Peter S. Nelson

Gene expression inference from cell-free DNA using uncertainty-aware deep learning

This paper develops a deep learning framework to infer gene expression from cell-free DNA, improving reliability and enabling functional genomics in precision oncology.

Genotoxic antibody-drug conjugates combined with Bcl-xL inhibitors enhance therapeutic efficacy in metastatic castration-resistant prostate cancer

Global mRNA 3'UTR lengthening in small-cell neuroendocrine carcinoma

The paper identifies global 3'UTR lengthening in SCNC through APA and develops a neural network model to classify SCNC using APA signatures.

Lack of synergy between AR targeted therapies and PARP inhibitors in homologous recombination-proficient prostate cancer

This study shows that AR inhibition does not enhance PARP inhibitor efficacy in HR-proficient prostate cancer and instead impairs response in castration-sensitive cells.

Genome-wide CRISPR screens identify PTGES3 as a novel AR modulator

This study uses CRISPR screens to identify PTGES3 as a novel modulator of AR protein levels and function in prostate cancer, showing its role in therapy resistance.

Moving Beyond Binary Biomarkers: Machine Learning Model Resolves Concurrent and Molecularly Heterogeneous Mismatch Repair and Homologous Recombination Deficiencies in Prostate Cancer

This paper develops a machine learning model to identify molecularly distinct DDR subgroups in prostate cancer, revealing concurrent repair deficiencies and improving therapeutic stratification.

Genetic and Epigenetic Reprogramming of Transposable Elements Drives ecDNA-Mediated Metastatic Prostate Cancer

The paper identifies a subgroup of mCRPC characterized by LINE1 repeat DNA elements flanking the AR gene, which drive AR overexpression and confer resistance to androgen signaling inhibitors.

Targeting the ITGA3B1 Complex with A Novel Antibody-Drug Conjugate for Metastatic Bladder Cancer

The paper identifies ITGA3B1 as a therapeutic target for metastatic bladder cancer using a phenotypic screening strategy and develops an ADC targeting this integrin complex, showing antitumor efficacy in preclinical models.

Defined cellular reprogramming of androgen receptor-active prostate cancer to neuroendocrine prostate cancer

This study reprograms AR-active prostate cancer to NEPC using ASCL1 and NeuroD1, revealing their role in silencing AR and altering chromatin structure.

Deciphering single-cell heterogeneity and cellular ecosystem dynamics during prostate cancer progression

This study constructs the Prostate Cancer Cell Atlas by analyzing ~710,000 single cells from 197 human samples to characterize cell states and dynamics across prostate cancer progression stages.

Molecular consequences of acute versus chronic CDK12 loss in prostate carcinoma nominates distinct therapeutic strategies

This study shows that acute CDK12 loss in prostate cancer causes HR deficiency via polyadenylation, but chronic loss leads to adaptation, making PARP inhibitors ineffective and suggesting CDK13 targeting as a new therapeutic approach.

Single Cell Analysis of Treatment-Resistant Prostate Cancer: Implications of Cell State Changes for Cell Surface Antigen Targeted Therapies

The paper uses single-cell analysis to study how cell surface antigen expression changes in treatment-resistant prostate cancer, revealing transcriptional heterogeneity and shared gene regulatory networks between NEPC and SCLC.

Patterns of Structural Variation Define Prostate Cancer Across Disease States

This study identifies distinct structural variation patterns in prostate cancer across disease states, defining clinically actionable subgroups based on whole genome profiling.

Discovery and reporting of clinically-relevant germline variants in advanced cancer patients assessed using whole-exome sequencing

This study reports that 17% of advanced cancer patients have clinically relevant germline variants, with higher rates of cancer-associated variants compared to control cohorts.