From a54599ffa04d5ee39124957f0ca97a7c8c16c4e0 Mon Sep 17 00:00:00 2001 From: Tatiana Gurbich Date: Wed, 29 Nov 2023 09:15:49 +0000 Subject: [PATCH 1/3] Readme edits --- README.md | 60 +++++++++++++++++++++++++++---------------------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index f0961f2a..09c0d5c7 100644 --- a/README.md +++ b/README.md @@ -7,36 +7,36 @@ Gurbich TA, Almeida A, Beracochea M, Burdett T, Burgin J, Cochrane G, Raj S, Ric Detailed information about existing MGnify catalogues: https://docs.mgnify.org/src/docs/genome-viewer.html ### Tools used in the pipeline -| Tool/Database | Version | Purpose | -| ----------- | ----------- |----------- | -| CheckM | 1.1.3 | Determining genome quality | -| dRep | 3.2.2 | Genome clustering | -| Mash | 2.3 | Sketch for the catalogue; placement of genomes into clusters (update only); strain tree | -| GUNC | 1.0.3 | Quality control | -| GUNC DB | 2.0.4 | Database for GUNC | -| GTDB-Tk | 2.3.0 | Assigning taxonomy; generating alignments | -| GTDB | r214 | Database for GTDB-Tk | -| Prokka | 1.14.6 | Protein annotation | -| IQ-TREE 2 | 2.2.0.3 | Generating a phylogenetic tree | -| Kraken 2 | 2.1.2 | Generating a kraken database | -| Bracken | 2.6.2 | Generating a bracken database | -| MMseqs2 | 13.45111 | Generating a protein catalogue | -| eggNOG-mapper | 2.1.11 | Protein annotation (eggNOG, KEGG, COG, CAZy) | -| eggNOG DB | 5.0 | Database for eggNOG-mapper | -| Diamond | 2.0.11 | Protein annotation (eggNOG) | -| InterProScan | 5.62-94.0 | Protein annotation (InterPro, Pfam) | -| CRISPRCasFinder | 4.3.2 | Annotation of CRISPR arrays | -| AMRFinderPlus | 3.11.4 | Antimicrobial resistance gene annotation; virulence factors, biocide, heat, acid, and metal resistance gene annotation | -| AMRFinderPlus DB | 3.11 2023-02-23.1 | Database for AMRFinderPlus | -| SanntiS | 0.9.3.2 | Biosynthetic gene cluster annotation | -| Infernal | 1.1.4 | RNA predictions | -| tRNAscan-SE | 2.0.9 | tRNA predictions | -| Rfam | 14.9 | Identification of SSU/LSU rRNA and other ncRNAs | -| Panaroo | 1.3.2 | Pan-genome computation | -| Seqtk | 1.3 | Generating a gene catalogue | -| VIRify | - | Viral sequence annotation | -| MoMofy | 1.0.0 | Mobilome annotation | -| samtools | 1.15 | FASTA indexing | +| Tool/Database | Version | Purpose | +|----------------------------------|------------------|----------- | +| CheckM | 1.1.3 | Determining genome quality | +| dRep | 3.2.2 | Genome clustering | +| Mash | 2.3 | Sketch for the catalogue; placement of genomes into clusters (update only); strain tree | +| GUNC | 1.0.3 | Quality control | +| GUNC DB | 2.0.4 | Database for GUNC | +| GTDB-Tk | 2.3.0 | Assigning taxonomy; generating alignments | +| GTDB | r214 | Database for GTDB-Tk | +| Prokka | 1.14.6 | Protein annotation | +| IQ-TREE 2 | 2.2.0.3 | Generating a phylogenetic tree | +| Kraken 2 | 2.1.2 | Generating a kraken database | +| Bracken | 2.6.2 | Generating a bracken database | +| MMseqs2 | 13.45111 | Generating a protein catalogue | +| eggNOG-mapper | 2.1.11 | Protein annotation (eggNOG, KEGG, COG, CAZy) | +| eggNOG DB | 5.0 | Database for eggNOG-mapper | +| Diamond | 2.0.11 | Protein annotation (eggNOG) | +| InterProScan | 5.62-94.0 | Protein annotation (InterPro, Pfam) | +| CRISPRCasFinder | 4.3.2 | Annotation of CRISPR arrays | +| AMRFinderPlus | 3.11.4 | Antimicrobial resistance gene annotation; virulence factors, biocide, heat, acid, and metal resistance gene annotation | +| AMRFinderPlus DB | 3.11 2023-02-23.1 | Database for AMRFinderPlus | +| SanntiS | 0.9.3.2 | Biosynthetic gene cluster annotation | +| Infernal | 1.1.4 | RNA predictions | +| tRNAscan-SE | 2.0.9 | tRNA predictions | +| Rfam | 14.9 | Identification of SSU/LSU rRNA and other ncRNAs | +| Panaroo | 1.3.2 | Pan-genome computation | +| Seqtk | 1.3 | Generating a gene catalogue | +| VIRify | 2.0.0 | Viral sequence annotation | +| [Mobilome annotation pipeline](https://github.com/EBI-Metagenomics/mobilome-annotation-pipeline) | 2.0.0-rc.1 | Mobilome annotation | +| samtools | 1.15 | FASTA indexing | ## Setup From 03a0daed9e187fcf8076e0e067c8f88f851e9f04 Mon Sep 17 00:00:00 2001 From: Tatiana Gurbich Date: Mon, 2 Oct 2023 17:42:29 +0100 Subject: [PATCH 2/3] Fixed bug in all_genomes directory organisation --- helpers/file_organiser.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/helpers/file_organiser.sh b/helpers/file_organiser.sh index 90864ca3..2a5084d7 100644 --- a/helpers/file_organiser.sh +++ b/helpers/file_organiser.sh @@ -40,7 +40,7 @@ function GenerateRNACentralJSON { echo "Copying GFFs" for R in $REPS do - cp ${RESULTS_PATH}/all_genomes/${R::-2}/${R}/${R}.gff* ${RESULTS_PATH}/additional_data/rnacentral/GFFs/ + cp ${RESULTS_PATH}/all_genomes/${R::-2}/${R}/genomes1/${R}.gff* ${RESULTS_PATH}/additional_data/rnacentral/GFFs/ done echo "Running JSON generation" From c66b327ca95104534d6658cc5a1655e92314545c Mon Sep 17 00:00:00 2001 From: Tatiana Gurbich Date: Wed, 29 Nov 2023 09:47:25 +0000 Subject: [PATCH 3/3] Edited comment --- helpers/file_organiser.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/helpers/file_organiser.sh b/helpers/file_organiser.sh index 2a5084d7..6da5cbc2 100644 --- a/helpers/file_organiser.sh +++ b/helpers/file_organiser.sh @@ -1,6 +1,6 @@ #!/usr/bin/env bash -# The script organises output from the catalogue generation + Virify + Momofy to prepare it for upload to MGnify +# The script organises output from the catalogue generation + Virify + Mobilome annotation pipeline to prepare it for upload to MGnify function Usage {