Classification of some chemical drugs by genetic algorithm and deep neural network hybrid method

Abstract

Summary Deep neural networks (DNN) and genetic algorithm (GA) are gaining importance quickly with many successful applications in the field of science and technology. They are indispensable tool for the numerical solution of difficult problems. It is possible to optimize DNNs using the GA and this combination can be used to classify data. In this article, some drugs are classified by Monte Carlo sampling with combination of GA and DNN due to stochastic nature of the domain, exponential number of variables and small number of chemical species. In addition to the values obtained from the databases of selected drugs, molecular dynamic and ab initio molecular mechanical calculation results were also used. The aim of this study is to generalize the molecular classification with the data obtained from chemical databases as well as molecular docking results by using the combination of deep learning and GA and its usability in drug design. The selected drugs are some agonist and antagonist drugs that bind to dopamine receptors, which are widely studied and well known in the literature. To train the DNN, input datasets were chosen by the GA framework written in pure Python named PyEvolve. Classification of drugs has been analyzed with the focus on orbital energies and docking results. It is possible to use this algorithm in many in silico calculations such as affinity and separation processes. The reliability of the algorithm was tested with the results given in the literature and the expected values were estimated at 93.8%.

Hybrid Genetic Algorithm and CMA-ES Optimization for RNN-Based Chemical Compound Classification

“…Nevertheless, there is a lack of definitive approaches for determining the appropriate number of nearest neighbors, as excessively high or low values of k result in unfavorable false positive or false negative rates, respectively. Karakaplan [23] generalized molecular classification with data obtained from chemical databases and molecular docking by using a combination of deep learning and GA for use in drug design. In their paper, the authors explored the feasibility of using GAs to optimize DNNs, demonstrating that this combination can be used to classify data.…”

“…Current chemical compound classification research encounters several prevailing trends and challenges. First, while several classification strategies [11][12][13][14][15][16][17][18][19][20][21][22][23][24] have been proposed, many encounter issues with low efficiency or low accuracy. This is particularly evident when handling large-scale datasets or complex chemical structures.…”

A deep neural network and random forests driven computer vision framework for identification and prediction of metanil yellow adulteration in turmeric powder

“…Traditionally deep neural network (DNN) is used for large dataset however it has been found suitable for small datasets in recent days. 17 The motivations of using DNN in our case are its remarkable performance possibilities with small dataset as well 18 and better scope of scalability in…”

Clustering Honey Samples with Unsupervised Machine Learning Methods using FTIR Data

“…They stated that this method, in which they used the color and electrical properties of the samples, found the botanical origin correctly with a 5% margin of error. While deep learning is used on large datasets, it has recently been found to be a good tool for classi cation examples containing small datasets [32,33].…”