Research assistant deep-learning applications to polygenic scores in neuroscience and mental health

5 Apr 2024
Job Information

Organisation/Company

University Medical Center Utrecht (UMC Utrecht)

Research Field

Medical sciences

Researcher Profile

Recognised Researcher (R2)

Country

Netherlands

Application Deadline

25 Apr 2024 - 21:59 (UTC)

Type of Contract

Temporary

Job Status

Not Applicable

Hours Per Week

32.0

Is the job funded through the EU Research Framework Programme?

Not funded by an EU programme

Is the Job related to staff position within a Research Infrastructure?

No

Offer Description

We offer a position as research assistant where you will work together with researchers from our group in developing and applying deep-learning models for the construction of polygenic scores. This project involves setting up a framework for the training and validation of deep-learning models that take genotyped DNA of human subjects as input to predict phenotypic traits, such as (longitudinal changes in) brain structures, cognition, and mental health. One part of this project is incorporating additional sources of knowledge into the models, such as prior knowledge on the association of the genetic marks with the trait, structure of the human genome, functional annotations of the genetic marks, and demographic and clinical variables of the subjects. Another part will be introducing explainable AI (XAI) into the models to better understand and help to improve how the models work. This project does not involve the collection of new data from human subjects as the models will be applied to data from existing cohorts. The aim of this project is to produce a framework for constructing polygenic scores that can be used by researchers in their study, with the goal to publish the method in a scientific journal and make the source code publicly available.

Requirements
Specific Requirements

We are looking for a candidate that has affinity with computational sciences. Preferably a candidate with experience in deep-learning or machine learning technologies, but any candidate with a background in bioinformatics, computer science, mathematics, or related fields are welcome to apply. We value any affinity with biology, genetics, and/or neuroscience, but this is not required. This position is also open to apply for master students who have not yet graduated. The ideal candidate would (partially) match the following skills:

• Experienced in computer programming, preferably Python.
• Experience with deep-learning or machine learning technologies, such as Keras, TensorFlow, PyTorch, or Scikit-learn, including training models on a GPU.
• Experience with responsible AI, in particular the topic of explainable AI (XAI).
• Experience with working on a high performance compute cluster and/or Unix systems.
• Affinity with genetics at the level of genotyped DNA, or at least a basic understanding of human genetics at high school level.
• Some affinity with neuroscience and/or behavioral sciences.
• Some affinity with research and/or ambition for a career in academic/scientific research.
• Proficiency in Dutch and/or English.

For questions, you can contact Hilleke Hulshoff Pol ([email protected] ) and Jalmar Teeuw ([email protected] ).

Additional Information
Benefits

The maximum salary for this position (32 - 32 hours) is € 3.772,00 gross per month based on full-time employment.

In addition, we offer an annual benefit of 8.3%, holiday allowance, travel expenses and career opportunities. The terms of employment are in accordance with the Cao University Medical Centers (UMC).

Additional comments

Contact our colleague:
Hilleke Hulshoff Pol
088 75 560 25
[email protected]

Website for additional job details

https://www.academictransfer.com/339883/

Work Location(s)

Number of offers available

1

Company/Institute

UMC Utrecht

Country

Netherlands

City

Utrecht

Postal Code

3584CX

Street

Heidelberglaan 100

Geofield

Where to apply

Website

https://www.academictransfer.com/en/339883/research-assistant-deep-learning-app…

Contact

City

Utrecht

Website

http://www.umcutrecht.nl/

Street

Heidelberglaan 100

Postal Code

3584 CX

STATUS: EXPIRED