A Computational Platform for Gene Expression Analysis

Abstract

The advent of next generation sequencing methods has revolutionized the field of molecular biology in the past few years. Nowadays, we are able to produce enormous amounts of biological information, both quickly and at low cost. As such, tools have to evolve accordingly, in order to cope with such large volumes of information. In this report we discuss the usage of computer tools capable of conducting gene expression profiling based on information obtained through RNA Sequencing techniques, applied to a specific set of biological problems. In particular, we present the idealization process and implementation details of a web platform capable of addressing these problems, as well as the actual platform prototype. The prototype's functionality is showcased with a real case study, produced in collaboration with biology researchers. This report also includes a literature review, covering both the biological and technical aspects of the work, with special emphasis in machine learning techniques applied to data mining tasks. Lastly, we review the work done and results obtained so far and outline the possible future of the web platform.