# Valence Discovery

**Canonical:** https://apis.io/providers/valence-discovery/  
**Website:** https://www.valencelabs.com/  
**APIs profiled:** 0

Valence Discovery is an AI-first drug discovery company, now operating as Valence Labs, the AI research engine of Recursion. Formed from the merger of Datamol and InVivo AI, the team builds machine-learning methods and foundation models for molecular design, cellular perturbation prediction, and biological discovery, trained on petabyte-scale phenomics and transcriptomics data. Rather than a public REST API, Valence's developer surface is a suite of first-party open-source Python libraries - datamol, molfeat, graphium, SAFE and OpenQDC - published under the datamol-io and valence-labs GitHub organizations for cheminformatics, molecular featurization, graph neural networks and ML-ready quantum datasets.

## Kin Score — 10.3 / 100 (minimal)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 10.3).

| Facet | Score |
|---|---|
| Discoverability | 50.0 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 2.6 |
| Developer Ergonomics | 19.0 |
| Commercial Clarity | 10.5 |
| Access Clarity | 10.5 |

Regulatory layer — **Health**: 12.5 (matched via tags).

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Valence Discovery Domain Security** — TLSv1.3

## Tags

Company, Drug Discovery, Machine-Learning, Cheminformatics, Molecular Design, Artificial Intelligence, Life Sciences, Open-Source, Python

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/valence-discovery/). Scores are computed from the provider's own public artifacts under a published rubric.