An open multiple instance learning framework and its application in drug activity prediction problems

Xin Huang, Shu Ching Chen, Mei-Ling Shyu

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

3 Citations (Scopus)

Abstract

In this paper, a powerful open Multiple Instance Learning (MIL) framework is proposed. Such an open framework is powerful since different sub-methods can be plugged into the framework to generate different specific Multiple Instance Learning algorithms. In our proposed framework, the Multiple Instance Learning problem is first converted to an unconstrained optimization problem by the Minimum Square Error (MSE) criterion, and then the framework can be constructed with an open form of hypothesis and gradient search method. The proposed Multiple Instance Learning framework is applied to the drug activity problems in bioinformatics applications. Specifically, experiments are conducted on the Musk-1 dataset to predict the binding activity of drug molecules. In the experiments, an algorithm with the exponential hypothesis model and the Quasi-Newton method is embedded into our proposed framework. We compare our proposed framework with other existing algorithms and the experimental results show that our proposed framework yields a good accuracy of classification, which demonstrates the feasibility and effectiveness of our framework.

Original languageEnglish (US)
Title of host publicationProceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages53-59
Number of pages7
ISBN (Print)0769519075, 9780769519074
DOIs
StatePublished - 2003
Event3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003 - Bethesda, United States
Duration: Mar 10 2003Mar 12 2003

Other

Other3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003
CountryUnited States
CityBethesda
Period3/10/033/12/03

Fingerprint

Newton-Raphson method
Bioinformatics
Learning algorithms
Experiments
Molecules

Keywords

  • Bioinformatics
  • Machine learning
  • Multiple instance learning
  • Neural networks

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Huang, X., Chen, S. C., & Shyu, M-L. (2003). An open multiple instance learning framework and its application in drug activity prediction problems. In Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003 (pp. 53-59). [1188929] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBE.2003.1188929

An open multiple instance learning framework and its application in drug activity prediction problems. / Huang, Xin; Chen, Shu Ching; Shyu, Mei-Ling.

Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003. Institute of Electrical and Electronics Engineers Inc., 2003. p. 53-59 1188929.

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

Huang, X, Chen, SC & Shyu, M-L 2003, An open multiple instance learning framework and its application in drug activity prediction problems. in Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003., 1188929, Institute of Electrical and Electronics Engineers Inc., pp. 53-59, 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003, Bethesda, United States, 3/10/03. https://doi.org/10.1109/BIBE.2003.1188929
Huang X, Chen SC, Shyu M-L. An open multiple instance learning framework and its application in drug activity prediction problems. In Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003. Institute of Electrical and Electronics Engineers Inc. 2003. p. 53-59. 1188929 https://doi.org/10.1109/BIBE.2003.1188929
Huang, Xin ; Chen, Shu Ching ; Shyu, Mei-Ling. / An open multiple instance learning framework and its application in drug activity prediction problems. Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003. Institute of Electrical and Electronics Engineers Inc., 2003. pp. 53-59
@inproceedings{029be03b677c444d88c571ee145835f1,
title = "An open multiple instance learning framework and its application in drug activity prediction problems",
abstract = "In this paper, a powerful open Multiple Instance Learning (MIL) framework is proposed. Such an open framework is powerful since different sub-methods can be plugged into the framework to generate different specific Multiple Instance Learning algorithms. In our proposed framework, the Multiple Instance Learning problem is first converted to an unconstrained optimization problem by the Minimum Square Error (MSE) criterion, and then the framework can be constructed with an open form of hypothesis and gradient search method. The proposed Multiple Instance Learning framework is applied to the drug activity problems in bioinformatics applications. Specifically, experiments are conducted on the Musk-1 dataset to predict the binding activity of drug molecules. In the experiments, an algorithm with the exponential hypothesis model and the Quasi-Newton method is embedded into our proposed framework. We compare our proposed framework with other existing algorithms and the experimental results show that our proposed framework yields a good accuracy of classification, which demonstrates the feasibility and effectiveness of our framework.",
keywords = "Bioinformatics, Machine learning, Multiple instance learning, Neural networks",
author = "Xin Huang and Chen, {Shu Ching} and Mei-Ling Shyu",
year = "2003",
doi = "10.1109/BIBE.2003.1188929",
language = "English (US)",
isbn = "0769519075",
pages = "53--59",
booktitle = "Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An open multiple instance learning framework and its application in drug activity prediction problems

AU - Huang, Xin

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

PY - 2003

Y1 - 2003

N2 - In this paper, a powerful open Multiple Instance Learning (MIL) framework is proposed. Such an open framework is powerful since different sub-methods can be plugged into the framework to generate different specific Multiple Instance Learning algorithms. In our proposed framework, the Multiple Instance Learning problem is first converted to an unconstrained optimization problem by the Minimum Square Error (MSE) criterion, and then the framework can be constructed with an open form of hypothesis and gradient search method. The proposed Multiple Instance Learning framework is applied to the drug activity problems in bioinformatics applications. Specifically, experiments are conducted on the Musk-1 dataset to predict the binding activity of drug molecules. In the experiments, an algorithm with the exponential hypothesis model and the Quasi-Newton method is embedded into our proposed framework. We compare our proposed framework with other existing algorithms and the experimental results show that our proposed framework yields a good accuracy of classification, which demonstrates the feasibility and effectiveness of our framework.

AB - In this paper, a powerful open Multiple Instance Learning (MIL) framework is proposed. Such an open framework is powerful since different sub-methods can be plugged into the framework to generate different specific Multiple Instance Learning algorithms. In our proposed framework, the Multiple Instance Learning problem is first converted to an unconstrained optimization problem by the Minimum Square Error (MSE) criterion, and then the framework can be constructed with an open form of hypothesis and gradient search method. The proposed Multiple Instance Learning framework is applied to the drug activity problems in bioinformatics applications. Specifically, experiments are conducted on the Musk-1 dataset to predict the binding activity of drug molecules. In the experiments, an algorithm with the exponential hypothesis model and the Quasi-Newton method is embedded into our proposed framework. We compare our proposed framework with other existing algorithms and the experimental results show that our proposed framework yields a good accuracy of classification, which demonstrates the feasibility and effectiveness of our framework.

KW - Bioinformatics

KW - Machine learning

KW - Multiple instance learning

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=84942581392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942581392&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2003.1188929

DO - 10.1109/BIBE.2003.1188929

M3 - Conference contribution

SN - 0769519075

SN - 9780769519074

SP - 53

EP - 59

BT - Proceedings - 3rd IEEE Symposium on BioInformatics and BioEngineering, BIBE 2003

PB - Institute of Electrical and Electronics Engineers Inc.

ER -