The role of different sampling methods in improving biological activity prediction using deep belief network

Abstract

Thousands of molecules and descriptors are available for a medicinal chemist thanks to the technological advancements in different branches of chemistry. This fact as well as the correlation between them has raised new problems in quantitative structure activity relationship studies. Proper parameter initialization in statistical modeling has merged as another challenge in recent years. Random selection of parameters leads to poor performance of deep neural network (DNN). In this research, deep belief network (DBN) was applied to initialize DNNs. DBN is composed of some stacks of restricted Boltzmann machine, an energy-based method that requires computing log likelihood gradient for all samples. Three different sampling approaches were suggested to solve this gradient. In this respect, the impact of DBN was applied based on the different sampling approaches mentioned above to initialize the DNN architecture in predicting biological activity of all fifteen Kaggle targets that contain more than 70k molecules. The same as other fields of processing research, the outputs of these models demonstrated significant superiority to that of DNN with random parameters. © 2016 Wiley Periodicals, Inc.

Using Deep Belief Network and Computational Methods to Improve Opioid Receptor Biological Activity Prediction, Novel Agonists and Antagonists, Structural Modeling

“…The designed variant expressed in high yield in Escherichia coli and was water soluble. The variant shared structural and functionally related features with the native human MOR [2], including helical secondary structure and comparable affinity for the antagonist naltrexone . The roles of cholesterol and disulfide bonds on the stability of the receptor variant were also investigated.…”

“…The best networks obtained scores of more than 90 % accuracy in predicting the degree of binding drug molecules to the mentioned receptors. After training the networks, tests were done on how well the systems could be used as an aid in designing candidate drug molecules [2,7]. These ligand characteristics could be total number of atoms, their types etc.…”

Artificial Intelligence in Drug Design: Algorithms, Applications, Challenges and Ethics

“…Ghasemi et al applied DBN using different sampling methods (contrastive divergence, persistent contrastive divergence and fast persistent contrastive divergence) to initiate DNNs for predicting biological activities of Kaggle targets [218]. Although not highly accurate (R 2 of DBN [with contrastive divergence sampling method]-DNN = 0.61], this model outperformed DNN models where parameters would be selected randomly (R 2 = 0.47).…”

A Feature Optimized Deep Learning Model for Clinical Data Mining

“…There are connections between layers, but there are no connections between cells in the layer. Hidden layer units are trained to capture the correlation of higher-order data in the visual layer [15] .…”