Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form
D-Scholarship @ Pitt Banner and Links to Homepage

Identification of Differentially Expressed Genes via Knockoff Statistics in Single-cell RNA Sequencing Data Analysis

Yi, Lixia (2024) Identification of Differentially Expressed Genes via Knockoff Statistics in Single-cell RNA Sequencing Data Analysis. Doctoral Dissertation, University of Pittsburgh. (Unpublished)

This is the latest version of this item.

[img]
Preview
 PDF
Download (3MB) | Preview

Abstract

Model-X knockoffs [Cand`es et al., 2018] is a recent statistical framework that allows scientists to discover true effects while controlling the false discovery rate (FDR) with finite sample guarantee by creating a synthetic copy of the original variables—knockoffs—as control. The framework works under arbitrary dimensional settings, but with the increase of dimensions, it becomes increasingly
difficult to create knockoffs due to the computational cost. The missingness of data, which is common in many high-dimensional datasets, adds another layer of difficulty for knockoff construction. We propose knockoff constructions based on a latent factor model that are able to handle the missing data, and are faster than the out-of-box method in Cand`es et al. [2018]. We apply our approach to differentially expressed gene analysis with single-cell RNA sequencing data to verify the FDR control and cross-reference the discovered genes with findings from other studies.

Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Yi, Lixialiy70@pitt.eduliy70
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Committee ChairLiu, Linxilinxi_liu@pitt.edu
Committee MemberMentch, Lucaslucasmentch@gmail.com
Committee MemberYu, Chengyucheng@pitt.edu
Committee MemberHe, Zihuaizihuai@stanford.edu
Date: 27 August 2024
Date Type: Publication
Defense Date: 24 May 2024
Approval Date: 27 August 2024
Submission Date: 22 July 2024
Access Restriction: No restriction; Release the ETD for access worldwide immediately.
Number of Pages: 75
Institution: University of Pittsburgh
Schools and Programs: Dietrich School of Arts and Sciences > Statistics
Degree: PhD - Doctor of Philosophy
Thesis Type: Doctoral Dissertation
Refereed: Yes
Uncontrolled Keywords: Model-X knockoffs; variable selection; false discovery rate; single-cell RNA sequencing; high-dimensionality
Date Deposited: 27 Aug 2024 13:34
Last Modified: 27 Aug 2024 13:34
URI: http://d-scholarship.pitt.edu/id/eprint/46735

Available Versions of this Item

  • Identification of Differentially Expressed Genes via Knockoff Statistics in Single-cell RNA Sequencing Data Analysis. (deposited 27 Aug 2024 13:34) [Currently Displayed]

Metrics

Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item