Multi-channel PINN: investigating scalable and transferable neural networks for drug discovery
| Autor: | Hyunwhan Joe, Munhwan Lee, Hye Yeon Kim, Hong-Gee Kim |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
0301 basic medicine
Computer science Library and Information Sciences Machine learning computer.software_genre 01 natural sciences Compound–protein interaction lcsh:Chemistry 03 medical and health sciences Deep neural networks Physical and Theoretical Chemistry Sparse matrix Artificial neural network lcsh:T58.5-58.64 business.industry Drug discovery lcsh:Information technology Cheminformatics Computer Graphics and Computer-Aided Design 0104 chemical sciences Computer Science Applications 010404 medicinal & biomolecular chemistry 030104 developmental biology lcsh:QD1-999 Proof of concept Scalability Artificial intelligence business computer Feature learning Classifier (UML) Proteochemometrics Research Article |
| Zdroj: | Journal of Cheminformatics, Vol 11, Iss 1, Pp 1-16 (2019) Journal of Cheminformatics |
| ISSN: | 1758-2946 |
| DOI: | 10.1186/s13321-019-0368-1 |
| Popis: | Analysis of compound–protein interactions (CPIs) has become a crucial prerequisite for drug discovery and drug repositioning. In vitro experiments are commonly used in identifying CPIs, but it is not feasible to discover the molecular and proteomic space only through experimental approaches. Machine learning’s advances in predicting CPIs have made significant contributions to drug discovery. Deep neural networks (DNNs), which have recently been applied to predict CPIs, performed better than other shallow classifiers. However, such techniques commonly require a considerable volume of dense data for each training target. Although the number of publicly available CPI data has grown rapidly, public data is still sparse and has a large number of measurement errors. In this paper, we propose a novel method, Multi-channel PINN, to fully utilize sparse data in terms of representation learning. With representation learning, Multi-channel PINN can utilize three approaches of DNNs which are a classifier, a feature extractor, and an end-to-end learner. Multi-channel PINN can be fed with both low and high levels of representations and incorporates each of them by utilizing all approaches within a single model. To fully utilize sparse public data, we additionally explore the potential of transferring representations from training tasks to test tasks. As a proof of concept, Multi-channel PINN was evaluated on fifteen combinations of feature pairs to investigate how they affect the performance in terms of highest performance, initial performance, and convergence speed. The experimental results obtained indicate that the multi-channel models using protein features performed better than single-channel models or multi-channel models using compound features. Therefore, Multi-channel PINN can be advantageous when used with appropriate representations. Additionally, we pretrained models on a training task then finetuned them on a test task to figure out whether Multi-channel PINN can capture general representations for compounds and proteins. We found that there were significant differences in performance between pretrained models and non-pretrained models. Electronic supplementary material The online version of this article (10.1186/s13321-019-0368-1) contains supplementary material, which is available to authorized users. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |