2025

  • Talk

    Deep Generative Modeling for Transcriptomics

    Seminar, LaBRI · Bordeaux, France

  • Talk

    Deep Generative Modeling for Transcriptomics

    Biopuces seminar, INRAE · France

    Link
  • Talk

    Deep Generative Modeling for Transcriptomics

    Département de Génétique, INRAE · France

2024

  • Talk

    Frugal Generative Modeling for Tabular Data

    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) · Vilnius, Lithuania

  • Poster

    Frugal Generative Modeling for Tabular Data

    PhD Days STIC, Univ. Paris-Saclay · Saclay, France

2023

  • Talk

    GAN-based Data Augmentation for Transcriptomics

    International Conference on Intelligent Systems for Molecular Biology (ISMB) · Lyon, France

    ▶ Video
    Summary

    Transcriptomics data are becoming more accessible due to high-throughput and less costly sequencing methods. However, data scarcity prevents exploiting deep learning models’ full predictive power for phenotypes prediction. Artificially enhancing the training sets, namely data augmentation, is suggested as a regularization strategy. Data augmentation corresponds to label-invariant transformations of the training set (e.g. geometric transformations on images and syntax parsing on text data). Such transformations are, unfortunately, unknown in the transcriptomic field. Therefore, deep generative models such as generative adversarial networks (GANs) have been proposed to generate additional samples. In this article, we analyze GAN-based data augmentation strategies with respect to performance indicators and the classification of cancer phenotypes.This work highlights a significant boost in binary and multiclass classification performances due to augmentation strategies. Without augmentation, training a classifier on only 50 RNA-seq samples yields an accuracy of, respectively, 94% and 70% for binary and tissue classification. In comparison, we achieved 98% and 94% of accuracy when adding 1000 augmented samples. Richer architectures and more expensive training of the GAN return better augmentation performances and generated data quality overall. Further analysis of the generated data shows that several performance indicators are needed to assess its quality correctly.All data used for this research are publicly available and comes from The Cancer Genome Atlas.

  • Talk

    Deep Generative Modelling for Transcriptomics

    PhD Days UDOPIA, CentraleSupélec · Saclay, France

2022

  • Organizer

    NewInML Workshop @ ICML 2022

    International Conference on Machine Learning (ICML) · Baltimore, USA

    Link
    Summary

    Following the previous NewInML workshop editions, our goal is to welcome newcomers in the community and provide them with some guidance to contribute to Machine Learning research fully and effectively. We intend to host presentations appealing to ICML audiences eager to learn how to conduct their research from experienced researchers. The following topics will be addressed: 1) Communicating your results, 2) Collaborations with ML researchers, 3) Coding best practices. Attendees who submit an extended abstract will get peer-reviewed and best selected abstracts will be presented by their authors. This year, we are also hosting a presentation on academic writing support tailored on the submissions. It is your opportunity to refine your academic writing skills and boost your chances to see your paper published at the next ICML conference.

  • Invited talk

    ML-CI: Machine Learning Confidence Intervals for Covid-19 Forecasts

    Women In Data Science (WiDS) Guayaquil · Guayaquil, Ecuador (online)

    ▶ Video
    Summary

    Epidemic forecasting has always been challenging and the recent Covid-19 outbreaks emphasizes it. We introduce a novel approach to address the problem of evaluating confidence intervals (CI) of time series prediction forecasts for compartmental models, using machine learning. We evaluate our approach using real data of the Covid pandemic on 27 countries. Compartmental models were trained taking into account non pharmaceutical governmental measures. A Random Forest regressor was trained, using various engineered features, to predict the forecasting error for various horizons on synthetic data, then applied to estimate CI on real data forecasts. Our method outperforms baselines using forecast likelihood as metric.

2021

  • Talk

    ML-CI: Machine Learning Confidence Intervals for Covid-19 Forecasts

    Junior Conference on Data Science and Engineering (JDSE) · Saclay, France

    Link
  • Poster

    ML-CI: Machine Learning Confidence Intervals for Covid-19 Forecasts

    BayLearn – Machine Learning Symposium · San Francisco, USA (online)

    ▶ Video
    Summary

    Epidemic forecasting has always been challenging and the recent Covid-19 outbreaks emphasizes it. We introduce a novel approach to address the problem of evaluating confidence intervals (CI) of time series prediction forecasts for compartmental models, using machine learning. We evaluate our approach using real data of the Covid pandemic on 27 countries. Compartmental models were trained taking into account non pharmaceutical governmental measures. A Random Forest regressor was trained, using various engineered features, to predict the forecasting error for various horizons on synthetic data, then applied to estimate CI on real data forecasts. Our method outperforms baselines using forecast likelihood as metric.

  • Talk

    Knowledge-Aware Data Augmentation for Transcriptomics

    PhD Days UDOPIA, CentraleSupélec · Saclay, France