All Competitors

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.

Ligand identification in cryoEM and X-ray density maps, classifying a density blob into one of 219 ligand groups from its 3D point cloud shape.

Vision transformers trained on Human Protein Atlas fluorescence microscopy for subcellular protein localization and cell morphology representation.

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

Codon optimization framework pairing a frozen ProtBert encoder with a masked codon head, so every designed coding sequence translates back exactly.

Antibody sequence design conditioned on antigen structure, generating CDRs or full variable regions without epitope annotation or docked frameworks.

Generates free-text descriptions of protein function, catalytic activity, subcellular localization, and domains from sequence alone.

SMILES language model pretrained by editing: substructures are dropped and restored, giving fragment-level supervision for property prediction.

Receptor activity inference from bulk or single-cell transcriptomes, reading the genes a receptor regulates instead of the receptor's own expression.

Tissue-aware foundation model that restores brain MRI quality across motion correction, super-resolution, denoising, and harmonization.

Protein structure tokenizer that discretizes backbones into 512 discrete tokens and reconstructs all-atom structures, including side chains.

Generative model that emulates protein equilibrium ensembles, sampling cryptic pockets and unfolded states far faster than molecular dynamics.

Per-residue prediction of where a receptor domain can be inserted into a protein without breaking it, for building allosteric and inducible switches.

Whole-slide pathology assistant that states the morphological findings behind each diagnosis, trained on 180k VQA pairs from 9,850 gigapixel slides.

Antibody structure prediction returning backbone and side-chain coordinates in about a second, driven by a 650M-parameter antibody language model.

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

De novo cyclic peptide binder design against a protein target, chaining a cyclized diffusion sampler, sequence design and structure prediction.

Latent diffusion model for controllable all-atom protein generation that co-designs sequence and structure while training on sequences alone.

Protein language model extending ESM-2 to 2,048-residue inputs with LongFormer-style local windowed attention, re-pretrained on Swiss-Prot.

Int4 LoRA adapters over long-context ESM-2 checkpoints, cutting the 33-layer load footprint to 664 MB and adding a 36-layer configuration.

Self-supervised vision foundation model for structural brain MRI, providing a reusable encoder for brain age, survival, and image classification.

Histopathology patch encoder turning 512x512 tiles into 768-dimensional features, trained with a CoCa objective on 1.26 million captioned images.