Description

A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes

Input

name:type
description
pattern

meta:map

Groovy Map containing sample information e.g. [ id:‘test’ ]

fasta:file

FASTA file containing gene-like sequences

*.{fasta,fa,fna}

model:string

Which model to use, depending on input data. Either ‘LS’ or ‘SS’ for long or short sequences respectively

LS|LS

db:directory

Path to a directory containing the deepARG pre-built models

*/

Output

name:type
description
pattern

daa

meta:map

Groovy Map containing sample information e.g. [ id:‘test’, single_end

]

*.align.daa:file

Sequences of ARG-like sequences from DIAMOND alignment

*.align.daa

daa_tsv

meta:map

Groovy Map containing sample information e.g. [ id:‘test’, single_end

]

*.align.daa.tsv:file

Alignments scores against ARG-like sequences from DIAMOND alignment

*.align.daa.tsv

arg

meta:map

Groovy Map containing sample information e.g. [ id:‘test’, single_end

]

*.mapping.ARG:file

Table containing sequences with an ARG-like probability of more than specified thresholds

*.mapping.ARG

potential_arg

meta:map

Groovy Map containing sample information e.g. [ id:‘test’, single_end

]

*.mapping.potential.ARG:file

Table containing sequences with an ARG-like probability of less than specified thresholds, and requires manual inspection

*.mapping.potential.ARG

versions

versions.yml:file

File containing software versions

versions.yml

Tools

deeparg
MIT

A deep learning based approach to predict Antibiotic Resistance Genes (ARGs) from metagenomes

github.com/gaarangoa/deeparg 10.1186/s40168-018-0401-z
funcscan
Github user jfy133
Ask a question on Slack Open an issue on GitHub