AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

GP-MoLFormer-Sim: Test Time Molecular Optimization Through Contextual Similarity Guidance

Jiří Navrátil, Jarret Ross, Payel Das, Youssef Mroueh, Samuel C Hoffman, Vijil Chenthamarakshan, Brian Belgodere

AAAI 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 2 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
add graph-based crossover (XO) (ablation)guided generation · PMO 23 tasks configuration ablationaverage top-10 AUC: 0.603 -> 0.672Improved
add random Fourier features (RFF768) alone (ablation)guided generation · PMO 23 tasks configuration ablationaverage top-10 AUC: 0.603 -> 0.597Hurt
add RFF768 on top of XO (ablation)GG+XO · PMO 23 tasks configuration ablationaverage top-10 AUC: 0.672 -> 0.682Improved
add diverse guides (DIV) on top of XO (ablation)GG+XO · PMO 23 tasks configuration ablationaverage top-10 AUC: 0.672 -> 0.678Improved
add DIV on top of RFF768+XO (ablation)GG+RFF768+XO · PMO 23 tasks configuration ablationaverage top-10 AUC: 0.682 -> 0.690Improved
redact molecule name from MOLLEO prompt (thiothixene) (ablation)MOLLEO GPT-4.1-mini · PMO thiothixene_rediscoverytop-10 AUC: 0.692 -> 0.462Hurt
redact molecule name from MOLLEO prompt (mestranol) (ablation)MOLLEO GPT-4.1-mini · PMO mestranol_similaritytop-10 AUC: 0.983 -> 0.644Hurt
give GPMFS+GA access to target SMILES in the oracleGPMFS+GA · PMO (tasks with known target)average top-10 AUC: 0.662 -> 0.737Improved
use GPMFS+GA instead of MOLLEO (redacted) in black-box settingMOLLEO GPT-4.1-mini redacted · PMO thiothixene_rediscoverytop-10 AUC: 0.462 -> 0.504Improved
use GPMFS+GA instead of MOLLEO GPT-4 with name in promptMOLLEO (GPT-4) · PMO benchmark (23 tasks, black-box oracle)average top-10 AUC: 0.777 -> 0.662Hurt
use GP-MoLFormer-Sim guidance instead of random generations (top-10000)random generation · Trypsin inhibitor similaritymean Tanimoto similarity: 0.225 -> 0.573Improved
use GP-MoLFormer-Sim guidance instead of RL-tuned S model (top-10000)S model · Trypsin inhibitor similaritymean Tanimoto similarity: 0.439 -> 0.573Improved

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