Proteomic Profiling and Artificial Intelligence for Hepatocellular Carcinoma Translational Medicine

Abstract

Hepatocellular carcinoma (HCC) is the most common primary cancer of the liver with high morbidity and mortality rates worldwide. Since 1963, when alpha-fetoprotein (AFP) was discovered as a first HCC serum biomarker, several other protein biomarkers have been identified and introduced into clinical practice. However, insufficient specificity and sensitivity of these biomarkers dictate the necessity of novel biomarker discovery. Remarkable advancements in integrated multiomics technologies for the identification of gene expression and protein or metabolite distribution patterns can facilitate rising to this challenge. Current multiomics technologies lead to the accumulation of a huge amount of data, which requires clustering and finding correlations between various datasets and developing predictive models for data filtering, pre-processing, and reducing dimensionality. Artificial intelligence (AI) technologies have an enormous potential to overcome accelerated data growth, complexity, and heterogeneity within and across data sources. Our review focuses on the recent progress in integrative proteomic profiling strategies and their usage in combination with machine learning and deep learning technologies for the discovery of novel biomarker candidates for HCC early diagnosis and prognosis. We discuss conventional and promising proteomic biomarkers of HCC such as AFP, lens culinaris agglutinin (LCA)-reactive L3 glycoform of AFP (AFP-L3), des-gamma-carboxyprothrombin (DCP), osteopontin (OPN), glypican-3 (GPC3), dickkopf-1 (DKK1), midkine (MDK), and squamous cell carcinoma antigen (SCCA) and highlight their functional significance including the involvement in cell signaling such as Wnt/β-catenin, PI3K/Akt, integrin αvβ3/NF-κB/HIF-1α, JAK/STAT3 and MAPK/ERK-mediated pathways dysregulated in HCC. We show that currently available computational platforms for big data analysis and AI technologies can both enhance proteomic profiling and improve imaging techniques to enhance the translational application of proteomics data into precision medicine.

Macrotrabecular-Massive Hepatocellular Carcinoma: Light and Shadow in Current Knowledge

“…The artificial intelligence (AI), computer-based algorithms for data analysis and by the construction of predictive models based on the usage of various imaging techniques, especially in combination with HCC molecular biomarkers, recently used for improving image recognition and representation in HCC diagnosis and prognosis. 55 For example, in their most recent article that represents a proof-of-principle study, Zeng et al 56 propose a novel approach using AI to predict activation of inflammatory gene signatures associated with increased sensitivity to immunotherapy, for improving personalized allocation of therapy. In this trend, the combination of artificial intelligence and automated computerized image analysis is likely to provide a new tool for MTM-HCC diagnosis and for characterisation of biomarkers to help in therapy work-up in the near future.…”

Proteomics, Personalized Medicine and Cancer

“…Integration of proteomics with artificial intelligence methods like machine and deep learning clearly represents the future trend for proteomics research and personalized/precision medicine and a number of platforms are being developed. Recent examples include applications for HCC [ 228 ], renal cell carcinoma [ 229 ] and lung cancer [ 230 ]. Researchers from the Technical University of Munich successfully used proteomic data to train a neural network, termed Prosit, facilitating the rapid and accurate error free mass analysis of proteins [ 231 ].…”

Smart Material‐Integrated Systems for Isolation and Profiling of Rare Cancer Cells and Emboli

“…Today, the healthcare system has benefited greatly from a number of advantages of artificial intelligence (AI)-based strategies, such as the chance of storing, comparing, and classifying enormous data via high-speed computers, and all these fashions have been precisely implemented into the fields of drug delivery, medicine, and cancer research (treatment, imaging, and cell sorting). [178][179][180][181][182][183] In particular, machine learning (ML)-an application of AI-enables automatically learning of the trained datasets without any internal programming. The attribution of recognizing and analyzing patterns employed in biomedical and clinical areas creates an enormous level of heterogeneous data.…”