Amin Emad

Membre académique associé

Professeur agrégé, McGill University, Département de génie électrique et informatique

Sujets de recherche

Apprentissage de représentations

Apprentissage multimodal

Apprentissage profond

Apprentissage sur graphes

Biologie computationnelle

Causalité

Modèles génératifs

Modèles probabilistes

Modélisation moléculaire

Réseaux de neurones en graphes

Biographie

Amin Emad est professeur adjoint au Département de génie électrique et informatique de l'Université McGill. Il est également affilié à l'Institut du cancer Rosalind et Morris Goodman, à l'Initiative de McGill en médecine computationnelle (MiCM), au programme des Sciences quantitatives de la vie et aux Laboratoires Meakins-Christie de l'Université McGill. Il est aussi membre associé de Mila – Institut québécois d'intelligence artificielle. Avant de se joindre à McGill, il a été associé de recherche postdoctorale au centre d'excellence KnowEnG des National Institutes of Health (NIH) en informatique des mégadonnées, un centre lié au Département d'informatique et à l'Institut de biologie génomique (IGB) de l'Université de l'Illinois à Urbana-Champaign (UIUC). Il a obtenu un doctorat de l'UIUC en 2015, une maîtrise de l'Université de l'Alberta en 2009 et une licence de l'Université technologique Sharif en 2007. Ses recherches se situent à l'intersection de l'IA et de la biologie informatique.

Étudiants actuels

Nicolas Bolouri

Baccalauréat - McGill

Doctorat - McGill

Doctorat - McGill

William Ma

Maîtrise recherche - McGill

Github

Ali Saberi

Doctorat - McGill

Cedrique Shum-Tim

Doctorat - McGill

Github

Kiri Stern

Doctorat - McGill

Chen Su

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Publications

Validation of ANG-1 and P-SEL as biomarkers of post-COVID-19 conditions using data from the Biobanque québécoise de la COVID-19 (BQC-19)

Eric Yamga

Antoine Soulé

Alain Piché

Amin Emad

Madeleine Durand

Simon Rousseau

2023-10-24

Clinical Proteomics (publié)

doi.org

Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?

Yihui Li

David Earl Hostallero

Amin Emad

Motivation: Recent advances in deep learning model development have enabled more accurate prediction of drug response in cancer. However, th… (voir plus)e black-box nature of these models still remains a hurdle in their adoption for precision cancer medicine. Recent efforts have focused on making these models interpretable by incorporating signaling pathway information in model architecture. While these models improve interpretability, it is unclear whether this higher interpretability comes at the cost of less accurate predictions, or a prediction improvement can also be obtained. Results: In this study, we comprehensively and systematically assessed four state-of-the-art interpretable models developed for drug response prediction to answer this question using three pathway collections. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. Moreover, in most evaluation setups the best performance is achieved using a simple black-box model. In addition, replacing the signaling pathways with randomly generated pathways shows a comparable performance for the majority of these interpretable models. Our results suggest that new interpretable models are necessary to improve the drug response prediction performance. In addition, the current study provides different baseline models and evaluation setups necessary for such new models to demonstrate their superior prediction performance. Availability and Implementation: Implementation of all methods are provided in https://github.com/Emad-COMBINE-lab/InterpretableAI_for_DRP. Generated uniform datasets are in https://zenodo.org/record/7101665#.YzS79HbMKUk. Contact: amin.emad@mcgill.ca Supplementary Information: Online-only supplementary data is available at the journal’s website.

2023-06-16

Bioinformatics (publié)

doi.org

MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores

Mohamed Reda El Khili

Safyan Aman Memon

Amin Emad

Motivation Combination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improv… (voir plus)e outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. Results Here, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and Implementation An implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY. Contact amin.emad@mcgill.ca Supplementary Information Online-only supplementary data is available at the journal’s website.

2023-04-06

Bioinformatics (publié)

doi.org

Analysis of gene expression and use of connectivity mapping to identify drugs for treatment of human glomerulopathies

Chen-Fang Chung

Joan Papillon

José R. Navarro-Betancourt

Julie Guillemette

Ameya Bhope

Amin Emad

Andrey V. Cybulsky

2023-03-13

Frontiers in Medicine (publié)

doi.org

Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL

David Earl Hostallero

Lixuan Wei

Liewei Wang

Junmei Cairns

Amin Emad

2023-02-01

Genomics, Proteomics & Bioinformatics (publié)

doi.org

A circulating proteome-informed prognostic model of COVID-19 disease activity that relies on 1 routinely available clinical laboratories 2

William Ma

Antoine Soulé

Karine Tremblay

Simon Rousseau

Amin Emad

Abstract

2023-01-01

(publié)

www.semanticscholar.org

A circulating proteome-informed prognostic model of COVID-19 disease activity that relies on 1 routinely available clinical laboratories 2

William Ma

Antoine Soulé

Karine Tremblay

Simon Rousseau

Amin Emad

Abstract

Poisson Group Testing: A Probabilistic Model for Boolean Compressed Sensing

Amin Emad

Olgica Milenkovic

We introduce a novel probabilistic group testing framework, termed Poisson group testing, in which the number of defectives follows a right-… (voir plus)truncated Poisson distribution. The Poisson model has a number of new applications, including dynamic testing with diminishing relative rates of defectives. We consider both nonadaptive and semi-adaptive identification methods. For nonadaptive methods, we derive a lower bound on the number of tests required to identify the defectives with a probability of error that asymptotically converges to zero; in addition, we propose test matrix constructions for which the number of tests closely matches the lower bound. For semiadaptive methods, we describe a lower bound on the expected number of tests required to identify the defectives with zero error probability. In addition, we propose a stage-wise reconstruction algorithm for which the expected number of tests is only a constant factor away from the lower bound. The methods rely only on an estimate of the average number of defectives, rather than on the individual probabilities of subjects being defective.

2015-08-15

IEEE Transactions on Signal Processing (publié)

doi.org

arxiv.org

Poisson Group Testing: A Probabilistic Model for Boolean Compressed Sensing

Amin Emad

Olgica Milenkovic

2014-10-20

ArXiv (prépublication)

doi.org

arxiv.org