AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Retrieval-based Controllable Molecule Generation

Zichao Wang, Weili Nie, Zhuoran Qiao, Chaowei Xiao, Richard Baraniuk, Anima Anandkumar

ICLR 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based molecule design with diffusion · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use RetMol retrieval and fusion for QED optimizationMolecule generation with ChemFormer · QED optimization, similarity δ=0.4success rate: 92.8 -> 94.5Improved
Use RetMol retrieval and fusion for penalized logP optimizationMolecule generation with ChemFormer · Penalized logP optimization, similarity δ=0.6average penalized logP improvement: 3.73±2.85 -> 3.78±3.29Improved
Use RetMol retrieval and fusion for penalized logP optimizationMolecule generation with ChemFormer · Penalized logP optimization, similarity δ=0.4average penalized logP improvement: 7.71±5.65 -> 11.55±11.27Improved
Use RetMol for four-property optimizationMolecule generation with ChemFormer · GSK3β and JNK3 inhibition with QED and SA constraintssuccess rate: 92.3 -> 96.9Improved
Use RetMol for SARS-CoV-2 main protease optimizationEight weak inhibitors · SARS-CoV-2 main protease optimization, similarity δ=0.6successful optimizations: 3/8 -> 5/8Improved
Use RetMol for SARS-CoV-2 main protease optimizationEight weak inhibitors · SARS-CoV-2 main protease optimization, similarity δ=0.4average binding affinity improvement (kcal/mol): 1.67 -> 2.84Improved
Train the fusion module to predict the nearest neighbor instead of reconstructing the input (ablation)RetMol · Unconditional molecule generationvalidity: 0.834 -> 0.902Improved
Train the fusion module to predict the nearest neighbor instead of reconstructing the input (ablation)RetMol · Unconditional molecule generationuniqueness: 0.665 -> 0.922Improved
Use a retrieval database satisfying GSK3β and JNK3 constraints, but not QED and SA (ablation)RetMol · GSK3β and JNK3 inhibition with QED and SA constraintssuccess rate: 96.9 -> 84.7Hurt
Use a retrieval database satisfying only GSK3β or JNK3 (ablation)RetMol · GSK3β and JNK3 inhibition with QED and SA constraintssuccess rate: 96.9 -> 44.1Hurt
Increase the retrieval database size (ablation)RetMol · Four-property molecule optimizationgeneration performanceImproved
Increase the number of optimization iterations (ablation)RetMol · Four-property molecule optimizationgeneration performanceImproved

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