All Competitors

Siamese protein language model whose embedding distances approximate TM-score and lDDT, enabling alignment-free protein structure comparison.

EEG foundation model whose learned queries map any electrode montage into a fixed latent space, scaling linearly in the number of channels.

Multimodal EHR foundation model that fuses polygenic risk scores into a GPT-2-style backbone by cross-attention for zero-shot disease risk prediction.

Perturbation-trained single-cell foundation models (up to 3B parameters) that jointly model genes, cells, and compounds for precision oncology tasks.

Vision Transformer foundation model for spatial metabolomics, pretrained on ~4,000 curated METASPACE mass spectrometry imaging datasets.

Sequence-based binding site predictor spanning protein-DNA, protein-RNA, protein-protein, and antibody-antigen interfaces via a fine-tuned ProtT5.

Multimodal LLM that tokenizes single cells into discrete VQ-VAE codebook tokens, letting one model reason jointly over transcriptomes and text.

Multimodal molecular large language model grounding molecule understanding and generation in fine-grained, multi-level chemical knowledge.

Transcription factor binding site prediction model that refines a DNABERT-2 backbone with contrastive learning across diverse TFBS types.

fMRI foundation model of the human brain connectome: 1.2B parameters and brain-environment interaction tokens for behavior and disease prediction.

Structure prediction backbone that swaps AlphaFold3-style triangle attention for triangle multiplication, cutting compute without losing accuracy.

Vision-language encoders for chest CT that align 3D volumes with radiology reports using contrastive, report-generation, and masked-image objectives.

Self-supervised models that embed gut metagenomic abundance profiles for robust phenotype prediction in data-limited, cross-cohort settings.

Protein-protein docking scorer that ranks interface poses from image-encoded patches, swapping PIsToN's Vision Transformer for Vision Mamba.

All-atom generative model for de novo protein design using SE(3) flow matching over oriented residue rigid bodies.

EEG foundation model for brain-computer interfaces, pairing masked pretraining with a mixture-of-experts transformer across electrode montages.

Flow-matching model that predicts protein conformational ensembles across the order-disorder continuum, from folded domains to disordered chains.

Suite of large language models fine-tuned with LoRA to generate antigen-targeted antibody Fv sequences from an antigen and its epitope.

Molecular docking model that predicts protein-ligand binding poses with multi-stage Riemannian flow matching, yielding physically valid geometry.

fMRI foundation model trained on cortical flat-map videos with masked autoencoding, showing power-law scaling on brain activity reconstruction.

Efficient sequence-to-function transformer for regulatory genomics, matching Borzoi-class models while training in about a day on a single GPU.

Proprietary family of multimodal protein language models (up to 102B parameters) for sequence and structure generation, editing, and design.

Single-cell foundation model learning technology-agnostic cell embeddings by contrasting cell views rather than reconstructing gene expression counts.

Protein conformational sampling framework that steers a retrained OpenFold with diverse secondary-structure predictions to recover alternative states.