Biology foundation models
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 10 |
| Companies | 40 |
| Part of | neural networks |
| Map changed | 2026-10-15 |
| Map | open the map |
Biology foundation models is a territory of the AI industry on map of ai. In short: biology foundation models are large-scale machine learning models trained on biological data including dna sequences, proteins, cells, and omics measurements to generate general-purpose representations. The map lists 40 products and companies in 10 categories.
The map of biology foundation models has 10 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
protein language models6 products and companies
Protein language models learn patterns from protein sequences and structures to generate embeddings and predictions about protein function and properties. Researchers, biotech companies, and drug discovery teams use them to understand proteins, design new ones, and prioritize candidates for experimental validation.
Products and companies
Open ground
ESMFold, ProtBERT, AlphaFold2, and OmegaFold all predict structure or generate sequence embeddings from single proteins; none of them yet takes as input a full cellular context or inter-protein interaction network to jointly optimize designs across multiple proteins in a pathway.
structure prediction models4 products and companies
Structure prediction models infer 3D molecular conformations from sequence data. Researchers, drug developers, and structural biologists use them to model proteins, RNA, and small molecules without experimental determination.
Products and companies
genomic dna models5 products and companies
Genomic DNA models are foundation models trained on large-scale DNA sequence data that perform tasks like sequence classification, variant effect prediction, and regulatory element identification. Researchers, clinical geneticists, and biotech companies use these models to interpret genetic variation and understand genome function.
Products and companies
single-cell and virtual cell models4 products and companies
Single-cell models simulate gene expression and cellular behavior in individual cells; virtual cell models computationally represent whole-cell dynamics including metabolism and signaling. Researchers in systems biology, cell biology, and drug development use these to understand cell-state transitions, predict drug responses, and model disease mechanisms.
Products and companies
generative protein design platforms4 products and companies
Platforms that computationally design novel protein sequences and structures from scratch or by modification, used by biotech researchers, drug developers, and synthetic biology teams to engineer proteins with specified functions.
Products and companies
bio model hosting and apis4 products and companies
Platforms and APIs that host pretrained biology foundation models and provide programmatic access to run inference or fine-tuning on biological sequences and structures. Researchers, biotech companies, and drug discovery teams use these services to query models without operating their own infrastructure.
Products and companies: nvidia bionemo, tamarind bio, neurosnap, rowan.
ai scientist agents for biology4 products and companies
AI agents that autonomously design and execute biology experiments, interpret results, and iterate on hypotheses. Used by research labs, biotech companies, and academic institutions to accelerate experimental workflows.
Products and companies: futurehouse, biomni, owkin, lila sciences.
drug discovery platforms3 products and companies · its own article →
Platforms that use foundation models trained on biological data to accelerate the identification and optimization of drug candidates. Pharmaceutical companies, biotech firms, and CROs use these to screen compounds, predict efficacy, and design novel molecules.
Products and companies: insilico medicine, schrodinger, valence labs.
Papers, last 30 days:- Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences 2026-11-11
- DrugCoding: A Scientific Programming Agent for Drug Discovery 2026-11-10
- PharmAgents2: Towards Autonomous End-to-End Drug Discovery 2026-11-05
- El Agente Fármaco: A Scalable AI Scientist for Drug Discovery 2026-11-02
bio ai infrastructure and tooling2 products and companies
Software platforms and APIs that host, serve, and manage access to biological foundation models for researchers and developers. Used by academic labs, biotech companies, and AI researchers who need to run inference on pre-trained models without maintaining their own infrastructure.
Products and companies: hugging face, benchling.
clinical and pathology foundation models4 products and companies
Foundation models trained on clinical notes, pathology reports, medical imaging, and lab results that learn patterns from clinical data. Hospitals, diagnostic labs, and clinical research groups use these models to process and understand patient data at scale.
Products and companies: paige, tempus, bioptimus, aignostics.
See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.