no code implementations • 7 Mar 2024 • Dimitar Georgiev, Álvaro Fernández-Galiana, Simon Vilms Pedersen, Georgios Papadopoulos, Ruoxiao Xie, Molly M. Stevens, Mauricio Barahona
Raman spectroscopy is widely used across scientific domains to characterize the chemical composition of samples in a non-destructive, label-free manner.
no code implementations • 31 Jul 2023 • Mihir Dhanakshirur, Felix Laumann, Junhyung Park, Mauricio Barahona
Understanding and adequately assessing the difference between a true and a learnt causal graphs is crucial for causal inference under interventions.
1 code implementation • NeurIPS 2023 • Zhaolu Liu, Robert L. Peach, Pedro A. M. Mediano, Mauricio Barahona
Models that rely solely on pairwise relationships often fail to capture the complete statistical structure of the complex multivariate data found in diverse domains, such as socio-economic, ecological, or biomedical systems.
1 code implementation • 15 May 2023 • Zhaolu Liu, Robert L. Peach, Felix Laumann, Sara Vallejo Mengod, Mauricio Barahona
Multivariate time series data that capture the temporal evolution of interconnected systems are ubiquitous in diverse areas.
1 code implementation • 7 May 2023 • Dominik J. Schindler, Mauricio Barahona
In many applications in data clustering, it is desirable to find not just a single partition into clusters but a sequence of partitions describing the data at different scales, or levels of coarseness.
1 code implementation • 6 Apr 2023 • Adam Gosztolai, Robert L. Peach, Alexis Arnaudon, Mauricio Barahona, Pierre Vandergheynst
The dynamics of neuron populations during many behavioural tasks evolve on low-dimensional manifolds.
no code implementations • 26 Mar 2023 • Thomas Wong, Mauricio Barahona
This paper is a work in progress.
no code implementations • 14 Mar 2023 • Thomas Wong, Mauricio Barahona
We present a robust deep incremental learning framework for regression tasks on financial temporal tabular datasets which is built upon the incremental use of commonly available tabular and time series prediction models to adapt to distributional shifts typical of financial datasets.
2 code implementations • 30 Dec 2022 • Thomas Wong, Mauricio Barahona
The application of deep learning to non-stationary temporal datasets can lead to overfitted models that underperform under regime changes.
no code implementations • 14 Jul 2022 • Nan Wu, Sophia N. Yaliraki, Mauricio Barahona
Key residues in both orthosteric and allosteric sites were identified and showed agreement with experimental results, and pivotal signalling residues along the pathway were also revealed, thus providing alternative targets for drug design.
1 code implementation • 5 Jul 2022 • Asem Alaa, Erik Mayer, Mauricio Barahona
Early diagnosis of disease can lead to improved health outcomes, including higher survival rates and lower treatment costs.
1 code implementation • 24 Feb 2021 • Zijing Liu, Mauricio Barahona
We propose a similarity measure for sparsely sampled time course data in the form of a log-likelihood ratio of Gaussian processes (GP).
no code implementations • 28 Oct 2020 • M. Tarik Altuncu, Sophia N. Yaliraki, Mauricio Barahona
Production of news content is growing at an astonishing rate.
no code implementations • 7 Oct 2020 • Mona K Tonn, Philipp Thomas, Mauricio Barahona, Diego A Oyarzún
The metabolite distributions take the form of Gaussian mixture models that are directly computable from single-cell expression data and standard deterministic models for metabolic pathways.
no code implementations • 5 Jun 2020 • Varshit Dusad, Denise Thiel, Mauricio Barahona, Hector C. Keun, Diego A. Oyarzún
Here we discuss the roles of two complementary strategies for the analysis of genome-scale metabolic models: Flux Balance Analysis (FBA) and network science.
1 code implementation • 4 Jun 2020 • Yun William Yu, Jean-Charles Delvenne, Sophia N. Yaliraki, Mauricio Barahona
A major goal of dynamical systems theory is the search for simplified descriptions of the dynamics of a large number of interacting states.
no code implementations • 16 May 2020 • Stamatina Lamprinakou, Mauricio Barahona, Seth Flaxman, Sarah Filippi, Axel Gandy, Emma McCoy
The effectiveness of Bayesian Additive Regression Trees (BART) has been demonstrated in a variety of contexts including non-parametric regression and classification.
1 code implementation • 8 May 2020 • Yifan Qian, Paul Expert, Pietro Panzarasa, Mauricio Barahona
Traditional classification tasks learn to assign samples to given classes based solely on sample features.
2 code implementations • 28 Nov 2019 • Sam F. Greenbury, Mauricio Barahona, Iain G. Johnston
The explosion of data throughout the biomedical sciences provides unprecedented opportunities to learn about the dynamics of evolution and disease progression, but harnessing these large and diverse datasets remains challenging.
Quantitative Methods Genomics Methodology
1 code implementation • 24 Sep 2019 • Robert L. Peach, Alexis Arnaudon, Mauricio Barahona
Classification tasks based on feature vectors can be significantly improved by including within deep learning a graph that summarises pairwise relationships between the samples.
no code implementations • 6 Sep 2019 • Zijing Liu, Mauricio Barahona
We present a graph-theoretical approach to data clustering, which combines the creation of a graph from the data with Markov Stability, a multiscale community detection framework.
no code implementations • 31 Aug 2019 • M. Tarik Altuncu, Eloise Sorin, Joshua D. Symons, Erik Mayer, Sophia N. Yaliraki, Francesca Toni, Mauricio Barahona
The large volume of text in electronic healthcare records often remains underused due to a lack of methodologies to extract interpretable content.
no code implementations • 20 Jul 2019 • Amadeus Maes, Mauricio Barahona, Claudia Clopath
Learning to produce spatiotemporal sequences is a common task that the brain has to solve.
1 code implementation • 30 May 2019 • Yifan Qian, Paul Expert, Tom Rieu, Pietro Panzarasa, Mauricio Barahona
We showcase the relationship between the SAM and the classification performance through the study of limiting cases of GCNs and systematic randomizations of both features and graph structure applied to a constructive example and several examples of citation networks of different origins.
no code implementations • 14 Nov 2018 • M. Tarik Altuncu, Erik Mayer, Sophia N. Yaliraki, Mauricio Barahona
Electronic Healthcare records contain large volumes of unstructured data in different forms.
no code implementations • 3 Aug 2018 • M. Tarik Altuncu, Sophia N. Yaliraki, Mauricio Barahona
The explosion in the amount of news and journalistic content being generated across the globe, coupled with extended and instantaneous access to information through online media, makes it difficult and time-consuming to monitor news developments and opinion formation in real time.
no code implementations • 7 Jul 2018 • M. Tarik Altuncu, Erik Mayer, Sophia N. Yaliraki, Mauricio Barahona
Electronic Healthcare Records contain large volumes of unstructured data, including extensive free text.
2 code implementations • 10 Apr 2018 • Michael T. Schaub, Jean-Charles Delvenne, Renaud Lambiotte, Mauricio Barahona
Complex systems and relational data are often abstracted as dynamical processes on networks.
Social and Information Networks Systems and Control Physics and Society
no code implementations • 12 Mar 2013 • Aivar Sootla, Natalja Strelkowa, Damien Ernst, Mauricio Barahona, Guy-Bart Stan
In this paper, we consider the problem of optimal exogenous control of gene regulatory networks.