AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

CoDrug: Conformal Drug Property Prediction with Density Estimation under Covariate Shift

Siddhartha Laghuvarapu, Zhen Lin, Jimeng Sun

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based 3D molecule generation · 3 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 energy-based density weighting (CoDrug Energy)conformal prediction · AMES(Y=1) fingerprint splitcoverage: 0.63 -> 0.88Improved
add energy-based density weightingconformal prediction · AMES(Y=0) fingerprint splitcoverage: 1.00(0.00) -> 0.93(0.03)Improved
add energy weightingconformal prediction · ClinTox(Y=1) fingerprint splitcoverage: 0.80(0.00) -> 0.73(0.00)Hurt
add energy weightingconformal prediction · Tox21(Y=0) fingerprint splitcoverage: 0.77(0.03) -> 0.90(0.02)Improved
weight by KDE on energies instead of penultimate featuresCoDrug · AMES/ClinTox/HIV/Tox21 alpha=0.1coverageImproved
remove energy regularization term (NoEnergy) (ablation)CoDrug · mean absolute coverage deviation, alpha=0.3deviation: 0.104 (0.09) -> 0.112 (0.11)Hurt
remove energy regularization term (NoEnergy) (ablation)CoDrug · mean absolute coverage deviation, alpha=0.1deviation: 0.052 (0.05) -> 0.047 (0.05)Improved
remove energy regularization term (NoEnergy) (ablation)CoDrug · tail 25% deviation, alpha=0.3deviation: 0.233 (0.05) -> 0.288 (0.05)Hurt
replace KDE with logistic classifier weights (ablation)CoDrug(Energy) · mean absolute coverage deviation, alpha=0.2deviation: 0.079 (0.07) -> 0.106 (0.13)Hurt
replace KDE with logistic classifier weights (ablation)CoDrug(Energy) · tail 25% deviation, alpha=0.1deviation: 0.11 (0.04) -> 0.222 (0.22)Hurt
apply CoDrug(Energy) to REINVENT samplesunweighted CP · GSK3b+QED Y=0coverage: 0.44 (0.16) -> 0.81 (0.04)Improved
apply CoDrug(Energy) to REINVENT samplesunweighted CP · JNK3+QED Y=0coverage: 0.62 (0.12) -> 0.95 (0.01)Improved

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