Net Good IndexSubmit a correction

Harm Ledger · provisional · Biology

Interaction Profiles as a Universal Language for Generative Molecular Design with ShEPhERD-2

Three-dimensional intermolecular interactions govern molecular recognition and are fundamental to the pharmacological activity of small-molecule drugs. We propose that an interaction profile, comprising shape, electrostatics, and directional pharmacophores, is a sufficient and transferable design specification for molecular design. We introduce ShEPhERD-2, a 3D generative model that generates molecular structures conditioned on explicit interaction profiles. ShEPhERD-2 generates low-strain, drug-like molecules more efficiently and with greater fidelity to target interaction profiles than its p

12 Sep 2026Tier 1 Limited HarmMethodology 0.1

Current score

0.00

1 base · Limited Harm (tier 1 of 5, 1 pts)
× 0.1000 attribution · Minor documented assistance
× 0.1000 evidence · Firsthand or social claim
× 0.2000 realization · Proposed
× 0.5000 durability
Event-level product before credit split: 0.00

Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.

What happened

Three-dimensional intermolecular interactions govern molecular recognition and are fundamental to the pharmacological activity of small-molecule drugs. We propose that an interaction profile, comprising shape, electrostatics, and directional pharmacophores, is a sufficient and transferable design specification for molecular design. We introduce ShEPhERD-2, a 3D generative model that generates molecular structures conditioned on explicit interaction profiles. ShEPhERD-2 generates low-strain, drug-like molecules more efficiently and with greater fidelity to target interaction profiles than its predecessor while enabling precise control over molecular design through pharmacophore prioritization, substructure constraints, and composition of multiple interaction profiles. We demonstrate the application of a single model to bioisosteric fragment merging, dual-target design, selectivity engineering, and modality hopping without task-specific retraining. These results establish interaction profiles as a chemotype-agnostic interface between structure hypotheses and molecular design.

Model attribution

Unspecified AI system
Version unspecified
0.00

Unspecified

Unspecified system mentioned or implied by a news item. Remap to a named release when identified.

News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.

Attribution 0.1000 · Credit share 100% · Unknown

Claims

  • Interaction Profiles as a Universal Language for Generative Molecular Design with ShEPhERD-2

    outcome · supported

Sources

Revision history

  • 13 Sep 2026 · 0.00 0.00

    Auto-published from news ingest without human review.