Efficient Computational Genomics and Proteomics Sequence Analysis Platform

With the advancement of next generation sequencing (NGS) approaches, the exponential growth of biological sequence data has opened new doors to understand inter and intracellular phenomenons within the life cycle by utilizing the power of artificial intelligence. Biological sequence data contains diverse information about physiological, biochemical, and pathological processes. Thorough analyses of biological sequence data can provide valuable insights into the functional paradigm of different living organisms and can help to unravel the core functionalities of biomolecules (nucleic acids and proteins), RNA expression levels, emergence, and progression of various diseases, and optimization of therapeutics. Such analyses through wet lab based experimentation is error-prone, expensive, time, skill, and labor-intensive which hinders the process of analyses among different species on a large scale. The world is looking to utilize the potential of artificial intelligence to empower the process of biological sequence analyses by facilitating low-cost, accurate, and fast analyses which can help to understand the hidden potential of biological sequence data.

Smart Data & Knowledge Services research group has utilized its several years of artificial intelligence expertise to develop practical applications for biological sequence analyses. To support the research community and provide a biological sequence analysis computational platform, the web-based platform "ECGPlat" ("Efficient Computational Genomics and Proteomics Sequence Analysis Platform") has now been launched. The platform provides computational tools that can be used for numerous tasks in the field of genomics (i.e. the field of DNA and RNA sequence analysis) as well as proteomics (i.e. the field of protein sequence analysis). For example, in the field of DNA sequence analyses, the "Histone-Net" tool can assist in the analysis of histones as the "packaging and control element" of DNA. "Histone-Net" aims to predict the status of a gene ("active" or "inactive"), but also to predict so-called "histone modifications". Both play a substantial role in a variety of biological processes and can be used in the long term, i.e, diagnosis and treatment of cancer/tumor. Another tool for DNA analyses with a similar field of the application addresses the so-called DNA methylation. In the field of RNA analysis, the platform provides tools for the identification of specific RNA in specific cell components as well as for the prediction of interactions between different RNA species. Finally, for protein sequence analysis, there are algorithms for predicting integrations between proteins or proteins and viruses which are crucial for designing antiviral strategies.