = "1.0.0"
+version = "1.0.2"
 readme = "README.md"
 license = {text = "Apache Software License 2.0"}
 authors = [
@@ -51,6 +51,7 @@ 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"
+convert_cmscan_to_cmsearch_tblout = "mgnify_pipelines_toolkit.analysis.shared.convert_cmscan_to_cmsearch_tblout: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"
@@ -65,7 +66,7 @@ mapseq_to_asv_table = "mgnify_pipelines_toolkit.analysis.amplicon.mapseq_to_asv_
 primer_val_classification = "mgnify_pipelines_toolkit.analysis.amplicon.primer_val_classification:main"
 # analysis.assembly
 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:combine_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"

mgnify_pipelines_toolkit-1.0.0/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()