Gustavo A. Stolovitzky

This study evaluates large language models' ability to generate predictive modeling code for reproductive health using standardized datasets, finding R code generation more successful than Python and some models matching top DREAM challenge teams.

The paper constructs context-specific brain gene regulatory networks from bulk and single-cell RNA-seq data using Bayesian and deep learning methods to study Autism Spectrum Disorder mechanisms.

The paper develops predictive models for preterm birth using maternal blood multi-omics data, finding transcriptomic and proteomic markers can predict gestational age and spontaneous preterm birth with high accuracy.

This paper introduces a baseline model for drug combination effects in cancer, showing its utility in both clinical and cell culture settings.

The paper analyzes proteo-transcriptomic profiles of extracellular vesicles and their donor cancer cells, finding distinct cargo enrichment patterns and suggesting coordinated disposal mechanisms.

The paper identifies exRNA signatures in circulating tumor extracellular vesicles (CTEVs) from prostate cancer patients and shows their differential expression post-tumor resection.

The paper predicts cellular positions in the Drosophila embryo using scRNA-seq data by benchmarking methods against spatially annotated genes.

An ensemble of six imputation methods, built through the NCI-CPTAC Proteogenomics DREAM Challenge, fills missing values in labeled LC-MS/MS proteomics data, helping most for low-abundance proteins.

The paper evaluates module identification methods across disease-relevant networks using GWAS data to identify top-performing algorithms and disease-associated modules.

The paper benchmarks somatic structural variant detection methods using synthetic tumors and crowd-sourced submissions, finding that ensembles do not always outperform individual methods.

The paper shows that variable mitochondria abundance affects cell survival and fractional cell death response to TRAIL through Bax effective concentration variation.

The paper develops an ontology to model subcellular processes and their interactions to predict whole cell functions from omics data.

This paper presents a crowdsourced challenge to predict early discontinuation of docetaxel in mCRPC patients using clinical data from multiple trials, finding that ensemble models outperform individual models.

The paper demonstrates that machine learning can accurately predict odor perception from molecular features, enabling reverse-engineering of smell.