Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge
This repository contains the implementation of the computational methods in the paper Sundin et al., Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge .
code/linreg_sns_ep.mcontains the expectation propagation inference algorithm for the sparse linear regression model given training data and user feedback.
code/compute_utilities.mcontains the experimental design computations to estimate the utilities for choosing the next query for the user.
simulation_example/run.mcontains an example of an experiment with simulated data and simulated user feedback.
If you use this code, please cite the paper:
 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, and Samuel Kaski. Improving genomics-based predictions for precision medicine through active elicitation of expert knowledge. Accepted to the ISMB 2018 conference proceedings, to be published in Bioinformatics.
* Equal contribution.
- Iiris Sundin, email@example.com
- Tomi Peltola, firstname.lastname@example.org
- Pekka Marttinen, email@example.com
- Samuel Kaski, firstname.lastname@example.org
hermitepolynomial.m is from EKF/UKF toolbox (GPLv2 or later) and written by Arno Solin.
dirrand.m is from GPStuff toolbox (GPLv3 or later) and written by Aki Vehtari.
This work was supported by the Academy of Finland [Finnish Center of Excellence in Computational Inference Research COIN, grant numbers 295503, 294238, 292334, 284642, 305780, 286607, 294015]; by Jenny and Antti Wihuri Foundation; and by Alfred Kordelin Foundation.