Zhihan Ruan

Predicting MammaPrint Recurrence Risk from Breast Cancer Pathological Images Using a Weakly Supervised Transformer

This paper develops CPMP, a weakly supervised transformer model, to predict MammaPrint recurrence risk from breast cancer histopathological slides, achieving an AUROC of 0.824.

Atlas of Breast Cancer in Chinese Young Women Revealed by Single-cell RNA and ATAC Sequencing

The paper establishes a single-cell atlas of breast cancer in young Chinese women, identifies new subtypes and therapeutic targets, and reveals distinct tumor progression patterns.

Single-Cell RNA and ATAC Sequencing Reveal Cellular Heterogeneity and Chromatin Accessibility Dynamics in Young Chinese Breast Cancer Patients across Pre- and Post-Neoadjuvant Therapy

This study uses scRNA-seq and scATAC-seq to analyze cellular heterogeneity and chromatin accessibility changes in young breast cancer patients before and after neoadjuvant therapy, identifying therapy-resistant genes and signaling pathways.

Triple-effect correction for Cell Painting data with contrastive and domain-adversarial learning

The paper introduces cpDistiller, a method to correct three technical effects in Cell Painting data using contrastive and domain-adversarial learning, improving analysis reliability and phenotypic response detection.

NeoTCR: an immunoinformatic database of experimentally-supported functional neoantigen-specific TCR sequences

NeoTCR is a database of experimentally validated neoantigen-specific TCR sequences across 18 cancer types, enabling query and analysis of TCR-clonotypes and neoantigen associations.