Improving platelet-RNA-based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classification.

Autor: Jopek MA; Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdańsk and the Medical University of Gdańsk, Poland.; Centre of Biostatistics and Bioinformatics, Medical University of Gdańsk, Poland., Pastuszak K; Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdańsk and the Medical University of Gdańsk, Poland.; Centre of Biostatistics and Bioinformatics, Medical University of Gdańsk, Poland.; Department of Algorithms and Systems Modelling, Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Poland., Sieczczyński M; Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdańsk and the Medical University of Gdańsk, Poland.; Centre of Biostatistics and Bioinformatics, Medical University of Gdańsk, Poland., Cygert S; Department of Multimedia Systems, Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Poland.; Ideas, NCBR, Warsaw, Poland., Żaczek AJ; Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdańsk and the Medical University of Gdańsk, Poland., Rondina MT; Molecular Medicine Program, University of Utah, Salt Lake City, UT, USA.; George E. Wahlen Veterans Affairs Medical Center Department of Internal Medicine and the Geriatric Research Education and Clinical Center (GRECC), Salt Lake City, UT, USA.; Department of Pathology, University of Utah, Salt Lake City, UT, USA.; Division of General Internal Medicine, Department of Internal Medicine, University of Utah, Salt Lake City, UT, USA., Supernat A; Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdańsk and the Medical University of Gdańsk, Poland.; Centre of Biostatistics and Bioinformatics, Medical University of Gdańsk, Poland.
Jazyk: angličtina
Zdroj: Molecular oncology [Mol Oncol] 2024 Nov; Vol. 18 (11), pp. 2743-2754. Date of Electronic Publication: 2024 Jun 17.
DOI: 10.1002/1878-0261.13689
Abstrakt: Liquid biopsy demonstrates excellent potential in patient management by providing a minimally invasive and cost-effective approach to detecting and monitoring cancer, even at its early stages. Due to the complexity of liquid biopsy data, machine-learning techniques are increasingly gaining attention in sample analysis, especially for multidimensional data such as RNA expression profiles. Yet, there is no agreement in the community on which methods are the most effective or how to process the data. To circumvent this, we performed a large-scale study using various machine-learning techniques. First, we took a closer look at existing datasets and filtered out some patients to assert data collection quality. The final data collection included platelet RNA samples acquired from 1397 cancer patients (17 types of cancer) and 354 asymptomatic, presumed healthy, donors. Then, we assessed an array of different machine-learning models and techniques (e.g., feature selection of RNA transcripts) in pan-cancer detection and multiclass classification. Our results show that simple logistic regression performs the best, reaching a 68% cancer detection rate at a 99% specificity level, and multiclass classification accuracy of 79.38% when distinguishing between five cancer types. In summary, by revisiting classical machine-learning models, we have exceeded the previously used method by 5% and 9.65% in cancer detection and multiclass classification, respectively. To ease further research, we open-source our code and data processing pipelines (https://gitlab.com/jopekmaksym/improving-platelet-rna-based-diagnostics), which we hope will serve the community as a strong baseline.
(© 2024 The Author(s). Molecular Oncology published by John Wiley & Sons Ltd on behalf of Federation of European Biochemical Societies.)
Databáze: MEDLINE
Externí odkaz: