Publications

Patient Engagement in the Implementation of Electronic Patient-Reported Outcome Tools: The Experience of Two Early-Adopter Institutions in the Pan-Canadian Radiotherapy Patient-Reported Outcome Initiative
Amanda Caissie
J. Lane
B. Barber
S. Chisholm
J. Kildea
2024-11-30
Clinics in oncology (publié)
doi.org
Predicting the Mathematics Literacy of Resilient Students from High‐performing Economies: A Machine Learning Approach
Yimei Zhang
Maria Cutumisu
2024-11-30
Studies in Educational Evaluation (publié)
doi.org
Towards AI-designed genomes using a variational autoencoder
Natasha K. Dudek
Natasha K. Dudek
Doina Precup
Genomes encode elaborate networks of genes whose products must seamlessly interact to support living organisms. Humans’ capacity to unders… (voir plus)tand these biological systems is limited by their sheer size and complexity. In this article, we develop a proof of concept framework for training a machine learning (ML) algorithm to model bacterial genome composition. To achieve this, we create simplified representations of genomes in the form of binary vectors that indicate the encoded genes, henceforth referred to as genome vectors. A denoising variational autoencoder was trained to accept corrupted genome vectors, in which most genes had been masked, and reconstruct the original. The resulting model, DeepGenomeVector, effectively captures complex dependencies in genomic networks, as evaluated by both qualitative and quantitative metrics. An in-depth functional analysis of a generated genome vector shows that its encoded pathways are interconnected, near complete, and ecologically cohesive. On the test set, where the model’s ability to reconstruct uncorrupted genome vectors was evaluated, Area Under the Receiver Operating Curve (AUROC) and F1 scores of 0.98 and 0.83, respectively, support the model’s strong performance. This article showcases the power of ML approaches for synthetic biology and highlights the possibility that artifical intelligence agents may one day be able to design genomes that animate carbon-based cells.
2024-11-30
Proceedings of the Royal Society B: Biological Sciences (publié)
doi.org
Uhura: A Benchmark for Evaluating Scientific Question Answering and Truthfulness in Low-Resource African Languages
Edward Bayes
Israel Abebe Azime
Jesujoba Oluwadara Alabi
Jonas Kgomo
Tyna Eloundou
Elizabeth Proehl
Kai Chen
Imaan Khadir
Naome Etori
Shamsuddeen Hassan Muhammad
C. Mpanza
Igneciah Pocia Thete
Dietrich Klakow
David Ifeoluwa Adelani
Evaluations of Large Language Models (LLMs) on knowledge-intensive tasks and factual accuracy often focus on high-resource languages primari… (voir plus)ly because datasets for low-resource languages (LRLs) are scarce. In this paper, we present Uhura -- a new benchmark that focuses on two tasks in six typologically-diverse African languages, created via human translation of existing English benchmarks. The first dataset, Uhura-ARC-Easy, is composed of multiple-choice science questions. The second, Uhura-TruthfulQA, is a safety benchmark testing the truthfulness of models on topics including health, law, finance, and politics. We highlight the challenges creating benchmarks with highly technical content for LRLs and outline mitigation strategies. Our evaluation reveals a significant performance gap between proprietary models such as GPT-4o and o1-preview, and Claude models, and open-source models like Meta's LLaMA and Google's Gemma. Additionally, all models perform better in English than in African languages. These results indicate that LMs struggle with answering scientific questions and are more prone to generating false claims in low-resource African languages. Our findings underscore the necessity for continuous improvement of multilingual LM capabilities in LRL settings to ensure safe and reliable use in real-world contexts. We open-source the Uhura Benchmark and Uhura Platform to foster further research and development in NLP for LRLs.
2024-11-30
ArXiv (prépublication)
doi.org
arxiv.org
Visual Modality Prompt for Adapting Vision-Language Object Detectors
Heitor Rapela Medeiros
Atif Belal
Srikanth Muralidharan
Eric Granger
Marco Pedersoli
The zero-shot performance of object detectors degrades when tested on different modalities, such as infrared and depth. While recent work ha… (voir plus)s explored image translation techniques to adapt detectors to new modalities, these methods are limited to a single modality and apply only to traditional detectors. Recently, vision-language detectors, such as YOLO-World and Grounding DINO, have shown promising zero-shot capabilities, however, they have not yet been adapted for other visual modalities. Traditional fine-tuning approaches tend to compromise the zero-shot capabilities of the detectors. The visual prompt strategies commonly used for classification with vision-language models apply the same linear prompt translation to each image making them less effective. To address these limitations, we propose ModPrompt, a visual prompt strategy to adapt vision-language detectors to new modalities without degrading zero-shot performance. In particular, an encoder-decoder visual prompt strategy is proposed, further enhanced by the integration of inference-friendly task residuals, facilitating more robust adaptation. Empirically, we benchmark our method for modality adaptation on two vision-language detectors, YOLO-World and Grounding DINO, and on challenging infrared (LLVIP, FLIR) and depth (NYUv2) data, achieving performance comparable to full fine-tuning while preserving the model's zero-shot capability. Our code is available at: https://github.com/heitorrapela/ModPrompt
2024-11-30
ArXiv (prépublication)
doi.org
arxiv.org
Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines
Kevin A. Kovalchik
David J. Hamelin
Peter Kubiniok
Benoîte Bourdin
Fatima Mostefai
Raphaël Poujol
Bastien Paré
Shawn M. Simpson
John Sidney
Éric Bonneil
Mathieu Courcelles
Sunil Kumar Saini
Mohammad Shahbazy
Saketh Kapoor
Vigneshwar Rajesh
Maya Weitzen
Jean-Christophe Grenier
Bayrem Gharsallaoui
Loïze Maréchal
Zhaoguan Wu … (voir 9 de plus)
Christopher Savoie
Alessandro Sette
Pierre Thibault
Isabelle Sirois
Martin A. Smith
Hélène Decaluwe
Julie G. Hussin
Mathieu Lavallée-Adam
Etienne Caron
Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 … (voir plus)variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.
2024-11-27
Nature Communications (publié)
doi.org
Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation
Shambhavi Mishra
Julio Silva-Rodríguez
Ismail Ben Ayed
Marco Pedersoli
Jose Dolz
Vision-language foundation models, such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, … (voir plus)these models may be unreliable under distributional shifts, as their performance is significantly degraded. In this work, we explore how to efficiently leverage class text information to mitigate these distribution drifts encountered by large pre-trained vision-language models (VLMs) during test-time inference. In particular, we propose to generate pseudo-labels for the test-time samples by exploiting generic class text embeddings as fixed centroids of a label assignment problem, which is efficiently solved with Optimal Transport. Furthermore, the proposed adaptation method (CLIP-OT) integrates a multiple template knowledge distillation approach, which replicates multi-view contrastive learning strategies in unsupervised representation learning but without incurring additional computational complexity. Extensive experiments on multiple popular test-time adaptation benchmarks presenting diverse complexity empirically show the superiority of CLIP-OT, achieving performance gains of up to 7% over recent state-of-the-art methods, yet being computationally and memory efficient.
2024-11-25
ArXiv (prépublication)
doi.org
arxiv.org
Comparative Analysis of Diffusion Generative Models in Computational Pathology
Denisha Thakkar
Vincent Quoc-Huy Trinh
Sonal Varma
S Ebrahimi Kahou
Hassan Rivaz
Mahdi S. Hosseini
Diffusion Generative Models (DGM) have rapidly surfaced as emerging topics in the field of computer vision, garnering significant interest a… (voir plus)cross a wide array of deep learning applications. Despite their high computational demand, these models are extensively utilized for their superior sample quality and robust mode coverage. While research in diffusion generative models is advancing, exploration within the domain of computational pathology and its large-scale datasets has been comparatively gradual. Bridging the gap between the high-quality generation capabilities of Diffusion Generative Models and the intricate nature of pathology data, this paper presents an in-depth comparative analysis of diffusion methods applied to a pathology dataset. Our analysis extends to datasets with varying Fields of View (FOV), revealing that DGMs are highly effective in producing high-quality synthetic data. An ablative study is also conducted, followed by a detailed discussion on the impact of various methods on the synthesized histopathology images. One striking observation from our experiments is how the adjustment of image size during data generation can simulate varying fields of view. These findings underscore the potential of DGMs to enhance the quality and diversity of synthetic pathology data, especially when used with real data, ultimately increasing accuracy of deep learning models in histopathology. Code is available from https://github.com/AtlasAnalyticsLab/Diffusion4Path
2024-11-23
ArXiv (prépublication)
doi.org
arxiv.org
Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
Heitor Rapela Medeiros
Masih Aminbeidokhti
Fidel A. Guerrero Peña
David Latortue
Eric Granger
Marco Pedersoli
A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domai… (voir plus)ns and tasks. While this approach works well in many application areas, it often fails drastically when processing data from a new modality with a significant distribution shift from the data used to pre-train the model. This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift. We propose Modality Translator (ModTr) as an alternative to the common approach of fine-tuning a large model to the new modality. ModTr adapts the IR input image with a small transformation network trained to directly minimize the detection loss. The original RGB model can then work on the translated inputs without any further changes or fine-tuning to its parameters. Experimental results on translating from IR to RGB images on two well-known datasets show that our simple approach provides detectors that perform comparably or better than standard fine-tuning, without forgetting the knowledge of the original model. This opens the door to a more flexible and efficient service-based detection pipeline, where a unique and unaltered server, such as an RGB detector, runs constantly while being queried by different modalities, such as IR with the corresponding translations model. Our code is available at: https://github.com/heitorrapela/ModTr.
2024-11-23
Lecture Notes in Computer Science (publié)
doi.org
arxiv.org
Gaps Between Research and Practice When Measuring Representational Harms Caused by LLM-Based Systems
Emma Harvey
Emily Sheng
Su Lin Blodgett
Alexandra Chouldechova
Jean Garcia-Gathright
A.R. Olteanu
Hanna Wallach
To facilitate the measurement of representational harms caused by large language model (LLM)-based systems, the NLP research community has p… (voir plus)roduced and made publicly available numerous measurement instruments, including tools, datasets, metrics, benchmarks, annotation instructions, and other techniques. However, the research community lacks clarity about whether and to what extent these instruments meet the needs of practitioners tasked with developing and deploying LLM-based systems in the real world, and how these instruments could be improved. Via a series of semi-structured interviews with practitioners in a variety of roles in different organizations, we identify four types of challenges that prevent practitioners from effectively using publicly available instruments for measuring representational harms caused by LLM-based systems: (1) challenges related to using publicly available measurement instruments; (2) challenges related to doing measurement in practice; (3) challenges arising from measurement tasks involving LLM-based systems; and (4) challenges specific to measuring representational harms. Our goal is to advance the development of instruments for measuring representational harms that are well-suited to practitioner needs, thus better facilitating the responsible development and deployment of LLM-based systems.
2024-11-22
ArXiv (prépublication)
doi.org
arxiv.org
Learning and fine-tuning a generic value-selection heuristic inside a constraint programming solver
Tom Marty
Léo Boisvert
Tristan François
Pierre Tessier
Louis Gautier
Louis-Martin Rousseau
Quentin Cappart
Constraint programming is known for being an efficient approach to solving combinatorial problems. Important design choices in a solver are … (voir plus)the branching heuristics, designed to lead the search to the best solutions in a minimum amount of time. However, developing these heuristics is a time-consuming process that requires problem-specific expertise. This observation has motivated many efforts to use machine learning to automatically learn efficient heuristics without expert intervention. Although several generic variable-selection heuristics are available in the literature, the options for value-selection heuristics are more scarce. We propose to tackle this issue by introducing a generic learning procedure that can be used to obtain a value-selection heuristic inside a constraint programming solver. This has been achieved thanks to the combination of a deep Q-learning algorithm, a tailored reward signal, and a heterogeneous graph neural network. Experiments on graph coloring, maximum independent set, maximum cut, and minimum vertex cover problems show that this framework competes with the well-known impact-based and activity-based search heuristics and can find solutions close to optimality without requiring a large number of backtracks. Additionally, we observe that fine-tuning a model with a different problem class can accelerate the learning process.
2024-11-22
Constraints (publié)
doi.org
MixEHR-Nest: Identifying Subphenotypes within Electronic Health Records through Hierarchical Guided-Topic Modeling
Ruohan Wang
Zilong Wang
Ziyang Song
David Buckeridge
Yue Li
Automatic subphenotyping from electronic health records (EHRs)provides numerous opportunities to understand diseases with unique subgroups a… (voir plus)nd enhance personalized medicine for patients. However, existing machine learning algorithms either focus on specific diseases for better interpretability or produce coarse-grained phenotype topics without considering nuanced disease patterns. In this study, we propose a guided topic model, MixEHR-Nest, to infer sub-phenotype topics from thousands of disease using multi-modal EHR data. Specifically, MixEHR-Nest detects multiple subtopics from each phenotype topic, whose prior is guided by the expert-curated phenotype concepts such as Phenotype Codes (PheCodes) or Clinical Classification Software (CCS) codes. We evaluated MixEHR-Nest on two EHR datasets: (1) the MIMIC-III dataset consisting of over 38 thousand patients from intensive care unit (ICU) from Beth Israel Deaconess Medical Center (BIDMC) in Boston, USA; (2) the healthcare administrative database PopHR, comprising 1.3 million patients from Montreal, Canada. Experimental results demonstrate that MixEHR-Nest can identify subphenotypes with distinct patterns within each phenotype, which are predictive for disease progression and severity. Consequently, MixEHR-Nest distinguishes between type 1 and type 2 diabetes by inferring subphenotypes using CCS codes, which do not differentiate these two subtype concepts. Additionally, MixEHR-Nest not only improved the prediction accuracy of short-term mortality of ICU patients and initial insulin treatment in diabetic patients but also revealed the contributions of subphenotypes. For longitudinal analysis, MixEHR-Nest identified subphenotypes of distinct age prevalence under the same phenotypes, such as asthma, leukemia, epilepsy, and depression. The MixEHR-Nest software is available at GitHub: https://github.com/li-lab-mcgill/MixEHR-Nest.
2024-11-21
Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (publié)
doi.org
arxiv.org