Cross-platform Normalization Enables Machine Learning Model Training on Microarray and RNA-seq Data Simultaneously

Overview

Journal Commun Biol

Specialty Biology

Date 2023 Feb 25

PMID 36841852

Authors

Steven M Foltz

Casey S Greene

Jaclyn N Taroni

Affiliations

Soon will be listed here.

Abstract

Large compendia of gene expression data have proven valuable for the discovery of novel biological relationships. Historically, most available RNA assays were run on microarray, while RNA-seq is now the platform of choice for many new experiments. The data structure and distributions between the platforms differ, making it challenging to combine them directly. Here we perform supervised and unsupervised machine learning evaluations to assess which existing normalization methods are best suited for combining microarray and RNA-seq data. We find that quantile and Training Distribution Matching normalization allow for supervised and unsupervised model training on microarray and RNA-seq data simultaneously. Nonparanormal normalization and z-scores are also appropriate for some applications, including pathway analysis with Pathway-Level Information Extractor (PLIER). We demonstrate that it is possible to perform effective cross-platform normalization using existing methods to combine microarray and RNA-seq data for machine learning applications.

Citing Articles

Normalization and selecting non-differentially expressed genes improve machine learning modelling of cross-platform transcriptomic data.

Deng F, Feng C, Gao N, Zhang L ArXiv. 2025; .

PMID: 39975431 PMC: 11838701.

Robust Cluster Prediction Across Data Types Validates Association of Sex and Therapy Response in GBM.

Gibbs D, Cioffi G, Aguilar B, Waite K, Pan E, Mandel J Cancers (Basel). 2025; 17(3).

PMID: 39941811 PMC: 11815886. DOI: 10.3390/cancers17030445.

Predicting the Progression from Asymptomatic to Symptomatic Multiple Myeloma and Stage Classification Using Gene Expression Data.

Karathanasis N, Spyrou G Cancers (Basel). 2025; 17(2).

PMID: 39858113 PMC: 11764453. DOI: 10.3390/cancers17020332.

Transcriptomic analysis of human cartilage identified potential therapeutic targets for hip osteoarthritis.

Huang J, Liu M, Furey A, Rahman P, Zhai G Hum Mol Genet. 2025; 34(5):444-453.

PMID: 39777501 PMC: 11834983. DOI: 10.1093/hmg/ddae200.

Investigating heart rate variability measures during pregnancy as predictors of postpartum depression and anxiety: an exploratory study.

Eriksson A, Kimmel M, Furmark T, Wikman A, Grueschow M, Skalkidou A Transl Psychiatry. 2024; 14(1):203.

PMID: 38744808 PMC: 11094065. DOI: 10.1038/s41398-024-02909-9.

References

Argelaguet R, Cuomo A, Stegle O, Marioni J . Computational principles and challenges in single-cell data integration. Nat Biotechnol. 2021; 39(10):1202-1215. DOI: 10.1038/s41587-021-00895-7. View

Foltz S, Greene C, Taroni J . Cross-platform normalization enables machine learning model training on microarray and RNA-seq data simultaneously. Commun Biol. 2023; 6(1):222. PMC: 9968332. DOI: 10.1038/s42003-023-04588-6. View

Athar A, Fullgrabe A, George N, Iqbal H, Huerta L, Ali A . ArrayExpress update - from bulk to single-cell expression data. Nucleic Acids Res. 2018; 47(D1):D711-D715. PMC: 6323929. DOI: 10.1093/nar/gky964. View

Crawford J, Christensen B, Chikina M, Greene C . Widespread redundancy in -omics profiles of cancer mutation states. Genome Biol. 2022; 23(1):137. PMC: 9238138. DOI: 10.1186/s13059-022-02705-y. View

Hao Y, Hao S, Andersen-Nissen E, Mauck 3rd W, Zheng S, Butler A . Integrated analysis of multimodal single-cell data. Cell. 2021; 184(13):3573-3587.e29. PMC: 8238499. DOI: 10.1016/j.cell.2021.04.048. View

Barrett T, Wilhite S, Ledoux P, Evangelista C, Kim I, Tomashevsky M . NCBI GEO: archive for functional genomics data sets--update. Nucleic Acids Res. 2012; 41(Database issue):D991-5. PMC: 3531084. DOI: 10.1093/nar/gks1193. View

Law C, Chen Y, Shi W, Smyth G . voom: Precision weights unlock linear model analysis tools for RNA-seq read counts. Genome Biol. 2014; 15(2):R29. PMC: 4053721. DOI: 10.1186/gb-2014-15-2-r29. View

Zhao T, Liu H, Roeder K, Lafferty J, Wasserman L . The huge Package for High-dimensional Undirected Graph Estimation in R. J Mach Learn Res. 2016; 13:1059-1062. PMC: 4729207. View

Heinaniemi M, Nykter M, Kramer R, Wienecke-Baldacchino A, Sinkkonen L, Zhou J . Gene-pair expression signatures reveal lineage control. Nat Methods. 2013; 10(6):577-83. PMC: 4131748. DOI: 10.1038/nmeth.2445. View

10.

Stuart T, Butler A, Hoffman P, Hafemeister C, Papalexi E, Mauck 3rd W . Comprehensive Integration of Single-Cell Data. Cell. 2019; 177(7):1888-1902.e21. PMC: 6687398. DOI: 10.1016/j.cell.2019.05.031. View

11.

Mancuso C, Canfield J, Singla D, Krishnan A . A flexible, interpretable, and accurate approach for imputing the expression of unmeasured genes. Nucleic Acids Res. 2020; 48(21):e125. PMC: 7708069. DOI: 10.1093/nar/gkaa881. View

12.

Luecken M, Buttner M, Chaichoompu K, Danese A, Interlandi M, Mueller M . Benchmarking atlas-level data integration in single-cell genomics. Nat Methods. 2021; 19(1):41-50. PMC: 8748196. DOI: 10.1038/s41592-021-01336-8. View

13.

Ellrott K, Bailey M, Saksena G, Covington K, Kandoth C, Stewart C . Scalable Open Science Approach for Mutation Calling of Tumor Exomes Using Multiple Genomic Pipelines. Cell Syst. 2018; 6(3):271-281.e7. PMC: 6075717. DOI: 10.1016/j.cels.2018.03.002. View

14.

Greene C, Krishnan A, Wong A, Ricciotti E, Zelaya R, Himmelstein D . Understanding multicellular function and disease with human tissue-specific networks. Nat Genet. 2015; 47(6):569-76. PMC: 4828725. DOI: 10.1038/ng.3259. View

15.

Chen Y, Li Y, Narayan R, Subramanian A, Xie X . Gene expression inference with deep learning. Bioinformatics. 2016; 32(12):1832-9. PMC: 4908320. DOI: 10.1093/bioinformatics/btw074. View

16.

Friedman J, Hastie T, Tibshirani R . Regularization Paths for Generalized Linear Models via Coordinate Descent. J Stat Softw. 2010; 33(1):1-22. PMC: 2929880. View

17.

Grossman R, Heath A, Ferretti V, Varmus H, Lowy D, Kibbe W . Toward a Shared Vision for Cancer Genomic Data. N Engl J Med. 2016; 375(12):1109-12. PMC: 6309165. DOI: 10.1056/NEJMp1607591. View

18.

Johnson W, Li C, Rabinovic A . Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2006; 8(1):118-27. DOI: 10.1093/biostatistics/kxj037. View

19.

Way G, Zietz M, Rubinetti V, Himmelstein D, Greene C . Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations. Genome Biol. 2020; 21(1):109. PMC: 7212571. DOI: 10.1186/s13059-020-02021-3. View

20.

Piccolo S, Sun Y, Campbell J, Lenburg M, Bild A, Johnson W . A single-sample microarray normalization method to facilitate personalized-medicine workflows. Genomics. 2012; 100(6):337-44. PMC: 3508193. DOI: 10.1016/j.ygeno.2012.08.003. View