Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge

Iiris Sundin; Tomi Peltola; Luana Micallef; Homayun Afrabandpey; Marta Soare; Muntasir Mamun Majumder; Pedram Daee; Chen He; Baris Serim; Aki Havulinna; Caroline Heckman; Giulio Jacucci; Pekka Marttinen; Samuel Kaski

doi:10.1093/bioinformatics/bty257

Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge

Iiris Sundin, Tomi Peltola, Luana Micallef, Homayun Afrabandpey, Marta Soare, Muntasir Mamun Majumder, Pedram Daee, Chen He, Baris Serim, Aki Havulinna, Caroline Heckman, Giulio Jacucci, Pekka Marttinen, Samuel Kaski

Research output: Contribution to journal › Article › Scientific › peer-review

11 Citations (Scopus)

160 Downloads (Pure)

Abstract

Motivation Precision medicine requires the ability to predict the efficacies of different treatments for a given individual using high-dimensional genomic measurements. However, identifying predictive features remains a challenge when the sample size is small. Incorporating expert knowledge offers a promising approach to improve predictions, but collecting such knowledge is laborious if the number of candidate features is very large.

Results: We introduce a probabilistic framework to incorporate expert feedback about the impact of genomic measurements on the outcome of interest and present a novel approach to collect the feedback efficiently, based on Bayesian experimental design. The new approach outperformed other recent alternatives in two medical applications: prediction of metabolic traits and prediction of sensitivity of cancer cells to different drugs, both using genomic features as predictors. Furthermore, the intelligent approach to collect feedback reduced the workload of the expert to approximately 11%, compared to a baseline approach.

Availability and implementation: Source code implementing the introduced computational methods is freely available at https://github.com/AaltoPML/knowledge-elicitation-for-precision-medicine.

Supplementary information: Supplementary data are available at Bioinformatics online.

Original language	English
Pages (from-to)	i395-i403
Journal	Bioinformatics
Volume	34
Issue number	13
DOIs	https://doi.org/10.1093/bioinformatics/bty257
Publication status	Published - 27 Jun 2018
MoE publication type	A1 Journal article-refereed

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1093/bioinformatics/bty257

bty257Final published version, 405 KBLicence: CC BY-NC

Co-Adaptation - Yhteismukauttaminen
Kaski, S. (Principal investigator), Kangas, J.-K. (Project Member), Micallef, L. (Project Member), Niinimäki, T. (Project Member), Celikok, M. M. (Project Member) & Eranti, P. (Project Member)
01/01/2017 → 31/12/2018
Project: Academy of Finland: Other research funding
Data-Driven Decision Support for Digital Health
Kaski, S. (Principal investigator), Vuollekoski, H. (Project Member), Strahl, J. (Project Member), Niinimäki, T. (Project Member), Sundin, I. (Project Member), Blomstedt, P. (Project Member), Hegde, P. (Project Member), Daee, P. (Project Member) & Eranti, P. (Project Member)
01/01/2016 → 30/06/2018
Project: Academy of Finland: Other research funding
Interactive machine learning from multiple biodata sources
Kaski, S. (Principal investigator) & Filstroff, L. (Project Member)
01/01/2016 → 31/08/2021
Project: Academy of Finland: Other research funding

Science-IT
Hakala, M. (Manager)
School of Science
Facility/equipment: Facility

Probabilistic user modelling methods for improving human-in-the-loop machine learning for prediction
Marttinen, P., Kaski, S., Vehtari, A. & Havulinna, A.
12/05/2021
1 item of Media coverage
Press/Media: Media appearance
Methods for probabilistic modeling of knowledge elicitation for improving machine learning predictions
Kaski, S.
04/12/2020
1 item of Media coverage
Press/Media: Media appearance

Cite this

Sundin, I., Peltola, T., Micallef, L., Afrabandpey, H., Soare, M., Majumder, M. M., Daee, P., He, C., Serim, B., Havulinna, A., Heckman, C., Jacucci, G., Marttinen, P., & Kaski, S. (2018). Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge. Bioinformatics, 34(13), i395-i403. https://doi.org/10.1093/bioinformatics/bty257

@article{e381d3411e2345f6aff93b385039b21a,

title = "Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge",

abstract = "Motivation Precision medicine requires the ability to predict the efficacies of different treatments for a given individual using high-dimensional genomic measurements. However, identifying predictive features remains a challenge when the sample size is small. Incorporating expert knowledge offers a promising approach to improve predictions, but collecting such knowledge is laborious if the number of candidate features is very large.Results: We introduce a probabilistic framework to incorporate expert feedback about the impact of genomic measurements on the outcome of interest and present a novel approach to collect the feedback efficiently, based on Bayesian experimental design. The new approach outperformed other recent alternatives in two medical applications: prediction of metabolic traits and prediction of sensitivity of cancer cells to different drugs, both using genomic features as predictors. Furthermore, the intelligent approach to collect feedback reduced the workload of the expert to approximately 11%, compared to a baseline approach.Availability and implementation: Source code implementing the introduced computational methods is freely available at https://github.com/AaltoPML/knowledge-elicitation-for-precision-medicine.Supplementary information: Supplementary data are available at Bioinformatics online.",

author = "Iiris Sundin and Tomi Peltola and Luana Micallef and Homayun Afrabandpey and Marta Soare and Majumder, {Muntasir Mamun} and Pedram Daee and Chen He and Baris Serim and Aki Havulinna and Caroline Heckman and Giulio Jacucci and Pekka Marttinen and Samuel Kaski",

year = "2018",

month = jun,

day = "27",

doi = "10.1093/bioinformatics/bty257",

language = "English",

volume = "34",

pages = "i395--i403",

journal = "Bioinformatics",

issn = "1367-4803",

publisher = "Oxford University Press",

number = "13",

}

Sundin, I, Peltola, T, Micallef, L, Afrabandpey, H, Soare, M, Majumder, MM, Daee, P, He, C, Serim, B, Havulinna, A, Heckman, C, Jacucci, G , Marttinen, P & Kaski, S 2018, 'Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge', Bioinformatics, vol. 34, no. 13, pp. i395-i403. https://doi.org/10.1093/bioinformatics/bty257

TY - JOUR

T1 - Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge

AU - Sundin, Iiris

AU - Peltola, Tomi

AU - Micallef, Luana

AU - Afrabandpey, Homayun

AU - Soare, Marta

AU - Majumder, Muntasir Mamun

AU - Daee, Pedram

AU - He, Chen

AU - Serim, Baris

AU - Havulinna, Aki

AU - Heckman, Caroline

AU - Jacucci, Giulio

AU - Marttinen, Pekka

AU - Kaski, Samuel

PY - 2018/6/27

Y1 - 2018/6/27

N2 - Motivation Precision medicine requires the ability to predict the efficacies of different treatments for a given individual using high-dimensional genomic measurements. However, identifying predictive features remains a challenge when the sample size is small. Incorporating expert knowledge offers a promising approach to improve predictions, but collecting such knowledge is laborious if the number of candidate features is very large.Results: We introduce a probabilistic framework to incorporate expert feedback about the impact of genomic measurements on the outcome of interest and present a novel approach to collect the feedback efficiently, based on Bayesian experimental design. The new approach outperformed other recent alternatives in two medical applications: prediction of metabolic traits and prediction of sensitivity of cancer cells to different drugs, both using genomic features as predictors. Furthermore, the intelligent approach to collect feedback reduced the workload of the expert to approximately 11%, compared to a baseline approach.Availability and implementation: Source code implementing the introduced computational methods is freely available at https://github.com/AaltoPML/knowledge-elicitation-for-precision-medicine.Supplementary information: Supplementary data are available at Bioinformatics online.

AB - Motivation Precision medicine requires the ability to predict the efficacies of different treatments for a given individual using high-dimensional genomic measurements. However, identifying predictive features remains a challenge when the sample size is small. Incorporating expert knowledge offers a promising approach to improve predictions, but collecting such knowledge is laborious if the number of candidate features is very large.Results: We introduce a probabilistic framework to incorporate expert feedback about the impact of genomic measurements on the outcome of interest and present a novel approach to collect the feedback efficiently, based on Bayesian experimental design. The new approach outperformed other recent alternatives in two medical applications: prediction of metabolic traits and prediction of sensitivity of cancer cells to different drugs, both using genomic features as predictors. Furthermore, the intelligent approach to collect feedback reduced the workload of the expert to approximately 11%, compared to a baseline approach.Availability and implementation: Source code implementing the introduced computational methods is freely available at https://github.com/AaltoPML/knowledge-elicitation-for-precision-medicine.Supplementary information: Supplementary data are available at Bioinformatics online.

U2 - 10.1093/bioinformatics/bty257

DO - 10.1093/bioinformatics/bty257

M3 - Article

SN - 1367-4803

VL - 34

SP - i395-i403

JO - Bioinformatics

JF - Bioinformatics

IS - 13

ER -

Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge

Abstract

UN SDGs

Access to Document

Fingerprint

Projects

Co-Adaptation - Yhteismukauttaminen

Data-Driven Decision Support for Digital Health

Interactive machine learning from multiple biodata sources

Equipment

Science-IT

Press/Media

Probabilistic user modelling methods for improving human-in-the-loop machine learning for prediction

Methods for probabilistic modeling of knowledge elicitation for improving machine learning predictions

Cite this