All Competitors

Enhancer RNA mapping model that locates eRNA loci genome-wide from DNA sequence and aggregated RNA-seq signal using a CNN-transformer architecture.

Plant genome foundation model for ab initio gene structure annotation, predicting genes, coding sequences, and exons at single-nucleotide resolution.

Gene representation framework fusing DNA, transcript, protein, text, and single-cell embeddings into one latent space that survives missing views.

Genomic language model from Radical Numerics with a 2 Mbp context window, built for zero-shot variant effect prediction and sequence design.

Generative transformer for phylogenetic inference that transduces sets of unaligned molecular sequences directly into Newick-format trees.

Family of ten compact GPT-2 decoder-only DNA language models spanning BPE vocabularies from 16 to 8192 tokens, built for lossless genome compression.

Genomic foundation model with 120M parameters that learns adaptive DNA token boundaries by dynamic chunking, not fixed k-mer or byte-pair tokens.

Zebrafish sequence-to-function model predicting cell-type-specific gene expression from DNA sequence across embryonic development.

Multimodal framework that detects and localizes DNA lesions from native nanopore signal, built on the damage-aware LesionBERT foundation model.

Multimodal Q-former that fuses DNA sequence, gene context, protein function, and text for zero-shot variant interpretation with a frozen LLM.

DNA language model combining Mamba state-space layers, gated dilated convolutions, and Fourier attention to capture multi-scale regulatory patterns.

Autoregressive DNA foundation model for variant effect prediction, using 6-mer tokenization to match Evo2-7B win rates at far higher throughput.

Generative multimodal foundation model spanning DNA, RNA, and protein, with any-to-any inference across genome, transcriptome, and proteome.

Autoregressive nucleotide-and-text foundation model generating DNA and RNA sequences from natural-language prompts that name species and function.

Leakage-controlled multimodal model predicting within-species relative protein expression across 385 bacterial species, with transfer to unseen phyla.

Genomic foundation model for rice, pretrained on 422 Oryza genomes with a 1 Mbp context window and a 1.25B-parameter mixture-of-experts transformer.

Chromatin-informed foundation model predicting regulatory activity and chromatin state directly from plant genomic sequence in Arabidopsis and rice.

Genomic foundation model that learns DNA representations by predicting masked regions in latent space rather than reconstructing raw nucleotides.

Long-context plant DNA language model, 676M parameters on a Mamba2 backbone, pretrained on 65 angiosperm genomes for cross-species variant annotation.

Discrete diffusion model that designs regulatory DNA with tunable cell-type-specific activity and learns activity-predictive representations.

DNA language model that replaces fixed tokenization with conservation-guided patching, letting models up to 10x smaller match top genomic benchmarks.

Genomic foundation model for Cypriniformes fish, built on a Mamba-2 state space model with a 32 kb context window for long-range genome modeling.

Self-supervised transformer for population genetics, pretrained on 1000 Genomes data, that detects positive selection via haplotype-wise attention.

DNA foundation model using masked discrete diffusion to unify bidirectional sequence understanding and de novo generation in one architecture.