Publications

IL1RAP is an immunotherapeutic target for normal karyotype triple-mutated acute myeloid leukemia

Arnaud Metois

Marie-Eve Bordeleau

Louis Theret

Azadeh Hajmirza

Ossama Moujaber

Jean-François Spinella

Jalila Chagraoui

Nadine Mayotte

Isabel Boivin

Éric Audemard

Léo Aubert

Véronique Lisi

Banafsheh Khakipoor

Azer Farah

Éric Bonneil

Alma Robert

Julie Lippens

Anna Moraitis

Francois Beliveau

Albert Feghaly … (see 10 more)

Geneviève Boucher

Richard Marcotte

Patrick Gendron

Pierre Thibault

Sébastien Lemieux

Guillaume Richard-Carpentier

Vincent-Philippe Lavallee

Josée Hébert

Philippe P. Roux

Guy Sauvageau

Surface antigens of potential clinical significance remain under-characterized in AML. The European Leukemia Network classifies normal karyo… (see more)type AML (NK-AML) mutated for NPM1 (NPM1c) as a distinct entity associated with favorable outcomes if not associated with FLT3-ITD mutation. A subset of NPM1c NK-AML shows additional mutations in 2 genes: FLT3 (FLT3-ITD) and DNMT3 A. These leukemias, also referred to as NK triple mutated AML (NKt-AML), are particularly difficult to eradicate with current treatment options. Therefore, novel therapies are necessary that use proteins specifically expressed at the surface. In order to identify surface antigens for immunotherapy in NKt-AML, an extensive multi-omic analysis was conducted on primary AML samples. Surface proteome enrichment was performed on 100 primary AML samples, twelve of which were NKt-AML. Transcriptome analysis was carried out on the 691 primary AML samples, and single-cell RNA sequencing was conducted on 23 primary AML samples. Herein, using multi-omics data from the Leucegene collection, we identify IL1RAP as a promising antigen for this AML subgroup. We demonstrate that IL1RAP is expressed at the surface of primitive AML cells reminiscent of leukemic stem cells in NKt-AML primary human AML specimens, while showing relatively low expression levels in normal bone marrow HSCs. Furthermore, results indicate that elevated IL1RAP expression associates with poor overall and relapse-free survival in the Leucegene cohort of AML patients and predicts nonresponse to hematopoietic stem cell transplantation. Finally, we show that IL1RAP protein is internalized following exposure to specific antibodies, suggesting that IL1RAP represents an interesting target for antibody–drug conjugate development in NKt-AML. IL1RAP exhibits preferential expression within NKt-AML, correlating with diminished overall survival rates and diminished responsiveness to hematopoietic stem cell transplantation. Moreover, internalization of IL1RAP presents a promising avenue for immunotherapeutic intervention. The online version contains supplementary material available at 10.1186/s40364-025-00769-z.

2025-04-13

Biomarker Research (published)

doi.org

Improving Quality Control of MRI Images Using Synthetic Motion Data

C Bricout

K Cho

M Harms

O Pasternak

C Bearden

PD McGorry

RS Kahn

JM Kane

B Nelson

SW Woods

ME Shenton

S Bouix

S Ebrahimi Kahou

MRI quality control (QC) is challenging due to unbalanced and limited datasets, as well as subjective scoring, which hin-der the development… (see more) of reliable automated QC systems. To address these issues, we introduce an approach that pretrains a model on synthetically generated motion artifacts before applying transfer learning for QC classification. This method not only improves the accuracy in identifying poor-quality scans but also reduces training time and resource requirements compared to training from scratch. By leveraging syn-thetic data, we provide a more robust and resource-efficient solution for QC automation in MRI, paving the way for broader adoption in diverse research settings.

2025-04-13

2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI) (published)

doi.org

arxiv.org

Logging Requirement for Continuous Auditing of Responsible Machine Learning-based Applications

Patrick Loic Foalem

Leuson Da Silva

Foutse Khomh

Heng Li

Ettore Merlo

Machine learning (ML) is increasingly applied across industries to automate decision-making, but concerns about ethical and legal compliance… (see more) remain due to limited transparency, fairness, and accountability. Monitoring through logging a long-standing practice in traditional software offers a potential means for auditing ML applications, as logs provide traceable records of system behavior useful for debugging, performance analysis, and continuous auditing. systematically auditing models for compliance or accountability. The findings underscore the need for enhanced logging practices and tooling that systematically integrate responsible AI metrics. Such practices would support the development of auditable, transparent, and ethically responsible ML systems, aligning with growing regulatory requirements and societal expectations. By highlighting specific deficiencies and opportunities, this work provides actionable guidance for both practitioners and tool developers seeking to strengthen the accountability and trustworthiness of ML applications.

2025-04-13

Empirical Software Engineering (published)

doi.org

arxiv.org

Open Problems in Technical AI Governance

Anka Reuel

Benjamin Bucknall

Stephen Casper

Timothy Fist

Lisa Soder

Onni Aarne

Lewis Hammond

Lujain Ibrahim

Alan Chan

Peter Wills

Markus Anderljung

Ben Garfinkel

Lennart Heim

Andrew Trask

Gabriel Mukobi

Rylan Schaeffer

Mauricio Baker

Sara Hooker

Irene Solaiman

Sasha Luccioni … (see 14 more)

Alexandra Luccioni

Nitarshan Rajkumar

Nicolas Moës

Jeffrey Ladish

David Bau

Paul Bricman

Neel Guha

Jessica Newman

Yoshua Bengio

Tobin South

Alex Pentland

Sanmi Koyejo

Mykel Kochenderfer

Robert Trager

AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the… (see more) barriers and uncertainties faced are at least partly technical. Technical AI governance, referring to technical analysis and tools for supporting the effective governance of AI, seeks to address such challenges. It can help to (a) identify areas where intervention is needed, (b) identify and assess the efficacy of potential governance actions, and (c) enhance governance options by designing mechanisms for enforcement, incentivization, or compliance. In this paper, we explain what technical AI governance is, why it is important, and present a taxonomy and incomplete catalog of its open problems. This paper is intended as a resource for technical researchers or research funders looking to contribute to AI governance.

2025-04-13

Transactions on Machine Learning Research (accepted)

doi.org

openreview.net

Predicting College Enrollment for Low-Socioeconomic-Status Students Using Machine Learning Approaches

Surina He

Mehrdad Yousefpoori-Naeim

Ying Cui

Maria Cutumisu

2025-04-11

Big Data and Cognitive Computing (published)

doi.org

BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning

Artem Zholus

Maksim Kuznetsov

Roman Schutski

Shayakhmetov Rim

Daniil Polykovskiy

A. Chandar

Alex Zhavoronkov

Generating novel active molecules for a given protein is an extremely challenging task for generative models that requires an understanding … (see more)of the complex physical interactions between the molecule and its environment. In this paper, we present a novel generative model, BindGPT which uses a conceptually simple but powerful approach to create 3D molecules within the protein's binding site. Our model produces molecular graphs and conformations jointly, eliminating the need for an extra graph reconstruction step. We pretrain BindGPT on a large-scale dataset and fine-tune it with reinforcement learning using scores from external simulation software. We demonstrate how a single pretrained language model can serve at the same time as a 3D molecular generative model, conformer generator conditioned on the molecular graph, and a pocket-conditioned 3D molecule generator. Notably, the model does not make any representational equivariance assumptions about the domain of generation. We show how such simple conceptual approach combined with pretraining and scaling can perform on par or better than the current best specialized diffusion models, language models, and graph neural networks while being two orders of magnitude cheaper to sample.

2025-04-10

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

Designing Ambiguity Sets for Distributionally Robust Optimization Using Structural Causal Optimal Transport

Ahmad-reza Ehyaei

Golnoosh Farnadi

Samira Samadi

Distributionally robust optimization tackles out-of-sample issues like overfitting and distribution shifts by adopting an adversarial approa… (see more)ch over a range of possible data distributions, known as the ambiguity set. To balance conservatism and accuracy, these sets must include realistic probability distributions by leveraging information from the nominal distribution. Assuming that nominal distributions arise from a structural causal model with a directed acyclic graph

2025-04-10

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

Engineering TCR-controlled fuzzy logic into CAR T cells enhances therapeutic specificity

Taisuke Kondo

François X.P. Bourassa

Sooraj Achar

MyLinh T. Duong

Anirvan Ghosh

Jérémy Biton

Grégoire Altan-Bonnet

Paul François

Naomi Taylor

2025-04-10

Cell (unknown)

doi.org

Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy

Khaoula Chehbouni

Martine De Cock

Gilles Caporossi

Afaf Taïk

Reihaneh Rabbany

Golnoosh Farnadi

The increased screen time and isolation caused by the COVID-19 pandemic have led to a significant surge in cases of online grooming, which i… (see more)s the use of strategies by predators to lure children into sexual exploitation. Previous efforts to detect grooming in industry and academia have involved accessing and monitoring private conversations through centrally-trained models or sending private conversations to a global server. In this work, we implement a privacy-preserving pipeline for the early detection of sexual predators. We leverage federated learning and differential privacy in order to create safer online spaces for children while respecting their privacy. We investigate various privacy-preserving implementations and discuss their benefits and shortcomings. Our extensive evaluation using real-world data proves that privacy and utility can coexist with only a slight reduction in utility.

2025-04-10

AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring

Nikolaos Ioannis Bountos

Arthur Ouaknine

Ioannis Papoutsis

David Rolnick

Forests are vital to ecosystems, supporting biodiversity and essential services, but are rapidly changing due to land use and climate change… (see more). Understanding and mitigating negative effects requires parsing data on forests at global scale from a broad array of sensory modalities, and using them in diverse forest monitoring applications. Such diversity in data and applications can be effectively addressed through the development of a large, pre-trained foundation model that serves as a versatile base for various downstream tasks. However, remote sensing modalities, which are an excellent fit for several forest management tasks, are particularly challenging considering the variation in environmental conditions, object scales, image acquisition modes, spatio-temporal resolutions, etc. With that in mind, we present the first unified Forest Monitoring Benchmark (FoMo-Bench), carefully constructed to evaluate foundation models with such flexibility. FoMo-Bench consists of 15 diverse datasets encompassing satellite, aerial, and inventory data, covering a variety of geographical regions, and including multispectral, red-green-blue, synthetic aperture radar and LiDAR data with various temporal, spatial and spectral resolutions. FoMo-Bench includes multiple types of forest-monitoring tasks, spanning classification, segmentation, and object detection. To enhance task and geographic diversity in FoMo-Bench, we introduce TalloS, a global dataset combining satellite imagery with ground-based annotations for tree species classification across 1,000+ categories and hierarchical taxonomic levels. Finally, we propose FoMo-Net, a pre-training framework to develop foundation models with the capacity to process any combination of commonly used modalities and spectral bands in remote sensing.

2025-04-10

Proceedings of the AAAI Conference on Artificial Intelligence (published)

doi.org

arxiv.org

A Layer Selection Approach to Test Time Adaptation

Sabyasachi Sahoo

Mostafa Elaraby

Jonas Ngnawe

Yann Batiste Pequignot

Frédéric Precioso

Christian Gagné

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When… (see more) faced with challenging shifts, most methods collapse and perform worse than the original pretrained model. In this paper, we find that not all layers are equally receptive to the adaptation, and the layers with the most misaligned gradients often cause performance degradation. To address this, we propose GALA, a novel layer selection criterion to identify the most beneficial updates to perform during test time adaptation. This criterion can also filter out unreliable samples with noisy gradients. Its simplicity allows seamless integration with existing TTA loss functions, thereby preventing degradation and focusing adaptation on the most trainable layers. This approach also helps to regularize adaptation to preserve the pretrained features, which are crucial for handling unseen domains. Through extensive experiments, we demonstrate that the proposed layer selection framework improves the performance of existing TTA approaches across multiple datasets, domain shifts, model architectures, and TTA losses.

2025-04-10

AAAI Conference on Artificial Intelligence (published)

doi.org

openreview.net

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery

Amirhossein Abaskohi

Amrutha Varshini Ramesh

Shailesh Nanisetty

Chirag Goel

David Vázquez

Christopher Pal

Spandana Gella