AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

On the Selectivity of Generative Models in Structure-Based Drug Design

Ella Miray Rajaonson, Jungyoon Lee, William Chau, Alan Aspuru-Guzik, Benjamin Sanchez-Lengeling, Dominique Beaini, Kirill Neklyudov, Marta Skreta

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies selectivity in structure-based drug design, noting that most generative models optimize binding to a single target and ignore off-target binding due to limited training data.

Problem

Most deep generative models for structure-based drug design optimize binding to a single target and ignore selectivity against off-target proteins, which contributes to clinical attrition from side effects.

Approach

Abstract is truncated; the paper addresses selectivity in generative SBDD models, which prior work largely neglects due to limited training data with multiple protein targets. Specific method not stated in the available text.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Z-score normalization of docking scores (ablation)docking delta-score · PARP1/PARP2 positive controlmean delta-score: -0.033 -> 0.207Improved
add Z-score normalization of docking scores (ablation)docking delta-score · CDK9/CDK2 positive controlmean delta-score: selective -0.691 -> 0.172; non-selective -1.074 -> -0.323Improved
train for selectivity (CMD-GEN, SpecLig) vs standard SBDD modelsselectivity-trained models · SelectBench-Casetop-10 delta z and selectivity rateNo clear effect
train for selectivity (CMD-GEN, SpecLig) vs standard SBDD modelsselectivity-trained models · SelectBench-Safety-Priorityaverage selectivity rate and R20Improved
train for selectivity vs standard SBDD modelsselectivity-trained models · SelectBench-XLtop-10 delta z and selectivity rateNo clear effect
use autoregressive models (Pocket2Mol, PocketFlow) instead of diffusion/flow modelsautoregressive SBDD models · SelectBench-Case and Safetyselectivity metricsHurt
add inference-time guidance (CFG or FKC) to diffusion modelsTargetDiff, DecompDiff, DiffSBDD · SelectBench-Caseselectivity metricsImproved
add inference-time guidance (CFG or FKC) to diffusion modelsdiffusion SBDD models · SelectBench-Safety-PriorityR20 z and average selectivity rateMixed
add inference-time guidancediffusion SBDD models · SelectBench-XL easy vs medium/hardselectivity metricsMixed
use aggressive negative guidance (beta1=1, beta2=-1) (ablation)FKC/CFG guidance · molecule validityvalidityHurt
add selectivity-focused guidancediffusion SBDD models · SelectBench-Case PARP taskpotency and synthesizabilityMixed

Limitations

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy