ABSTRACT
With the development of artificial intelligence, the project of using deep learning for molecular property prediction has gained much attention. The current widely used molecular description methods, such as Morgan molecular fingerprinting, need further improvement in their molecular description capability, and the current networks widely used for molecular property classification, such as feed forward neural networks (FFN), also have the problem of insufficient molecular feature extraction capability. To address the above problems, we propose the 1DCNN+Self-Attention model, which is applied to the molecular hidden fingerprint obtained by the Directed Message Passing Neural Network (D-MPNN) model processing. Unlike the traditional molecular description methods, this molecular hidden fingerprint is a bond-centered molecular description method, which has shown better molecular description ability after experiments. 1DCNN+Self-Attention model can extract data features better than FFN model and improve the classification effect. The proposed method was validated on four datasets, BBBP (Blood-brain barrier penetration) dataset, ClinTox dataset, SIDER (Side Effect Resource ) dataset, and Tox21 (Toxicology in the 21st Century) dataset, and the AUC index was applied as the network classification ability evaluation index, and the final experimental results showed that the results achieved by the classification method in this paper were better than the classification methods adopted in previous experiments.
Supplemental Material
Available for Download
- Duvenaud, D. K.; Maclaurin, D.; Iparraguirre, J.; Bombarell, R.;Hirzel, T.; Aspuru-Guzik, A.; Adams, R. P. Convolutional Networks onGraphs for Learning Molecular Fingerprints. Advances in Neural Information Processing Systems 2015, 2224−2232.Google Scholar
- Wu, Z.; Ramsundar, B.; Feinberg, E.; Gomes, J.; Geniesse, C.; Pappu, A. S.; Leswing, K.; Pande, V. MoleculeNet: A Benchmark for Molecular Machine Learning. Chem. Sci. 2018, 9, 513−530.Google ScholarCross Ref
- Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E. Neural Message Passing for Quantum Chemistry. Proceedings of the 34th International Conference on Machine Learning 2017, 70, 1263−1272.Google ScholarDigital Library
- Coley, C. W.; Barzilay, R.; Green, W. H.; Jaakkola, T. S.; Jensen, K. F. Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction. J. Chem. Inf. Model. 2017, 57, 1757−1772.Google ScholarCross Ref
- Mayr, A.; Klambauer, G.; Unterthiner, T.; Steijaert, M.; Wegner, J. K.; Ceulemans, H.; Clevert, D.-A.; Hochreiter, S. Large-Scale Comparison of Machine Learning Methods for Drug Target Prediction on ChEMBL. Chem. Sci. 2018, 9, 5441−5451.Google ScholarCross Ref
- Yang K , Swanson K , Jin W , Analyzing Learned Molecular Representations for Property Prediction[J]. Journal of Chemical Information and Modeling, 2019, 59(8).Google ScholarCross Ref
- Stokes J M , Yang K , Swanson K , A Deep Learning Approach to Antibiotic Discovery[J]. Cell, 2020, 180(4): pp. 688-702.e13.Google ScholarCross Ref
- J.H. Zhu, J.H. Pei, Y. Zhao, Research on convolution kernel initialization method in convolutional neural network (CNN) training, Signal Process. 35 (4) , 2019, 641–648.Google Scholar
- Shaw P , Uszkoreit J , Vaswani A . Self-Attention with Relative Position Representations[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). 2018.Google Scholar
Recommendations
DEGAT: A Graph Neural Network Algorithm Based on Dynamic Attention Mechanism for Molecular Property Prediction
ICBET '23: Proceedings of the 2023 13th International Conference on Biomedical Engineering and TechnologyAccurately predicting the physicochemical, biophysical, and physiological properties of molecules plays a vital role in drug design and drug discovery, and it is also one of the fundamental tasks in computer-aided drug design(CADD). In recent years, ...
Stacking Multiple Molecular Fingerprints for Improving Ligand-Based Virtual Screening
Intelligent Computing Theories and ApplicationAbstractCurrently, most of machine learning based virtual screening methods use a molecular fingerprint. There are numerous fingerprints proposed for various aims, and it is known that the best fingerprint is different for each target, and it is difficult ...
Molecular signatures-based prediction of enzyme promiscuity
Motivation: Enzyme promiscuity, a property with practical applications in biotechnology and synthetic biology, has been related to the evolvability of enzymes. At the molecular level, several structural mechanisms have been linked to enzyme ...
Comments