Kenneth Aldape

SCLC TumorMiner is a genomics platform that provides molecular classification, biomarker identification, and drug-response analysis for small cell lung cancer using integrated datasets from multiple institutions.

Qombucha infers unobserved progenitor methylation profiles in GBM, revealing subtype-specific developmental programs and improved subtype classification.

The paper identifies ependymomas as originating from the pre-neural crest/roof plate lineage using single-cell transcriptomics and lineage tracing.

Path2Space predicts spatial gene expression and tumor microenvironment from histopathology slides, identifying new breast cancer subgroups and improving biomarker prediction.

The paper develops CSI-TME to identify prognostic cell state interactions in IDH-mutant gliomas, revealing a pro-tumor network associated with immune checkpoint therapy response.

The paper identifies variable merlin inactivation in schwannomas and shows TEAD1 inhibition can reverse hippo signaling and suppress tumor growth.

Path2Omics predicts gene expression and methylation from histopathology slides across 23 cancer types, outperforming previous models and showing effectiveness in predicting patient outcomes.

HERE is an image retrieval engine for H&E tumor pathology images that uses AI encoding and indexing to efficiently find similar images across large datasets.

This study identifies phosphoproteomic dysregulation as a driver of tumor proliferation in Cushing's disease and demonstrates reversibility using an FDA-approved PP2A agonist.

This paper introduces EXPAND, an interpretable AI model that predicts breast cancer subtypes and survival using nuclear features, achieving performance comparable to black-box models.

This study identifies genetic changes in IDH-mutant gliomas that correlate with treatment response and tumor evolution using longitudinal genomic data from 206 patient samples.

This paper introduces TIME_ACT, a transcriptomic signature predicting immune checkpoint blockade response across cancers, validated using histopathology and multiple cohorts.

The paper introduces OpenPedCan, a harmonized multi-omic dataset of pediatric cancer patients, providing integrated genomic, transcriptomic, and proteomic data for research and clinical applications.

The paper investigates the co-occurrence of chromosome 10 loss and chromosome 7 gain in gliomas, finding functional rescue interactions on chromosome 7 that may compensate for chromosome 10 loss.

This study analyzes the epigenetic evolution of IDH1-mutant and IDH1-wildtype gliomas under treatment, showing IDHmut tumors undergo epigenomic changes resembling IDHwt tumors, with implications for treatment strategies.

This paper introduces Sgootr, a method to infer tumor lineage trees from single-cell methylation data, revealing metastatic progression models and identifying lineage-informative CpG sites.

ENLIGHT predicts patient response to targeted and immunotherapies using tumor transcriptomes without prior treatment response data, showing better accuracy than existing transcriptomics-based signatures.

This paper introduces PERCEPTION, a framework using single-cell transcriptomics to predict cancer treatment response and resistance, outperforming bulk expression-based methods in clinical trials.

The paper examines how somatic structural variations affect TAD boundaries and gene regulation in human cancers using whole genome sequencing data.

This study identifies germline genetic variants influencing somatic mutation patterns in 2,642 cancer genomes across 39 cancer types.

This study characterizes mitochondrial genomes in 2,700 cancer patients across 37 types using whole-genome sequencing and RNA-seq, revealing mutational patterns, truncating mutations, and nuclear transfer of mitochondrial DNA.

This study analyzes chromothripsis in 2,658 cancers using whole-genome sequencing, finding it prevalent across multiple cancer types with complex structural alterations.