Eric Paquet

Eric Paquet
National Research Council Canada | NRC · Information and Communications Technologies

PhD, Computer Vision and Optical Processing

About

189
Publications
52,421
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,617
Citations

Publications

Publications (189)
Preprint
Full-text available
With the approach of the High Luminosity Large Hadron Collider (HL-LHC) era set to begin particle collisions by the end of this decade, it is evident that the computational demands of traditional collision simulation methods are becoming increasingly unsustainable. Existing approaches, which rely heavily on first-principles Monte Carlo simulations...
Preprint
Full-text available
Particle collisions at accelerators such as the Large Hadron Collider, recorded and analyzed by experiments such as ATLAS and CMS, enable exquisite measurements of the Standard Model and searches for new phenomena. Simulations of collision events at these detectors have played a pivotal role in shaping the design of future experiments and analyzing...
Article
Full-text available
Recent breakthroughs in deep learning have revolutionized protein sequence and structure prediction. These advancements are built on decades of protein design efforts, and are overcoming traditional time and cost limitations. Diffusion models, at the forefront of these innovations, significantly enhance design efficiency by automating knowledge acq...
Article
Full-text available
Protein generation has numerous applications in designing therapeutic antibodies and creating new drugs. Still, it is a demanding task due to the inherent complexities of protein structures and the limitations of current generative models. Proteins possess intricate geometry, and sampling their conformational space is challenging due to its high di...
Chapter
Protein structural properties are often determined by experimental techniques such as X-ray crystallography and nuclear magnetic resonance. However, both approaches are time-consuming and expensive. Conversely, protein amino acid sequences may be readily obtained from inexpensive high-throughput techniques, although such sequences lack structural i...
Article
Full-text available
This paper presents a new approach for protein generation based on one-shot learning and hybrid quantum neural networks. Given a single protein complex, the system learns how to predict the remaining unknown properties, without resorting to autoregression, from the physicochemical properties of the receptor and a prior on the physicochemical proper...
Article
Full-text available
The design of binder proteins for specific target proteins using deep learning is a challenging task that has a wide range of applications in both designing therapeutic antibodies and creating new drugs. Machine learning-based solutions, as opposed to laboratory design, streamline the design process and enable the design of new proteins that may be...
Conference Paper
Studies of protein-protein interactions facilitate the development of new drugs and can aid understanding of the mechanisms behind disease pathogenesis. Finding the sites of interaction on the molecular surface is key to understanding protein-protein interactions and the role of molecular pathways. However, this is still an open area of research. T...
Chapter
Protein-protein interactions play an important role in the development of new therapeutic treatments and prophylactic vaccines. For instance, the efficacy of a vaccine strongly depends to what extent an antibody may form a stable bond with an antigen. In-laboratory experiments are both time-consuming and expensive, which limits their scope to only...
Article
Full-text available
Proteins mainly perform their functions by interacting with other proteins. Protein–protein interactions underpin various biological activities such as metabolic cycles, signal transduction, and immune response. However, due to the sheer number of proteins, experimental methods for finding interacting and non-interacting protein pairs are time-cons...
Article
Full-text available
Flattening shapes without distortion is a problem that has been intriguing scientists for centuries. It is a fundamental problem of high importance in computer vision as many approaches may greatly benefit from its implementation. This paper introduces a new approach that allows flattening without distortion, by transforming the shape from Riemanni...
Article
Full-text available
Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain biological insights into protein functions, disease prevalence, and therapy development by identifying protein–protein interactions (PPI). However, finding the interacting and non-interacting protein pairs through experimental app...
Chapter
Online semi-supervised learning (SSL) from data streams is an emerging area of research with many applications due to the fact that it is often expensive, time-consuming, and sometimes even unfeasible to collect labelled data from streaming domains. State-of-the-art online SSL algorithms use clustering techniques to maintain micro-clusters, or, alt...
Article
Full-text available
This paper introduces a new hybrid deep quantum neural network for financial predictions, the QuantumLeap system. This system consists of an encoder that transforms a partitioned financial time series into a sequence of density matrices; a deep quantum network that predicts the density matrix at a later time; and a classical network that measures,...
Article
Full-text available
The classification of deformable protein shapes, based solely on their macromolecular surfaces, is a challenging problem in proteinprotein interaction prediction and protein design. Shape classification is made difficult by the fact that proteins are dynamic, flexible entities with high geometrical complexity. In this paper, we introduce a novel de...
Article
Full-text available
This paper presents a new deep learning framework, QuantumPath, for long-term stock price prediction, which is of great significance in portfolio management and risk mitigation, especially when the market becomes volatile due to unpredictable circumstances such as a pandemic. Our approach is based on stochastic equations, the Feynman–Dirac path int...
Article
Full-text available
This work introduces novel approaches, based on geometrical deep learning, for predicting protein–protein interactions. A dataset containing both interacting and non-interacting proteins is selected from the Negatome Database. Interactions are predicted from a graph representing the proteins’ three-dimensional macromolecular surfaces. The nodes are...
Preprint
Portfolio management aims at maximizing the return on investment while minimizing risk by continuously reallocating the assets forming the portfolio. These assets are not independent but correlated during a short time period. A graph convolutional reinforcement learning framework called DeepPocket is proposed whose objective is to exploit the time-...
Article
Portfolio management aims at maximizing the return on investment while minimizing risk by continuously reallocating the assets forming the portfolio. These assets are not independent but correlated during a short time period. A graph convolutional reinforcement learning framework called DeepPocket is proposed whose objective is to exploit the time-...
Article
Full-text available
Glycosylation of hydrophobic peptides at one terminus effectively increases their water-solubility, and conjugation through the opposing end to a carrier protein, renders them more immunogenic. Moreover, the glycosylation minimizes antibody responses to potentially deleterious, non-productive terminal neo-epitope regions of the peptides, and conseq...
Conference Paper
We address the problem of 3D protein deformable shape classification. Proteins are macromolecules characterized by deformable and complex shapes which are related to their function making their classification an important task. Their molecular surface is represented by graphs such as triangular tessellations or meshes. In this paper, we propose a n...
Chapter
In e-business, recommender systems have been instrumental in guiding users through their online experiences. However, these systems are often limited by the lack of labels data and data sparsity. Increasingly, data-mining techniques are utilized to address this issue. In most research, recommendations to be made are achieved via supervised learning...
Article
Full-text available
The process of continuously reallocating funds into financial assets, aiming to increase the expected return of investment and minimizing the risk, is known as portfolio management. In this paper, a portfolio management framework is developed based on a deep reinforcement learning framework called DeepBreath. The DeepBreath methodology combines a r...
Chapter
Full-text available
Recommendation systems, which are employed to mitigate the information overload e-commerce users face, have succeeded in aiding customers during their online shopping experience. However, to be able to make accurate recommendations, these systems require information about the items for sale and about users’ individual preferences. Making recommenda...
Cover Page
Full-text available
We propose a novel fast graph matching approach based on a new formulation of the stable marriage problem, to measure the distance between graphs. The proposed approach is optimal in terms of execution time, i.e. quadratic time complexity O(n 2). Our technique is based on the decomposition of graphs into a set of substructures which are subsequentl...
Conference Paper
Full-text available
Nous traitons le problème de la comparaison des objets 3D déformables représentés par des graphes tels que les tessellations triangulaires. Nous proposons une nouvelle technique d'appariement de graphes pour mesurer la distance entre ces graphes. L'approche proposée est basée sur une nouvelle décomposition de tessellations triangulaires en étoiles-...
Article
We address the problem of comparing deformable 3D objects represented by graphs such as triangular tessellations. We propose a new graph matching technique to measure the distance between these graphs. The proposed approach is based on a new decomposition of triangular tessellations into triangle-stars. The algorithm ensures a minimum number of dis...
Conference Paper
Recommendation systems, which are employed to mitigate the information overload faced by e-commerce users, have succeeded in aiding customers during their online shopping experience. However, to be able to make accurate recommendations, these systems require information about the items for sale and information about users’ individual preferences. M...
Article
Full-text available
The last decade has seen a surge of interest in adaptive learning algorithms for data stream classification, with applications ranging from predicting ozone level peaks, learning stock market indicators, to detecting computer security violations. In addition, a number of methods have been developed to detect concept drifts in these streams. Conside...
Article
Full-text available
Ab initio molecular dynamics is an irreplaceable technique for the realistic simulation of complex molecular systems and processes from first principles. This paper proposes a comprehensive and self-contained review of ab initio molecular dynamics from a computational perspective and from first principles. Quantum mechanics is presented from a mole...
Article
Full-text available
The success of data stream mining techniques has allowed decision makers to analyze their data in multiple domains, ranging from monitoring network intrusion to financial markets analysis and online sales transactions exploration. Specifically, online ensembles that construct accurate models against drifting data streams have been developed. Recent...
Article
Full-text available
Increasingly, Internet of Things (IoT) domains, such as sensor networks, smart cities, and social networks, generate vast amounts of data. Such data are not only unbounded and rapidly evolving. Rather, the content thereof dynamically evolves over time, often in unforeseen ways. These variations are due to so-called concept drifts, caused by changes...
Conference Paper
The identification of changes in data distributions associated with data streams is critical in understanding the mechanics of data generating processes and ensuring that data models remain representative through time. To this end, concept drift detection methods often utilize statistical techniques that take numerical data as input. However, many...
Preprint
The last decade has seen a surge of interest in adaptive learning algorithms for data stream classification, with applications ranging from predicting ozone level peaks, learning stock market indicators, to detecting computer security violations. In addition, a number of methods have been developed to detect concept drifts in these streams. Conside...
Article
Full-text available
Vaccination is the most effective course of action to prevent influenza. About 150 million doses of influenza vaccines were distributed for the 2015–2016 season in the USA alone according to the Centers for Disease Control and Prevention. Vaccine dosage is calculated based on the concentration of hemagglutinin (HA), the main surface glycoprotein ex...
Data
Signal obtained by dot blot with 6 μg mAb F211-11H12, 6 μg mAb F211-10A9, and 6 μg of both mAb (cocktail). (DOCX)
Data
Description of the computational approach. (DOCX)
Data
Uncropped and unaltered original blots obtained with viruses produced in eggs and probed with mAb F211-11H12 (Panel A) or mAb F211-10A9 (Panel B). (TIF)
Data
Recombinant HA proteins were detected by mAb F211-11H12 (A), F211-10A9 (B), or a cocktail made of both antibodies (D). An anti-GFP antibody was used as a negative control (C). The influenza strain loaded in each lane is indicated in the table in the bottom panel. Anti-GFP (clone 3E6) negative control mAb was produced and purified in our laboratory...
Data
Standard curves generated with standards produced using different platforms. A) H1N1 A/Puerto Rico/8/34 virus was produced in HEK293 cells and quantified by SRID. As a comparison, a standard curve obtained using a recombinant protein (Protein Sciences) is shown. B) H1N1 A/California/07/2009 standard from NIBSC (Code 09/174) was produced in MDCK cel...
Data
Standard curve generated with strains presenting a low signal by dot blot when probed with pan-HA antibodies. A) H3N2 A/Aichi/2/1968 is a non-purified virus produced in-house in HEK293 cells. B) H3N2/A/Texas/50/2012 is a standard reagent produced in HEK293 cells by NIBSC and inactivated with formalin. (TIF)
Chapter
Data mining has been successfully applied in many businesses, thus aiding managers to make informed decisions that are based on facts, rather than having to rely on guesswork and incorrect extrapolations. Data mining algorithms equip institutions to predict the movements of financial indicators, enable companies to move towards more energy-efficien...
Conference Paper
Adaptive online learning algorithms have been successfully applied to fast-evolving data streams. Such streams are susceptible to concept drift, which implies that the most suitable type of classifier often changes over time. In this setting, a system that is able to seamlessly select the type of learner that presents the current “best” model holds...
Conference Paper
Online ensemble methods have been very successful to create accurate models against data streams that are susceptible to concept drift. The success of data stream mining has allowed diverse users to analyse their data in multiple domains, ranging from monitoring stock markets to analysing network traffic and exploring ATM transactions. Increasingly...
Conference Paper
Full-text available
We consider the problem of comparing deformable 3D objects represented by graphs, i.e., triangular tessellations. We propose a new algorithm to measure the distance between triangular tessellations using a new decomposition of triangular tessellations into triangle-Stars. The proposed algorithm assures a minimum number of disjoint triangle-Stars, o...
Article
Full-text available
Macromolecular structures, such as neuraminidases, hemagglutinins, and monoclonal antibodies, are not rigid entities. Rather, they are characterised by their flexibility, which is the result of the interaction and collective motion of their constituent atoms. This conformational diversity has a significant impact on their physicochemical and biolog...
Conference Paper
Class imbalance is a crucial problem in machine learning and occurs in many domains. Specifically, the two-class problem has received interest from researchers in recent years, leading to solutions for oil spill detection, tumour discovery and fraudulent credit card detection, amongst others. However, handling class imbalance in datasets that conta...
Article
Acquisition systems based on laser triangulation or structured light are becoming commonplace in anthropometry. Such systems allow one to capture very detailed data to be used when addressing the sizing problem. This chapter introduces state-of-the-art approaches to describe, to segment and to cluster the data acquired by such systems. We describe...
Conference Paper
Finding correspondences between deformable objects has wide application in many domains. In information retrieval, researchers may be interested in finding similar objects, while computer animation experts may be considering ways to morph shapes. The correspondence problem is especially challenging when the objects under consideration are suspect t...
Conference Paper
Non-rigid shapes are generally known as objects where the three dimensional geometry may deform by internal and/or external forces. Deformable shapes are all around us, ranging from macromolecules, to natural objects such as the trees in the forest or the fruits in our gardens, and even human bodies. The development of measurements to accurately de...
Conference Paper
The protein docking problem refers to the task of predicting the appropriate matching of one protein molecule (the receptor) to another (the ligand), when attempting to bind them to form a stable complex. Research shows that matching the three-dimensional geometric structures of proteins plays a key role in determining a so-called docking pair. How...
Conference Paper
Recently, a number of researchers have turned their attention to the creation of isometrically invariant shape descriptors based on the heat equation. The reason for this surge in interest is that the Laplace-Beltrami operator, associated with the heat equation, is highly dependent on the topology of the underlying manifold, which may lead to the c...
Conference Paper
Research has shown that the functionalities of proteins are largely influenced by their three dimensional (3D) shapes. This observation is especially relevant in drug design, where the knowledge of the 3D structure of a protein enables pharmacologists to select the best binding proteins when aiming to moderate functions. However, a relatively small...
Article
Multirelational classification aims to discover patterns across multiple interlinked tables (relations) in a relational database. In many large organizations, such a database often spans numerous departments and/or subdivisions, which are involved in different aspects of the enterprise such as customer profiling, fraud detection, inventory manageme...
Article
The comparison of macromolecular structures, in terms of functionalities, is a crucial step when aiming to identify potential docking sites. Drug designers require the identification of such docking sites for the binding of two proteins, in order to form a stable complex. This paper presents a review of current approaches to macromolecular structur...
Conference Paper
Consider a scenario where one aims to learn models from data being characterized by very large fluctuations that are neither attributable to noise nor outliers. This may be the case, for instance, when predicting the potential future damages of earthquakes or oil spills, or when conducting financial data analysis. If follows that, in such a situati...
Conference Paper
The aim of privacy-preserving data mining is to construct highly accurate predictive models while not disclosing privacy information. Aggregation functions, such as sum and count are often used to pre-process the data prior to applying data mining techniques to relational databases. Often, it is implicitly assumed that the aggregated (or summarized...
Conference Paper
Full-text available
Consider a multi-relational database, to be used for classification, that contains a large number of unlabeled data. It follows that the cost of labeling such data is prohibitive. Transductive learning, which learns from labeled as well as from unlabeled data already known at learning time, is highly suited to address this scenario. In this paper,...
Article
Full-text available
The modelling of complex objects and sites involve the acquisition of a large number of texture maps and range images; each one of them representing a particular viewing angle. These views must be combined and registered in order to create an accurate model of the original. The complexity of the resultant models, and consequently the number of view...
Conference Paper
This paper presents a theoretical analysis of the occurrence of fractal geometry within index spaces and discusses the impact for multimedia retrieval. Firstly, we explain how to detect the presence of such a fractal geometry. Then, with the fractal hypothesis in hand, we analyze the impact of this geometry when calculating the distance between ind...
Article
The apparel industry aims to produce comfortable and aesthetically pleasing garments that fit populations well. However, repeated studies of apparel customers’ levels of satisfaction indicate that their needs are often not being met. In order to produce better fitting clothes, it is crucial to understand the body profiles of typical consumers. Expl...
Article
Functional clothing encompasses a wide range of apparels such as protective equipments, functional garments and fire-retardant clothing. Depending on the application, they must adapt to the shape of the human body, should not interfere with the body motion and should isolate the body from a potentially hazardous environment. In order to achieve the...
Conference Paper
Full-text available
Multirelational classification algorithms aim to discover patterns across multiple interlinked tables in a relational database. However, when considering a complex database schema, it becomes difficult to identify all possible relationships between attributes. This is because a database often contains a very large number of attributes which come fr...
Conference Paper
Consider a scenario where one aims to learn models from data being characterized by very large fluctuations that are neither attributable to noise nor outliers. This may be the case, for instance, when examining supermarket ketchup sales, predicting earthquakes and when conducting financial data analysis. In such a situation, the standard central l...
Article
Full-text available
There has recently been a surge of interest in relational database mining that aims to discover useful patterns across multiple interlinked database relations. It is crucial for a learning algorithm to explore the multiple inter-connected relations so that important attributes are not excluded when mining such relational repositories. However, from...
Conference Paper
Complex systems, such as proteins, are inherently difficult to describe, analyse and interpret. A multimodal methodology which utilizes various diverse representations is needed to further our understanding of such intrinsically multifaceted systems. This paper presents a multimodal system designed to describe and interpret the content of the Prote...
Article
Full-text available
When considering probabilistic pattern recognition methods, especially methods based on Bayesian analysis, the probabilistic distribution is of the utmost importance. However, despite the fact that the geometry associated with the probability distribution constitutes essential background information, it is often not ascertained. This paper discusse...
Article
Full-text available
Relational database mining, where data are mined across multiple relations, is increasingly commonplace. When considering a complex database schema, it becomes difficult to identify all possible relationships between attributes from the different relations. That is, seemingly harmless attributes may be linked to confidential information, leading to...
Article
Full-text available
Increasingly, resources are "born digital" and their associated formats are short-lived. Subsequently, the development of environments to preserve such digital content over the very long-term (50 years or more) has become a critical issue. To date, however, the preservation of data as contained in object-relational databases has been widely overloo...
Article
Full-text available
Distance is a fundamental concept when considering the information retrieval and cluster analysis of 3D information. That is, a large number of information retrieval descriptor comparison and cluster analysis algorithms are built around the very concept of the distance, such as the Mahalanobis or Manhattan distances, between points. Although not al...
Article
Full-text available
Preservation metadata, information that supports and documents the long term preservation of a digital object, is an essential component of any preservation environment that must manage knowledge over time. It describes the digital object's associated semantic information. Furthermore, in the case of preserving 3D data, it can also support future p...
Article
Consider a protein (P(X)) that has been identified, during drug design, to constitute a new breakthrough in the design of a drug for treating a terminal illness. That is, this protein has the ability to dock on active sites and mask the subsequent docking of harmful foreign proteins. Unfortunately, protein X has serious side effects and is therefor...