[BBC] Vacancy for a structural bioinformatician at Radboudumc Nijmegen

[Hanka.Venselaar at radboudumc.nl]

Dear all,

we would like to draw your attention to this vacancin our structural bioinformatics group at Radboudumc Nijmegen.

Full tekst and details can be foud here:
https://www.radboudumc.nl/en/vacancies/89341-postdoc-diagnostics-in-3d

GRTZ from Nijmegen,
Hanka


"Job description

The increasing pace at which genomes are being sequenced and at which protein 3D structures are being solved opens the possibilities to predict the effect of mutations on the functioning of a protein at an unprecedented scale. Furthermore, advances in Artificial Intelligence (AI) allow us to efficiently exploit that information to make reliable predictions about disease causing mutations.

Such predictions can be applied in diagnostics, solving the many variants in patients' genomes for which we do not know whether they are responsible for disease. The project, named Diagnostics-in-3D, will therewith have a significant impact on diagnosis of (rare disease) patients. Your role in this project is to investigate how to optimally exploit protein 3D structure information in an AI framework that discriminates between benign and damaging mutations in human genomes. For that you will use our protein 3D modeling project HOPE, our deep learning platform for 3D protein structures DeepRank and our expertise in deep learning approaches to protein structures, comparative genomics and diagnostic classifiers.

You will be working with a scientific programmer to turn your solutions into professional software. You will furthermore be collaborating with two companies, one from which you will to obtain relevant 3D data and sequence alignments and one with which we will implement parallel/distributed CPU/GPU computing solutions for this data and computation intensive project. Your job thus entices both scientific research into the effect of protein 3D structures and regular communication with the scientific and industrial partners.

Tasks and responsibilities
Obtain relevant data and find the best representation of 3D structure data for deep learning.
Modeling effects of mutations on protein 3D structure.
Extend DeepRank to work with single protein structures.
Developing and training classifiers using DeepRank to predict the effect of mutations on protein function.
Communicate with a scientific programmer about implementation of software.
Reporting your results in the form of publications and presentation.
Profile

You either have a PhD in computational structural biology, with a strong computational background in modeling and interpreting 3D structures, or you have a PhD in machine learning and AI with a proven interest in protein 3D structures and biochemistry. Furthermore, you are enthusiastic about genetics and biomedical research. Lastly, you have strong communication skills and you have a collaborative mindset. "






De informatie in dit bericht is uitsluitend bestemd voor de geadresseerde. Aan dit bericht en de bijlagen kunnen geen rechten worden ontleend. Heeft u deze e-mail onbedoeld ontvangen? Dan verzoeken wij u het te vernietigen en de afzender te informeren. Openbaar maken, kopiëren en verspreiden van deze e-mail of informatie uit deze e-mail is alleen toegestaan met voorafgaande schriftelijke toestemming van de afzender. Het Radboudumc staat geregistreerd bij de Kamer van Koophandel in het handelsregister onder nummer 41055629.

The content of this message is intended solely for the addressee. No rights can be derived from this message or its attachments. If you are not the intended recipient, we kindly request you to delete the message and inform the sender. It is strictly prohibited to disclose, copy or distribute this email or the information inside it, without a written consent from the sender. Radboud university medical center is registered with the Dutch Chamber of Commerce trade register with number 41055629.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://maillist.psb.ugent.be/pipermail/bbclist/attachments/20201111/5d6677bb/attachment.html>