Hepatocellular carcinoma (HCC) is the fifth most common cancer worldwide. In this study, our objective was to identify differentially regulated proteins in HCC through a quantitative proteomic approach using iTRAQ. More than 600 proteins were quantitated of which 59 proteins were overexpressed and 92 proteins were underexpressed in HCC as compared to adjacent normal tissue. Several differentially expressed proteins were not implicated previously in HCC. A subset of these proteins (six each from upregulated and downregulated groups) was further validated using immunoblotting and immunohistochemical labeling. Some of the overexpressed proteins with no previous description in the context of HCC include fibroleukin, interferon induced 56 kDa protein, milk fat globule-EGF factor 8, and myeloidassociated differentiation marker. Interestingly, all the enzymes of urea metabolic pathway were dramatically downregulated. Immunohistochemical labeling confirmed differential expression of fibroleukin, myeloid associated differentiation marker and ornithine carbamoyl transferase in majority of HCC samples analyzed. Our results demonstrate quantitative proteomics as a robust discovery tool for the identification of differentially regulated proteins in cancers.

Summary Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

No abstract