MACHINE LEARNING ALGORITHMS FOR MAKING INFERENCES ON NETWORKS AND ANSWERING QUESTIONS IN BIOLOGY AND MEDICINE
An important idea that has emerged recently is that a cell can be viewed as a set of complex networks of interacting bio-molecules. In this talk, I will present novel machine learning algorithms for solving problems in systems biology and medicine that can be phrased in terms of inference in such large-scale networks.
I will begin by describing a semi-supervised learning method that can accurately predict protein function for newly sequenced organisms and is currently the state-of-the-art method for predicting function in bacteria. I will then show how these same ideas can be exploited for drug repositioning for COVID-19 – here we used graph kernels to rank drugs according to the perturbation that they induce on a subnetwork of the human interactome that is crucial for SARS-CoV-2 infection/replication.
I will then present another method for drug repositioning for COVID-19 that targets SARS-CoV-2 directly and is based on a new non-negative matrix factorisation algorithm. Finally, if time allows, I will present how we are currently extending these types of models for predicting side effects that are caused by drug combinations.
*Texto informado pelo autor.
Apoiadores / Parceiros / Patrocinadores
Alberto Paccanaro - is Full Professor at the School of Applied Mathematics (EMAp) at FGV in Rio de Janeiro, which he joined in 2020. He completed his undergraduate studies in Computer Science at the University of Milan and received his PhD from the University of Toronto in 2002, specializing in machine learning under the supervision of Geoffrey Hinton. From 2002 to 2006, he was a postdoc in Mansoor Saqi’s lab at Queen Mary University of London and in Mark Gerstein’s lab at Yale University. He became a PI in 2006, obtaining a Lecturer position at Royal Holloway University of London, where he started his lab (www.paccanarolab.org). In 2014 he became Full Professor of Machine Learning and Computational Biology and Director of the Centre for Systems and Synthetic Biology, in the same University. He has been visiting professor at Cornell, Yale, the University of Venice and the Catholic University of Asuncion in Paraguay. He is responsible for several international collaborations in the field of Machine Learning applied to Biology and Medicine and co-directs research grants together with academics at Yale University, Cornell University, Liverpool School of Tropical Medicine and the Catholic University of Asuncion, Paraguay. His research interests are in developing machine learning algorithms for solving problems in molecular biology, medicine and pharmacology.