Machine learning classifier approaches for predicting response to RTK-type-III inhibitors demonstrate high accuracy using transcriptomic signatures and ex vivo data

Mauricio H Ferrato; Adam G Marsh; Karl R Franke; Benjamin J Huang; E Anders Kolb; Deborah DeRyckere; Douglas K Grahm; Sunita Chandrasekaran; Erin L Crowgey

doi:10.1093/bioadv/vbad034

Machine learning classifier approaches for predicting response to RTK-type-III inhibitors demonstrate high accuracy using transcriptomic signatures and ex vivo data

Bioinform Adv. 2023 Mar 22;3(1):vbad034. doi: 10.1093/bioadv/vbad034. eCollection 2023.

Authors

Mauricio H Ferrato¹, Adam G Marsh¹, Karl R Franke², Benjamin J Huang^{3

4}, E Anders Kolb², Deborah DeRyckere⁵, Douglas K Grahm⁵, Sunita Chandrasekaran¹, Erin L Crowgey²

Affiliations

¹ University of Delaware, Newark, DE 19716, USA.
² Nemours Children Health System, Wilmington, DE 19803, USA.
³ Department of Pediatrics, University of California San Francisco, San Francisco, CA 94143, USA.
⁴ Helen Diller Family Comprehensive Cancer Center, University of California San Francisco, San Francisco, CA 94143, USA.
⁵ Department of Pediatrics, Emory University School of Medicine, Atlanta, GA 30322, USA.

Abstract

Motivation: The application of machine learning (ML) techniques in the medical field has demonstrated both successes and challenges in the precision medicine era. The ability to accurately classify a subject as a potential responder versus a nonresponder to a given therapy is still an active area of research pushing the field to create new approaches for applying machine-learning techniques. In this study, we leveraged publicly available data through the BeatAML initiative. Specifically, we used gene count data, generated via RNA-seq, from 451 individuals matched with ex vivo data generated from treatment with RTK-type-III inhibitors. Three feature selection techniques were tested, principal component analysis, Shapley Additive Explanation (SHAP) technique and differential gene expression analysis, with three different classifiers, XGBoost, LightGBM and random forest (RF). Sensitivity versus specificity was analyzed using the area under the curve (AUC)-receiver operating curves (ROCs) for every model developed.

Results: Our work demonstrated that feature selection technique, rather than the classifier, had the greatest impact on model performance. The SHAP technique outperformed the other feature selection techniques and was able to with high accuracy predict outcome response, with the highest performing model: Foretinib with 89% AUC using the SHAP technique and RF classifier. Our ML pipelines demonstrate that at the time of diagnosis, a transcriptomics signature exists that can potentially predict response to treatment, demonstrating the potential of using ML applications in precision medicine efforts.

Availability and implementation: https://github.com/UD-CRPL/RCDML.

Supplementary information: Supplementary data are available at Bioinformatics Advances online.