AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

LipoPU: Pocket-level Prediction of Lipid-Protein Interactions via Positive-Unlabeled Learning

Yuxing Wang, Wenyi Zhang, Yilong Zou, Jing Huang

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data

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 ranking-based PU objective instead of weighted BCELipoPU · Easy test setBinary PR-AUC: 0.630 -> 0.839Improved
use ranking-based PU objective instead of weighted BCELipoPU · Easy test setMicro PR-AUC: 0.453 -> 0.766Improved
use ranking-based PU objective instead of weighted BCELipoPU · Hard test setBinary PR-AUC: 0.557 -> 0.650Improved
use ranking-based PU objective instead of weighted BCELipoPU · Hard test setMicro PR-AUC: 0.195 -> 0.280Improved
add positive-guaranteed batch sampler to BCEBCE baseline · Easy test setBinary PR-AUC: 0.630 -> 0.651No clear effect
use LipoPU instead of SLiPPpocket-level lipid binding · Easy-fpocketBinary PR-AUC: 0.239 -> 0.792Improved
use LipoPU instead of SLiPPpocket-level lipid binding · Hard-fpocketBinary ROC-AUC: 0.726 -> 0.881Improved
add positive-guaranteed batch sampler (ablation)LipoPU · Easy test setMicro PR-AUC: 0.696 -> 0.766Improved
add positive-guaranteed batch sampler (ablation)LipoPU · Hard test setMicro PR-AUC: 0.250 -> 0.280Improved
use ranking-based PU loss instead of standard PU loss (ablation)LipoPU · Easy test setBinary PR-AUC: 0.449 -> 0.839Improved
use ranking-based PU loss instead of standard PU loss (ablation)LipoPU · Hard test setMicro PR-AUC: 0.208 -> 0.280Improved
use attention MIL pooling instead of mean pooling (ablation)LipoPU · Easy test setMicro PR-AUC: 0.731 -> 0.766Improved

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