Author

Zhicai Wang

Scinetics CompanyPrimary ORCID profile (0000-0002-3186-2135 · 1 paper)Unclaimed ORCID profile · follow to get notified of new preprints

Listed by name: these papers carry no ORCID for this author, so different people with the same name may be mixed together.

Same name, identified by ORCID

Zhicai WangiD1 paper · Tongji University

Biology Disciplines

Click to filter author papers

Bioinformatics· 3

Signature Assays, Organisms & Methods

Click to filter · or open tag

Approach:deep learning· 3 Research Focus:benchmarking· 1 Research Focus:protein design· 1 Assay:protein sequence· 1 Assay:protein structure· 1 Research Focus:protein structure prediction· 1 Approach:transformer / foundation model· 1

Frequent Co-Authors

Jiaxian YaniD· 3 shared Mingyang XuiD· 3 shared Zaixi ZhangiD· 3 shared Dongchu Xie· 1 shared Qingran Cai· 1 shared Qizhi PeiiD· 1 shared Xun Xu· 1 shared Yufeng Liu· 1 shared

Activity by Year

2026-2026 · peak 3/yr

Co-Author Collaboration Network

8 top collaborators · 21 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

3 shared papersBioinformatics

Jiaxian YanORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

All-Atom Structure Tokenizer: AtomLM-9b for Biomolecular Structure Prediction

Jiaxian Yan, Dongchu Xie, Zhicai Wang, Mingyang Xu, Zaixi Zhang

The paper introduces AtomLM-9b, a language model using an all-atom structure tokenizer to predict protein structures with performance comparable to AlphaFold 3.

bioRxiv · Nov 4, 2026 · PreprintBioinformatics

ScienceRSI: Recursive Scientific Self-Improvement

Xun Xu, Jiaxian Yan, Zhicai Wang, Mingyang Xu, Zaixi Zhang

ScienceRSI improves scientific AI through recursive self-improvement by transferring capabilities across model scales, achieving top performance on multiple benchmarks.

bioRxiv · Oct 25, 2026 · PreprintBioinformatics

Chain of Structures: Connecting Reasoning and Generation for Protein Design

Qingran Cai, Mingyang Xu, Jiaxian Yan, Zhicai Wang, Yufeng Liu, Qizhi Pei, Zaixi Zhang

The paper introduces a method for protein design that connects reasoning and generation through structural states, achieving high performance on a benchmark.

bioRxiv · Oct 11, 2026 · PreprintBioinformatics