Extend annotations

.editorconfig

@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml,html,css,scss,js}]
+[*.{md,yml,yaml,html,css,scss,js,json}]
 indent_size = 2
 
 # These files are edited and tested upstream in nf-core/modules

.github/workflows/linting.yml

@@ -78,7 +78,7 @@ jobs:
 
       - uses: actions/setup-python@v4
         with:
-          python-version: "3.8"
+          python-version: "3.11"
           architecture: "x64"
 
       - name: Install dependencies

assets/multiqc_config.yml

@@ -9,11 +9,24 @@ report_section_order:
   "ebi-metagenomics-mettannotator-summary":
     order: -1002
 
+run_modules:
+  - quast
+  - prokka
+  - custom_content
+
 top_modules:
   - quast
+  - prokka
+
+prokka_table: true
+prokka_fn_snames: true
 
 sp:
   quast_config:
     fn: "*.tsv"
 
 export_plots: true
+
+## Prettification
+custom_logo_url: https://github.com/ebi-metagenomics/mettannotator
+custom_logo_title: "ebi-metagenomics/mettannotator"

bin/antismash_to_gff.py

@@ -0,0 +1,155 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+# Copyright 2023 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 json
+from collections import namedtuple
+
+import logging
+
+logger = logging.getLogger(__name__)
+
+BGC = namedtuple("BGC", "contig_name bgc_name start end orfs")
+ORF = namedtuple("ORF", "locus_tag start end strand type product")
+
+
+def load_regions_json(json_file) -> list[BGC]:
+    """Load the gene types from the json
+    The structure of the json is:
+    {
+        "length": 4688977,
+        "seq_id": "contig_4",
+        "regions": [{
+            "start": 1185393,
+            "end": 1205746,
+            "idx": 1,
+            "orfs": [
+                {
+                "start": 1187624,
+                "end": 1188664,
+                "strand": 1,
+                "locus_tag": "BU_ATCC8492_00951",
+                "type": "biosynthetic-additional",
+                "description": "<div class=\"focus-intro\">\n <strong><span class=\"serif\">BU_ATCC8492_00951</span></strong><br>... ",
+                "dna": "ATGCAGAAACGACCTCT...",
+                "translation": "MQKRPLLGLT...",
+                "product": "Dual-specificity RNA methyltransferase RlmN"
+            },...
+        ],..
+    }
+    Note: this json file is build from the regions.js file of the html output of antiSMASH.
+    To build the json file:
+    echo ";var fs = require('fs'); fs.writeFileSync('./regions.json', JSON.stringify(recordData));" >> convert_to_json.js
+    node geneclusters.js # this will generate the geneclusters.json file
+    """
+
+    bgcs = []
+
+    with open(json_file) as json_handle:
+        json_dict = json.load(json_handle)
+        for bgc_entry in json_dict:
+            regions = bgc_entry.get("regions")
+            if not regions:
+                # ignore this contig, no bgc found
+                continue
+            for region in regions:
+                index = region["idx"]
+                region_start = region["start"]
+                region_end = region["end"]
+                bgc_orfs = []
+                for orf in region.get("orfs", []):
+                    bgc_orfs.append(
+                        ORF(
+                            locus_tag=orf["locus_tag"],
+                            start=orf["start"],
+                            end=orf["end"],
+                            strand=int(orf["strand"]),
+                            product=orf["product"],
+                            type=orf["type"],
+                        )
+                    )
+                bgcs.append(
+                    BGC(
+                        contig_name=bgc_entry["seq_id"],
+                        bgc_name=f"{bgc_entry['seq_id']}_bgc{index}",
+                        start=region_start,
+                        end=region_end,
+                        orfs=bgc_orfs,
+                    )
+                )
+
+    return bgcs
+
+
+def build_gff(regions_json, antismash_version):
+    """Build the GFF from the geneclusters and the EMBL file"""
+    bgc_regions: list[BGC] = load_regions_json(regions_json)
+    for bgc in bgc_regions:
+        # BGC region "parent"
+        yield [
+            bgc.contig_name,
+            f"antiSMASH:{antismash_version}",
+            "biosynthetic-gene-cluster",
+            bgc.start,
+            bgc.end,
+            ".",
+            ".",
+            ".",
+            f"ID={bgc.bgc_name}",
+        ]
+        orf: ORF
+        for orf in bgc.orfs:
+            yield [
+                bgc.contig_name,
+                f"antiSMASH:{antismash_version}",
+                "CDS",
+                orf.start, # FIXME, shoud we correct offset (gff are +1)?
+                orf.end,
+                ".",  # TODO, it should be possible to get the confidence score from the antismash gbk result file
+                "+" if orf.strand == 1 else "-",
+                ".",
+                ";".join(
+                    [
+                        f"ID={orf.locus_tag}",
+                        f"Parent={bgc.bgc_name}",
+                        f"product={orf.product}",
+                        f"function={orf.type}"
+                    ]
+                ),
+            ]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Build an antiSMASH gff from the gbk and regionsjs json~fied file")
+    parser.add_argument(
+        "-r",
+        dest="regions",
+        help="antiSMASH json-fied regions.js file (it should be regions.json not .js)",
+        required=True,
+    )
+    parser.add_argument(
+        "-a",
+        dest="antismash_version",
+        help="The version of antiSMASH",
+        required=True,
+    )
+    parser.add_argument("-o", dest="out", help="Ouput GFF file name", required=True)
+    args = parser.parse_args()
+
+    with open(args.out, "w") as out_handle:
+        print("##gff-version 3", file=out_handle)
+        for row in build_gff(args.regions, args.antismash_version):
+            print("\t".join(map(str, row)), file=out_handle)