Colin C. Collins

This study uses longitudinal scRNA-seq to track neuroendocrine transdifferentiation in a prostate cancer model, identifying transcriptional changes and key regulators during treatment-induced NEPC progression.

This study uses longitudinal single-cell RNA sequencing to identify RUNX1T1 as a key regulator in the transition and maintenance of treatment-induced neuroendocrine prostate cancer.

This study identifies rare germline variants associated with metastatic prostate cancer using an extreme phenotype cohort and validates their functional impact.

scMUSCL improves scRNA-seq clustering by transferring knowledge from multiple annotated datasets without requiring batch correction or prior cluster number knowledge.

This study identifies lineage-specific transcription factor profiles in prostate cancer progression, revealing dynamic shifts during NE transdifferentiation and proposing a three-phase model.

This paper identifies m-APTA, an MTA analogue that reduces NBA toxicity without hypothermia, improving safety for MTAP-deficient cancer treatment.

This study shows AR-V7 forms condensates independently of androgens and AR-FL in CRPC, driving oncogenic transcription through both condensate-dependent and -independent mechanisms.

ScRAT predicts clinical phenotypes from scRNA-seq data using attention-based neural networks, outperforming existing methods with limited samples and identifying critical cell types.

Velodrome improves drug response prediction by generalizing across data distributions using labeled and unlabeled gene expression data from diverse sources.

This paper introduces CONETT, a method to identify conserved tumor evolution trajectories across multiple cancers, finding both previously reported and novel trajectories in renal and lung cancer datasets.

AITL improves drug response prediction by addressing input and output space discrepancies between pre-clinical and clinical pharmacogenomics datasets.

MOLI integrates multi-omics data using deep neural networks to predict drug response, achieving higher accuracy than single-omics and early integration methods.

The paper introduces cd-CAP, a method to detect conserved alteration patterns in cancer subnetworks across tumor samples.

This study introduces DGS, a method combining denoising autoencoders and transfer learning to predict prostate cancer metastasis using both labelled and unlabelled gene expression data, achieving higher accuracy than existing signatures.

MechRNA predicts lncRNA mechanisms by integrating RNA-RNA and RNA-protein interaction predictions to identify potential targets and mechanisms for cancer-related lncRNAs.

The paper introduces a computational framework integrating genomic, transcriptomic, and proteomic data to identify and interpret translated fusions and micro structural variations in cancer, finding many novel peptides and private aberrations in breast cancer.