Welcome to the InfoSci Platform
Reference Hub2
Anatomical Therapeutic Chemical Classification (ATC) With Multi-Label Learners and Deep Features

Anatomical Therapeutic Chemical Classification (ATC) With Multi-Label Learners and Deep Features

Loris Nanni, Sheryl Brahnam, Gianluca Maguolo
Copyright: © 2020 |Volume: 9 |Issue: 3 |Pages: 14
ISSN: 1947-928X|EISSN: 1947-9298|EISBN13: 9781799806677|DOI: 10.4018/IJNCR.2020070102
Cite Article Cite Article

MLA

Nanni, Loris, et al. "Anatomical Therapeutic Chemical Classification (ATC) With Multi-Label Learners and Deep Features." IJNCR vol.9, no.3 2020: pp.16-29. http://doi.org/10.4018/IJNCR.2020070102

APA

Nanni, L., Brahnam, S., & Maguolo, G. (2020). Anatomical Therapeutic Chemical Classification (ATC) With Multi-Label Learners and Deep Features. International Journal of Natural Computing Research (IJNCR), 9(3), 16-29. http://doi.org/10.4018/IJNCR.2020070102

Chicago

Nanni, Loris, Sheryl Brahnam, and Gianluca Maguolo. "Anatomical Therapeutic Chemical Classification (ATC) With Multi-Label Learners and Deep Features," International Journal of Natural Computing Research (IJNCR) 9, no.3: 16-29. http://doi.org/10.4018/IJNCR.2020070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Automatic anatomical therapeutic chemical (ATC) classification predicts an unknown compound's therapeutic and chemical characteristics. Predicting the organs/systems an unidentified compound will act on has the potential of expediting drug development and research. That a given compound can affect multiple organs/systems makes automatic ATC classification a complex problem. In this paper, the authors experimentally develop a multi-label ensemble for ATC prediction. The proposed approach extracts a 1D feature vector based on a compound's chemical-chemical interaction and its structural and fingerprint similarities to other compounds, as defined by the ATC coding system. This 1D vector is reshaped into 2D matrices and fed into seven pre-trained convolutional neural networks (CNN). A bidirectional long short-term memory network (BiLSTM) is trained on the 1D vector. Features extracted from both deep learners are then trained on multi-label classifiers, with results fused. The best system proposed here is shown to outperform other methods reported in the literature.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.