Responsive image

Adam Gayoso

PhD Student,
Computational Biology,
UC Berkeley
adamgayoso [at] berkeley [dot] edu

I am a second year graduate student in the Center for Computational Biology at UC Berkeley co-advised by Aaron Streets and Nir Yosef. I am interested in using deep generative models to derive insights from single-cell data.

I received my BS in Operations Research: Engineering Management Systems and MS in Computer Science at Columbia University. As a Columbia graduate student, I developed computational models for single-cell RNA-sequencing data with the Dana Pe'er Lab.


Journal Articles

Interpretable factor models of single-cell RNA-seq via variational autoencoders.
Valentine Svensson, Adam Gayoso, Nir Yosef, Lior Pachter.
Bioinformatics, 2020. [Paper]

Characterization of cell fate probabilities in single-cell data with Palantir.
Manu Setty, Vaidotas Kiseliovas, Jacob Levine, Adam Gayoso, Linas Mazutis, Dana Pe’er.
Nature Biotechnology, 2019. [Paper]

Stress-adaptive responses associated with high-level carbapenem resistance in kpc-producing klebsiella pneumoniae.
Sheila Adams-Sapper, Adam Gayoso, Lee. W. Riley.
Journal of Pathogens, 2018. [Paper]

Refereed Workshop Papers

A joint model of RNA expression and surface protein abundance in single cells.
Adam Gayoso, Romain Lopez, Zoë Steier, Jeffrey Regier, Aaron Streets, Nir Yosef
Machine Learning in Computational Biology (MLCB), 2019. [bioRxiv]

Detecting zero-inflated genes in single-cell transcriptomics data
Oscar Clivio, Romain Lopez, Jeffrey Regier, Adam Gayoso, Michael I. Jordan, Nir Yosef
Machine Learning in Computational Biology (MLCB), Spotlight talk, 2019. [bioRxiv]

Deep generative models for detecting differential expression in single cells.
Pierre Boyeau, Romain Lopez, Jeffrey Regier, Adam Gayoso, Michael I. Jordan, Nir Yosef.
Machine Learning in Computational Biology (MLCB), 2019. [bioRxiv]


single-cell Variational Inference (scVI)

scVI is an end-to-end analysis framework for single-cell transcriptomics.


DoubletDetection is a package to detect cross-type doublets in scRNA-seq datasets.