Google DeepMind

Medically tuned SigLIP encoder from Google that maps medical images and text into one embedding space for zero-shot classification and retrieval.

Open medical multimodal models from Google, built on Gemma 3 with a medically tuned SigLIP vision encoder for clinical text and image understanding.

DNA foundation model that predicts thousands of functional genomic tracks, from expression and splicing to chromatin, at single base-pair resolution.

Sensor-language foundation models aligning wearable biosignals with text for zero-shot activity recognition, retrieval, and sensor captioning.

Single-cell foundation model reading scRNA-seq profiles as ranked gene-name sentences, scaled on Gemma-2 for annotation, reasoning and drug screens.

Open therapeutics foundation models from Google, built on Gemma-2, for drug-discovery property prediction and conversational reasoning.

Epitope-conditioned T cell receptor generator that writes its own in-context examples, so receptors can be designed for targets with no known binders.

De novo enzyme design conditioned on the reaction to be catalysed: substrate and product SMILES in, catalytic pocket, enzyme, and docked complex out.

Enzyme catalytic pocket design conditioned on a reaction: substrate and product in, pocket backbone, sequence, and EC class out.

Protein function prediction model that conditions a T5 encoder-decoder on retrieved homologs to assign EC numbers, GO terms and Pfam families.

Diffusion-based structure prediction model for biomolecular complexes, spanning proteins with DNA, RNA, small molecules, ions, and modified residues.

Family of medical multimodal models built on Gemini, adding uncertainty-guided web search, custom modality encoders, and long-context EHR reasoning.

Missense variant pathogenicity predictor built on AlphaFold 2 representations, scoring variants across the human proteome at 0.940 AuROC on ClinVar.

Self-supervised foundation model for retinal imaging, pretrained on 1.6 million unlabelled fundus and OCT scans to detect ocular and systemic disease.

Google's generalist multimodal biomedical AI that encodes clinical text, medical images, and genomics with a single set of weights across 14 tasks.

Protein complex structure prediction model extending AlphaFold 2 with paired MSA processing and ipTM scoring for multi-chain, multimeric assemblies.

Transformer that predicts gene expression and epigenomic signals from 200kb of DNA sequence, capturing distal enhancers up to 100kb from a promoter.

Protein structure prediction model that folds amino acid sequences into 3D structures with atomic accuracy, scoring a median GDT of 92.4 at CASP14.