Publications

Universal antigen encoding of T cell activation from high-dimensional cytokine dynamics
Sooraj R. Achar
François X. P. Bourassa
Thomas J. Rademaker
Angela Lee
Taisuke Kondo
Emanuel Salazar-Cavazos
John S. Davies
Naomi Taylor
Paul François
Grégoire Altan-Bonnet
2022-05-20
Science (published)
doi.org
Human brain anatomy reflects separable genetic and environmental components of socioeconomic status
Hyeokmoon Kweon
Gökhan Aydogan
Alain Dagher
Danilo Bzdok
Christian C. Ruff
Gideon Nave
Martha J Farah
Philipp Koellinger
Recent studies report that socioeconomic status (SES) correlates with brain structure. Yet, such findings are variable and little is known a… (see more)bout underlying causes. We present a well-powered voxel-based analysis of grey matter volume (GMV) across levels of SES, finding many small SES effects widely distributed across the brain, including cortical, subcortical and cerebellar regions. We also construct a polygenic index of SES to control for the additive effects of common genetic variation related to SES, which attenuates observed SES-GMV relations, to different degrees in different areas. Remaining variance, which may be attributable to environmental factors, is substantially accounted for by body mass index, a marker for lifestyle related to SES. In sum, SES affects multiple brain regions through measurable genetic and environmental effects. One-sentence Summary Socioeconomic status is linked with brain anatomy through a varying balance of genetic and environmental influences.
2022-05-18
Science Advances (published)
doi.org
Multi-tract multi-symptom relationships in pediatric concussion
Guido I Guberman
Sonja Stojanovski
Eman Nishat
Alain Ptito
Danilo Bzdok
Anne L Wheeler
Maxime Descoteaux
The heterogeneity of white matter damage and symptoms in concussions has been identified as a major obstacle to therapeutic innovation. In c… (see more)ontrast, the vast majority of diffusion MRI studies on concussion have traditionally employed group-comparison approaches. Such studies do not consider heterogeneity of damage and symptoms in concussion. To parse concussion heterogeneity, the present study combines diffusion MRI (dMRI) and multivariate statistics to investigate multi-tract multi-symptom relationships. Using dMRI data from a sample of 306 children ages 9 and 10 with a history of concussion from the Adolescent Brain Cognitive Development Study (ABCD study), we built connectomes weighted by classical and emerging diffusion measures. These measures were combined into two informative indices, the first capturing a mixture of patterns suggestive of microstructural complexity, the second representing almost exclusively axonal density. We deployed pattern-learning algorithms to jointly decompose these connectivity features and 19 behavioural measures that capture well-known symptoms of concussions. We found idiosyncratic symptom-specific multi-tract connectivity features, which would not be captured in traditional univariate analyses. Multivariable connectome-symptom correspondences were stronger than all single-tract/single-symptom associations. Multi-tract connectivity features were also expressed equally across different sociodemographic strata and their expression was not accounted for by injury-related variables. In a replication dataset, the expression of multi-tract connectivity features predicted adverse psychiatric outcomes after accounting for other psychopathology-related variables. By defining cross-demographic multi-tract multi-symptom relationships to parse concussion heterogeneity, the present study can pave the way for the development of improved stratification strategies that may contribute to the success of future clinical trials and the improvement of concussion management.
2022-05-17
eLife (published)
doi.org
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
Zhepei Wang
Cem Subakan
Xilin Jiang
Junkai Wu
Efthymios Tzinis
Mirco Ravanelli
Paris Smaragdis
In this article, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framew… (see more)ork where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.
2022-05-15
ArXiv (preprint)
doi.org
arxiv.org
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
Courtney Paquette
Elliot Paquette
Ben Adlam
Jeffrey Pennington
We develop a stochastic differential equation, called homogenized SGD, for analyzing the dynamics of stochastic gradient descent (SGD) on a … (see more)high-dimensional random least squares problem with
2022-05-14
ArXiv (preprint)
arxiv.org
arxiv.org
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
Courtney Paquette
Elliot Paquette
Ben Adlam
Jeffrey Pennington
2022-05-14
ArXiv (preprint)
arxiv.org
arxiv.org
Learning active tactile perception through belief-space control
Jean-François Tremblay
Johanna Hansen
David Meger
Francois Hogan
Gregory Dudek
Robot operating in an open world can encounter novel objects with unknown physical properties, such as mass, friction, or size. It is desira… (see more)ble to be able to sense those property through contact-rich interaction, before performing downstream tasks with the objects. We propose a method for autonomously learning active tactile perception policies, by learning a generative world model leveraging a differentiable bayesian filtering algorithm, and designing an information- gathering model predictive controller. We test the method on three simulated tasks: mass estimation, height estimation and toppling height estimation. Our method is able to discover policies which gather information about the desired property in an intuitive manner.
2022-05-12
ICRA.org/2022/Workshop/Contact-Rich (poster)
doi.org
openreview.net
Reconstruction of full-length LINE-1 progenitors from ancestral genomes
Laura F. Campitelli
Isaac Yellan
Mihai Tudor Albu
Marjan Barazandeh
Zain M. Patel
Mathieu Blanchette
T. Hughes
Abstract Sequences derived from the Long INterspersed Element-1 (L1) family of retrotransposons occupy at least 17% of the human genome, wit… (see more)h 67 distinct subfamilies representing successive waves of expansion and extinction in mammalian lineages. L1s contribute extensively to gene regulation, but their molecular history is difficult to trace, because most are present only as truncated and highly mutated fossils. Consequently, L1 entries in current databases of repeat sequences are composed mainly of short diagnostic subsequences, rather than full functional progenitor sequences for each subfamily. Here, we have coupled 2 levels of sequence reconstruction (at the level of whole genomes and L1 subfamilies) to reconstruct progenitor sequences for all human L1 subfamilies that are more functionally and phylogenetically plausible than existing models. Most of the reconstructed sequences are at or near the canonical length of L1s and encode uninterrupted ORFs with expected protein domains. We also show that the presence or absence of binding sites for KRAB-C2H2 Zinc Finger Proteins, even in ancient-reconstructed progenitor L1s, mirrors binding observed in human ChIP-exo experiments, thus extending the arms race and domestication model. RepeatMasker searches of the modern human genome suggest that the new models may be able to assign subfamily resolution identities to previously ambiguous L1 instances. The reconstructed L1 sequences will be useful for genome annotation and functional study of both L1 evolution and L1 contributions to host regulatory networks.
2022-05-12
Genetics (published)
doi.org
Reconstruction of full-length LINE-1 progenitors from ancestral genomes
Laura F Campitelli
Isaac Yellan
Mihai Albu
Marjan Barazandeh
Zain M Patel
Mathieu Blanchette
Timothy R Hughes
2022-05-12
Genetics (published)
doi.org
Block Contextual MDPs for Continual Learning
Shagun Sodhani
Franziska Meier
Joelle Pineau
Amy Zhang
In reinforcement learning (RL), when defining a Markov Decision Process (MDP), the environment dynamics is implicitly assumed to be stationa… (see more)ry. This assumption of stationarity, while simplifying, can be unrealistic in many scenarios. In the continual reinforcement learning scenario, the sequence of tasks is another source of nonstationarity. In this work, we propose to examine this continual reinforcement learning setting through the Block Contextual MDP (BC-MDP) framework, which enables us to relax the assumption of stationarity. This framework challenges RL algorithms to handle both nonstationarity and rich observation settings and, by additionally leveraging smoothness properties, enables us to study generalization bounds for this setting. Finally, we take inspiration from adaptive control to propose a novel algorithm that addresses the challenges introduced by this more realistic BC-MDP setting, allows for zero-shot adaptation at evaluation time, and achieves strong performance on several nonstationary environments.
2022-05-11
Proceedings of The 4th Annual Learning for Dynamics and Control Conference (published)
proceedings.mlr.press
openreview.net
Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation
Yuyan Chen
Yanghua Xiao
Bang Liu
Interpreting the predictions of existing Question Answering (QA) models is critical to many real-world intelligent applications, such as QA … (see more)systems for healthcare, education, and finance. However, existing QA models lack interpretability and provide no feedback or explanation for end-users to help them understand why a specific prediction is the answer to a question. In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models. Unlike previous research that simply extracts several sentence(s) in the context as evidence, we are the first to explicitly define the concept of evidence as the supporting facts in a context which are informative, concise, and readable. Besides, we provide effective strategies to quantitatively measure the informativeness, conciseness and readability of evidence. Furthermore, we propose Grow-and-Clip Evidence Distillation (GCED) algorithm to extract evidences from the contexts by trade-off informativeness, conciseness, and readability. We conduct extensive experiments on the SQuAD and TriviaQA datasets with several baseline models to evaluate the effect of GCED on interpreting answers to questions. Human evaluation are also carried out to check the quality of distilled evidences. Experimental results show that automatic distilled evidences have human-like informativeness, conciseness and readability, which can enhance the interpretability of the answers to questions.
2022-05-09
2022 IEEE 38th International Conference on Data Engineering (ICDE) (published)
doi.org
arxiv.org
Metrics Reloaded - A new recommendation framework for biomedical image analysis validation
Annika Reinke
Lena Maier-Hein
Evangelia Christodoulou
Ben Glocker
Patrick Scholz
Fabian Isensee
Jens Kleesiek
Michal Kozubek
Mauricio Reyes
Michael Alexander Riegler
Manuel Wiesenfarth
Michael Baumgartner
Matthias Eisenmann
DOREEN HECKMANN-NÖTZEL
Ali Emre Kavur
TIM RÄDSCH
Minu D. Tizabi
LAURA ACION
Michela Antonelli
Tal Arbel … (see 48 more)
Spyridon Bakas
Peter Bankhead
Arriel Benis
M. Jorge Cardoso
Veronika Cheplygina
Beth A Cimini
Gary S. Collins
Keyvan Farahani
Bram van Ginneken
Fred A Hamprecht
Daniel A. Hashimoto
Michael M. Hoffman
Merel Huisman
Pierre Jannin
Charles Kahn
ALEXANDROS KARARGYRIS
Alan Karthikesalingam
Hannes Kenngott
Annette Kopp-Schneider
Anna Kreshuk
Tahsin Kurc
Bennett Landman
GEERT LITJENS
Amin Madani
Klaus Maier-Hein
Anne Martel
Peter Mattson
ERIK MEIJERING
Bjoern Menze
David Moher
KAREL G.M. MOONS
Henning Müller
Brennan Nichyporuk
Felix Nickel
Jens Petersen
NASIR RAJPOOT
Nicola Rieke
Julio Saez-Rodriguez
Clara I. Sánchez
SHRAVYA SHETTY
Maarten van Smeden
Carole H. Sudre
Ronald M. Summers
Abdel A. Taha
Sotirios A. Tsaftaris
Ben Van Calster
Gael Varoquaux
Paul F Jaeger
Meaningful performance assessment of biomedical image analysis algorithms depends on objective and appropriate performance metrics. There ar… (see more)e major shortcomings in the current state of the art. Yet, so far limited attention has been paid to practical pitfalls associated when using particular metrics for image analysis tasks. Therefore, a number of international initiatives have collaborated to offer researchers with guidance and tools for selecting performance metrics in a problem-aware manner. In our proposed framework, the characteristics of the given biomedical problem are first captured in a problem fingerprint, which identifies properties related to domain interests, the target structure(s), the input datasets, and algorithm output. A problem category-specific mapping is applied in the second step to match fingerprints to metrics that reflect domain requirements. Based on input from experts from more than 60 institutions worldwide, we believe our metric recommendation framework to be useful to the MIDL community and to enhance the quality of biomedical image analysis algorithm validation.
2022-05-09
MIDL.io/2022/Conference/Short (published)
openreview.net
openreview.net