Xian Mallory

OncoSpot benchmarks cancer spatial transcriptomics methods across tumor evolutionary modes by simulating realistic cancer data with known subclonal and copy-number features.

CNVeil infers haplotype-specific copy number and subclonal architecture from single-cell cancer genomes, outperforming existing methods in accuracy and resolution.

DeepMalignant identifies malignant cells in scRNA-seq data by integrating gene expression and CNA, outperforming existing methods across multiple cancer types and platforms.

SCGclust integrates SNVs and CNAs using a graph autoencoder for cell clustering, achieving higher accuracy than existing methods on simulated and real cancer data.

CNVeil improves tumor subclone identification and copy number estimation in single-cell DNA sequencing by addressing noise and bias through novel computational methods.

scLongTree infers subclonal trees from longitudinal scDNA-seq data, outperforming existing tools in accuracy and scalability.

SCsnvcna places SNVs on a CNA tree using independent cell sets, improving accuracy in predicting SNV placement and losses due to copy number changes.

This paper benchmarks six cell clustering tools for single-cell DNA sequencing data, finding BnpC and SCG have highest accuracy, SBMClone excels in ultra-low coverage data.