Theme — drug-design

Items in corpus: 23

Papers

• RFdiffusion — Watson et al., Nature, 2023
  Diffusion-based de novo protein design exemplar.
• PerturbFate — Xu et al., Nature, 2026
  Perturbation screening mapping convergent regulators of melanoma drug resistance.
• sc-FM Perturbation Adapter — Maleki et al., ICLR LMRL workshop, 2026
  Drug-conditional adapter (<1% trainable params) on a frozen FM — generalises where CPA/GEARS/scGen don't.
• AIVEVs — AI Virtual Extracellular Vesicles — Bioactive Materials, 2026
  EV-focused AIVC paper — small but exists.
• TxGNN — knowledge-graph FM for therapeutics — Zitnik et al., Nature Medicine, 2024
  Graph FM bridging gene-level and patient-level AI.
• UNAGI — generative model for cellular dynamics + in-silico drug discovery — Ding lab et al., Nature Biomedical Engineering, 2025
  Time-series scRNA generative model used as a virtual-disease simulator for in-silico perturbation screens.
• DrugCLIP — contrastive protein-molecule virtual screening — NeurIPS 2023, 2023
  CLIP for protein-molecule retrieval — zero-shot virtual screen baseline that DrugReflector and successors build on.

Tools

• MAP — knowledge-driven perturbation framework — bioRxiv, 2026
  Zero-shot perturbation prediction for unprofiled drugs.
• AlphaFold 3 — Nature, 2024
  Structure prediction extended to complexes (proteins + nucleic acids + ions + ligands).
• Proteina / Proteina Complexa
  Generative protein-design FMs; Complexa reports 63.5% wet-lab hit on PDGFR binders.
• DrugReflector — 2026
  2026 AI drug-screening foundation model picked up in industry coverage — provenance still firming up.

Benchmarks

• Polaris Hub — drug-discovery ML benchmark community
  Public leaderboard for drug-discovery models.
• Therapeutics Data Commons (TDC-2) — Marinka Zitnik
  Therapeutic ML benchmark suite.

Organisations

• Isomorphic Labs
  DeepMind's commercial drug-discovery arm; bought Ahlmann-Eltze.
• Recursion Pharmaceuticals
  AI-native biotech using FMs for drug discovery.
• Insitro — Daphne Koller
  Applied virtual-cell case study in drug discovery.
• Cellarity
  Cell-state engineering company.

People

• Marinka Zitnik — Harvard Med
  TxGNN, TDC-2 creator; KG-FM-therapeutics axis.

Move

• Turbine raises $25M — 2026
  Validates commercial market for VC-style perturbation simulators.
• JPM 2026 — Lilly + NVIDIA $1B AI Co-Innovation Lab — 2026
  Largest pharma–AI infrastructure commitment, JPM Day 1.

Commentary

• Owl Posting — Biology + ML essays — Abhishaike Mahajan
  Long-form bio+ML essays — one of the better field-walkthrough writers.
• Decoding Bio — weekly biotech + AI — Substack
  Weekly biotech + FM-paper digest.
• M2D2 — Molecular Modelling & Drug Discovery — Valence Labs & Mila
  Weekly reading group + podcast on ML for discovery.

---

Regenerated 2026-05-15 from a 277-item corpus by resourcelib-views.