Computational drug discovery with dyadic positive-unlabeled learning

Yashu Liu, Shuang Qiu, Ping Zhang, Pinghua Gong, Fei Wang, Guoliang Xue, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Computational Drug Discovery, which uses computational techniques to facilitate and improve the drug discovery process, has aroused considerable interests in recent years. Drug Repositioning (DR) and Drug- Drug Interaction (DDI) prediction are two key problems in drug discovery and many computational techniques have been proposed for them in the last decade. Although these two problems have mostly been researched separately in the past, both DR and DDI can be formulated as the problem of detecting positive interactions between data entities (DR is between drug and disease, and DDI is between pairwise drugs). The challenge in both problems is that we can only observe a very small portion of positive interactions. In this paper, we propose a novel framework called Dyadic Positive-Unlabeled learning (DyPU) to solve the problem of detecting positive interactions. DyPU forces positive data pairs to rank higher than the average score of unlabeled data pairs. Moreover, we also derive the dual formulation of the proposed method with the rectifier scoring function and we show that the associated non-trivial proximal operator admits a closed form solution. Extensive experiments are conducted on real drug data sets and the results show that our method achieves superior performance comparing with the state-of-the-art.

Original languageEnglish (US)
Title of host publicationProceedings of the 17th SIAM International Conference on Data Mining, SDM 2017
PublisherSociety for Industrial and Applied Mathematics Publications
Pages45-53
Number of pages9
ISBN (Electronic)9781611974874
StatePublished - Jan 1 2017
Event17th SIAM International Conference on Data Mining, SDM 2017 - Houston, United States
Duration: Apr 27 2017Apr 29 2017

Other

Other17th SIAM International Conference on Data Mining, SDM 2017
CountryUnited States
CityHouston
Period4/27/174/29/17

Fingerprint

Drug interactions
Drug Discovery
Experiments

Keywords

  • DDI prediction
  • Drug repositioning
  • Dyadic PU learning

ASJC Scopus subject areas

  • Software
  • Computer Science Applications

Cite this

Liu, Y., Qiu, S., Zhang, P., Gong, P., Wang, F., Xue, G., & Ye, J. (2017). Computational drug discovery with dyadic positive-unlabeled learning. In Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017 (pp. 45-53). Society for Industrial and Applied Mathematics Publications.

Computational drug discovery with dyadic positive-unlabeled learning. / Liu, Yashu; Qiu, Shuang; Zhang, Ping; Gong, Pinghua; Wang, Fei; Xue, Guoliang; Ye, Jieping.

Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, 2017. p. 45-53.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, Y, Qiu, S, Zhang, P, Gong, P, Wang, F, Xue, G & Ye, J 2017, Computational drug discovery with dyadic positive-unlabeled learning. in Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, pp. 45-53, 17th SIAM International Conference on Data Mining, SDM 2017, Houston, United States, 4/27/17.
Liu Y, Qiu S, Zhang P, Gong P, Wang F, Xue G et al. Computational drug discovery with dyadic positive-unlabeled learning. In Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications. 2017. p. 45-53
Liu, Yashu ; Qiu, Shuang ; Zhang, Ping ; Gong, Pinghua ; Wang, Fei ; Xue, Guoliang ; Ye, Jieping. / Computational drug discovery with dyadic positive-unlabeled learning. Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017. Society for Industrial and Applied Mathematics Publications, 2017. pp. 45-53
@inproceedings{40003c91da634cc3aea30a295c88ae51,
title = "Computational drug discovery with dyadic positive-unlabeled learning",
abstract = "Computational Drug Discovery, which uses computational techniques to facilitate and improve the drug discovery process, has aroused considerable interests in recent years. Drug Repositioning (DR) and Drug- Drug Interaction (DDI) prediction are two key problems in drug discovery and many computational techniques have been proposed for them in the last decade. Although these two problems have mostly been researched separately in the past, both DR and DDI can be formulated as the problem of detecting positive interactions between data entities (DR is between drug and disease, and DDI is between pairwise drugs). The challenge in both problems is that we can only observe a very small portion of positive interactions. In this paper, we propose a novel framework called Dyadic Positive-Unlabeled learning (DyPU) to solve the problem of detecting positive interactions. DyPU forces positive data pairs to rank higher than the average score of unlabeled data pairs. Moreover, we also derive the dual formulation of the proposed method with the rectifier scoring function and we show that the associated non-trivial proximal operator admits a closed form solution. Extensive experiments are conducted on real drug data sets and the results show that our method achieves superior performance comparing with the state-of-the-art.",
keywords = "DDI prediction, Drug repositioning, Dyadic PU learning",
author = "Yashu Liu and Shuang Qiu and Ping Zhang and Pinghua Gong and Fei Wang and Guoliang Xue and Jieping Ye",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
pages = "45--53",
booktitle = "Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017",
publisher = "Society for Industrial and Applied Mathematics Publications",
address = "United States",

}

TY - GEN

T1 - Computational drug discovery with dyadic positive-unlabeled learning

AU - Liu, Yashu

AU - Qiu, Shuang

AU - Zhang, Ping

AU - Gong, Pinghua

AU - Wang, Fei

AU - Xue, Guoliang

AU - Ye, Jieping

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Computational Drug Discovery, which uses computational techniques to facilitate and improve the drug discovery process, has aroused considerable interests in recent years. Drug Repositioning (DR) and Drug- Drug Interaction (DDI) prediction are two key problems in drug discovery and many computational techniques have been proposed for them in the last decade. Although these two problems have mostly been researched separately in the past, both DR and DDI can be formulated as the problem of detecting positive interactions between data entities (DR is between drug and disease, and DDI is between pairwise drugs). The challenge in both problems is that we can only observe a very small portion of positive interactions. In this paper, we propose a novel framework called Dyadic Positive-Unlabeled learning (DyPU) to solve the problem of detecting positive interactions. DyPU forces positive data pairs to rank higher than the average score of unlabeled data pairs. Moreover, we also derive the dual formulation of the proposed method with the rectifier scoring function and we show that the associated non-trivial proximal operator admits a closed form solution. Extensive experiments are conducted on real drug data sets and the results show that our method achieves superior performance comparing with the state-of-the-art.

AB - Computational Drug Discovery, which uses computational techniques to facilitate and improve the drug discovery process, has aroused considerable interests in recent years. Drug Repositioning (DR) and Drug- Drug Interaction (DDI) prediction are two key problems in drug discovery and many computational techniques have been proposed for them in the last decade. Although these two problems have mostly been researched separately in the past, both DR and DDI can be formulated as the problem of detecting positive interactions between data entities (DR is between drug and disease, and DDI is between pairwise drugs). The challenge in both problems is that we can only observe a very small portion of positive interactions. In this paper, we propose a novel framework called Dyadic Positive-Unlabeled learning (DyPU) to solve the problem of detecting positive interactions. DyPU forces positive data pairs to rank higher than the average score of unlabeled data pairs. Moreover, we also derive the dual formulation of the proposed method with the rectifier scoring function and we show that the associated non-trivial proximal operator admits a closed form solution. Extensive experiments are conducted on real drug data sets and the results show that our method achieves superior performance comparing with the state-of-the-art.

KW - DDI prediction

KW - Drug repositioning

KW - Dyadic PU learning

UR - http://www.scopus.com/inward/record.url?scp=85027865441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027865441&partnerID=8YFLogxK

M3 - Conference contribution

SP - 45

EP - 53

BT - Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017

PB - Society for Industrial and Applied Mathematics Publications

ER -