Xun Lan

LoCoFlow improves trajectory inference in single-cell data by incorporating local geometry and fate uncertainty, achieving better performance than existing methods.

This study identifies a myeloid bypass pathway that supports long-term HSC reconstitution by analyzing single-cell transplantation data with a mathematical model.

COMSE improves scRNA-seq analysis by selecting informative genes via community detection, enhancing clustering and distinguishing biological variation from batch effects.

VitTCR predicts TCR-peptide interactions using a vision transformer-based model, outperforming existing methods in classification accuracy.

CIBER is a causal inference framework for analyzing cell state transitions, identifying key features in differentiation processes and predicting novel regulatory associations.

The paper identifies frequent non-allelic gene conversion in human gene duplicates and estimates its parameters, showing it has a small average effect on sequence divergence.