Add agat sp merge annotations

CHANGELOG.md

@@ -21,6 +21,8 @@
 
 * `agat/agat_convert_sp_gff2gtf`: convert any GTF/GFF file into a proper GTF file (PR #76).
 
+* `agat/agat_sp_merge_annotations`: merge different gff annotation files in one (PR #106).
+
 ## MINOR CHANGES
 
 * `busco` components: update BUSCO to `5.7.1` (PR #72).

src/agat/agat_sp_merge_annotations/config.vsh.yaml

@@ -0,0 +1,72 @@
+name: agat_sp_merge_annotations
+namespace: agat
+description: |
+  This script merge different gff annotation files in one. It uses the
+  AGAT parser that takes care of duplicated names and fixes other oddities
+  met in those files.
+keywords: [gene annotations]
+links:
+  homepage: https://github.com/NBISweden/AGAT
+  documentation: https://agat.readthedocs.io/en/latest/tools/agat_sp_merge_annotations.html
+  issue_tracker: https://github.com/NBISweden/AGAT/issues
+  repository: https://github.com/NBISweden/AGAT
+references: 
+  doi: 10.5281/zenodo.3552717
+license: GPL-3.0
+authors:
+  - __merge__: /src/_authors/leila_paquay.yaml
+    roles: [ author, maintainer ]
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --gff
+        alternatives: [-f]
+        description: |
+          Input GTF/GFF file(s).
+        type: file
+        multiple: true
+        required: true
+        direction: input
+        example: input1.gff;input2.gff
+  - name: Outputs
+    arguments:       
+      - name: --output
+        alternatives: [-o, --out]
+        description: Output gff3 file where the gene incriminated will be write.
+        type: file
+        direction: output
+        required: true
+        example: output.gff
+  - name: Arguments
+    arguments:
+      - name: --config
+        alternatives: [-c]
+        description: |
+          String - Input AGAT config file. By default, AGAT takes as input
+          agat_config.yaml file from the working directory if any,
+          otherwise it takes the original agat_config.yaml shipped with
+          AGAT. To get the agat_config.yaml locally type: "agat config
+          --expose". The --config option gives you the possibility to use
+          your own AGAT config file (located elsewhere or named
+          differently).
+        type: file
+        required: false
+        example: custom_agat_config.yaml
+resources:
+  - type: bash_script
+    path: script.sh
+test_resources:
+  - type: bash_script
+    path: test.sh
+  - type: file
+    path: test_data
+engines:
+  - type: docker
+    image: quay.io/biocontainers/agat:1.4.0--pl5321hdfd78af_0
+    setup:
+      - type: docker
+        run: |
+          agat --version | sed 's/AGAT\s\(.*\)/agat: "\1"/' > /var/software_versions.txt
+runners:
+  - type: executable
+  - type: nextflow

src/agat/agat_sp_merge_annotations/help.txt

@@ -0,0 +1,64 @@
+```sh
+agat_sp_merge_annotations.pl --help
+```
+
+  ------------------------------------------------------------------------------
+|   Another GFF Analysis Toolkit (AGAT) - Version: v1.4.0                      |
+|   https://github.com/NBISweden/AGAT                                          |
+|   National Bioinformatics Infrastructure Sweden (NBIS) - www.nbis.se         |
+ ------------------------------------------------------------------------------
+
+
+Name:
+    agat_sp_merge_annotations.pl
+
+Description:
+    This script merge different gff annotation files in one. It uses the
+    AGAT parser that takes care of duplicated names and fixes other oddities
+    met in those files.
+
+Usage:
+        agat_sp_merge_annotations.pl --gff infile1 --gff infile2 --out outFile
+        agat_sp_merge_annotations.pl --help
+
+Options:
+    --gff or -f
+            Input GTF/GFF file(s). You can specify as much file you want
+            like so: -f file1 -f file2 -f file3
+
+    --out, --output or -o
+            Output gff3 file where the gene incriminated will be write.
+
+    -c or --config
+            String - Input agat config file. By default AGAT takes as input
+            agat_config.yaml file from the working directory if any,
+            otherwise it takes the orignal agat_config.yaml shipped with
+            AGAT. To get the agat_config.yaml locally type: "agat config
+            --expose". The --config option gives you the possibility to use
+            your own AGAT config file (located elsewhere or named
+            differently).
+
+    --help or -h
+            Display this helpful text.
+
+Feedback:
+  Did you find a bug?:
+    Do not hesitate to report bugs to help us keep track of the bugs and
+    their resolution. Please use the GitHub issue tracking system available
+    at this address:
+
+                https://github.com/NBISweden/AGAT/issues
+
+     Ensure that the bug was not already reported by searching under Issues.
+     If you're unable to find an (open) issue addressing the problem, open a new one.
+     Try as much as possible to include in the issue when relevant:
+     - a clear description,
+     - as much relevant information as possible,
+     - the command used,
+     - a data sample,
+     - an explanation of the expected behaviour that is not occurring.
+
+  Do you want to contribute?:
+    You are very welcome, visit this address for the Contributing
+    guidelines:
+    https://github.com/NBISweden/AGAT/blob/master/CONTRIBUTING.md

src/agat/agat_sp_merge_annotations/script.sh

@@ -0,0 +1,18 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+# Convert a list of file names to multiple -gff arguments
+input_files=""
+IFS=";" read -ra file_names <<< "$par_gff"
+for file in "${file_names[@]}"; do
+    input_files+="--gff $file "
+done
+unset IFS
+
+# run agat_sp_merge_annotations
+agat_sp_merge_annotations.pl \
+  $input_files \
+  -o "$par_output" \
+  ${par_config:+--config "${par_config}"}

src/agat/agat_sp_merge_annotations/test.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+test_dir="${meta_resources_dir}/test_data"
+out_dir="${meta_resources_dir}/out_data"
+
+echo "> Run $meta_name with test data 1"
+"$meta_executable" \
+  --gff "$test_dir/file1.gff;$test_dir/file2.gff" \
+  --output "$out_dir/output.gff"
+
+echo ">> Checking output"
+[ ! -f "$out_dir/output.gff" ] && echo "Output file output.gff does not exist" && exit 1
+
+echo ">> Check if output is empty"
+[ ! -s "$out_dir/output.gff" ] && echo "Output file output.gff is empty" && exit 1
+
+echo ">> Check if output matches expected output"
+diff "$out_dir/output.gff" "$test_dir/agat_sp_merge_annotations_1.gff"
+if [ $? -ne 0 ]; then
+  echo "Output file output.gff does not match expected output"
+  exit 1
+fi
+
+rm -rf "$out_dir/output.gff"
+
+echo "> Run $meta_name with test data 2"
+"$meta_executable" \
+  --gff "$test_dir/fileA.gff;$test_dir/fileB.gff" \
+  --output "$out_dir/output.gff"
+
+echo ">> Checking output"
+[ ! -f "$out_dir/output.gff" ] && echo "Output file output.gff does not exist" && exit 1
+
+echo ">> Check if output is empty"
+[ ! -s "$out_dir/output.gff" ] && echo "Output file output.gff is empty" && exit 1
+
+echo ">> Check if output matches expected output"
+diff "$out_dir/output.gff" "$test_dir/agat_sp_merge_annotations_2.gff"
+if [ $? -ne 0 ]; then
+  echo "Output file output.gff does not match expected output"
+  exit 1
+fi
+
+echo "> Test successful"

src/agat/agat_sp_merge_annotations/test_data/agat_sp_merge_annotations_1.gff

@@ -0,0 +1,13 @@
+##gff-version 3
+chr10	BestRefSeq	gene	123237824	123357992	.	-	.	ID=gene-FGFR2;ontology=G0222
+chr10	BestRefSeq	mRNA	123237824	123357992	.	-	.	ID=rna-NM_022970.3;Parent=gene-FGFR2;ontology=G0222;merged_ID=IDmodified-mrna-1;merged_Ontology=G0333;merged_Parent=IDmodified-gene-1
+chr10	BestRefSeq	exon	123237824	123239535	.	-	.	ID=exon-NM_022970.3-18;Parent=rna-NM_022970.3
+chr10	BestRefSeq	exon	123243212	123243317	.	-	.	ID=exon-NM_022970.3-17;Parent=rna-NM_022970.3
+chr10	BestRefSeq	exon	123353223	123353481	.	-	.	ID=exon-NM_022970.3-2;Parent=rna-NM_022970.3
+chr10	BestRefSeq	exon	123357476	123357992	.	-	.	ID=exon-NM_022970.3-1;Parent=rna-NM_022970.3
+chr10	BestRefSeq	CDS	123239371	123239535	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3
+chr10	BestRefSeq	CDS	123243212	123243317	.	-	1	ID=cds-NP_075259.4;Parent=rna-NM_022970.3
+chr10	BestRefSeq	CDS	123353223	123353331	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3
+chr10	BestRefSeq	five_prime_UTR	123353332	123353481	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3
+chr10	BestRefSeq	five_prime_UTR	123357476	123357992	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3
+chr10	BestRefSeq	three_prime_UTR	123237824	123239370	.	-	.	ID=agat-three_prime_utr-54427;Parent=rna-NM_022970.3

src/agat/agat_sp_merge_annotations/test_data/agat_sp_merge_annotations_2.gff

@@ -0,0 +1,3 @@
+##gff-version 3
+chr1	AUGUSTUS	gene	1000424	1039237	.	+	.	ID=A
+chr1	AUGUSTUS	mRNA	1000424	1039237	.	+	.	ID=A.t1;Parent=A;merged_ID=B.t1;merged_Parent=B

src/agat/agat_sp_merge_annotations/test_data/file1.gff

@@ -0,0 +1,14 @@
+chr10	BestRefSeq	gene	123237824	123357992	.	-	.	ID=gene-FGFR2;Ontology=G0222;
+chr10	BestRefSeq	mRNA	123237824	123357992	.	-	.	ID=rna-NM_022970.3;Parent=gene-FGFR2;Ontology=G0222;
+chr10	BestRefSeq	exon	123237824	123239535	.	-	.	ID=exon-NM_022970.3-18;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123243212	123243317	.	-	.	ID=exon-NM_022970.3-17;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123353223	123353481	.	-	.	ID=exon-NM_022970.3-2;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123357476	123357992	.	-	.	ID=exon-NM_022970.3-1;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123239371	123239535	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123243212	123243317	.	-	1	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123353223	123353331	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	five_prime_UTR	123353332	123353481	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	five_prime_UTR	123357476	123357992	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	three_prime_UTR	123237824	123239370	.	-	.	ID=agat-three_prime_utr-54427;Parent=rna-NM_022970.3;
+
+

src/agat/agat_sp_merge_annotations/test_data/file2.gff

@@ -0,0 +1,12 @@
+chr10	BestRefSeq	gene	123237824	123357992	.	-	.	ID=gene-FGFR2;Ontology=G0222;
+chr10	BestRefSeq	mRNA	123237824	123357992	.	-	.	ID=rna-NM_022970.3;Parent=gene-FGFR2;Ontology=G0333;
+chr10	BestRefSeq	exon	123237824	123239535	.	-	.	ID=exon-NM_022970.3-18;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123243212	123243317	.	-	.	ID=exon-NM_022970.3-17;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123353223	123353481	.	-	.	ID=exon-NM_022970.3-2;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	exon	123357476	123357992	.	-	.	ID=exon-NM_022970.3-1;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123239371	123239535	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123243212	123243317	.	-	1	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	CDS	123353223	123353331	.	-	0	ID=cds-NP_075259.4;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	five_prime_UTR	123353332	123353481	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	five_prime_UTR	123357476	123357992	.	-	.	ID=agat-five_prime_utr-54403;Parent=rna-NM_022970.3;
+chr10	BestRefSeq	three_prime_UTR	123237824	123239370	.	-	.	ID=agat-three_prime_utr-54427;Parent=rna-NM_022970.3;

src/agat/agat_sp_merge_annotations/test_data/fileA.gff

@@ -0,0 +1,2 @@
+chr1	AUGUSTUS	gene	1000424	1039237	.	+	.	ID=A;
+chr1	AUGUSTUS	mRNA	1000424	1039237	.	+	.	ID=A.t1;Parent=A;

src/agat/agat_sp_merge_annotations/test_data/fileB.gff

@@ -0,0 +1,2 @@
+chr1	AUGUSTUS	gene	1000424	1039237	.	+	.	ID=B;
+chr1	AUGUSTUS	mRNA	1000424	1039237	.	+	.	ID=B.t1;Parent=B;

src/agat/agat_sp_merge_annotations/test_data/script.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+# clone repo
+if [ ! -d /tmp/agat_source ]; then
+  git clone --depth 1 --single-branch --branch master https://github.com/NBISweden/AGAT /tmp/agat_source
+fi
+
+# copy test data
+cp -r /tmp/agat_source/t/scripts_output/in/agat_sp_merge_annotations/file1.gff src/agat/agat_sp_merge_annotations/test_data
+cp -r /tmp/agat_source/t/scripts_output/in/agat_sp_merge_annotations/file2.gff src/agat/agat_sp_merge_annotations/test_data
+cp -r /tmp/agat_source/t/scripts_output/out/agat_sp_merge_annotations_1.gff src/agat/agat_sp_merge_annotations/test_data
+
+cp -r /tmp/agat_source/t/scripts_output/in/agat_sp_merge_annotations/fileA.gff src/agat/agat_sp_merge_annotations/test_data
+cp -r /tmp/agat_source/t/scripts_output/in/agat_sp_merge_annotations/fileB.gff src/agat/agat_sp_merge_annotations/test_data
+cp -r /tmp/agat_source/t/scripts_output/out/agat_sp_merge_annotations_2.gff src/agat/agat_sp_merge_annotations/test_data