Portrait of Marc-André Legault

Marc-André Legault

Associate Academic Member
Assistant Professor, Université de Montréal, Pharmacogenetics
Research Topics
Causality
Computational Biology
Medical Machine Learning

Biography

Marc-André Legault obtained his Ph.D. in bioinformatics from Université de Montréal and the Montreal Heart Institute where he developed and applied new computational methods for drug target validation. He subsequently completed his postdoctoral training at McGill University and Mila - Quebec Artificial Intelligence Institute, working on instrumental variable estimation and machine learning for genetic epidemiology more broadly.

He is now an Assistant Professor in pharmacogenetics at the Université de Montréal's Faculty of pharmacy and a researcher at the CHU Sainte-Justine Azrieli research centre. His research program aims to develop and use computational approaches for drug target validation to better understand treatment heterogeneity and improve our ability to anticipate the on-target effect of new drug classes. He is also an Associate Academic member at Mila - Quebec Institute of Artificial Intelligence.

Current Students

Independent visiting researcher - Université de Montréal (research assistant)

Publications

Diet Networks: Thin Parameters for Fat Genomics
pierre luc carrier
Akram Erraqabi
Tristan Sylvain
Alex Auvolat
Etienne Dejoie
Marie-Pierre Dubé
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (see more) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.
Diet Networks: Thin Parameters for Fat Genomics
pierre luc carrier
Akram Erraqabi
Tristan Sylvain
Alex Auvolat
Etienne Dejoie
Marie-Pierre Dubé
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (see more) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.