The fundamental understanding of the human organism and how it is perturbed by variants and drugs forms the basis of delivering tailored care. How can we predict the specific effect a drug has on its known cellular target(s) based on its cellular interaction network?
Apply until April 18, 2021 / Xplorers Camp on May 11, 2021
How can we predict the specific effect a drug has on its known cellular target(s) (e.g., activation, inhibition, antagonism) based on its cellular interaction network?
In personalized healthcare, the fundamental understanding of the human organism and how it is perturbed by variants and drugs forms the basis of delivering care tailored to the individual patient. To enable this, the complex interplay between the biological entities that drive disease at the molecular level can be modeled as a multimodal network which can be leveraged for machine learning applications, including the prediction of polypharmacology, drug combinations, or candidates for drug repurposing.
However, many machine learning applications on biomedical graphs struggle with lacking detail driven by 1) missing data in the data sources used to build the network and 2) an incomplete picture of the organism elucidated by different types of experiments. In particular, the lack of detail on drug effects on their molecular targets can cause issues with utilization of the graph for pharmaceutical applications. In this challenge, we ask for your help to develop computational methods to overcome the missing data problem of drug effects in multimodal networks to open up the full potential of biological networks for personalizing healthcare.
Dr. Charlotta Fruechtenicht
Senior Data Scientist, PHC Analytics
Preferred scale: 6 months full-time (likely remote) internship
Possible format: Full-time internship, with potential to develop into Master Thesis or part of PhD research project
We do not expect a bullet proof solution, but please present your idea on machine learning approaches to solve the task including ideas for suitable training data and validation strategy in a short and concise format (3-5 slides or max 1 page written document plus possible figures to illustrate the concept)
By sending this to us via the submit button you agree to the following: