Cross-Platform Omics Prediction procedure: a statistical machine learning framework for wider implementation of precision medicine

NPJ Digit Med. 2022 Jul 4;5(1):85. doi: 10.1038/s41746-022-00618-5.

Authors

Kevin Y X Wang^{1

2}, Gulietta M Pupo^{3

4}, Varsha Tembe^{3

4}, Ellis Patrick^{1

2

3

5}, Dario Strbenac^{1

2}, Sarah-Jane Schramm^{3

4}, John F Thompson^{4

6

7}, Richard A Scolyer^{1

4

7

8}, Samuel Muller^{2

9}, Garth Tarr^{2

5}, Graham J Mann^{10

11

12}, Jean Y H Yang^{13

14

15}

Affiliations

¹ Charles Perkins Centre, The University of Sydney, Sydney, NSW, 2006, Australia.
² School of Mathematics and Statistics, The University of Sydney, Sydney, NSW, 2006, Australia.
³ The Westmead Institute for Medical Research, The University of Sydney, Sydney, NSW, 2006, Australia.
⁴ Melanoma Institute Australia, The University of Sydney, North Sydney, NSW, 2006, Australia.
⁵ Laboratory of Data Discovery for Health Limited (D²4H) Science Park, Hong Kong, SAR, China.
⁶ Department of Melanoma and Surgical Oncology, Royal Prince Alfred Hospital, Sydney, NSW, 2050, Australia.
⁷ Faculty of Medicine and Health, The University of Sydney, Sydney, NSW, 2006, Australia.
⁸ Tissue Pathology and Diagnostic Oncology, Royal Prince Alfred Hospital and NSW Health Pathology, Sydney, NSW, 2050, Australia.
⁹ School of Mathematical and Physical Sciences, Macquarie University, Sydney, NSW, 2109, Australia.
¹⁰ The Westmead Institute for Medical Research, The University of Sydney, Sydney, NSW, 2006, Australia. graham.mann@anu.edu.au.
¹¹ Melanoma Institute Australia, The University of Sydney, North Sydney, NSW, 2006, Australia. graham.mann@anu.edu.au.
¹² John Curtin School of Medical Research, Australian National University, Canberra, ACT, 2601, Australia. graham.mann@anu.edu.au.
¹³ Charles Perkins Centre, The University of Sydney, Sydney, NSW, 2006, Australia. jean.yang@sydney.edu.au.
¹⁴ School of Mathematics and Statistics, The University of Sydney, Sydney, NSW, 2006, Australia. jean.yang@sydney.edu.au.
¹⁵ Laboratory of Data Discovery for Health Limited (D²4H) Science Park, Hong Kong, SAR, China. jean.yang@sydney.edu.au.

Abstract

In this modern era of precision medicine, molecular signatures identified from advanced omics technologies hold great promise to better guide clinical decisions. However, current approaches are often location-specific due to the inherent differences between platforms and across multiple centres, thus limiting the transferability of molecular signatures. We present Cross-Platform Omics Prediction (CPOP), a penalised regression model that can use omics data to predict patient outcomes in a platform-independent manner and across time and experiments. CPOP improves on the traditional prediction framework of using gene-based features by selecting ratio-based features with similar estimated effect sizes. These components gave CPOP the ability to have a stable performance across datasets of similar biology, minimising the effect of technical noise often generated by omics platforms. We present a comprehensive evaluation using melanoma transcriptomics data to demonstrate its potential to be used as a critical part of a clinical screening framework for precision medicine. Additional assessment of generalisation was demonstrated with ovarian cancer and inflammatory bowel disease studies.