Samin Rahman Khan

Inferring Multi-Stage Pathway Progression Models from Tumor Phylogenies

PhyloStage infers multi-stage pathway-level cancer progression models from tumor phylogenies, aligning with known AML progression and stratifying NSCLC patients by tumor size.

Quantifying Pathological Progression from Single-Cell Data

This paper introduces scPSS, a method to quantify pathological shifts in single-cell data by comparing diseased cells to healthy references, showing it can predict individual health conditions.

Exploring the Space of Tumor Phylogenies Consistent with Single-Cell Whole-Genome Sequencing Data

SCOPE explores the space of tumor phylogenies consistent with scWGS data, showing multiple phylogenies are possible and highlighting how data quality and evolutionary constraints affect uncertainty.

DeepBend: An Interpretable Model of DNA Bendability

DeepBend is a convolutional neural network that identifies DNA bendability motifs and their spatial patterns, revealing known and novel motifs and their role in chromatin structure.