AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Regularized Molecular Conformation Fields

Lihao Wang, Yi Zhou, Yiqun Wang, Xiaoqing Zheng, Xuanjing Huang, Hao Zhou

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Diffusion for molecular conformations · 0 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
cluster 10,000 samples then pick one per cluster instead of direct samplingRMCF · GEOM-DrugsCOV-R mean: 82.25 -> 87.12Improved
cluster 10,000 samples then pick one per cluster instead of direct samplingRMCF · GEOM-DrugsMAT-R mean: 0.839 -> 0.749Improved
cluster samples instead of direct samplingRMCF · GEOM-DrugsCOV-P mean: 83.02 -> 82.01No clear effect
replace gold dihedral angles Xd with random ones (gold Xf) (ablation)RMCF · GEOM-DrugsCOV-R mean: 99.16 -> 66.21Hurt
replace gold fragment configuration Xf with random ones (gold Xd) (ablation)RMCF · GEOM-DrugsCOV-R mean: 99.16 -> 96.74Hurt
replace gold dihedral angles with random ones (gold Xf) (ablation)RMCF · GEOM-DrugsMAT-P mean: 0.290 -> 1.429Hurt
replace gold Xf with random Xf (gold Xd) (ablation)RMCF · GEOM-DrugsMAT-P mean: 0.290 -> 0.634Hurt
randomize both fragment configuration and dihedrals (ablation)RMCF · GEOM-DrugsCOV-R mean: 99.16 -> 63.60Hurt
use RMCF-C instead of GeoDiffRMCF-C · GEOM-DrugsCOV-P mean: 61.47 -> 82.01Improved
use RMCF-C instead of GeoDiffRMCF-C · GEOM-DrugsCOV-R mean: 89.13 -> 87.12Hurt
use RMCF-C instead of DMCGRMCF-C · GEOM-DrugsCOV-R mean: 96.69 -> 87.12Hurt
use RMCF-C instead of OMEGARMCF-C · GEOM-DrugsMAT-R mean: 0.851 -> 0.749Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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