Rohan Koodli

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2022-113

May 13, 2022

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-113.pdf

Single-cell multimodal sequencing methods, which measure multiple different modalities simultaneously (such as gene expression, chromatin accessibility, and surface protein data) are an exciting new space in the field of genomics as they provide a more comprehensive picture of cellular state than technologies that assay a single modality. Here I present PolyVI, a suite of three deep generative models to analyze DOGMA-seq (gene expression, protein, chromatin), ASAP-seq (chromatin, protein), and SNARE-seq (gene expression, chromatin) datasets. PolyVI is able to map the data to a low dimensional latent space, batch correct, and de-noise the data.

Advisors: Nir Yosef

---

BibTeX citation:

@mastersthesis{Koodli:EECS-2022-113,
    Author= {Koodli, Rohan},
    Title= {PolyVI: Deep Generative Models for Gene Expression, Chromatin Accessibility, and Surface Protein Expression Data},
    School= {EECS Department, University of California, Berkeley},
    Year= {2022},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-113.html},
    Number= {UCB/EECS-2022-113},
    Abstract= {Single-cell multimodal sequencing methods, which measure multiple different modalities simultaneously (such as gene expression, chromatin accessibility, and surface protein data) are an exciting new space in the field of genomics as they provide a more comprehensive picture of cellular state than technologies that assay a single modality. Here I present PolyVI, a suite of three deep generative models to analyze DOGMA-seq (gene expression, protein, chromatin), ASAP-seq (chromatin, protein), and SNARE-seq (gene expression, chromatin) datasets. PolyVI is able to map the data to a low dimensional latent space, batch correct, and de-noise the data.},
}

EndNote citation:

%0 Thesis
%A Koodli, Rohan 
%T PolyVI: Deep Generative Models for Gene Expression, Chromatin Accessibility, and Surface Protein Expression Data
%I EECS Department, University of California, Berkeley
%D 2022
%8 May 13
%@ UCB/EECS-2022-113
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-113.html
%F Koodli:EECS-2022-113