Selection of Potential Ligands for TRPM8 Using Deep Neural Networks and Intermolecular Docking by the "AUTODOCK" Software

The introduction of new topologies and training procedures to deep neural networks has solicited a renewed interest in the field of neural computation. The use of deep structures has significantly improved the state of the art in many applications, such as computer vision, speech and text processing, medical applications, and IoT (Internet of Things). The probability of a successful outcome from a neural network is linked to selection of an appropriate network architecture and training algorithm. Accordingly, much of the recent research on neural networks is devoted to the study and proposal of novel architectures, including solutions tailored to specific problems. The papers of this Special Issue make significant contributions to the above-mentioned fields by merging theoretical aspects and relevant applications. Twelve papers are collected in the issue, addressing many relevant aspects of the topic.

Download Full-text

Guided Dropout

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33014065 ◽

2019 ◽

Vol 33 ◽

pp. 4065-4072 ◽

Cited By ~ 4

Author(s):

Rohit Keshari ◽

Richa Singh ◽

Mayank Vatsa

Keyword(s):

Neural Network ◽

Neural Networks ◽

Experimental Evaluation ◽

Deep Neural Network ◽

Deep Neural Networks ◽

Multiple Datasets ◽

Selection Of

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes random drop of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the traditional dropout. In this research, we propose “guided dropout” for training deep neural network which drop nodes by measuring the strength of each node. We also demonstrate that conventional dropout is a specific case of the proposed guided dropout. Experimental evaluation on multiple datasets including MNIST, CIFAR10, CIFAR100, SVHN, and Tiny ImageNet demonstrate the efficacy of the proposed guided dropout.

Download Full-text

Stochastic Selection of Activation Layers for Convolutional Neural Networks

Sensors ◽

10.3390/s20061626 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1626 ◽

Cited By ~ 1

Author(s):

Loris Nanni ◽

Alessandra Lumini ◽

Stefano Ghidoni ◽

Gianluca Maguolo

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Deep Neural Networks ◽

Activation Function ◽

Computational Time ◽

Activation Functions ◽

Practical Applications ◽

Functional Blocks ◽

Stochastic Selection ◽

Selection Of

In recent years, the field of deep learning has achieved considerable success in pattern recognition, image segmentation, and many other classification fields. There are many studies and practical applications of deep learning on images, video, or text classification. Activation functions play a crucial role in discriminative capabilities of the deep neural networks and the design of new “static” or “dynamic” activation functions is an active area of research. The main difference between “static” and “dynamic” functions is that the first class of activations considers all the neurons and layers as identical, while the second class learns parameters of the activation function independently for each layer or even each neuron. Although the “dynamic” activation functions perform better in some applications, the increased number of trainable parameters requires more computational time and can lead to overfitting. In this work, we propose a mixture of “static” and “dynamic” activation functions, which are stochastically selected at each layer. Our idea for model design is based on a method for changing some layers along the lines of different functional blocks of the best performing CNN models, with the aim of designing new models to be used as stand-alone networks or as a component of an ensemble. We propose to replace each activation layer of a CNN (usually a ReLU layer) by a different activation function stochastically drawn from a set of activation functions: in this way, the resulting CNN has a different set of activation function layers.

Download Full-text

Survey and Evaluation of Neural 3D Shape Classification Approaches

10.36227/techrxiv.14447250 ◽

2021 ◽

Author(s):

Martin Mirbauer ◽

Miroslav Krabec ◽

Jaroslav Křivánek ◽

Elena Šikudová

Keyword(s):

Neural Networks ◽

Network Architecture ◽

Deep Neural Networks ◽

Shape Classification ◽

3D Shape ◽

3D Objects ◽

Multiple Neural Networks ◽

Survey And Evaluation ◽

Selection Of

<div> <div> <div> <p>Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on three 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being generally unable to reach the accuracies reported in the original papers, we can compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. </p> </div> </div> </div>

Download Full-text

Survey and Evaluation of Neural 3D Shape Classification Approaches

10.36227/techrxiv.14447250.v1 ◽

2021 ◽

Author(s):

Martin Mirbauer ◽

Miroslav Krabec ◽

Jaroslav Křivánek ◽

Elena Šikudová

Keyword(s):

Neural Networks ◽

Network Architecture ◽

Deep Neural Networks ◽

Shape Classification ◽

3D Shape ◽

3D Objects ◽

Multiple Neural Networks ◽

Survey And Evaluation ◽

Selection Of

<div> <div> <div> <p>Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on three 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being generally unable to reach the accuracies reported in the original papers, we can compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. </p> </div> </div> </div>

Download Full-text

Selection of potential ligands for TRPM8 using deep neural networks and intermolecular docking

Bulletin physiology and pathology of respiration ◽

10.36604/1998-5029-2021-80-26-33 ◽

2021 ◽

pp. 26-33

Author(s):

E. A. Borodin ◽

A. P. Chupalov ◽

P. D. Timkin ◽

E. A. Timofeev ◽

N. Yu. Leusova

Keyword(s):

Neural Network ◽

Neural Networks ◽

Binding Energy ◽

In Silico ◽

Deep Neural Networks ◽

Learning Tools ◽

Computing Device ◽

Technical Problems ◽

Selection Of ◽

In Silico Methods

Introduction. TRPM8 has been implicated in the development of bronchial hypersensitivity to cold and is considered a potential target for computer-generated drugs.Aim. Development of a strategy for the selection of ligands for TRPM8 by in silico methods.Materials and methods. Using machine learning tools based on deep neural networks and further verification by intermolecular docking, a strategy has been proposed for predicting potential ligands for TRPM8, which consists in using a neural network to screen out potential drug candidates and thereby reduce the list of candidate ligands for verification using AutoDock program, which allows assessing the affinity of a protein for a ligand by the minimum binding energy and identifying possible conformations of a ligand upon binding to certain centers (amino acid residues) of a protein. The latter were used: Y745 (tyrosine 745 is a critical center for TRPM8), R1008 (phenylalanine 1008) and L1009 (alanine 1009).Results. Of the 10 potential ligands predicted by the neural network, eight showed a high minimum binding energy and a greater number of conformations compared to the classic TRPM8 ligand, menthol, when verified by the AutoDock program. The two predicted ligands did not show the ability to interact with TRPM8, which may be due to insufficient allocated memory of the computing device for successful docking or other technical problems.Conclusion. The proposed strategy is universal; it will accelerate the search for ligands for various proteins and will facilitate the accelerated search for potential drugs by in silico methods.

Download Full-text