Compliance & Validation — Documented
SOC 2 Type II
Numerion Labs
Deep learning platform for structure-based drug discovery, specializing in small molecule design (formerly Atomwise).
Numerion Labs — the company formerly known as Atomwise, rebranded in 2025 — applies deep learning to structure-based drug discovery. Its AtomNet convolutional neural network technology is trained on large datasets of protein-small molecule interactions to predict binding affinity and drug-like properties, and has been used across drug discovery programs with pharmaceutical companies and academic institutions. The company markets an AI platform for exploring chemical space to identify novel, drug-like molecules.
- Headquarters
- San Francisco, United States
- Founded
- 2012
- Compliance
- SOC 2 Type II
- Deployment options
- cloud
- Website
- https://numerionlabs.ai
- https://www.linkedin.com/company/numerion-labs
Categories
AI Use Cases
- ADMET & Toxicity Prediction
- Hit Identification & Lead Optimization
Vendor Scorecard
100% — Complete coverage. Coverage score — how completely Atlas documents Numerion Labs across 7 buyer-evaluation areas. Reflects available Atlas data, not solution quality.
Deployment & Hosting — Documented
cloud
Pricing Transparency — Documented
Project based / SaaS
Implementation & Onboarding — Documented
1–3 months
Organization & Role Fit — Documented
Biotech Startup, Mid-Size Biotech, Large Pharma, Drug Discovery
Solution Scope — Documented
ADMET Prediction, Molecular Generation, Protein Structure Prediction
Company Viability — Documented
Series C, $219M raised, 130+ employees, Founded 2012
Always ask the vendor
Not captured in Atlas data — confirm directly. Excluded from the score above.
Data Rights & IP
Who owns model outputs? Is our proprietary data used to train models others can access, and where does our data reside?
Model Credibility & Explainability
Can you share validation studies or benchmarks, explain how the model reaches its conclusions, and describe how bias and drift are monitored?
Questions to Ask This Vendor
- What is the average enrichment factor across your retrospective benchmarks?
- Do you offer custom model training on proprietary assay data?
- How do you handle confidentiality of protein structures?