1
|
Bernaola N, Michiels M, Larrañaga P, Bielza C. Learning massive interpretable gene regulatory networks of the human brain by merging Bayesian networks. PLoS Comput Biol 2023; 19:e1011443. [PMID: 38039337 PMCID: PMC10745139 DOI: 10.1371/journal.pcbi.1011443] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Revised: 12/22/2023] [Accepted: 08/19/2023] [Indexed: 12/03/2023] Open
Abstract
We present the Fast Greedy Equivalence Search (FGES)-Merge, a new method for learning the structure of gene regulatory networks via merging locally learned Bayesian networks, based on the fast greedy equivalent search algorithm. The method is competitive with the state of the art in terms of the Matthews correlation coefficient, which takes into account both precision and recall, while also improving upon it in terms of speed, scaling up to tens of thousands of variables and being able to use empirical knowledge about the topological structure of gene regulatory networks. To showcase the ability of our method to scale to massive networks, we apply it to learning the gene regulatory network for the full human genome using data from samples of different brain structures (from the Allen Human Brain Atlas). Furthermore, this Bayesian network model should predict interactions between genes in a way that is clear to experts, following the current trends in explainable artificial intelligence. To achieve this, we also present a new open-access visualization tool that facilitates the exploration of massive networks and can aid in finding nodes of interest for experimental tests.
Collapse
Affiliation(s)
- Niko Bernaola
- Computational Intelligence Group, Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Madrid, Spain
| | - Mario Michiels
- Centro Integral de Neurociencias Abarca Campal, Hospital Universitario HM Puerta del Sur, Madrid, Spain
| | - Pedro Larrañaga
- Computational Intelligence Group, Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Madrid, Spain
| | - Concha Bielza
- Computational Intelligence Group, Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Madrid, Spain
| |
Collapse
|
2
|
Soriano B, Hafez AI, Naya-Català F, Moroni F, Moldovan RA, Toxqui-Rodríguez S, Piazzon MC, Arnau V, Llorens C, Pérez-Sánchez J. SAMBA: Structure-Learning of Aquaculture Microbiomes Using a Bayesian Approach. Genes (Basel) 2023; 14:1650. [PMID: 37628701 PMCID: PMC10454057 DOI: 10.3390/genes14081650] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2023] [Revised: 08/14/2023] [Accepted: 08/17/2023] [Indexed: 08/27/2023] Open
Abstract
Gut microbiomes of fish species consist of thousands of bacterial taxa that interact among each other, their environment, and the host. These complex networks of interactions are regulated by a diverse range of factors, yet little is known about the hierarchy of these interactions. Here, we introduce SAMBA (Structure-Learning of Aquaculture Microbiomes using a Bayesian Approach), a computational tool that uses a unified Bayesian network approach to model the network structure of fish gut microbiomes and their interactions with biotic and abiotic variables associated with typical aquaculture systems. SAMBA accepts input data on microbial abundance from 16S rRNA amplicons as well as continuous and categorical information from distinct farming conditions. From this, SAMBA can create and train a network model scenario that can be used to (i) infer information of how specific farming conditions influence the diversity of the gut microbiome or pan-microbiome, and (ii) predict how the diversity and functional profile of that microbiome would change under other variable conditions. SAMBA also allows the user to visualize, manage, edit, and export the acyclic graph of the modelled network. Our study presents examples and test results of Bayesian network scenarios created by SAMBA using data from a microbial synthetic community, and the pan-microbiome of gilthead sea bream (Sparus aurata) in different feeding trials. It is worth noting that the usage of SAMBA is not limited to aquaculture systems as it can be used for modelling microbiome-host network relationships of any vertebrate organism, including humans, in any system and/or ecosystem.
Collapse
Affiliation(s)
- Beatriz Soriano
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
- Biotechvana, Parc Científic Universitat de València, 46980 Paterna, Spain; (A.I.H.); (R.A.M.); (C.L.)
- Institute for Integrative Systems Biology (I2SysBio), Universitat de Valencia and CSIC (UVEG-CSIC), 46980 Paterna, Spain;
| | - Ahmed Ibrahem Hafez
- Biotechvana, Parc Científic Universitat de València, 46980 Paterna, Spain; (A.I.H.); (R.A.M.); (C.L.)
| | - Fernando Naya-Català
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
| | - Federico Moroni
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
| | - Roxana Andreea Moldovan
- Biotechvana, Parc Científic Universitat de València, 46980 Paterna, Spain; (A.I.H.); (R.A.M.); (C.L.)
- Health Research Institute INCLIVA, 46010 Valencia, Spain
- Bioinformatics and Biostatistics Unit, Principe Felipe Research Center (CIPF), 46012 Valencia, Spain
| | - Socorro Toxqui-Rodríguez
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
| | - María Carla Piazzon
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
| | - Vicente Arnau
- Institute for Integrative Systems Biology (I2SysBio), Universitat de Valencia and CSIC (UVEG-CSIC), 46980 Paterna, Spain;
- Foundation for the Promotion of Sanitary and Biomedical Research of the Valencian Community (FISABIO), 46020 Valencia, Spain
| | - Carlos Llorens
- Biotechvana, Parc Científic Universitat de València, 46980 Paterna, Spain; (A.I.H.); (R.A.M.); (C.L.)
| | - Jaume Pérez-Sánchez
- Institute of Aquaculture Torre de la Sal (IATS), Consejo Superior de Investigaciones Científicas (CSIC), 12595 Ribera de Cabanes, Spain; (F.N.-C.); (F.M.); (S.T.-R.); (M.C.P.)
| |
Collapse
|
3
|
Moreno-Rodríguez JL, Larrañaga P, Bielza C. NeuroSuites: An online platform for running neuroscience, statistical, and machine learning tools. Front Neuroinform 2023; 17:1092967. [PMID: 36938360 PMCID: PMC10016263 DOI: 10.3389/fninf.2023.1092967] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 01/31/2023] [Indexed: 02/19/2023] Open
Abstract
Nowadays, an enormous amount of high dimensional data is available in the field of neuroscience. Handling these data is complex and requires the use of efficient tools to transform them into useful knowledge. In this work we present NeuroSuites, an easy-access web platform with its own architecture. We compare our platform with other software currently available, highlighting its main strengths. Thanks to its defined architecture, it is able to handle large-scale problems common in some neuroscience fields. NeuroSuites has different neuroscience-oriented applications and tools to integrate statistical data analysis and machine learning algorithms commonly used in this field. As future work, we want to further expand the list of available software tools as well as improve the platform interface according to user demands.
Collapse
Affiliation(s)
- José Luis Moreno-Rodríguez
- Computational Intelligence Group, Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Madrid, Spain
| | | | | |
Collapse
|
4
|
Kitson NK, Constantinou AC, Guo Z, Liu Y, Chobtham K. A survey of Bayesian Network structure learning. Artif Intell Rev 2023. [DOI: 10.1007/s10462-022-10351-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/19/2023]
Abstract
AbstractBayesian Networks (BNs) have become increasingly popular over the last few decades as a tool for reasoning under uncertainty in fields as diverse as medicine, biology, epidemiology, economics and the social sciences. This is especially true in real-world areas where we seek to answer complex questions based on hypothetical evidence to determine actions for intervention. However, determining the graphical structure of a BN remains a major challenge, especially when modelling a problem under causal assumptions. Solutions to this problem include the automated discovery of BN graphs from data, constructing them based on expert knowledge, or a combination of the two. This paper provides a comprehensive review of combinatoric algorithms proposed for learning BN structure from data, describing 74 algorithms including prototypical, well-established and state-of-the-art approaches. The basic approach of each algorithm is described in consistent terms, and the similarities and differences between them highlighted. Methods of evaluating algorithms and their comparative performance are discussed including the consistency of claims made in the literature. Approaches for dealing with data noise in real-world datasets and incorporating expert knowledge into the learning process are also covered.
Collapse
|
5
|
Batista Tsukahara VH, de Oliveira Júnior JN, de Oliveira Barth VB, de Oliveira JC, Rosa Cota V, Maciel CD. Data-Driven Network Dynamical Model of Rat Brains During Acute Ictogenesis. Front Neural Circuits 2022; 16:747910. [PMID: 36034337 PMCID: PMC9399918 DOI: 10.3389/fncir.2022.747910] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2021] [Accepted: 06/08/2022] [Indexed: 11/16/2022] Open
Abstract
Epilepsy is one of the most common neurological disorders worldwide. Recent findings suggest that the brain is a complex system composed of a network of neurons, and seizure is considered an emergent property resulting from its interactions. Based on this perspective, network physiology has emerged as a promising approach to explore how brain areas coordinate, synchronize and integrate their dynamics, both under perfect health and critical illness conditions. Therefore, the objective of this paper is to present an application of (Dynamic) Bayesian Networks (DBN) to model Local Field Potentials (LFP) data on rats induced to epileptic seizures based on the number of arcs found using threshold analytics. Results showed that DBN analysis captured the dynamic nature of brain connectivity across ictogenesis and a significant correlation with neurobiology derived from pioneering studies employing techniques of pharmacological manipulation, lesion, and modern optogenetics. The arcs evaluated under the proposed approach achieved consistent results based on previous literature, in addition to demonstrating robustness regarding functional connectivity analysis. Moreover, it provided fascinating and novel insights, such as discontinuity between forelimb clonus and generalized tonic-clonic seizure (GTCS) dynamics. Thus, DBN coupled with threshold analytics may be an excellent tool for investigating brain circuitry and their dynamical interplay, both in homeostasis and dysfunction conditions.
Collapse
Affiliation(s)
- Victor Hugo Batista Tsukahara
- Signal Processing Laboratory, School of Engineering of São Carlos, Department of Electrical Engineering, University of São Paulo, São Carlos, Brazil
| | - Jordão Natal de Oliveira Júnior
- Signal Processing Laboratory, School of Engineering of São Carlos, Department of Electrical Engineering, University of São Paulo, São Carlos, Brazil
| | - Vitor Bruno de Oliveira Barth
- Signal Processing Laboratory, School of Engineering of São Carlos, Department of Electrical Engineering, University of São Paulo, São Carlos, Brazil
| | - Jasiara Carla de Oliveira
- Laboratory of Neuroengineering and Neuroscience, Department of Electrical Engineering, Federal University of São João Del-Rei, São João Del Rei, Brazil
| | - Vinicius Rosa Cota
- Laboratory of Neuroengineering and Neuroscience, Department of Electrical Engineering, Federal University of São João Del-Rei, São João Del Rei, Brazil
| | - Carlos Dias Maciel
- Signal Processing Laboratory, School of Engineering of São Carlos, Department of Electrical Engineering, University of São Paulo, São Carlos, Brazil
- *Correspondence: Carlos Dias Maciel
| |
Collapse
|
6
|
Geometry interaction network alignment. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.06.077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
7
|
Zisk AH, Borgheai SB, McLinden J, Deligani RJ, Shahriari Y. Improving longitudinal P300-BCI performance for people with ALS using a data augmentation and jitter correction approach. BRAIN-COMPUTER INTERFACES 2021. [DOI: 10.1080/2326263x.2021.2014678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
- Alyssa Hillary Zisk
- Interdisciplinary Neuroscience Program, University of Rhode Island, Kingston, RI, –USA
| | - Seyyed Bahram Borgheai
- Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Fascitelli Center for Advanced Engineering, –USA Kingston, RI, USA
| | - John McLinden
- Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Fascitelli Center for Advanced Engineering, –USA Kingston, RI, USA
| | - Roohollah Jafari Deligani
- Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Fascitelli Center for Advanced Engineering, –USA Kingston, RI, USA
| | - Yalda Shahriari
- Interdisciplinary Neuroscience Program, University of Rhode Island, Kingston, RI, –USA
- Department of Electrical, Computer, and Biomedical Engineering, University of Rhode Island, Fascitelli Center for Advanced Engineering, –USA Kingston, RI, USA
| |
Collapse
|