Description

Apply a Convolutional Neural Net to filter annotated variants

Input

name:type
description
pattern

meta:map

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

vcf:file

VCF file

*.vcf.gz

tbi:file

VCF index file

*.vcf.gz.tbi

aligned_input:file

BAM/CRAM file from alignment (optional)

*.{bam,cram}

intervals:file

Bed file with the genomic regions included in the library (optional)

fasta:file

The reference fasta file

*.fasta

fai:file

Index of reference fasta file

*.fasta.fai

dict:file

GATK sequence dictionary

*.dict

architecture:file

Neural Net architecture configuration json file (optional)

*.json

weights:file

Keras model HD5 file with neural net weights. (optional)

*.hd5

Output

name:type
description
pattern

vcf

meta:map

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

*cnn.vcf.gz:file

Annotated VCF file

*.vcf

tbi

meta:map

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

*cnn.vcf.gz.tbi:file

VCF index file

*.vcf.gz.tbi

versions

versions.yml:file

File containing software versions

versions.yml

Tools

gatk4
Apache-2.0

Developed in the Data Sciences Platform at the Broad Institute, the toolkit offers a wide variety of tools with a primary focus on variant discovery and genotyping. Its powerful processing engine and high-performance computing features make it capable of taking on projects of any size.