Molecular Property Prediction Based on a Multichannel Substructure Graph

Wang, Shuang; Li, Zhen; Zhang, Shuguang; Jiang, Mingjian; Wei, Zhiqiang

doi:10.1109/access.2020.2968535

Cited by 22 publications

(13 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This representation was never applied for RI prediction but gives good results for prediction of other molecular properties. Finally, there are more complex methods for using a deep neural network directly with a molecular graph [47][48][49], such as molecular graph convolutional networks. A molecule can be featurized in many ways, as shown above, and each of these ways can be used as input for a model, and the simultaneous use of various representations and machine learning models will give better results than using only one model and representation [42,45,50].…”

Section: Introductionmentioning

confidence: 99%

Gas Chromatographic Retention Index Prediction Using Multimodal Machine Learning

Matyushin

Buryak

2020

IEEE Access

View full text Add to dashboard Cite

Gas chromatography is a widely used method in analytical chemistry and metabolomics. Using gas chromatography, vaporizable compounds can be separated for their further identification. Retention indices are standardized values that depend only on a chemical structure of a compound and on a stationary phase and characterize the retention of a compound in a chromatographic system. Retention index prediction is an important task because databases contain experimental values for a small fraction of all possible molecules, while this information is usable for untargeted analysis. In this work, we consider four machine learning models for retention index prediction: 1D and 2D convolutional neural networks, deep residual multilayer perceptron, and gradient boosting. String representation of the molecule, 2D representation of the chemical structure, molecular descriptors and fingerprints, and molecular descriptors are used as inputs of these four models, respectively, along with information about the stationary phase. The first and third models show the best performance, while the other two perform slightly worse. The models predict retention index values for various standard and semi-standard non-polar stationary phases. Further improvement in performance was achieved using a linear model that uses the results of four previous models as inputs (model stacking). The models were tested using various diverse data sets: flavor compounds, essential oils, metabolomics-related compounds. Achieved accuracy: median absolute and percentage errors -6-40 units and 0.8-2.2%. Accuracy depends on a test data set. The stacking model outperforms previously reported approaches for all test data sets. Parameters of a pre-trained model and some source code are provided.INDEX TERMS Analytical chemistry, convolutional neural network, deep learning, gas chromatography, gradient boosting, residual neural network, retention index, untargeted chemical analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Gas Chromatographic Retention Index Prediction Using Multimodal Machine Learning

Matyushin

Buryak

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A large number of studies have shown that the advantage of deep learning is that it can obtain a robust descriptor of the original data after nonlinear transformation [2], which could promote the model to learn the task-related features from the data. With the establishment of more and more datasets of protein structures and compound-protein interactions, more and more studies have attempted to introduce deep learning methods into both drug discovery [3][4][5] and the predictive task of compound-protein interaction [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

MCN-CPI: Multiscale Convolutional Network for Compound–Protein Interaction Prediction

et al. 2021

Self Cite

View full text Add to dashboard Cite

In the process of drug discovery, identifying the interaction between the protein and the novel compound plays an important role. With the development of technology, deep learning methods have shown excellent performance in various situations. However, the compound–protein interaction is complicated and the features extracted by most deep models are not comprehensive, which limits the performance to a certain extent. In this paper, we proposed a multiscale convolutional network that extracted the local and global features of the protein and the topological feature of the compound using different types of convolutional networks. The results showed that our model obtained the best performance compared with the existing deep learning methods.

show abstract

“…Wang et al . [ 15 ] proposed a multichannel substructure-graph gated recurrent unit architecture for molecular property prediction and used grid search for hyperparameter optimization. Duvenaud et al .…”

Section: Introductionmentioning

confidence: 99%

A general optimization protocol for molecular property prediction using a deep learning network

Chen

Tseng

2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

The key to generating the best deep learning model for predicting molecular property is to test and apply various optimization methods. While individual optimization methods from different past works outside the pharmaceutical domain each succeeded in improving the model performance, better improvement may be achieved when specific combinations of these methods and practices are applied. In this work, three high-performance optimization methods in the literature that have been shown to dramatically improve model performance from other fields are used and discussed, eventually resulting in a general procedure for generating optimized CNN models on different properties of molecules. The three techniques are the dynamic batch size strategy for different enumeration ratios of the SMILES representation of compounds, Bayesian optimization for selecting the hyperparameters of a model and feature learning using chemical features obtained by a feedforward neural network, which are concatenated with the learned molecular feature vector. A total of seven different molecular properties (water solubility, lipophilicity, hydration energy, electronic properties, blood–brain barrier permeability and inhibition) are used. We demonstrate how each of the three techniques can affect the model and how the best model can generally benefit from using Bayesian optimization combined with dynamic batch size tuning.

show abstract

Molecular Property Prediction Based on a Multichannel Substructure Graph

Cited by 22 publications

References 51 publications

Gas Chromatographic Retention Index Prediction Using Multimodal Machine Learning

Gas Chromatographic Retention Index Prediction Using Multimodal Machine Learning

MCN-CPI: Multiscale Convolutional Network for Compound–Protein Interaction Prediction

A general optimization protocol for molecular property prediction using a deep learning network

Contact Info

Product

Resources

About