All Competitors

Chromatin loop caller for Hi-C, Micro-C, DNA SPRITE, and single-cell contact maps, pairing axial attention with a U-Net to work at very low coverage.

Multiomic foundation model for zero-shot in silico perturbation, predicting gene regulation and cell fate transitions from DNA and ATAC signal.

Single-cell epigenomic foundation model that reads scATAC-seq as cell sentences of accessible cCREs, pretrained on about 5 million human cells.

Transcription factor binding-site prediction from DNA sequence, recast as 23-way DNA-binding-domain classification with a fine-tuned DNABERT.

Hi-C foundation model pretrained on 118 million contact submatrices, fine-tuned for loop detection, resolution enhancement and epigenomic prediction.

Resolution enhancement for sparse single-cell Hi-C contact matrices, using a cascading residual GAN with self-attention over chromatin loci.

DNA- and RNA-binding residue prediction from a nucleic-acid-adapted protein language model and an equivariant graph network over protein structure.

Variant-origin classifier for cell-free DNA, separating clonal hematopoiesis from tumor-derived mutations without matched white blood cell sequencing.

Disease embeddings learned from human genetic evidence and phenotype ontologies, placing rare and common conditions in one mechanistic vector space.

DNA language model for unassembled metagenomic reads, pretrained to recover coding fraction and reading frame from 60-300 bp fragments.

Reference-free enzyme class annotation of single unassembled metagenomic reads, assigning top-level EC classes without assembly or homology search.

Diffusion surrogate for DNA breathing simulations, generating biophysical features genome-wide to sharpen transcription factor binding prediction.

Plant regulatory genomics model predicting RNA-seq and epigenomic coverage from 65 kbp of DNA, pretrained across 12 species with per-species heads.

Contrastive learning framework for nucleotide sequence embeddings, generalizing to taxa and genes absent from training via FAISS retrieval.

Phage lifestyle prediction from raw nucleotide fragments, separating virulent from temperate genomes without database search or curated pipelines.

Decoder-only genomic language model at single-nucleotide resolution, fine-tuned to predict which DNA contacts the nuclear lamina or nuclear speckles.

Nanopore basecaller extending Bonito to a six-letter alphabet, reading the unnatural bases Ds and Px alongside canonical A, T, C and G.

DNA foundation model scaling an encoder-only transformer to 7 billion parameters for variant effect prediction, gene expression, and sequence design.

Instruction-tuned gene language model extending LLaMA-7B with merged DNA and protein BPE vocabularies to answer sequence tasks as chat prompts.

Enhancer-promoter interaction prediction from DNA sequence and ATAC-seq alone. Spearman above 0.90 on cell types unseen during training.

Context-aware protein sequence search, where a genomic language model fine-tuned for retrieval lets neighboring genes shape the query embedding.

Genomic foundation model with 7B parameters that models prokaryotic DNA, RNA, and protein at single-nucleotide resolution over a 131k-token context.

Missense pathogenicity prediction that folds wild-type and mutant sequences with ESMFold and encodes each structure as a graph autoencoder embedding.