Author

Li Tian

Novartis (China)ORCID 0000-0002-9972-0299Unclaimed ORCID profile · follow to get notified of new preprints

Additional preprints under this name without ORCID

Li Tian9 papers · Wenzhou University

Biology Disciplines

Click to filter author papers

Bioinformatics· 3

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:statistical model· 2 Approach:benchmark study· 1 Research Focus:benchmarking· 1 Approach:deep learning· 1 Research Focus:drug response / drug discovery· 1 Approach:machine learning (classical)· 1

Frequent Co-Authors

Chi‐Ming CheiD· 1 shared Eric Martin· 1 shared Éric MartiniD· 1 shared Hugh Hongkai Huang· 1 shared Junzhou HuangiD· 1 shared Prasenjit K. MukherjeeiD· 1 shared Shaoyong XuiD· 1 shared Valery R. PolyakoviD· 1 shared

Activity by Year

2019-2026 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 16 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

1 shared paperBioinformatics

Chi‐Ming CheORCID

Author profile →

3 papers

Recent·Most cited

Benchmarking Uncertainty and Improving Risk Ranking in Multi-task Bioactivity Prediction

Zijian Wang, Li Tian, Chi‐Ming Che

The paper benchmarks uncertainty estimation and risk ranking in multi-task bioactivity prediction, introducing ICSR to improve reliability of kernel-based predictions.

bioRxiv · Sep 22, 2026 · PreprintBioinformatics

Transfer learning applied in predicting small molecule bioactivity

Li Tian, Hugh Hongkai Huang, Eric Martin, Ying Wei, Shaoyong Xu, Junzhou Huang

This study compares two transfer learning approaches for predicting small molecule bioactivity, finding similar performance but different strengths in handling smaller assays.

bioRxiv · Jan 9, 2025 · PreprintBioinformatics

All-Assay-Max2 pQSAR: Activity predictions as accurate as 4-concentration IC50s for 8,558 Novartis assays

Éric Martin, Valery R. Polyakov, Xiang‐Wei Zhu, Li Tian, Prasenjit K. Mukherjee, Xin Liu

The paper introduces All-Assay-Max2 pQSAR, a multi-task machine learning method that achieves IC50 prediction accuracy comparable to 4-concentration experiments across 8,558 Novartis assays.

Journal of Chemical Information and Modeling · Sep 13, 2019Peer-reviewedBioinformatics