Publications related to Learning the language of the genome: AI- and data-driven decoding of genetic variants and disease mechanisms

Related publications (16)

Transferability of Learnt Speech Representations for Decoding Non-Human Vocal Communication

Humans and animals both use acoustic signals for vocal communication. The advent of self-supervised learning (SSL) has enabled neural networks to learn robust and general feature representations through the intrinsic acoustic structure of input signals, wi ...

EPFL2025

TimeGPT in load forecasting: A large time series model perspective

Fernando Porté Agel, Jiannong Fang, Wenlong Liao

Machine learning models have made significant progress in load forecasting, but their forecast accuracy is limited in cases where historical load data is scarce. Inspired by the outstanding performance of large language models (LLMs) in computer vision and ...

2025

Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians

Luciano Loris Viteritti, Giuseppe Carleo

Foundation models are highly versatile neural-network architectures capable of processing different data types, such as text and images, and generalizing across various tasks like classification and generation. Inspired by this success, we propose Foundati ...

2025

Musculoskeletal motor control with reinforcement learning

Alberto Silvio Chiappa

Animals, including humans, interact with the external environment primarily through motion. Replicating their motor control skills in artificial embodied agents is a major objective of artificial intelligence research. This thesis presents a collection of ...

EPFL2025

Enhanced Architectures and Optimization Methods for Efficient Language Modeling

Amirkeivan Mohtashami

This thesis investigates methods to construct more capable models more efficiently, focusing on two aspects: improved architectures and optimization. We examine principled architectural modifications that reduce computational costs or introduce features fo ...

EPFL2025

MARBLE: interpretable representations of neural population dynamics using geometric deep learning

Pierre Vandergheynst

The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation lear ...

Nature Publishing Group2025

Teaching oxidation states to neural networks

Nicola Marzari

While the accurate description of redox reactions remains a challenge for first-principles calculations, it has been shown that extended Hubbard functionals (DFT+U+V) can provide a reliable approach, mitigating self-interaction errors, in materials with st ...

2025

Allosteric Modulation of GCase Enhances Lysosomal Activity and Reduces ER Stress in GCase-Related Disorders

Mikhail Rudinskiy, Maurizio Molinari

Variants in the GBA1 gene, encoding the lysosomal enzyme glucosylceramidase beta 1 (GCase), are linked to Parkinson’s disease (PD) and Gaucher disease (GD). Heterozygous variants increase PD risk, while homozygous variants lead to GD, a lysosomal storage d ...

MDPI AG2025

Assessing Sample Quality via the Latent Space of Generative Models

Minh Hieu Lê

Advances in generative models increase the need for sample quality assessment. To do so, previous methods rely on a pre-trained feature extractor to embed the generated samples and real samples into a common space for comparison. However, different feature ...

Springer Science and Business Media Deutschland GmbH2025

Fingerprints of brain disease: connectome identifiability in Alzheimer’s disease

Dimitri Nestor Alice Van De Ville, Olaf Blanke, Maria Giulia Preti, Enrico Amico, Sara Stampacchia

Functional connectivity patterns in the human brain, like the friction ridges of a fingerprint, can uniquely identify individuals. Does this “brain fingerprint” remain distinct even during Alzheimer’s disease (AD)? Using fMRI data from healthy and patholog ...

Springer Science and Business Media LLC2024

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Anatomy-Informed Multimodal Learning for Myocardial Infarction Prediction

Pascal Frossard, Emmanuel Abbé, Ntorina Thanou, Ortal Yona Senouf, Ivan-Daniel Sievering

Goal: In patients with coronary artery disease, the prediction of future cardiac events such as myocardial infarction (MI) remains a major challenge. In this work, we propose a novel anatomy-informed multimodal deep learning framework to predict future MI ...

2024

The influence of data on adversarial robustness

Javier Alejandro Maroto Morales

Deep learning models are generally vulnerable to small perturbations, raising concerns about safety, security, and performance guarantees. Achieving robustness has been shown to be costly in terms of computational resources and quantity of data. This thesi ...

EPFL2024

Protein Engineering and Directed Evolution for Nanocarrier Innovation

Angela Steinauer

The design of nonviral protein-based delivery systems has gained significant attention as an alternative to viral vectors and lipid nanoparticles (LNPs) for gene therapy. While viral vectors offer efficient gene delivery, they present challenges such as im ...

2024

Training a Filter-Based Model of the Cochlea in the Context of Pre-Trained Acoustic Models

Philip Neil Garner, Louise Clothilde Coppieters De Gibson

Auditory research aims in general to lead to understanding of physiological processes. By contrast, the state of the art in automatic speech processing (notably recognition) is dominated by large pre-trained models that are meant to be used as black-boxes. ...

2024

Germline loss-of-function variant in the E3 ubiquitin ligase TRAF2 in a young adult patient with medulloblastoma: a case report

Sebastian Martin Waszak

We identified a rare heterozygous germline loss-of-function variant in the tumor necrosis factor receptor-associated factor 2 (TRAF2) in a young adult patient diagnosed with medulloblastoma. This variant is located within the TRAF-C domain of the E3 ubiqui ...

BioMed Central2024