Machine Learning applied to Biology : future opportunities for biologists

Francesco Russo is a researcher in Bioinformatics with more than 12 years of working experience in the field. He is involved in the development of several computational tools for several different types of bioinformatics analyses, such as: algorithms, data analysis platforms (such as: RNASeqGUI, ImageR, Golgi Motif Explorer, REDAC) and various tools for the analysis of biological data of different type. Moreover, he has developed several methods to classify putative oncogenes based on Copy Number Alteration data from more than 11000 patients affected by 32 different cancers collected from the TGCA database. His research activity is mainly focused on the development of novel methods, algorithms and platforms for the analysis of several bio-data. Francesco Russo is an expert analyst of NGS data produced by RNA-seq experiments and also an expert of Machine Learning techniques applied to omics data.

The unprecedented expansion of both the amount of data and their complexity in Biology have pushed the need to use Machine Learning techniques to help biologists to exploit all the information hidden in the biological data to build predictive models that can help the discovery of novel therapeutic strategies to cure several types of diseases and to unravel new biological mechanisms, as well. This presentation introduces some basic concepts, ideas and challenges of Machine Learning techniques and how they have been applied to Biology so far. Some simple machine learning algorithms are shown and discussed. We address the frequent problems that arise when we apply machine learning algorithms to biological data and what are the main current challenges and promising future opportunities that may arise using machine learning tools in Biology.