Active learning framework of informative p53 cancer rescue mutants

Haijin Wang; Ruhui Shen; Haichao Wang; Haohan Wang

doi:10.1109/AEEICB.2017.7972384

Active learning framework of informative p53 cancer rescue mutants

Haijin Wang, Ruhui Shen, Haichao Wang, Haohan Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

P53 mutants are closely related to humor tumors. Unfortunately, in vitro testing of all possible mutation combinations to determine their cancer rescue effects is infeasible due to time and expense. Therefore, it would be very desirable to have a computer model to run in silico experiments. In this paper, we propose a framework for active learning that can be used in any membership model active learning which does not consider predicted class as a criterion. Because the number of positive instances is much more than the number of negative instances. An active learning strategy is proposed to dynamically balance the number of positive and negative instances. As a result, we get a relatively balanced training set relative to both positive and negative instances, which leads to results showing good performance relative to high precision as well as high recall.

Original language	English (US)
Title of host publication	Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017
Editors	P. L.N. Ramesh, M. Moorthi
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	61-66
Number of pages	6
ISBN (Electronic)	9781509054343
DOIs	https://doi.org/10.1109/AEEICB.2017.7972384
State	Published - Jul 7 2017
Externally published	Yes
Event	3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017 - Chennai, India Duration: Feb 27 2017 → Feb 28 2017

Conference

Conference	3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017
Country/Territory	India
City	Chennai
Period	2/27/17 → 2/28/17

Keywords

Dynamically balance
Machine learning
Negative instances
P53
Positive instances

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Information Systems
Electrical and Electronic Engineering
Health Informatics
Instrumentation

Online availability

10.1109/AEEICB.2017.7972384

Library availability

Discover UIUC Full Text

Cite this

Wang, H., Shen, R., Wang, H., & Wang, H. (2017). Active learning framework of informative p53 cancer rescue mutants. In P. L. N. Ramesh, & M. Moorthi (Eds.), Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017 (pp. 61-66). Article 7972384 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AEEICB.2017.7972384

Active learning framework of informative p53 cancer rescue mutants. / Wang, Haijin; Shen, Ruhui; Wang, Haichao et al.
Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017. ed. / P. L.N. Ramesh; M. Moorthi. Institute of Electrical and Electronics Engineers Inc., 2017. p. 61-66 7972384.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wang, H, Shen, R, Wang, H & Wang, H 2017, Active learning framework of informative p53 cancer rescue mutants. in PLN Ramesh & M Moorthi (eds), Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017., 7972384, Institute of Electrical and Electronics Engineers Inc., pp. 61-66, 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017, Chennai, India, 2/27/17. https://doi.org/10.1109/AEEICB.2017.7972384

Wang H, Shen R, Wang H, Wang H. Active learning framework of informative p53 cancer rescue mutants. In Ramesh PLN, Moorthi M, editors, Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 61-66. 7972384 doi: 10.1109/AEEICB.2017.7972384

Wang, Haijin ; Shen, Ruhui ; Wang, Haichao et al. / Active learning framework of informative p53 cancer rescue mutants. Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017. editor / P. L.N. Ramesh ; M. Moorthi. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 61-66

@inproceedings{8f0ab42c8e7140338e232182f42ceb17,

title = "Active learning framework of informative p53 cancer rescue mutants",

abstract = "P53 mutants are closely related to humor tumors. Unfortunately, in vitro testing of all possible mutation combinations to determine their cancer rescue effects is infeasible due to time and expense. Therefore, it would be very desirable to have a computer model to run in silico experiments. In this paper, we propose a framework for active learning that can be used in any membership model active learning which does not consider predicted class as a criterion. Because the number of positive instances is much more than the number of negative instances. An active learning strategy is proposed to dynamically balance the number of positive and negative instances. As a result, we get a relatively balanced training set relative to both positive and negative instances, which leads to results showing good performance relative to high precision as well as high recall.",

keywords = "Dynamically balance, Machine learning, Negative instances, P53, Positive instances",

author = "Haijin Wang and Ruhui Shen and Haichao Wang and Haohan Wang",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017 ; Conference date: 27-02-2017 Through 28-02-2017",

year = "2017",

month = jul,

day = "7",

doi = "10.1109/AEEICB.2017.7972384",

language = "English (US)",

pages = "61--66",

editor = "Ramesh, {P. L.N.} and M. Moorthi",

booktitle = "Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

TY - GEN

T1 - Active learning framework of informative p53 cancer rescue mutants

AU - Wang, Haijin

AU - Shen, Ruhui

AU - Wang, Haichao

AU - Wang, Haohan

PY - 2017/7/7

Y1 - 2017/7/7

N2 - P53 mutants are closely related to humor tumors. Unfortunately, in vitro testing of all possible mutation combinations to determine their cancer rescue effects is infeasible due to time and expense. Therefore, it would be very desirable to have a computer model to run in silico experiments. In this paper, we propose a framework for active learning that can be used in any membership model active learning which does not consider predicted class as a criterion. Because the number of positive instances is much more than the number of negative instances. An active learning strategy is proposed to dynamically balance the number of positive and negative instances. As a result, we get a relatively balanced training set relative to both positive and negative instances, which leads to results showing good performance relative to high precision as well as high recall.

AB - P53 mutants are closely related to humor tumors. Unfortunately, in vitro testing of all possible mutation combinations to determine their cancer rescue effects is infeasible due to time and expense. Therefore, it would be very desirable to have a computer model to run in silico experiments. In this paper, we propose a framework for active learning that can be used in any membership model active learning which does not consider predicted class as a criterion. Because the number of positive instances is much more than the number of negative instances. An active learning strategy is proposed to dynamically balance the number of positive and negative instances. As a result, we get a relatively balanced training set relative to both positive and negative instances, which leads to results showing good performance relative to high precision as well as high recall.

KW - Dynamically balance

KW - Machine learning

KW - Negative instances

KW - P53

KW - Positive instances

UR - http://www.scopus.com/inward/record.url?scp=85026659756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026659756&partnerID=8YFLogxK

U2 - 10.1109/AEEICB.2017.7972384

DO - 10.1109/AEEICB.2017.7972384

M3 - Conference contribution

AN - SCOPUS:85026659756

SP - 61

EP - 66

BT - Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017

A2 - Ramesh, P. L.N.

A2 - Moorthi, M.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017

Y2 - 27 February 2017 through 28 February 2017

ER -

Active learning framework of informative p53 cancer rescue mutants

Abstract

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this