Machine Intelligence Toronto @ MaRS


Details
6:35pm: Welcomes and Thank You, you can use #miToronto to follow along
6:40pm:
Deep siamese neural networks for prediction of long-range interactions in chromatin
Davide Chicco ( http://www.DavideChicco.it | @DavideChicco_it )
Abstract
Chromatin is the combination of DNA and proteins that form chromosomes within the nucleus of human cells, and has a significant role in gene expression. In gene expression, transcriptional regulation depends on physical interactions between enhancers and promoters, often not adjacent on the DNA backbone, but rather interacting in the folded 3D conformation of chromatin. Unfortunately, these 3D long-range interactions are not easy to find. Current molecular biology techniques such as chromosome conformation capture (3C) and Hi-C are too expensive for widespread use. To solve this problem, we propose a machine-learning approach based upon a deep siamese neural network model, previously used for the detection of forged hand-written signatures. This artificial neural network learns the mathematical representation of pairs of chromosome region DNase profiles and state whether they represent a long-range interaction. We tested the effectiveness of our method through a standard optimization approach, built on Matthews correlation coefficient (MCC) test results. Preliminary results confirm the efficacy of our algorithm.
Bio
Davide Chicco is a postdoctoral researcher at the Princess Margaret Cancer Centre (University of Toronto). He obtained Bachelor of Science and Master of Science degrees in computer science at University of Genoa (Genoa, Italy), and then a PhD degree in computer engineering at Politecnico di Milano university (Milan, Italy), after spending also a semester at University of California Irvine (USA). His research topics focus upon mainly machine learning algorithms applied to bioinformatics.
7:55pm: Thank Yous
Thank you to Georgian Partners (http://georgianpartners.com/) for the extra space!
Both audiences, those who are interested in data science, those who are practitioners of data science are invited, and can both expect to learn something new.
Attendees can expect to learn what machine intelligence is, its applications, and what's going on in Toronto's data science community. Significant 'getting to know you' time, and Q&A time is deliberately set aside.

Machine Intelligence Toronto @ MaRS