M. El-Kebir

Sapling: Inferring and Summarizing Tumor Phylogenies from Bulk Data using Backbone Trees

Sapling infers and summarizes tumor phylogenies from bulk data using backbone trees, demonstrating high-quality results on simulated and real data.

Evolution-Aware Deep Reinforcement Learning for Single-Cell DNA Copy Number Calling

DeepCopy improves haplotype-specific copy number calling in single-cell DNA sequencing by incorporating evolutionary constraints, leading to more accurate and biologically plausible CNA phylogenies.

TRIBAL: Tree Inference of B cell Clonal Lineages

TRIBAL infers B cell lineage trees from scRNA-seq data by integrating isotype information, improving accuracy in capturing somatic mutations and class switch dynamics.

Consensus Tree under the Ancestor-Descendant Distance is NP-hard

The paper proves that finding a consensus tree minimizing the total ancestor-descendant distance is NP-hard for tumor phylogenies.

Modeling and Predicting Cancer Clonal Evolution with Reinforcement Learning

CloMu is a reinforcement learning-based model for predicting cancer clonal evolution, outperforming existing methods in mutation causality and fitness prediction.

ClonArch: Visualizing the Spatial Clonal Architecture of Tumors

ClonArch visualizes the spatial clonal architecture of tumors by integrating phylogenetic trees and spatial data to examine intratumor heterogeneity.