Xiaomin Ni

This study identifies backdoor vulnerabilities in genomic foundation models through data poisoning during fine-tuning and proposes an auditing framework to detect such threats.

This study benchmarks single-cell foundation models for aging biology, finding that Geneformer excels in age prediction and pseudotime concordance, while SCimilarity outperforms others in rare state identification.

The paper identifies fragment binders and mutationally intolerant sites in Zika virus NS2B-NS3 protease to develop resistance-resilient antiviral inhibitors.

The paper solves the crystal structure of Arabidopsis thaliana FatA and identifies fragments that target novel regions, enabling the design of new herbicides with improved potency and novel interaction modes.

The paper identifies orally bioavailable inhibitors of the Zika virus NS2B-NS3 protease that show antiviral activity in vitro and reduce viral RNA load in a murine infection model.

The paper identifies chemical fragments targeting the Chikungunya virus nsP3 macrodomain through crystallographic screening, revealing novel binding sites and potential inhibitors.

This study identifies fragments binding to EV-D68 3C protease through crystallography and expands them into lead-like compounds, revealing novel binding modes and structural insights for drug design.

The paper identifies 75 fragments that bind to Coxsackievirus A16 2A protease, including 38 unique compounds in the active site, offering a path for broad-spectrum anti-enteroviral inhibitors.

This study uses high-throughput crystallographic fragment screening to identify 46 fragment binding poses on ZIKV NS3Hel, providing templates for antiviral drug design.