NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations
Many drugs can be metabolized by human microbes; the drug metabolites would significantly alter pharmacological effects and result in low therapeutic efficacy for patients. Hence, it is crucial to identify potential drug–microbe associations (DMAs) before the drug administrations. Nevertheless, trad...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2022.846915/full |
| _version_ | 1818238871410835456 |
|---|---|
| author | Bei Zhu Yi Xu Pengcheng Zhao Siu-Ming Yiu Hui Yu Jian-Yu Shi |
| author_facet | Bei Zhu Yi Xu Pengcheng Zhao Siu-Ming Yiu Hui Yu Jian-Yu Shi |
| author_sort | Bei Zhu |
| collection | DOAJ |
| description | Many drugs can be metabolized by human microbes; the drug metabolites would significantly alter pharmacological effects and result in low therapeutic efficacy for patients. Hence, it is crucial to identify potential drug–microbe associations (DMAs) before the drug administrations. Nevertheless, traditional DMA determination cannot be applied in a wide range due to the tremendous number of microbe species, high costs, and the fact that it is time-consuming. Thus, predicting possible DMAs in computer technology is an essential topic. Inspired by other issues addressed by deep learning, we designed a deep learning-based model named Nearest Neighbor Attention Network (NNAN). The proposed model consists of four components, namely, a similarity network constructor, a nearest-neighbor aggregator, a feature attention block, and a predictor. In brief, the similarity block contains a microbe similarity network and a drug similarity network. The nearest-neighbor aggregator generates the embedding representations of drug–microbe pairs by integrating drug neighbors and microbe neighbors of each drug–microbe pair in the network. The feature attention block evaluates the importance of each dimension of drug–microbe pair embedding by a set of ordinary multi-layer neural networks. The predictor is an ordinary fully-connected deep neural network that functions as a binary classifier to distinguish potential DMAs among unlabeled drug–microbe pairs. Several experiments on two benchmark databases are performed to evaluate the performance of NNAN. First, the comparison with state-of-the-art baseline approaches demonstrates the superiority of NNAN under cross-validation in terms of predicting performance. Moreover, the interpretability inspection reveals that a drug tends to associate with a microbe if it finds its top-l most similar neighbors that associate with the microbe. |
| first_indexed | 2024-12-12T12:48:32Z |
| format | Article |
| id | doaj.art-becc6ea88e5c474697624744ba14467a |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-12-12T12:48:32Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-becc6ea88e5c474697624744ba14467a2022-12-22T00:24:03ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2022-04-011310.3389/fmicb.2022.846915846915NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe AssociationsBei Zhu0Yi Xu1Pengcheng Zhao2Siu-Ming Yiu3Hui Yu4Jian-Yu Shi5School of Life Sciences, Northwestern Polytechnical University, Xi’an, ChinaSchool of Life Sciences, Northwestern Polytechnical University, Xi’an, ChinaSchool of Life Sciences, Northwestern Polytechnical University, Xi’an, ChinaDepartment of Computer Science, The University of Hong Kong, Hong Kong, ChinaSchool of Computer Science, Northwestern Polytechnical University, Xi’an, ChinaSchool of Life Sciences, Northwestern Polytechnical University, Xi’an, ChinaMany drugs can be metabolized by human microbes; the drug metabolites would significantly alter pharmacological effects and result in low therapeutic efficacy for patients. Hence, it is crucial to identify potential drug–microbe associations (DMAs) before the drug administrations. Nevertheless, traditional DMA determination cannot be applied in a wide range due to the tremendous number of microbe species, high costs, and the fact that it is time-consuming. Thus, predicting possible DMAs in computer technology is an essential topic. Inspired by other issues addressed by deep learning, we designed a deep learning-based model named Nearest Neighbor Attention Network (NNAN). The proposed model consists of four components, namely, a similarity network constructor, a nearest-neighbor aggregator, a feature attention block, and a predictor. In brief, the similarity block contains a microbe similarity network and a drug similarity network. The nearest-neighbor aggregator generates the embedding representations of drug–microbe pairs by integrating drug neighbors and microbe neighbors of each drug–microbe pair in the network. The feature attention block evaluates the importance of each dimension of drug–microbe pair embedding by a set of ordinary multi-layer neural networks. The predictor is an ordinary fully-connected deep neural network that functions as a binary classifier to distinguish potential DMAs among unlabeled drug–microbe pairs. Several experiments on two benchmark databases are performed to evaluate the performance of NNAN. First, the comparison with state-of-the-art baseline approaches demonstrates the superiority of NNAN under cross-validation in terms of predicting performance. Moreover, the interpretability inspection reveals that a drug tends to associate with a microbe if it finds its top-l most similar neighbors that associate with the microbe.https://www.frontiersin.org/articles/10.3389/fmicb.2022.846915/fulldeep learningbipartite graph networklink predictiondrug–microbe associationattention matrix |
| spellingShingle | Bei Zhu Yi Xu Pengcheng Zhao Siu-Ming Yiu Hui Yu Jian-Yu Shi NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations Frontiers in Microbiology deep learning bipartite graph network link prediction drug–microbe association attention matrix |
| title | NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations |
| title_full | NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations |
| title_fullStr | NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations |
| title_full_unstemmed | NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations |
| title_short | NNAN: Nearest Neighbor Attention Network to Predict Drug–Microbe Associations |
| title_sort | nnan nearest neighbor attention network to predict drug microbe associations |
| topic | deep learning bipartite graph network link prediction drug–microbe association attention matrix |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2022.846915/full |
| work_keys_str_mv | AT beizhu nnannearestneighborattentionnetworktopredictdrugmicrobeassociations AT yixu nnannearestneighborattentionnetworktopredictdrugmicrobeassociations AT pengchengzhao nnannearestneighborattentionnetworktopredictdrugmicrobeassociations AT siumingyiu nnannearestneighborattentionnetworktopredictdrugmicrobeassociations AT huiyu nnannearestneighborattentionnetworktopredictdrugmicrobeassociations AT jianyushi nnannearestneighborattentionnetworktopredictdrugmicrobeassociations |