AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing

Ziyu Fan, Zhijian Huang, Yahan Li, Xiaowen Hu, Siyuan Shen, Yunliang Wang, Zeyu Zhong, Shuhong Liu, Shuning Yang, Shangqian Wu, Min Wu, Lei Deng

AAAI 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based molecule design with diffusion · 1 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 clip-based data augmentation (ablation)HSPAG · 15.0% data: property predictionaverage AUC: 82.98 -> 86.36Improved
add clip-based data augmentation (ablation)HSPAG · 15.0% data: conditional generationRMSE: 0.419 -> 0.263Improved
add clip-based data augmentation (ablation)HSPAG · 15.0% data: generationuniqueness: 0.985 -> 0.864Hurt
add molecular-level-only alignment instead of hierarchical alignment (ablation)HSPAG · 15.0% data: conditional generationRMSE: 0.285 -> 0.263Improved
add any clip alignment (ablation)HSPAG · 15.0% data: property predictionaverage AUC: 82.44 -> 86.36Improved
add decoder to the model (HSPAG vs HSPAG-ND) (ablation)HSPAG · 15.0% data: property predictionaverage AUC: 85.12 -> 86.36Improved
add pre-training (ablation)HSPAG · BACEROC-AUC (%): 80.2 -> 88.1Improved
add pre-training (ablation)HSPAG · Tox21ROC-AUC (%): 78.5 -> 80.9Improved
add challenging set on top of random-only training (ablation)HSPAG · complex moleculesRMSE: 0.5207 -> 0.3906Improved
add challenging set on top of example-only training (ablation)HSPAG · complex moleculesavailability: 0.6157 -> 0.6845Improved
use HSPAG instead of GCPN for low logP targetHSPAG · outlier region logP -2.5 to -2success rate (%): 85.5% -> 33.3%Hurt
use HSPAG instead of LIMOHSPAG · molecular distribution learningvalidity: 1.000 -> .9483Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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