Erfan Sadeqi Azer

This paper reviews methods for inferring tumor evolutionary trees using binary matrix optimization and discusses a deep learning approach for topological inference.

Trisicell infers subclonal expansion patterns and therapeutic impact of intratumor heterogeneity from scRNAseq data, revealing correlations between mutational composition and tumor aggressiveness.

This paper introduces deep learning methods to infer tumor phylogeny topology and feasibility from single-cell genotype data, demonstrating the potential of data-driven approaches in cancer evolution analysis.

PhISCS-BnB computes the most likely perfect tumor phylogeny from single-cell sequencing data, offering optimality guarantees and significant speed improvements over existing methods.