Improving quantitative structure–activity relationship models using Artificial Neural Networks trained with dropout

Mendenhall, Jeffrey L.; Meiler, Jens

doi:10.1007/s10822-016-9895-2

Cited by 49 publications

(75 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…QSAR methods have been used successfully on various drug targets such as carbonic anhydrase [252–253], thrombin [254–255] and renin [256]. Different machine learning techniques have also been used in constructing QSAR models [257–259]. In classical or 2D QSAR methods, the biological activity is correlated to physical and chemical properties such as electronic hydrophobic and steric features of compounds [260].…”

Section: Reviewmentioning

confidence: 99%

Computational methods in drug discovery

Leelananda

Lindert

2016

Beilstein J. Org. Chem.

472

309

View full text Add to dashboard Cite

The process for drug discovery and development is challenging, time consuming and expensive. Computer-aided drug discovery (CADD) tools can act as a virtual shortcut, assisting in the expedition of this long process and potentially reducing the cost of research and development. Today CADD has become an effective and indispensable tool in therapeutic development. The human genome project has made available a substantial amount of sequence data that can be used in various drug discovery projects. Additionally, increasing knowledge of biological structures, as well as increasing computer power have made it possible to use computational methods effectively in various phases of the drug discovery and development pipeline. The importance of in silico tools is greater than ever before and has advanced pharmaceutical research. Here we present an overview of computational methods used in different facets of drug discovery and highlight some of the recent successes. In this review, both structure-based and ligand-based drug discovery methods are discussed. Advances in virtual high-throughput screening, protein structure prediction methods, protein–ligand docking, pharmacophore modeling and QSAR techniques are reviewed.

show abstract

Section: Reviewmentioning

confidence: 99%

Computational methods in drug discovery

Leelananda

Lindert

2016

Beilstein J. Org. Chem.

472

309

View full text Add to dashboard Cite

show abstract

“…To prevent overfitting problems, dropout technology [39,40] is used on the fully connected layer. Dropout is used to make neurons stop working with a certain probability in each training batch, which means it makes the values of activation function turn to be zero with the probability.…”

Section: Dropoutmentioning

confidence: 99%

Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors

Wang

Tian

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

Near-infrared (NIR) spectral sensors can deliver the spectral response of light absorbed by materials. Data analysis technology based on NIR sensors has been a useful tool for quality identification. In this paper, an improved deep convolutional neural network (CNN) with batch normalization and MSRA (Microsoft Research Asia) initialization is proposed to discriminate the tobacco cultivation regions using data collected from NIR sensors. The network structure is created with six convolutional layers and three full connection layers, and the learning rate is controlled by exponential attenuation method. One-dimensional kernel is applied as the convolution kernel to extract features. Meanwhile, the methods of L2 regularization and dropout are used to avoid the overfitting problem, which improve the generalization ability of the network. Experimental results show that the proposed deep network structure can effectively extract the complex characteristics inside the spectrum, which proves that it has excellent recognition performance on tobacco cultivation region discrimination, and it also demonstrates that the deep CNN is more suitable for information mining and analysis of big data.

show abstract

“…Deep learning can extract the high-level hidden features of the input very well and get good performance on many tasks such as image classification, face and speech recognition [29], molecular function prediction [34,14], protein secondary [40] and tertiary structure prediction [2], protein contact prediction [13]. Inspired by the success of deep learning and the importance of secondary structure for pre-miRNA identification, we propose an end-to-end deep learning method using the given input sequence and its secondary structure.…”

Section: Introductionmentioning

confidence: 99%

Precursor microRNA Identification Using Deep Convolutional Neural Networks

Golkov

et al. 2018

Preprint

View full text Add to dashboard Cite

Precursor microRNA (pre-miRNA) identification is the basis for identifying microRNAs (miRNAs), which have important roles in post-transcriptional regulation of gene expression. In this paper, we propose a deep learning method to identify whether a small non-coding RNA sequence is a pre-miRNA or not. We outperform state-ofthe-art methods on three benchmark datasets, namely the human, cross-species, and new datasets. The key of our method is to use a matrix representation of predicted secondary structure as input to a 2D convolutional network. The neural network extracts optimized features automatically instead of using a large number of handcrafted features as most existing methods do. Code and results are available at https://github.com/peace195/ miRNA-identification-conv2D. * Work done as an exchange student of ERASMUS+ Key Action 1 program between HUST and TUM.

show abstract

Improving quantitative structure–activity relationship models using Artificial Neural Networks trained with dropout

Cited by 49 publications

References 32 publications

Computational methods in drug discovery

Computational methods in drug discovery

Improved Deep CNN with Parameter Initialization for Data Analysis of Near-Infrared Spectroscopy Sensors

Precursor microRNA Identification Using Deep Convolutional Neural Networks

Contact Info

Product

Resources

About