mgnify-pipelines-toolkit 1.0.1__py3-none-any.whl → 1.0.2__py3-none-any.whl

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/analysis/shared/get_subunits.py

@@ -14,53 +14,65 @@
 # 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):
+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[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")
+    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
 
 
@@ -75,65 +87,55 @@ def main():
         "-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 = "sequence-categorisation"
+    directory = DIRECTORY_SEQ_CAT
     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,
-    ]
+    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 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 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")
-        if model in (LSU_rRNA_archaea, LSU_rRNA_bacteria, LSU_rRNA_eukarya):
+        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 len(os.listdir(directory_ncrna)) == 0:
-        os.rmdir(directory_ncrna)
-
 
 if __name__ == "__main__":
     main()

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-1.0.1.dist-info → mgnify_pipelines_toolkit-1.0.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.0.1
+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-1.0.1.dist-info → mgnify_pipelines_toolkit-1.0.2.dist-info}/RECORD

@@ -22,15 +22,17 @@ mgnify_pipelines_toolkit/analysis/assembly/gff_toolkit.py,sha256=uUIo97gmzO2zzN-
 mgnify_pipelines_toolkit/analysis/assembly/go_utils.py,sha256=5D-9rB3omTxKwZuS_WjgyjsaaSPNnvZoXeThofWrK7k,5452
 mgnify_pipelines_toolkit/analysis/assembly/summarise_goslims.py,sha256=07CbJdpo-Gy2aglCFiu2mHbkY18pYMlLFLPnYoD7tyk,5839
 mgnify_pipelines_toolkit/analysis/shared/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mgnify_pipelines_toolkit/analysis/shared/convert_cmscan_to_cmsearch_tblout.py,sha256=0Ot1j4LPsEPyPbySSAh6n9s5Dilm_8_M9YQvTnQ-1PQ,4415
 mgnify_pipelines_toolkit/analysis/shared/dwc_summary_generator.py,sha256=hggPqv9QawWAccm5tmru4VF9VnQAHF5LCXnqyLw_BWI,6727
 mgnify_pipelines_toolkit/analysis/shared/fastq_suffix_header_check.py,sha256=ye0Jka6_lNn4dQGb2QG3YT46y7QK0QvyaIitIaS8JVQ,4026
-mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=NhX6cSLu9QB9I5JKNUJwJVMmcRcbG-0MJCEgDJ5DxtE,4777
+mgnify_pipelines_toolkit/analysis/shared/get_subunits.py,sha256=j_UN3hItF7KhJrhGrSqjvZMg-ZwKAMc2sc0vHdJzjQw,4908
 mgnify_pipelines_toolkit/analysis/shared/get_subunits_coords.py,sha256=EH5RyzesLqsonnTQbSDs7kAOV6IskS4oyqZYlex1tAY,1934
 mgnify_pipelines_toolkit/analysis/shared/library_strategy_check.py,sha256=6Ck2NhwRWw66GctUtKDdPT5fwJhWFR_YOZq-Vxwoa8A,1996
 mgnify_pipelines_toolkit/analysis/shared/mapseq2biom.py,sha256=7-U0DN1joVu0ifLOoDUK2Pfqy8rb1RDKT6khVg3jky0,5559
 mgnify_pipelines_toolkit/analysis/shared/markergene_study_summary.py,sha256=sKAo_rKEyVAZXSaIFMkpSoYZxiWwXMA3XDA6Z-hbHgg,7904
 mgnify_pipelines_toolkit/analysis/shared/study_summary_generator.py,sha256=OOqKaQmKGAya6_BZgfcWBZSVlmZ918PQTVMv6KwGIns,13827
 mgnify_pipelines_toolkit/constants/db_labels.py,sha256=omPINMylAjO2PxeFhSk2MbYNcGZH3P82optSlMey3dw,858
+mgnify_pipelines_toolkit/constants/ncrna.py,sha256=RCpV2EG1gwm_5v3yJH0SFB-T3_z0aAz0X-02b5LTHGk,1707
 mgnify_pipelines_toolkit/constants/regex_ambiguous_bases.py,sha256=7nEOODQq35y9wx9YnvJuo29oBpwTpXg_kIbf_t7N4TQ,1093
 mgnify_pipelines_toolkit/constants/regex_fasta_header.py,sha256=G-xrc9b8zdmPTaOICD2b3RCVeFAEOVkfRkIfotQ7gek,1193
 mgnify_pipelines_toolkit/constants/tax_ranks.py,sha256=kMq__kOJcbiwsgolkdvb-XLo3WMnJdEXgedjUyMOYjI,1081
@@ -40,9 +42,9 @@ mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pnH8LUH8i2ACNvFNWyG-n-eIHZcI5
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=lgYIR1S4crURY7C7nFtgE6QMV4u4zCNsUrVkcRnsEEo,3996
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=aS9bWrC9CP7tpxoEVg6eEYt18-pmjG7fJl5Mchz4YOU,798
-mgnify_pipelines_toolkit-1.0.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.0.1.dist-info/METADATA,sha256=3xW9nS84AonTMO6tWU03fii6CqyV5-oa7pa4XrlYvWE,6181
-mgnify_pipelines_toolkit-1.0.1.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-mgnify_pipelines_toolkit-1.0.1.dist-info/entry_points.txt,sha256=MsQXFdzL_dd7-2V6kHtA-QCf_iSQ-FmDcB9nZMLzJ98,2301
-mgnify_pipelines_toolkit-1.0.1.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.0.1.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.0.2.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.0.2.dist-info/METADATA,sha256=YWs_6ycCLrZFbrsScKxtMb-_xhj2lZuxnaAmOBOGPyk,6203
+mgnify_pipelines_toolkit-1.0.2.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
+mgnify_pipelines_toolkit-1.0.2.dist-info/entry_points.txt,sha256=v0fD1Qi0NUGgkBinQp34VLxqwMvXOkof7BvuX9B5Q-o,2417
+mgnify_pipelines_toolkit-1.0.2.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.0.2.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.0.1.dist-info → mgnify_pipelines_toolkit-1.0.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: setuptools (77.0.3)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{mgnify_pipelines_toolkit-1.0.1.dist-info → mgnify_pipelines_toolkit-1.0.2.dist-info}/entry_points.txt

@@ -5,6 +5,7 @@ assess_inflection_point_mcp = mgnify_pipelines_toolkit.analysis.amplicon.assess_
 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.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