Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction
Brain Connectome Networks (BCNs) are defined by brain cortex regions (nodes) interacting with others by electrophysiological co-activation (edges). The experimental prediction of new interactions in BCNs represents a difficult task due to the large number of edges and the complex connectivity patter...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/4/1308 |
| _version_ | 1819025056125157376 |
|---|---|
| author | Enrique Barreiro Cristian R. Munteanu Marcos Gestal Juan Ramón Rabuñal Alejandro Pazos Humberto González-Díaz Julián Dorado |
| author_facet | Enrique Barreiro Cristian R. Munteanu Marcos Gestal Juan Ramón Rabuñal Alejandro Pazos Humberto González-Díaz Julián Dorado |
| author_sort | Enrique Barreiro |
| collection | DOAJ |
| description | Brain Connectome Networks (BCNs) are defined by brain cortex regions (nodes) interacting with others by electrophysiological co-activation (edges). The experimental prediction of new interactions in BCNs represents a difficult task due to the large number of edges and the complex connectivity patterns. Fortunately, we can use another special type of networks to achieve this goal—Artificial Neural Networks (ANNs). Thus, ANNs could use node descriptors such as Shannon Entropies (Sh) to predict node connectivity for large datasets including complex systems such as BCN. However, the training of a high number of ANNs for BCNs is a time-consuming task. In this work, we propose the use of a method to automatically determine which ANN topology is more efficient for the BCN prediction. Since a network (ANN) is used to predict the connectivity in another network (BCN), this method was entitled Net-Net AutoML. The algorithm uses Sh descriptors for pairs of nodes in BCNs and for ANN predictors of BCNs. Therefore, it is able to predict the efficiency of new ANN topologies to predict BCNs. The current study used a set of 500,470 examples from 10 different ANNs to predict node connectivity in BCNs and 20 features. After testing five Machine Learning classifiers, the best classification model to predict the ability of an ANN to evaluate node interactions in BCNs was provided by Random Forest (mean test AUROC of 0.9991 ± 0.0001, 10-fold cross-validation). Net-Net AutoML algorithms based on entropy descriptors may become a useful tool in the design of automatic expert systems to select ANN topologies for complex biological systems. The scripts and dataset for this project are available in an open GitHub repository. |
| first_indexed | 2024-12-21T05:04:36Z |
| format | Article |
| id | doaj.art-fb0f5cd254d34107bfdb28664b795af6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T05:04:36Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fb0f5cd254d34107bfdb28664b795af62022-12-21T19:15:10ZengMDPI AGApplied Sciences2076-34172020-02-01104130810.3390/app10041308app10041308Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome PredictionEnrique Barreiro0Cristian R. Munteanu1Marcos Gestal2Juan Ramón Rabuñal3Alejandro Pazos4Humberto González-Díaz5Julián Dorado6RNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainRNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainRNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainRNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainRNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainDepartment of Organic Chemistry II, University of the Basque Country UPV/EHU, 48940 Leioa, SpainRNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, SpainBrain Connectome Networks (BCNs) are defined by brain cortex regions (nodes) interacting with others by electrophysiological co-activation (edges). The experimental prediction of new interactions in BCNs represents a difficult task due to the large number of edges and the complex connectivity patterns. Fortunately, we can use another special type of networks to achieve this goal—Artificial Neural Networks (ANNs). Thus, ANNs could use node descriptors such as Shannon Entropies (Sh) to predict node connectivity for large datasets including complex systems such as BCN. However, the training of a high number of ANNs for BCNs is a time-consuming task. In this work, we propose the use of a method to automatically determine which ANN topology is more efficient for the BCN prediction. Since a network (ANN) is used to predict the connectivity in another network (BCN), this method was entitled Net-Net AutoML. The algorithm uses Sh descriptors for pairs of nodes in BCNs and for ANN predictors of BCNs. Therefore, it is able to predict the efficiency of new ANN topologies to predict BCNs. The current study used a set of 500,470 examples from 10 different ANNs to predict node connectivity in BCNs and 20 features. After testing five Machine Learning classifiers, the best classification model to predict the ability of an ANN to evaluate node interactions in BCNs was provided by Random Forest (mean test AUROC of 0.9991 ± 0.0001, 10-fold cross-validation). Net-Net AutoML algorithms based on entropy descriptors may become a useful tool in the design of automatic expert systems to select ANN topologies for complex biological systems. The scripts and dataset for this project are available in an open GitHub repository.https://www.mdpi.com/2076-3417/10/4/1308artificial neural networksbrain connectome networksmachine learningnet-net automl |
| spellingShingle | Enrique Barreiro Cristian R. Munteanu Marcos Gestal Juan Ramón Rabuñal Alejandro Pazos Humberto González-Díaz Julián Dorado Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction Applied Sciences artificial neural networks brain connectome networks machine learning net-net automl |
| title | Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction |
| title_full | Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction |
| title_fullStr | Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction |
| title_full_unstemmed | Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction |
| title_short | Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction |
| title_sort | net net automl selection of artificial neural network topology for brain connectome prediction |
| topic | artificial neural networks brain connectome networks machine learning net-net automl |
| url | https://www.mdpi.com/2076-3417/10/4/1308 |
| work_keys_str_mv | AT enriquebarreiro netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT cristianrmunteanu netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT marcosgestal netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT juanramonrabunal netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT alejandropazos netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT humbertogonzalezdiaz netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction AT juliandorado netnetautomlselectionofartificialneuralnetworktopologyforbrainconnectomeprediction |