Optimal Bayesian supervised domain adaptation for RNA sequencing data

Boluki, Shahin; Qian, Xiaoning; Dougherty, Edward R.; Gorodkin, Jan

doi:10.1093/bioinformatics/btab228

Optimal Bayesian supervised domain adaptation for RNA sequencing data

Journal Article · 05 April 2021 · Bioinformatics

DOI:https://doi.org/10.1093/bioinformatics/btab228· OSTI ID:1853183

^[1]; Qian, Xiaoning ^[2]; Dougherty, Edward R. ^[3]; Gorodkin, Jan

Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA; OSTI
Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA; TEES-AgriLife Center for Bioinformatics & Genomic Systems Engineering, Texas A&M University, College Station, TX 77843, USA
Department of Electrical & Computer Engineering, Texas A&M University, College Station, TX 77843, USA

Abstract Motivation

When learning to subtype complex disease based on next-generation sequencing data, the amount of available data is often limited. Recent works have tried to leverage data from other domains to design better predictors in the target domain of interest with varying degrees of success. But they are either limited to the cases requiring the outcome label correspondence across domains or cannot leverage the label information at all. Moreover, the existing methods cannot usually benefit from other information available a priori such as gene interaction networks.

Results

In this article, we develop a generative optimal Bayesian supervised domain adaptation (OBSDA) model that can integrate RNA sequencing (RNA-Seq) data from different domains along with their labels for improving prediction accuracy in the target domain. Our model can be applied in cases where different domains share the same labels or have different ones. OBSDA is based on a hierarchical Bayesian negative binomial model with parameter factorization, for which the optimal predictor can be derived by marginalization of likelihood over the posterior of the parameters. We first provide an efficient Gibbs sampler for parameter inference in OBSDA. Then, we leverage the gene-gene network prior information and construct an informed and flexible variational family to infer the posterior distributions of model parameters. Comprehensive experiments on real-world RNA-Seq data demonstrate the superior performance of OBSDA, in terms of accuracy in identifying cancer subtypes by utilizing data from different domains. Moreover, we show that by taking advantage of the prior network information we can further improve the performance.

Availability and implementation

The source code for implementations of OBSDA and SI-OBSDA are available at the following link. https://github.com/SHBLK/BSDA.

Supplementary information

Supplementary data are available at Bioinformatics online.

Research Organization:: Duke Univ., Durham, NC (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

DOE Contract Number:: SC0019393;

OSTI ID:: 1853183

Journal Information:: Bioinformatics, Journal Name: Bioinformatics Journal Issue: 19 Vol. 37; ISSN 1367-4803

Publisher:: International Society for Computational Biology - Oxford University Press

Country of Publication:: United States

Language:: English

References (28)

The Cancer Genome Atlas: Creating Lasting Value beyond Its Data Hutter, Carolyn; Zenklusen, Jean Claude Cell, Vol. 173, Issue 2 https://doi.org/10.1016/j.cell.2018.03.042	journal	April 2018
Optimal classifiers with minimum expected error within a Bayesian framework—Part I: Discrete and Gaussian models Dalton, Lori A.; Dougherty, Edward R. Pattern Recognition, Vol. 46, Issue 5 https://doi.org/10.1016/j.patcog.2012.10.018	journal	May 2013
An Introduction to Variational Methods for Graphical Models Jordan, Michael I.; Ghahramani, Zoubin; Jaakkola, Tommi S. Machine Learning, Vol. 37, Issue 2, p. 183-233 https://doi.org/10.1023/A:1007665907178	journal	January 1999
Integrated genomic characterization of endometrial carcinoma Levine, Douglas A. Nature, Vol. 497, Issue 7447 https://doi.org/10.1038/nature12113	journal	May 2013
Toward understanding and exploiting tumor heterogeneity Alizadeh, Ash A.; Aranda, Victoria; Bardelli, Alberto Nature Medicine, Vol. 21, Issue 8 https://doi.org/10.1038/nm.3915	journal	August 2015
Found In Translation: a machine learning model for mouse-to-human inference Normand, Rachelly; Du, Wenfei; Briller, Mayan Nature Methods, Vol. 15, Issue 12 https://doi.org/10.1038/s41592-018-0214-9	journal	November 2018
Searching the overlap between network modules with specific betweeness (S2B) and its application to cross-disease analysis Garcia-Vaquero, Marina L.; Gama-Carvalho, Margarida; Rivas, Javier De Las Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-29990-7	journal	August 2018
Variational Inference: A Review for Statisticians Blei, David M.; Kucukelbir, Alp; McAuliffe, Jon D. Journal of the American Statistical Association, Vol. 112, Issue 518 https://doi.org/10.1080/01621459.2017.1285773	journal	July 2016
BNP-Seq: Bayesian Nonparametric Differential Expression Analysis of Sequencing Count Data Dadaneh, Siamak Zamani; Qian, Xiaoning; Zhou, Mingyuan Journal of the American Statistical Association, Vol. 113, Issue 521 https://doi.org/10.1080/01621459.2017.1328358	journal	January 2018
Integrating structured biological data by Kernel Maximum Mean Discrepancy Borgwardt, K. M.; Gretton, A.; Rasch, M. J. Bioinformatics, Vol. 22, Issue 14 https://doi.org/10.1093/bioinformatics/btl242	journal	July 2006
edgeR: a Bioconductor package for differential expression analysis of digital gene expression data Robinson, M. D.; McCarthy, D. J.; Smyth, G. K. Bioinformatics, Vol. 26, Issue 1 https://doi.org/10.1093/bioinformatics/btp616	journal	November 2009
The IntAct molecular interaction database in 2010 Aranda, B.; Achuthan, P.; Alam-Faruque, Y. Nucleic Acids Research, Vol. 38, Issue suppl_1 https://doi.org/10.1093/nar/gkp878	journal	October 2009
The BioGRID Interaction Database: 2011 update Stark, C.; Breitkreutz, B. -J.; Chatr-aryamontri, A. Nucleic Acids Research, Vol. 39, Issue Database https://doi.org/10.1093/nar/gkq1116	journal	November 2010
Taking the Human Out of the Loop: A Review of Bayesian Optimization Shahriari, Bobak; Swersky, Kevin; Wang, Ziyu Proceedings of the IEEE, Vol. 104, Issue 1 https://doi.org/10.1109/JPROC.2015.2494218	journal	January 2016
Visual Domain Adaptation: A survey of recent advances Patel, Vishal M.; Gopalan, Raghuraman; Li, Ruonan IEEE Signal Processing Magazine, Vol. 32, Issue 3 https://doi.org/10.1109/MSP.2014.2347059	journal	May 2015
Constructing Pathway-Based Priors within a Gaussian Mixture Model for Bayesian Regression and Classification Boluki, Shahin; Esfahani, Mohammad Shahrokh; Qian, Xiaoning IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 16, Issue 2 https://doi.org/10.1109/TCBB.2017.2778715	journal	March 2019
A Survey on Transfer Learning Pan, Sinno Jialin; Yang, Qiang IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10 https://doi.org/10.1109/TKDE.2009.191	journal	October 2010
Domain Adaptation via Transfer Component Analysis Pan, Sinno Jialin; Tsang, Ivor W.; Kwok, James T. IEEE Transactions on Neural Networks, Vol. 22, Issue 2 https://doi.org/10.1109/TNN.2010.2091281	journal	February 2011
Negative Binomial Process Count and Mixture Modeling Zhou, Mingyuan; Carin, Lawrence IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 37, Issue 2 https://doi.org/10.1109/TPAMI.2013.211	journal	February 2015
Optimal Bayesian Transfer Learning Karbalayghareh, Alireza; Qian, Xiaoning; Dougherty, Edward R. IEEE Transactions on Signal Processing, Vol. 66, Issue 14 https://doi.org/10.1109/TSP.2018.2839583	journal	July 2018
Uncovering disease-disease relationships through the incomplete interactome Menche, J.; Sharma, A.; Kitsak, M. Science, Vol. 347, Issue 6224 https://doi.org/10.1126/science.1257601	journal	February 2015
Incorporating biological prior knowledge for Bayesian learning via maximal knowledge-driven information priors Boluki, Shahin; Esfahani, Mohammad Shahrokh; Qian, Xiaoning BMC Bioinformatics, Vol. 18, Issue S14 https://doi.org/10.1186/s12859-017-1893-4	journal	December 2017
Application of transfer learning for cancer drug sensitivity prediction Dhruba, Saugato Rahman; Rahman, Raziur; Matlock, Kevin BMC Bioinformatics, Vol. 19, Issue S17 https://doi.org/10.1186/s12859-018-2465-y	journal	December 2018
Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2 Love, Michael I.; Huber, Wolfgang; Anders, Simon Genome Biology, Vol. 15, Issue 12 https://doi.org/10.1186/s13059-014-0550-8	journal	December 2014
Modules, networks and systems medicine for understanding disease and aiding diagnosis Gustafsson, Mika; Nestor, Colm E.; Zhang, Huan Genome Medicine, Vol. 6, Issue 10 https://doi.org/10.1186/s13073-014-0082-6	journal	October 2014
A survey of transfer learning Weiss, Karl; Khoshgoftaar, Taghi M.; Wang, DingDing Journal of Big Data, Vol. 3, Issue 1 https://doi.org/10.1186/s40537-016-0043-6	journal	May 2016
Bayesian joint modeling of multiple gene networks and diverse genomic data to identify target genes of a transcription factor Wei, Peng; Pan, Wei The Annals of Applied Statistics, Vol. 6, Issue 1 https://doi.org/10.1214/11-AOAS502	journal	March 2012
Nonparametric Bayesian Negative Binomial Factor Analysis Zhou, Mingyuan Bayesian Analysis, Vol. 13, Issue 4 https://doi.org/10.1214/17-BA1070	journal	December 2018

Similar Records

ACTINN: automated identification of cell types in single cell RNA sequencing

Journal Article · 2019 · Bioinformatics · OSTI ID:1799618

ACTINN: automated identification of cell types in single cell RNA sequencing

Journal Article · 2019 · Bioinformatics · OSTI ID:1922564

Related Subjects

Biochemistry & Molecular Biology
Biotechnology & Applied Microbiology
Computer Science
Mathematical & Computational Biology
Mathematics

Optimal Bayesian supervised domain adaptation for RNA sequencing data

Citation Formats

References (28)

Similar Records

Related Subjects