Digging for Meaning in the Big Data of Mass Spectrometry-based Proteomics

Mass spectrometry is an indispensable method in proteomic studies, including protein identification, peptide sequencing, protein-protein interactions, post-translational modifications, etc. A wide breadth of knowledge about how a cell responds to different stimuli producing diverse protein profiles can provide detailed information regarding signal transduction and metabolic pathways, which can help to generate more specific treatments, reducing disease risks. The main challenge of studying the proteome data is related to its intrinsic complexity, in terms of data quality, format and noise processing. When compared with the genome, the proteins of a singular entity present more factors to be analyzed since one gene can encode more than one protein and these can present post-translational modifications, a wide range of concentrations and interaction networks. Proteomics is thus a powerful discipline to supplement genomics, producing a deeper understanding of cell and molecular biology.
In the last decade, Artificial intelligence (AI) has been developing rapidly in terms of clinical applications in a vast number of biomedical areas, including biomarkers detection, disease diagnostics, and drug discovery. You can keep track of new clinical applications and the tremendous potential of AI in proteome data, and to provide researchers in related fields with inspiration through this talk. The application of AI in genomics and proteomics is still in a very early stage; therefore, new progress and breakthroughs will continue to push the frontier and widen the scope of AI applications in biomedicine in the near future.