no code implementations • 13 Nov 2023 • Xingyu Chen, Xiaochen Zheng, Amina Mollaysa, Manuel Schürch, Ahmed Allam, Michael Krauthammer
Here, we introduce TADA, a Two-stageAggregation process with Dynamic local Attention to harmonize time-wise and feature-wise irregularities in multivariate time series.
no code implementations • 13 Nov 2023 • Amina Mollaysa, Ahmed Allam, Michael Krauthammer
To speed up this process, we present an attention-based two-stage machine learning model that learns to predict the likelihood of all possible editing outcomes for a given genomic target sequence.
no code implementations • 4 Oct 2023 • Amina Mollaysa, Ahmed Allam, Michael Krauthammer
To speed up this process, we present an attention-based two-stage machine learning model that learns to predict the likelihood of all possible editing outcomes for a given genomic target sequence.
no code implementations • 28 Sep 2023 • Manuel Schürch, Xiang Li, Ahmed Allam, Giulia Rathmes, Amina Mollaysa, Claudia Cavelti-Weder, Michael Krauthammer
We propose a novel framework that combines deep generative time series models with decision theory for generating personalized treatment strategies.
1 code implementation • 31 Mar 2023 • Xiaochen Zheng, Xingyu Chen, Manuel Schürch, Amina Mollaysa, Ahmed Allam, Michael Krauthammer
Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification.
1 code implementation • 3 Oct 2022 • Kyriakos Schwarz, Alicia Pliego-Mendieta, Amina Mollaysa, Lara Planas-Paz, Chantal Pauli, Ahmed Allam, Michael Krauthammer
In contrast to conventional models relying on pre-computed chemical features, our GNN-based approach learns task-specific drug representations directly from the graph structure of the drugs, providing superior performance in predicting drug synergies.
no code implementations • NeurIPS 2020 • Amina Mollaysa, Brooks Paige, Alexandros Kalousis
Unfortunately, maximum likelihood training of such models often fails with the samples from the generative model inadequately respecting the input properties.
no code implementations • 25 Sep 2019 • Amina Mollaysa, Brooks Paige, Alexandros Kalousis
Though machine learning approaches have shown great success in estimating properties of small molecules, the inverse problem of generating molecules with desired properties remains challenging.
no code implementations • ICML 2017 • Amina Mollaysa, Pablo Strasser, Alexandros Kalousis
In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance.