All Competitors

Post-hoc method that restores monotonic scaling to ESM-2 embeddings, yielding Matryoshka-style nested representations for variant effect prediction.

Bacterial proteome foundation model that learns contextualized gene and whole-genome representations from tens of thousands of complete genomes.

EEG-to-text foundation model that turns raw recordings into clinically grounded natural-language narratives instead of fixed-label classifications.

Protein inverse folding model aligning ProteinMPNN by multi-objective preference optimization to improve developability without losing fold fidelity.

Cross-modal protein encoder that aligns ESM-2 sequence embeddings with ProteinMPNN structure embeddings in a shared space for cross-modal retrieval.

Neural Hamiltonian flow for protein sequence generation with inference-time control over composition and net charge via analytical bias potentials.

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

Generative single-cell foundation model trained on 100M+ transcriptomes that predicts how genetic perturbations reshape cell trajectories over time.

Small-molecule drug discovery foundation model covering ADMET, retrosynthesis, drug-target activity, and molecular optimization in a 2.6B checkpoint.

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

Self-supervised SE(3) geometric pretraining for protein backbone generators, improving designability, motif scaffolding, and conformational ensembles.

Contrastive model built on a genomic language model that predicts physical protein-protein interactions across a microbial proteome in linear time.

Graph-transformer foundation model pretrained on 3M protein pockets and 5M molecules as E(3)-equivariant graphs for protein-ligand representation.

Multimodal foundation model pretrained on ~500K unlabeled PubChem molecules that jointly predicts nine thermophysical properties of small molecules.

Large language model trained on functional genomics data to prioritize novel therapeutic targets from genome-wide CRISPR knockout screens.

Contrastive antibody language model predicting antibody-antigen binding specificity from sequence with a dual-encoder, cross-attentive architecture.

Temporal diffusion framework for single-cell developmental dynamics, interpolating and forecasting cell states from irregularly sampled time series.

Learning-to-rank variant effect predictor that aligns overlapping deep mutational scanning assays into an assay-agnostic tolerance measure.

Foundation model for 3D genome architecture, using masked locus modeling over genome-wide contact profiles to capture chromosome-scale organization.

Multimodal deep learning model that predicts protein-mediated chromatin contact maps and loops de novo from protein-binding profiles and sequence.

Knowledge-graph-grounded model that predicts single-cell transcriptomic responses to small molecules, with zero-shot prediction for unprofiled drugs.

Plant genomic foundation models from 0.1B to 1B parameters, pretrained on 43 phylogenetically diverse plant genomes for variant effect prediction.

Knowledge-graph foundation model for drug repurposing, grounding a biomedical graph in cell-type-specific genetic associations to rank indications.

Enzyme function prediction model that uses contrastive learning to assign the first three EC digits to enzymes with functions unseen during training.