Explainable machine learning identifies features and thresholds predictive of immunotherapy response

Scientific Reports, vol. 16

Abstract

ABSTRACT Background Immunotherapy has improved patient survival for multiple cancer types, including melanoma. While a variety of molecular features have been linked to response to immune checkpoint inhibitors (ICI) treatment, clinically established biomarkers, such as tumour mutation burden (TMB) and PD-L1 expression, have shown limitations in accurately categorising responders versus non-responders. Due to the complex nature of ICI response, which includes cancer intrinsic and extrinsic features within the tumour microenvironment (TME), using a single biomarker to predict response is insufficient, necessitating the need to identify accurate clinical and multi-omic molecular predictors. Methods We integrate clinical, DNA and RNA sequencing data from four datasets, comprising 138 melanoma patients treated with ICI, to develop machine learning models for predicting ICI response. The performance of each model was evaluated using an independent dataset of patients with cutaneous melanoma (n=53). Interactions between trained models and features were rationalised using the explainability method SHAP. Results The most optimal model was the multi-omic random forest model, with AUC-ROC of 0.78 when predicting response in the independent test dataset. Using SHAP, we predicted thresholds for mutational signatures, neoantigen load, immune cell-type abundance and immune receptor LAG3 expression. The relationship between these influential features and their SHAP scores revealed numerical thresholds constituting good and poor patient response. Conclusions This approach highlights patient response to ICI is influenced by both cancer intrinsic and extrinsic features, as well as identifies candidate biomarkers that could inform the use of ICI and potentially assist in the selection of combination therapy in melanoma treatment.

Authors 13

1. Khoa Anh Tran

   Queensland University of Technology · QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia. khoa.tran@qimrb.edu.au

   School of Biomedical Sciences, Queensland University of Technology (QUT), Brisbane, Australia. khoa.tran@qimrb.edu.au

2. Venkateswar Addala

   QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

3. Lambros T. Koufariotis

   QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

4. Jia Zhang

   QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

5. Scott Wood

   QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

6. Conrad Leonard

   QIMR Berghofer Medical Research Institute

   Affiliation as printed

   Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

7. Lotte L. Hoeijmakers

   The Netherlands Cancer Institute

   Affiliation as printed

   Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands

8. Christian U. Blank Aachen Department of Medical Oncology

   Leiden University Medical Center · The Netherlands Cancer Institute

   Affiliation as printed

   Department of Medical Oncology, Leiden University Medical Center, Leiden, The Netherlands

   Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands

9. Mireia Crispin‐Ortuzar

   University of Cambridge · Cancer Research UK Cambridge Center

   Affiliation as printed

   Cancer Research UK Cambridge Centre, University of Cambridge, Cambridge, UK

   Department of Oncology, University of Cambridge, Cambridge, UK

10. Elizabeth D. Williams

    Queensland University of Technology

    Affiliation as printed

    Australian Prostate Cancer Research Centre - Queensland (APCRC-Q) and Queensland Bladder Cancer Initiative (QBCI), Brisbane, Australia

    Centre for Genomics and Personalised Health, Queensland University of Technology (QUT), Brisbane, QLD, Australia

    School of Biomedical Sciences, Queensland University of Technology (QUT), Brisbane, Australia

11. Olga Kondrashova

    Queensland University of Technology · QIMR Berghofer Medical Research Institute

    Affiliation as printed

    Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

    School of Biomedical Sciences, Queensland University of Technology (QUT), Brisbane, Australia

12. John V. Pearson

    QIMR Berghofer Medical Research Institute

    Affiliation as printed

    Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia

13. Nicola Waddell

    Queensland University of Technology · QIMR Berghofer Medical Research Institute

    Affiliation as printed

    Cancer Program, QIMR Berghofer Medical Research Institute, 300 Herston Road, Brisbane, Australia. nic.waddell@qimrberghofer.edu.au

    School of Biomedical Sciences, Queensland University of Technology (QUT), Brisbane, Australia. nic.waddell@qimrberghofer.edu.au