Platelet-Based Liquid Biopsies through the Lens of Machine Learning

SIMPLE SUMMARY: Liquid biopsies are a non-invasive way to diagnose and monitor cancer using blood tests. Machine learning can help understand the genetic data from these tests, but it is challenging to validate clinical applications. In our study, we first compiled a large-scale dataset for cancer classification. Then, we extracted relevant features from the data and performed a binary classification, with the prediction outcome of either a sample collected from a cancer patient or a sample collected from an asymptomatic control. We used different convolutional neural networks (CNNs) and boosting methods to evaluate the classification performance. We have obtained an impressive result of 0.96 area under the curve. Finally, we tested the robustness of the models using test data from novel hospitals and performed data inspection to find the most relevant features for the prediction. Our work proves the great potential of using liquid biopsies for cancer patient classification. ABSTRACT: Liquid biopsies offer minimally invasive diagnosis and monitoring of cancer disease. This biosource is often analyzed using sequencing, which generates highly complex data that can be used using machine learning tools. Nevertheless, validating the clinical applications of such methods is challenging. It requires: (a) using data from many patients; (b) verifying potential bias concerning sample collection; and (c) adding interpretability to the model. In this work, we have used RNA sequencing data of tumor-educated platelets (TEPs) and performed a binary classification (cancer vs. no-cancer). First, we compiled a large-scale dataset with more than a thousand donors. Further, we used different convolutional neural networks (CNNs) and boosting methods to evaluate the classifier performance. We have obtained an impressive result of 0.96 area under the curve. We then identified different clusters of splice variants using expert knowledge from the Kyoto Encyclopedia of Genes and Genomes (KEGG). Employing boosting algorithms, we identified the features with the highest predictive power. Finally, we tested the robustness of the models using test data from novel hospitals. Notably, we did not observe any decrease in model performance. Our work proves the great potential of using TEP data for cancer patient classification and opens the avenue for profound cancer diagnostics.