All Competitors

Masked DNA language model with a learnable, adaptive tokenizer that produces context-dependent, variable-length segments instead of fixed k-mers.

Gut microbiome foundation model pretrained on human shotgun metagenomes, learning species-level taxonomic representations for disease prediction.

Annotation-free metagenome embedding pipeline that encodes raw DNA reads with genomic language models and pools them via FAISS k-means clustering.

Transformer foundation model pretrained on a biomedical knowledge graph for zero-shot drug repurposing, target, and adverse-effect prediction.

Peptide developability predictor scoring solubility, permeability, toxicity, and binding from amino-acid sequences or chemically modified SMILES.

Multimodal architecture coupling pretrained DNA, RNA, and protein language models with directional cross-attention into one Virtual Cell Embedding.

Generative language model for phenotype-driven drug discovery, proposing small-molecule structures from up- and down-regulated gene signatures.

3D vision-language foundation model for abdominal CT, pretrained on scans, radiology reports, and EHR codes for zero-shot interpretation.

Ab initio heterogeneous cryo-EM reconstruction seeds its encoder with foundation-model priors, sorting 100 structures from one simulated mixture.

Native 3D vision transformer self-supervised on unlabeled fluorescence microscopy volumes, segmenting subcellular structures without voxel labels.

470M-parameter microbial genome foundation model trained on 234.5B base pairs for multi-scale genomic representation and trait prediction.

Transcriptomic foundation model pretrained on 67M single-cell and spatial profiles, modeling gene expression and inter-cellular dependencies.

Peptide language model trained on HELM notation, a DeBERTa encoder for property prediction on macrocyclic and non-canonical medium-sized peptides.

Mixture-of-Experts generative model turning DNA sequence plus cell-type ATAC-seq into unified epigenomic, transcriptomic, and 3D chromatin profiles.

Antibody-antigen binding affinity prediction from sequence alone, with antigen and both antibody chains embedded by a frozen protein language model.

Spatially aware transcriptomic foundation models for cancer, pairing 50um-Local and 250um-Extended views of spot-resolution spatial transcriptomes.

Microscopy image restoration foundation model unifying 8 tasks across 5 modalities and 2D/3D data, with zero-shot inference on unseen systems.

GPT-style generative language model for mRNA coding sequences, pretrained across bacteria, eukaryotes, and archaea for de novo CDS design.

Generative foundation model that imputes genes and denoises spatial transcriptomics, conditioned on H&E histology, scRNA-seq, and spatial priors.

All-atom protein design diffusion model conditioned on ligands, nucleic acids, and other non-protein atoms, supporting enzyme and DNA binder design.

Multi-species genomics foundation model spanning representation learning, functional-track prediction, and sequence generation at 1 Mb context.

Protein-family language model trained on unaligned homolog sets for zero-shot variant fitness prediction and design. ProFam-1 holds 251M parameters.

Structure-aware transformer that makes zero-shot, per-adenosine predictions of ADAR-mediated A-to-I RNA editing to guide therapeutic guide-RNA design.