54 Hits in 6.4 sec

Protein modeling with hybrid Hidden Markov Model/neural network architectures

P Baldi, Y Chauvin
1995 Proceedings. International Conference on Intelligent Systems for Molecular Biology  
Hidden Markov Models (HMMs) are useful in a number of tasks in computational molecular biology, and in particular to model and align protein families.  ...  Hybrid HMM/Neural Network (NN) architectures attempt to overcome these limitations. In hybrid HMM/NN, the HMM parameters are computed by a NN.  ...  Here we train a hybrid HMM/NN architecture with the following characteristics. The basic model is a HMM with the architecture of Fig. 1 .  ... 
pmid:7584463 fatcat:dpuopwf74fgjzk3ysyfpdcgmjm

A Hybrid System Of Hidden Markov Models And Recurrent Neural Networks For Learning Deterministic Finite State Automata

Pavan K. Rallabandi, Kailash C. Patidar
2015 Zenodo  
) and Hidden Markov models (HMMs).  ...  Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models.  ...  METHODS AND MODELS Neural networks and Hidden Markov models are mostly used in the process of sequence recognition or pattern recognition/classification problems.  ... 
doi:10.5281/zenodo.1109542 fatcat:dt6cqpfsyjhgbar4hwhe734jly

Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey [article]

Chenqing Hua
2022 arXiv   pre-print
Probabilistic Graphical Models (PGMs) have been well-developed in the past years to mathematically model real-world scenarios in compact graphical representations of distributions of variables.  ...  Graph Neural Networks (GNNs) are new inference methods developed in recent years and are attracting growing attention due to their effectiveness and flexibility in solving inference and learning problems  ...  Probabilistic Graphical Models Enhanced Graph Neural Networks In this section, we present our taxonomy of graph neural networks (GNN) with refinements of probabilistic graphical models (PGM) and Markov  ... 
arXiv:2206.06089v1 fatcat:twv6sh5f3ngkrjfiyoger6vuuq

NN approach and its comparison with NN-SVM to beta-barrel prediction

Hassan Kazemian, Syed Adnan Yusuf, Kenneth White, Cedric Maxime Grimaldi
2016 Expert systems with applications  
This paper is concerned with applications of a dual Neural Network (NN) and Support Vector Machine (SVM) to prediction and analysis of beta barrel transmembrane proteins.  ...  The computer simulation results demonstrate a significant impact and a superior performance of NN-SVM tests with a 5 residue overlap for signal protein over NN 2 with and without redundant proteins for  ...  Other researchers used various machine learning techniques, such as Hidden Markov Model (HMM), Bayesian networks, Genetic Algorithm (GA) and SVM (Bigelow, Petrey, Liu, Przybylski and Rost, 2004; Taylor  ... 
doi:10.1016/j.eswa.2016.05.025 fatcat:ddnkct4lzrallbnqfptwwczdu4

Machine Learning Methods for Protein Structure Prediction

Jianlin Cheng, A.N. Tegge, P. Baldi
2008 IEEE Reviews in Biomedical Engineering  
In this paper, we review the development and application of hidden Markov models, neural networks, support vector machines, Bayesian methods, and clustering methods in 1-D, 2-D, 3-D, and 4-D protein structure  ...  Here, we review the development of machine learning methods for protein structure prediction, one of the most fundamental problems in structural biology and bioinformatics.  ...  We focus primarily on unsupervised clustering methods and three supervised machine learning methods including hidden Markov models (HMMs) [21] , [36] , [37] , neural networks [21] , [38] , and support  ... 
doi:10.1109/rbme.2008.2008239 pmid:22274898 fatcat:4zx2zv2tojamtm6bruuuby2kbi

A review of deep learning applications for genomic selection

Osval Antonio Montesinos-López, Abelardo Montesinos-López, Paulino Pérez-Rodríguez, José Alberto Barrón-López, Johannes W. R. Martini, Silvia Berenice Fajardo-Flores, Laura S. Gaytan-Lugo, Pedro C. Santana-Mancilla, José Crossa
2021 BMC Genomics  
with mixed model equations.  ...  The DL methods are nonparametric models providing flexibility to adapt to complicated associations between data and output with the ability to adapt to very complex patterns.  ...  [40] used DL with a convolutional network architecture to predict specificities of DNA-and RNA-binding proteins. Tavanaei et al.  ... 
doi:10.1186/s12864-020-07319-x pmid:33407114 pmcid:PMC7789712 fatcat:xfxkuhsbhfhbzcqqr5xgsxqsou

Template-based prediction of protein structure with deep learning

Haicang Zhang, Yufeng Shen
2020 BMC Genomics  
Template-based modeling, including protein threading and homology modeling, is a popular method for protein tertiary structure prediction.  ...  ThreaderAI formulates the task of aligning query sequence with template as the classical pixel classification problem in computer vision and naturally applies deep residual neural network in prediction  ...  Neural network architecture We employed a deep residual neural network [18] (ResNet) model to predict residue-residue aligning probability matrix.  ... 
doi:10.1186/s12864-020-07249-8 pmid:33372607 fatcat:432lwpfz3jajblvo5boi7h4o34

Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network

Haowen Fang, Amar Shrestha, Ziyi Zhao, Qinru Qiu
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
To address the above issues, and exploit the temporal dynamics of SNNs, we formulate SNN as a network of infinite impulse response (IIR) filters with neuron nonlinearity.  ...  The recently discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications.  ...  Further, this distribution can be used as a surrogate for the learned model. Neural Network MRFs We propose to model the MRF potential functions using NNs.  ... 
doi:10.24963/ijcai.2020/384 dblp:conf/ijcai/XiongR20 fatcat:i6bh3gis35bxvinnp67wsk3rm4

MCP: a Multi-Component learning machine to Predict protein secondary structure [article]

Leila Khalatbari, Mohammad Reza Kangavari, Saeid Hosseini, Hongzhi Yin, Ngai-Man Cheung
2019 arXiv   pre-print
We conduct comprehensive experiments to compare our model with the current state-of-the-art approaches.  ...  Nevertheless, the effectiveness of our unified model an be further enhanced through framework configuration.  ...  A more recent probabilistic approach for protein secondary structure prediction is Hidden Markov Model (HMM) [7, 8] . The HMM graphical models well adapt to one-dimensional sequence processinsg.  ... 
arXiv:1806.06394v4 fatcat:g77q4sottndxnj746ocvlf6s3i

Towards Context-Aware Neural Performance-Score Synchronisation [article]

Ruchit Agrawal
2022 arXiv   pre-print
music performance using a Bayesian Hidden Markov Model.  ...  Methods based on Hidden Markov Models In addition to DTW-based methods, several methods based on Hidden Markov Models (HMMs) have been proposed over the years for the alignment task [Cano et al., 1999  ...  A further advantage of the proposed method over Henkel et al. [2020] is the ability to work with pieces containing several pages of sheet music, as opposed to only one.  ... 
arXiv:2206.00454v1 fatcat:ropvbb4vsva5xid5whtrdca3ee

Protein Function Analysis through Machine Learning

Chris Avery, John Patterson, Tyler Grear, Theodore Frater, Donald J. Jacobs
2022 Biomolecules  
With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function.  ...  We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function.  ...  Neural networks with rigid input structures are sensitive to not only these requirements, but also systems with variable numbers of atoms.  ... 
doi:10.3390/biom12091246 pmid:36139085 fatcat:yx37j5tyubhkrf5unj462mlvnm

Mining Spatio-Temporal Datasets: Relevance, Challenges and Current Research Directions [chapter]

M-Tahar Kechadi, Michela Bertolotto, Filomena Ferrucci, Sergio Di
2009 Data Mining and Knowledge Discovery in Real Life Applications  
The model-based methods are techniques that use some powerful existing models such as Hidden Markov models, neural networks, support vector machines, etc.  ...  For instance the data inputs of a neural network technique are different from the inputs of a support vector machine or a hidden Markov model.  ...  Twenty six chapters cover different special topics with proposed novel ideas. Each chapter gives an overview of the subjects and some of the chapters have cases with offered data mining solutions.  ... 
doi:10.5772/6450 fatcat:2ecajvw3yzbbrennzcplgufcqi

Deep learning in neural networks: An overview

Jürgen Schmidhuber
2015 Neural Networks  
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning.  ...  learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks  ...  In IEEE International Joint Conference on Neural Networks, pages 969-976.Fine, S., Singer, Y., and Tishby, N. (1998). The hierarchical hidden Markov model: Analysis and applications.  ... 
doi:10.1016/j.neunet.2014.09.003 pmid:25462637 fatcat:fniwacdkurh2pgbspkaf6uyhyq

Neural Fields in Visual Computing and Beyond [article]

Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar
2022 arXiv   pre-print
Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physical properties of scenes  ...  In Part I, we focus on techniques in neural fields by identifying common components of neural field methods, including different representations, architectures, forward mapping, and generalization methods  ...  It has been pointed out that positional encoding with Fourier features is equivalent to periodic nonlinearities with one hidden layer as the first neural network layer [BHumRZ21] .  ... 
arXiv:2111.11426v4 fatcat:yteqzbu6gvgdzobnfzuqohix2e


Kun-Mao Chao
2004 Selected Topics in Post-Genome Knowledge Discovery  
, regression models, neural networks.  ...  In addition, Hidden-Markov-Models (HMM) [15] have been developed to work with proteins or with a protein families database such as the PFAM database (Washington University, St. Louis).  ...  As shown above, these two properties of rules are relatively convenient to work with.  ... 
doi:10.1142/9789812794840_0001 fatcat:d2c7nvvc75fwbpmhrak74vhm4u
« Previous Showing results 1 — 15 out of 54 results