Add agat sp complement annotations

CHANGELOG.md

@@ -25,6 +25,7 @@
   - `agat/agat_convert_embl2gff`: convert an EMBL file into GFF format (PR #99).
   - `agat/agat_convert_sp_gff2tsv`: convert gtf/gff file into tabulated file (PR #102).
   - `agat/agat_convert_sp_gxf2gxf`: fixes and/or standardizes any GTF/GFF file into full sorted GTF/GFF file (PR #103).
+  - `agat/agat_sp_complement_annotations`: complement a reference annotation with other annotations (PR #129).
 
 * `bedtools`:
   - `bedtools/bedtools_intersect`: Allows one to screen for overlaps between two sets of genomic features (PR #94).

src/agat/agat_sp_complement_annotations/config.vsh.yaml

@@ -0,0 +1,95 @@
+name: agat_sp_complement_annotations
+namespace: agat
+description: |
+    The script allows to complement a reference annotation with other annotations. 
+
+      * A l1 feature from the addfile.gff that does not overlap a l1 feature from the reference annotation will be added. 
+      * A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added. 
+      * A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added. 
+      * A l1 feature from the addfile.gff with a CDS that overlaps a l1 feature with a CDS from the reference annotation will be added only if the CDSs don't overlap. 
+      * A l1 feature from the addfile.gff without a CDS that overlaps a l1 feature without a CDS from the reference annotation will be added only if none of the l3 features overlap. 
+
+      ! It is sufficient that only one isoform is overlapping to prevent the whole gene (l1 feature) from the addfile.gff to be added in the output.
+keywords: [gene annotations, GFF]
+links:
+  homepage: https://github.com/NBISweden/AGAT
+  documentation: https://agat.readthedocs.io/en/latest/tools/agat_sp_complement_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
+requirements:
+  - commands: [agat]
+authors:
+  - __merge__: /src/_authors/leila_paquay.yaml
+    roles: [ author, maintainer ]
+argument_groups:
+  - name: Inputs
+    arguments:
+      - name: --ref
+        alternatives: [-r, -i]
+        description: Input GTF/GFF file used as reference.
+        type: file
+        required: true
+        direction: input
+        example: reference.gff
+      - name: --add
+        alternatives: [-a]
+        description: |
+          Annotation(s) file you would like to use to complement the
+          reference annotation. You can specify as much file you want like.
+          The order you provide these files matter. Once the reference file has been
+          complemented by file1, this new annotation becomes the new
+          reference that will be complemented by file2 etc. 
+          So, be aware of what you want if you use several addfiles.
+        type: file
+        required: true
+        direction: input
+        multiple: true
+        example: addfile1.gff
+  - name: Outputs
+    arguments:       
+      - name: --output
+        alternatives: [-o, --out, --outfile]
+        description: Output gff3 containing the reference annotation with all the non-overlapping newly added genes from addfiles.gff.
+        type: file
+        direction: output
+        required: true
+        example: output.gff
+  - name: Arguments
+    arguments:
+      - name: --size_min
+        alternatives: [-s]
+        description: |
+          Option to keep the non-overlapping gene only if the CDS size (in
+          nucleotide) is over the minimum size defined. Default = 0 that
+          means all of them are kept.
+        type: integer
+        required: false
+        example: 100
+      - name: --config
+        alternatives: [-c]
+        description: |
+          AGAT config file. By default AGAT takes the original agat_config.yaml shipped with AGAT. 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_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_complement_annotations/help.txt

@@ -0,0 +1,91 @@
+```sh
+agat_sp_complement_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_complement_annotations.pl
+
+Description:
+    The script allows to complement a reference annotation with other
+    annotations. A l1 feature from the addfile.gff that does not overlap a
+    l1 feature from the reference annotation will be added. A l1 feature
+    from the addfile.gff without a CDS that overlaps a l1 feature with a CDS
+    from the reference annotation will be added. A l1 feature from the
+    addfile.gff with a CDS that overlaps a l1 feature without a CDS from the
+    reference annotation will be added. A l1 feature from the addfile.gff
+    with a CDS that overlaps a l1 feature with a CDS from the reference
+    annotation will be added only if the CDSs don't overlap. A l1 feature
+    from the addfile.gff without a CDS that overlaps a l1 feature without a
+    CDS from the reference annotation will be added only if none of the l3
+    features overlap. /!\ It is sufficiant that only one isoform is
+    overlapping to prevent the whole gene (l1 feature) from the addfile.gff
+    to be added in the output.
+
+Usage:
+        agat_sp_complement_annotations.pl --ref annotation_ref.gff --add addfile1.gff --add addfile2.gff --out outFile
+        agat_sp_complement_annotations.pl --help
+
+Options:
+    --ref, -r or -i
+            Input GTF/GFF file used as reference.
+
+    --add or -a
+            Annotation(s) file you would like to use to complement the
+            reference annotation. You can specify as much file you want like
+            so: -a addfile1 -a addfile2 -a addfile3 /!\ The order you
+            provide these files matter. Once the reference file has been
+            complemented by file1, this new annotation becomes the new
+            reference that will be complemented by file2 etc. /!\ The result
+            with -a addfile1 -a addfile2 will differ to the result from -a
+            addfile2 -a addfile1. So, be aware of what you want if you use
+            several addfiles.
+
+    --size_min or -s
+            Option to keep the non-overlping gene only if the CDS size (in
+            nucleotide) is over the minimum size defined. Default = 0 that
+            means all of them are kept.
+
+    --out, --output, --outfile or -o
+            Output gff3 containing the reference annotation with all the
+            non-overlapping newly added genes from addfiles.gff.
+
+    -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_complement_annotations/script.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+set -eo pipefail
+
+## VIASH START
+## VIASH END
+
+# unset flags
+[[ "$par_verbose" == "false" ]] && unset par_verbose
+
+# Convert a list of file names to multiple --add arguments
+input_files=""
+IFS=";" read -ra file_names <<< "$par_add"
+for file in "${file_names[@]}"; do
+    input_files+="--add $file "
+done
+
+# run agat_sp_complement_annotations.pl
+agat_sp_complement_annotations.pl \
+  --ref "$par_ref" \
+  $input_files \
+  -o "$par_output" \
+  ${par_size_min:+--size_min "${par_size_min}"} \
+  ${par_config:+--config "${par_config}"} \
+  ${par_verbose:+--verbose}

src/agat/agat_sp_complement_annotations/test.sh

@@ -0,0 +1,56 @@
+#!/bin/bash
+
+set -eo pipefail
+
+## VIASH START
+## VIASH END
+
+test_dir="${meta_resources_dir}/test_data"
+
+# create temporary directory and clean up on exit
+TMPDIR=$(mktemp -d "$meta_temp_dir/$meta_functionality_name-XXXXXX")
+function clean_up {
+ [[ -d "$TMPDIR" ]] && rm -rf "$TMPDIR"
+}
+trap clean_up EXIT
+
+echo "> Run $meta_name with test data"
+"$meta_executable" \
+  --ref "$test_dir/25_test.gff" \
+  --add "$test_dir/9_test.gff" \
+  --output "$TMPDIR/output.gff" 
+
+echo ">> Checking output"
+[ ! -f "$TMPDIR/output.gff" ] && echo "Output file output.gff does not exist" && exit 1
+
+echo ">> Check if output is empty"
+[ ! -s "$TMPDIR/output.gff" ] && echo "Output file output.gff is empty" && exit 1
+
+echo ">> Check if output matches expected output"
+diff "$TMPDIR/output.gff" "$test_dir/agat_sp_complement_annotations_1.gff"
+if [ $? -ne 0 ]; then
+  echo "Output file output.gff does not match expected output"
+  exit 1
+fi
+
+rm -rf "$TMPDIR/output.gff"
+
+echo "> Run $meta_name with test data"
+"$meta_executable" \
+  --ref "$test_dir/agat_sp_complement_annotations_ref.gff" \
+  --add "$test_dir/agat_sp_complement_annotations_add.gff" \
+  --output "$TMPDIR/output.gff" 
+
+echo ">> Checking output"
+[ ! -f "$TMPDIR/output.gff" ] && echo "Output file output.gff does not exist" && exit 1
+
+echo ">> Check if output is empty"
+[ ! -s "$TMPDIR/output.gff" ] && echo "Output file output.gff is empty" && exit 1
+
+echo ">> Check if output matches expected output"
+diff "$TMPDIR/output.gff" "$test_dir/agat_sp_complement_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_complement_annotations/test_data/25_test.gff

@@ -0,0 +1,32 @@
+# gffread all_merged.stringtie.gtf -E -F -o -
+# gffread v0.9.9
+##gff-version 3
+scaffold1	StringTie	transcript	2551	2965	1000.00	.	.	ID=MSTRG.1.1;geneID=MSTRG.1
+scaffold1	StringTie	exon	2551	2965	1000.00	.	.	Parent=MSTRG.1.1;cov=68.607231
+scaffold1	StringTie	transcript	8147	13353	1000.00	-	.	ID=MSTRG.6.1;geneID=MSTRG.6
+scaffold1	StringTie	exon	8147	8981	1000.00	-	.	Parent=MSTRG.6.1;cov=529.868042
+scaffold1	StringTie	exon	9082	9171	1000.00	-	.	Parent=MSTRG.6.1;cov=451.066681
+scaffold1	StringTie	exon	9328	9433	1000.00	-	.	Parent=MSTRG.6.1;cov=548.889893
+scaffold1	StringTie	exon	9682	9875	1000.00	-	.	Parent=MSTRG.6.1;cov=416.032471
+scaffold1	StringTie	exon	10018	10228	1000.00	-	.	Parent=MSTRG.6.1;cov=268.398773
+scaffold1	StringTie	exon	10436	10511	1000.00	-	.	Parent=MSTRG.6.1;cov=263.012329
+scaffold1	StringTie	exon	10665	10744	1000.00	-	.	Parent=MSTRG.6.1;cov=262.177094
+scaffold1	StringTie	exon	10901	10996	1000.00	-	.	Parent=MSTRG.6.1;cov=285.484375
+scaffold1	StringTie	exon	11277	11348	1000.00	-	.	Parent=MSTRG.6.1;cov=272.513885
+scaffold1	StringTie	exon	11521	11718	1000.00	-	.	Parent=MSTRG.6.1;cov=323.955170
+scaffold1	StringTie	exon	11802	12004	1000.00	-	.	Parent=MSTRG.6.1;cov=258.021729
+scaffold1	StringTie	exon	12106	13353	1000.00	-	.	Parent=MSTRG.6.1;cov=192.039612
+scaffold1	StringTie	transcript	21499	23178	1000.00	.	.	ID=MSTRG.7.1;geneID=MSTRG.7
+scaffold1	StringTie	exon	21499	23178	1000.00	.	.	Parent=MSTRG.7.1;cov=207.398804
+scaffold1	StringTie	transcript	44218	47964	1000.00	-	.	ID=MSTRG.11.1;geneID=MSTRG.11
+scaffold1	StringTie	exon	44218	45365	1000.00	-	.	Parent=MSTRG.11.1;cov=3001.629883
+scaffold1	StringTie	exon	47660	47706	1000.00	-	.	Parent=MSTRG.11.1;cov=4399.870117
+scaffold1	StringTie	exon	47827	47964	1000.00	-	.	Parent=MSTRG.11.1;cov=2103.559082
+scaffold1	StringTie	transcript	44218	47964	1000.00	-	.	ID=MSTRG.11.2;geneID=MSTRG.11
+scaffold1	StringTie	exon	44218	45365	1000.00	-	.	Parent=MSTRG.11.2;cov=487.085846
+scaffold1	StringTie	exon	47660	47718	1000.00	-	.	Parent=MSTRG.11.2;cov=557.812744
+scaffold1	StringTie	exon	47824	47964	1000.00	-	.	Parent=MSTRG.11.2;cov=242.265823
+scaffold1	StringTie	transcript	44427	47958	1000.00	-	.	ID=MSTRG.11.3;geneID=MSTRG.11
+scaffold1	StringTie	exon	44427	45365	1000.00	-	.	Parent=MSTRG.11.3;cov=2892.249023
+scaffold1	StringTie	exon	47660	47723	1000.00	-	.	Parent=MSTRG.11.3;cov=2083.479492
+scaffold1	StringTie	exon	47827	47958	1000.00	-	.	Parent=MSTRG.11.3;cov=734.545044

src/agat/agat_sp_complement_annotations/test_data/9_test.gff

@@ -0,0 +1,20 @@
+##gff-version 3
+#!gff-spec-version 1.14
+#!source-version NCBI C++ formatter 0.2
+##Type DNA NC_003070.9
+NC_003070.9	RefSeq	source	1	30427671	.	+	.	organism=Arabidopsis thaliana;mol_type=genomic DNA;db_xref=taxon:3702;chromosome=1;ecotype=Columbia
+NC_003070.9	RefSeq	gene	3631	5899	.	+	.	ID=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	3631	3913	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	3996	4276	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	4486	4605	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	4706	5095	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	5174	5326	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	exon	5439	5899	.	+	.	ID=NM_099983.2;Parent=NC_003070.9:NAC001;gbkey=mRNA;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	3760	3913	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	3996	4276	.	+	2	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	4486	4605	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	4706	5095	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	5174	5326	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	CDS	5439	5627	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	start_codon	3760	3762	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;
+NC_003070.9	RefSeq	stop_codon	5628	5630	.	+	0	ID=NM_099983.2;Parent=NC_003070.9:NAC001;locus_tag=AT1G01010;