google/deepvariant
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
Converts aligned reads (BAM/CRAM) into pileup image tensors that are classified by a convolutional neural network, outputting results as VCF/gVCF files. Supports multiple sequencing platforms (Illumina, PacBio HiFi, Oxford Nanopore, Complete Genomics, Roche SBX) and specialized modes including trio-based calling via DeepTrio, pangenome-aware variant calling, RNA-seq analysis, and hybrid data integration. Deployable via Docker with GPU acceleration and multi-threaded execution across standard bioinformatics workflows.
3,654 stars. Actively maintained with 1 commit in the last 30 days.
Stars
3,654
Forks
775
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 05, 2026
Commits (30d)
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google/deepvariant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
cgoliver/rnaglib
Toolkit for structure-based deep learning on RNA.
Kuanhao-Chao/OpenSpliceAI
🤖 Open‑source deep-learning-based splice‑site predictor that decodes splicing patterns across species
google/deepsomatic
DeepSomatic is an analysis pipeline that uses a deep neural network to call somatic variants...
Tom-Ellis-Lab/yorzoi
RNA-seq coverage prediction from DNA sequence in Yeast
Merck/deepbgc
BGC Detection and Classification Using Deep Learning