A novel machine learning algorithm selects proteome signature to specifically identify cancer exosomes

Abstract

Non-invasive early cancer diagnosis remains challenging due to the low sensitivity and specificity of current diagnostic approaches. Exosomes are membrane-bound nanovesicles secreted by all cells that contain DNA, RNA, and proteins that are representative of the parent cells. This property, along with the abundance of exosomes in biological fluids makes them compelling candidates as biomarkers. However, a rapid and flexible exosome-based diagnostic method to distinguish human cancers across cancer types in diverse biological fluids is yet to be defined. Here, we describe a novel machine learning-based computational method to distinguish cancers using a panel of proteins associated with exosomes. Employing datasets of exosome proteins from human cell lines, tissue, plasma, serum and urine samples from a variety of cancers, we identify Clathrin Heavy Chain (CLTC), Ezrin, (EZR), Talin-1 (TLN1), Adenylyl cyclase-associated protein 1 (CAP1) and Moesin (MSN) as highly abundant universal biomarkers for exosomes and define three panels of pan-cancer exosome proteins that distinguish cancer exosomes from other exosomes and aid in classifying cancer subtypes employing random forest models. All the models using proteins from plasma, serum, or urine-derived exosomes yield AUROC scores higher than 0.91 and demonstrate superior performance compared to Support Vector Machine, K Nearest Neighbor Classifier and Gaussian Naive Bayes. This study provides a reliable protein biomarker signature associated with cancer exosomes with scalable machine learning capability for a sensitive and specific non-invasive method of cancer diagnosis.

Exosomes: a promising avenue for cancer diagnosis beyond treatment

“…Machine learning algorithms are adept at identifying patterns in large datasets, making them ideal for interpreting exosome profiles ( Li J et al, 2023 ). Li et al present a machine learning approach for non-invasive cancer diagnosis using exosome protein markers, achieving high accuracy in identifying cancer types with an advanced biomarker signature and sophisticated data models, marking a significant leap in early cancer detection methodologies ( Li B et al, 2023 ). Wang et al employed the Least Absolute Shrinkage and Selection Operator (LASSO) regression algorithm to construct a prognostic model based on differentially expressed genes (DEGs).…”

A review on trends in development and translation of omics signatures in cancer

“…Since then different classifier training algorithms have been used for identification of diagnostic protein signatures while no single type of technique consistently outperformed the others. It is common that multiple methods were used in a single study and the investigators eventually selected the best-performing model [206] , [207] .…”

Application of a Machine Learning-Based Classification Approach for Developing Host Protein Diagnostic Models for Infectious Disease

“…Machine learning (ML) is a subfield of artificial intelligence that has rapidly gained traction in recent years in several areas, including biology [ 15 , 16 , 17 ]. ML approaches have recently been utilized to untangle complex, interdependent features to elucidate new biomedical insights, particularly in the cancer and infectious disease fields [ 18 , 19 , 20 , 21 ]. The sophisticated algorithms employed have demonstrated the capability to discern subtle differences and detect correlations that might elude traditional statistical methods or human analysis; this is especially true with multivariate datasets.…”