Conformal Predictors for Compound Activity Prediction

Paolo Toccaceli; Ilia Nouretdinov; Alexander Gammerman

doi:10.1007/978-3-319-33395-3_4

Conformal Predictors for Compound Activity Prediction

Paolo Toccaceli, Ilia Nouretdinov, Alexander Gammerman

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

Abstract

The paper presents an application of Conformal Predictors to a chemoinformatics problem of identifying activities of chemical compounds. The paper addresses some specific challenges of this domain: a large number of compounds (training examples), high-dimensionality of feature space, sparseness and a strong class imbalance. A variant of conformal predictors called Inductive Mondrian Conformal Predictor is applied to deal with these challenges. Results are presented for several non-conformity measures (NCM) extracted from underlying algorithms and different kernels. A number of performance measures are used in order to demonstrate the flexibility of Inductive Mondrian Conformal Predictors in dealing with such a complex set of data.

Original language	English
Title of host publication	Conformal and Probabilistic Prediction with Applications
Subtitle of host publication	5th International Symposium, COPA 2016 Madrid, Spain, April 20–22, 2016 Proceedings
Publisher	Springer
Pages	51-66
Number of pages	16
Volume	9653
ISBN (Electronic)	978-3-319-33395-3
ISBN (Print)	978-3-319-33394-6
DOIs	https://doi.org/10.1007/978-3-319-33395-3_4
Publication status	Published - 17 Apr 2016

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer International Publishing
Volume	9653
ISSN (Print)	0302-9743

Access to Document

10.1007/978-3-319-33395-3_4

http://link.springer.com/chapter/10.1007%2F978-3-319-33395-3_4

Cite this

Toccaceli, P., Nouretdinov, I., & Gammerman, A. (2016). Conformal Predictors for Compound Activity Prediction. In Conformal and Probabilistic Prediction with Applications: 5th International Symposium, COPA 2016 Madrid, Spain, April 20–22, 2016 Proceedings (Vol. 9653, pp. 51-66). (Lecture Notes in Computer Science; Vol. 9653). Springer. https://doi.org/10.1007/978-3-319-33395-3_4

@inproceedings{4873a579b7ff4d5cbf4b42a783342895,

title = "Conformal Predictors for Compound Activity Prediction",

abstract = "The paper presents an application of Conformal Predictors to a chemoinformatics problem of identifying activities of chemical compounds. The paper addresses some specific challenges of this domain: a large number of compounds (training examples), high-dimensionality of feature space, sparseness and a strong class imbalance. A variant of conformal predictors called Inductive Mondrian Conformal Predictor is applied to deal with these challenges. Results are presented for several non-conformity measures (NCM) extracted from underlying algorithms and different kernels. A number of performance measures are used in order to demonstrate the flexibility of Inductive Mondrian Conformal Predictors in dealing with such a complex set of data.",

author = "Paolo Toccaceli and Ilia Nouretdinov and Alexander Gammerman",

year = "2016",

month = apr,

day = "17",

doi = "10.1007/978-3-319-33395-3_4",

language = "English",

isbn = "978-3-319-33394-6",

volume = "9653",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "51--66",

booktitle = "Conformal and Probabilistic Prediction with Applications",

}

Toccaceli, P, Nouretdinov, I & Gammerman, A 2016, Conformal Predictors for Compound Activity Prediction. in Conformal and Probabilistic Prediction with Applications: 5th International Symposium, COPA 2016 Madrid, Spain, April 20–22, 2016 Proceedings. vol. 9653, Lecture Notes in Computer Science, vol. 9653, Springer, pp. 51-66. https://doi.org/10.1007/978-3-319-33395-3_4

Conformal Predictors for Compound Activity Prediction. / Toccaceli, Paolo; Nouretdinov, Ilia ; Gammerman, Alexander.
Conformal and Probabilistic Prediction with Applications: 5th International Symposium, COPA 2016 Madrid, Spain, April 20–22, 2016 Proceedings. Vol. 9653 Springer, 2016. p. 51-66 (Lecture Notes in Computer Science; Vol. 9653).

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

TY - GEN

T1 - Conformal Predictors for Compound Activity Prediction

AU - Toccaceli, Paolo

AU - Nouretdinov, Ilia

AU - Gammerman, Alexander

PY - 2016/4/17

Y1 - 2016/4/17

N2 - The paper presents an application of Conformal Predictors to a chemoinformatics problem of identifying activities of chemical compounds. The paper addresses some specific challenges of this domain: a large number of compounds (training examples), high-dimensionality of feature space, sparseness and a strong class imbalance. A variant of conformal predictors called Inductive Mondrian Conformal Predictor is applied to deal with these challenges. Results are presented for several non-conformity measures (NCM) extracted from underlying algorithms and different kernels. A number of performance measures are used in order to demonstrate the flexibility of Inductive Mondrian Conformal Predictors in dealing with such a complex set of data.

AB - The paper presents an application of Conformal Predictors to a chemoinformatics problem of identifying activities of chemical compounds. The paper addresses some specific challenges of this domain: a large number of compounds (training examples), high-dimensionality of feature space, sparseness and a strong class imbalance. A variant of conformal predictors called Inductive Mondrian Conformal Predictor is applied to deal with these challenges. Results are presented for several non-conformity measures (NCM) extracted from underlying algorithms and different kernels. A number of performance measures are used in order to demonstrate the flexibility of Inductive Mondrian Conformal Predictors in dealing with such a complex set of data.

U2 - 10.1007/978-3-319-33395-3_4

DO - 10.1007/978-3-319-33395-3_4

M3 - Conference contribution

SN - 978-3-319-33394-6

VL - 9653

T3 - Lecture Notes in Computer Science

SP - 51

EP - 66

BT - Conformal and Probabilistic Prediction with Applications

PB - Springer

ER -