🧾 Best AI tools for Genomics & DNA models (2026)
DNA language models, sequence-to-function models, variant calling and splicing prediction.
21 tools · 16 open source · each entry links to its website, code and paper.
1.2B DNA model that annotates protein-coding genes across eukaryotes; ships a 48K-assembly annotation database.
Illumina's successor to SpliceAI: predicts splice-site usage and full transcript isoforms from sequence.
DeepMind model predicting regulatory effects of DNA variants at base resolution.
Genome language model across all domains of life with 1M-token context.
Bidirectional, reverse-complement-equivariant DNA language model.
7B genomic foundation model (StripedHyena) for prokaryotic DNA, RNA and protein design at single-nucleotide resolution.
Genomic language model over multi-species alignments for genome-wide variant effect prediction.
Proteome-wide pathogenicity predictions for 71M missense variants (repo archived; precomputed scores available).
Predicts RNA-seq coverage from DNA sequence.
Long-range genomic foundation model at single-nucleotide resolution.
Missense variant pathogenicity model trained on primate population variation and 3D protein structure.
Bias-corrected base-resolution deep learning models of ATAC/DNase-seq chromatin accessibility and TF motifs.
DNA foundation models pretrained on 3,200+ human and 850 species genomes.
Predicts 21,907 chromatin profiles from sequence and maps variants to regulatory sequence classes.
Predicts gene expression from sequence with long-range interactions.
Unsupervised evolutionary VAE for predicting pathogenicity of missense variants.
Base-resolution neural network for TF binding profiles (ChIP-nexus/ChIP-seq) and motif syntax discovery.
Deep learning prediction of splicing effects from pre-mRNA sequence (repo archived).
PyTorch library for training and applying sequence-level deep learning models (DeepSEA-style).
Sequence-to-function CNNs predicting chromatin accessibility, histone marks and expression tracks from DNA.