Filters








221 Hits in 3.1 sec

Protein Sequences Classification Using Modular RBF Neural Networks [chapter]

Dianhui Wang, N.K. Lee, T.S. Dillon, N.J. Hoogenraad
2002 Lecture Notes in Computer Science  
The architecture of the proposed model is a modular RBF neural network with a compensational combination at the transition output layer.  ...  This paper presents a modular neural classifier for protein sequences with improved classification criteria.  ...  The architecture of the proposed model is a modular RBF neural network with a compensational combination at the transition output layer.  ... 
doi:10.1007/3-540-36187-1_42 fatcat:p3zj6ruglzezxcnevfbkjdshce

RMSD Protein Tertiary Structure Prediction with Soft Computing

Mohammad Saber Iraji, Hakimeh Ameri
2016 International Journal of Mathematical Sciences and Computing  
Protein structure and RMSD prediction is very essential. In 2013, the estimated RMSD proteins based on nine features were obtained best results using D2N (Distance to the native).  ...  We presented in This paper proposed approach to reduce predicted RMSD Error Than the actual amount for RMSD and calculate mean absolute error (MAE), through feed forward neural network, adaptive neuro  ...  These RBF neural networks were trained to predict the protein-protein interaction sites.  ... 
doi:10.5815/ijmsc.2016.02.03 fatcat:doxzgszojffolduicexnkfcngu

A Performance Appraisal Of Neural Networks Developed For Response Prediction Across Heterogeneous Domains

H. Soleimanjahi, M. J. Nategh, S. Falahi
2009 Zenodo  
Deciding the numerous parameters involved in designing a competent artificial neural network is a complicated task.  ...  Several neural network architectures with different parameters were developed for each application and the results were compared.  ...  Among several other networks tried for modeling the oncogenicity level, generalized feed forward (GF), modular neural network (MNN), and RBF/GRNN/PNN network yielded acceptable results which are presented  ... 
doi:10.5281/zenodo.1073039 fatcat:fok3pmgzfrekrobqkvjydx22xy

Two-Stage Approach for Protein Superfamily Classification

Swati Vipsita, Santanu Ku. Rath
2013 Computational Biology Journal  
We deal with the problem of protein superfamily classification in which the family membership of newly discovered amino acid sequence is predicted.  ...  In the second stage, recursive orthogonal least square algorithm (ROLSA) is used for training radial basis function network (RBFN) to select optimal number of hidden centres as well as update the output  ...  Zhao et al. in [15] developed a hybrid GA/RBFNN technique which selects features from protein sequences and trains the RBF neural network simultaneously.  ... 
doi:10.1155/2013/898090 fatcat:37lasfpuifflvhtndekjhg36fe

Prediction of Protein Subcellular Multi-localization by Using a Min-Max Modular Support Vector Machine [chapter]

Yang Yang, Bao-Liang Lu
2009 Advances in Soft Computing  
, and learn all of the subproblems by using the min-max modular support vector machine (M 3 -SVM).  ...  Regarding the protein multi-location problem as a multi-label pattern classification problem, we propose a new predicting method for dealing with the protein subcellular localization problem in this paper  ...  Prediction of Protein Subcellular Multi-locations  ... 
doi:10.1007/978-3-642-03156-4_14 fatcat:o7kpzi3k2nhkxl2u5skqn67m2y

Prediction of Protein Subcellular Multi-locations with a Min-Max Modular Support Vector Machine [chapter]

Yang Yang, Bao-Liang Lu
2006 Lecture Notes in Computer Science  
, and learn all of the subproblems by using the min-max modular support vector machine (M 3 -SVM).  ...  Regarding the protein multi-location problem as a multi-label pattern classification problem, we propose a new predicting method for dealing with the protein subcellular localization problem in this paper  ...  Prediction of Protein Subcellular Multi-locations  ... 
doi:10.1007/11760191_98 fatcat:4j35kvia6nhkxen3rerwz5kkl4

DeepProteomics: Protein family classification using Shallow and Deep Networks [article]

Anu Vazhayil, Vinayakumar R, Soman KP
2018 bioRxiv   pre-print
We pass it to recurrent neural network (RNN), long short term memory (LSTM) and gated recurrent unit (GRU) model and compare it by applying trigram with deep neural network and shallow neural network on  ...  The laboratory experiments take a considerable amount of time for annotation of the sequences. This arises the need to use computational techniques to classify proteins based on their functions.  ...  it performance by applying trigram with deep and shallow neural networks for protein family classification.  ... 
doi:10.1101/414631 fatcat:oo4ecaydprdufb4pztcpyogvoe

Utilizing Domain Knowledge in Neural Network Models for Peptide-Allele Binding Prediction

V. Megalooikonomou, D. Kontos, N. DeClaris, P. Cano
2005 2005 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology  
We developed Radial Basis Function Neural Networks (RBFNN) for allele-peptide binding prediction. We explored utilizing prior domain knowledge in order to optimize the prediction.  ...  An overview of Radial Basis Function Neural Networks Radial Basis Function Neural Networks (RBFNNs) are considered a subclass of Modular Neural Networks (MNNs).  ...  We employ the modular neural network (MNN) model based on Radial Basis Functions (RBFNN) which provides the ability to apply different criteria in the modules and easily adapt the network to the domain  ... 
doi:10.1109/cibcb.2005.1594941 fatcat:rzgyn6bzezfrvc42yipzufvhgi

Bioinformatics with soft computing

S. Mitra, Y. Hayashi
2006 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
Genomic sequence, protein structure, gene expression microarrays, and gene regulatory networks are some of the application areas described.  ...  In this paper, we survey the role of different soft computing paradigms, like fuzzy sets (FSs), artificial neural networks (ANNs), evolutionary computation, rough sets (RSes), and support vector machines  ...  An RBF neural network is employed to optimize the classification by tuning the membership functions. D.  ... 
doi:10.1109/tsmcc.2006.879384 fatcat:owim7m6genf6xc7s2bbhjuz7gu

Classifying gene expression data of cancer using classifier ensemble with mutually exclusive features

Sung-Bae Cho, Jungwon Ryu
2002 Proceedings of the IEEE  
Gene expression profiles are just sequences of numbers, and the necessity of tools analyzing them to get useful information has risen significantly.  ...  The explosion of DNA and protein sequence data in public and private databases has been encouraging interdisciplinary research on biology and information technology.  ...  Related Works Many researchers have been working on the ensemble of modular neural networks.  ... 
doi:10.1109/jproc.2002.804682 fatcat:spzlt33aeza6flphxfz2qelx6u

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients [article]

Léon-Charles Tranchevent, Francisco Azuaje, Jagath Chandana Rajapakse
2019 bioRxiv   pre-print
Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.  ...  Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.  ...  Maris and Dr Alvin Farrel for helping us with the clinical data of their cohort. We thank Liyanaarachchi Lekamalage Chamara Kasun for helpful discussion about the DNN models.  ... 
doi:10.1101/750364 fatcat:etwctzgvmfazlnb36js65b3loa

Machine Learning Approaches for the Prioritization of Genomic Variants Impacting Pre-mRNA Splicing

Charlie F Rowlands, Diana Baralle, Jamie M Ellingford
2019 Cells  
A critical comparative approach is then used to describe seven recent machine learning-based splice prediction tools, revealing highly diverse approaches and common caveats.  ...  Despite the advent of next-generation sequencing, allowing a deeper insight into a patient's variant landscape, the ability to characterize variants causing splicing defects has not progressed with the  ...  network GENCODE v24 pre-mRNA transcript sequence for human protein-coding genes Direct encoding of the sequence PR-AUC = 0.98 in correct prediction of splice site location from raw sequence  ... 
doi:10.3390/cells8121513 pmid:31779139 pmcid:PMC6953098 fatcat:4wxj7hv5d5fpndh37yjtx7jcji

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

Léon-Charles Tranchevent, Francisco Azuaje, Jagath C. Rajapakse
2019 BMC Medical Genomics  
Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.  ...  Maris and Dr Alvin Farrel for helping us with the clinical data of their cohort. We thank Dr Liyanaarachchi Lekamalage Chamara Kasun for helpful discussion about the DNN models.  ...  Deep Neural Networks (DNN) are feed forward neural networks with hidden layers, which can be trained to solve classification and regression problems.  ... 
doi:10.1186/s12920-019-0628-y pmid:31856829 pmcid:PMC6923884 fatcat:f5kw4zait5h3fj5qlmsp4mcyza

BRNN-SVM: Increasing the Strength of Domain Signal to Improve Protein Domain Prediction Accuracy [chapter]

Kalsum U., Razib M., Rohayanti Hassan, Hishammuddin Asmuni, Jumail Taliba, Shahreen Kasim
2012 Recurrent Neural Networks and Soft Computing  
Bidirectional Recurrent Neural Network (BRNN) is used to generate secondary structure from alignment of protein sequence in order to highlight the signal of protein domain boundaries.  ...  Previously, Neural Network (NN) is used as a classifier to detect protein domain such as in the work of Armadillo, Biozon, Dompred-DPS, and DOMpro.  ... 
doi:10.5772/36188 fatcat:da6m6wz3bzaujfchcyqv5fwgpm

A review of modularization techniques in artificial neural networks

Mohammed Amer, Tomás Maul
2019 Artificial Intelligence Review  
Modular neural networks (MNNs) are neural networks that embody the concepts and principles of modularity. MNNs adopt a large number of different techniques for achieving modularization.  ...  to emphasise the strengths and weaknesses of different modularization approaches in order to highlight good practices for neural network practitioners.  ...  Neural Network (CNN), in order to enhance classification performance.  ... 
doi:10.1007/s10462-019-09706-7 fatcat:g4xp6dktvncu5dao53dcvoexoa
« Previous Showing results 1 — 15 out of 221 results