Reuben D. Sarwal

Reuben D. Sarwal

Auto-generated profile, based on publicly available information

Reuben D. Sarwal

Bakar Computational Health Sciences Institute, University of California, San Francisco

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 March 2020 in Science Translational Medicine
Verified
Journal Article
Closed access
Joshua YangJoshua Yang
Joshua Yang
RSReuben D. Sarwal
Reuben D. Sarwal
TSTara K. Sigdel
Tara K. Sigdel
IDIzabella Damm
Izabella Damm
BRBen Rosenbaum
Ben Rosenbaum
MSMinnie Sarwal
Minnie Sarwal
A urinary assay enables the noninvasive diagnosis of kidney transplant rejection in concordance with biopsy histology reports.

10 July 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
RSReuben Sarwal
Reuben Sarwal
VTVictor Tarca
Victor Tarca
CDClaire Dubin
Claire Dubin
NKNikolas Kalavros
Nikolas Kalavros
GBGaurav Bhatti
Gaurav Bhatti
MSMarina Sirota
Marina Sirota
Generative AI, particularly large language models (LLMs), is increasingly being used in computational biology to support code generation for data analysis. In this study, we evaluated the ability of LLMs to generate functional R and Python code for predictive modeling tasks, leveraging standardized molecular datasets from several recent DREAM (Dialogue for Reverse Engineering Assessments and Methods) Challenges focused on reproductive health. We assessed LLM performance across four predictive tasks derived from three DREAM challenges: gestational age regression from gene expression, gestational age regression from DNA methylation profiles, and classification of preterm birth and early preterm birth from microbiome data. LLMs were prompted with task descriptions, data locations, and target outcomes. LLM-generated code was then run to fit and apply prediction models and generate graphics, and they were ranked based on their success in completing the tasks and achieving strong test set performance. Among the eight LLMs tested, o3-mini-high, 4o, DeepseekR1 and Gemini 2.0 completed at least one task without error. Overall, R code generation was more successful (14/16 tasks) than Python (7/16), attributed to the utility of Bioconductor packages for querying Gene Expression Omnibus data. OpenAI’s o3-mini-high outperformed others, completing 7/8 tasks. Test set performance of the top LLM matched or exceeded top-performing teams from the original DREAM challenges. These findings underscore the potential of LLMs to enhance exploratory analysis and democratize access to predictive modeling in omics by automating key components of analysis pipelines, and highlight the potential to increase research output when conducting analyses of standardized datasets from public repositories.