[Turing-Southampton] Turing Data Study Group Dementia Project PI Opportunities

Tue Jun 8 14:24:21 BST 2021

***apologies if you receive this more than once***

The Turing is offering an exciting opportunity for early career researchers and post-docs to become Data Study Group PIs for projects relating to Dementia Research.  (Experience in the field of dementia is not a requirement, the useful data science skills listed below each project is really what we are looking for.)

The Data Study Group (DSG) PIs will scope and shape a challenge for the Turing's DSG<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fcollaborate-turing%2Fdata-study-groups&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C49e717b1367947ef2c0a08d92a80ba5b%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637587554624948318%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=u9Q%2BgCvAETwkfdxxOjIC6WrqilQy6Uunx8vywxW85yg%3D&reserved=0> with potential for continued and expanded follow up work after the event. The Turing will administrate contracts, IT and researchers, and fully support the DSG PI, while their sole focus will be on the scientific questions to be investigated. For further information on the DSG PI role please visit  https://www.turing.ac.uk/collaborate-turing/data-study-groups/get-involved-pi<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.turing.ac.uk%2Fcollaborate-turing%2Fdata-study-groups%2Fget-involved-pi&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C49e717b1367947ef2c0a08d92a80ba5b%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637587554624958274%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=5FdrffalrTL9abnFEgpAp4ojEFCXcLBArsu%2BUI8emEA%3D&reserved=0>.

This is an exceptional opportunity to

  *   Build industry connections whilst working alongside challenge owners.
  *   Generate projects from loosely defined questions
  *   Work at the cross section of industry and academia
  *   Be involved in multidisciplinary teams
  *   Get involved with The Turing Institute

The projects have come through the UK Dementia Research Institute (UK DRI) & the details are:

Challenge: Predicting amyloid plaque morphology from gene expression data in Alzheimer's disease

Essential skills: Experience of spatial & predictive modelling, Machine Learning, feature selection, image analysis

Useful skills: Omics data, gene expression, multi model data

Description: One of the major hallmarks of Alzheimer's Disease (AD) are protein aggregates (amyloid plaques) that accumulate in the brain. Last year UK DRI published a gene expression atlas (of ~20k genes) showing many processes (such as inflammation and myelination) that are spatially affected by the presence of plaques (see alzmap.org<https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Falzmap.org%2F&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C49e717b1367947ef2c0a08d92a80ba5b%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637587554624958274%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=J95w3JZoXnx5WnCMRWM%2BBF1sB%2FUtTo33b6iKLbeZtNY%3D&reserved=0>).

Using spatial transcriptomics and microscopy imaging data, this project will investigate the relation between plaque morphology and the gene expression data. By better understanding what drives amyloid plaque morphology and distribution in an Alzheimer's brain UK DRI hope to better understand the role of plaques during the onset of AD, and ultimately find ways to treat this disease.

Challenge: Predicting where DNA binds proteins from sequence data: can computational models pay attention to distant genetic variants which experiments show affect binding?

Essential: Machine learning, predictive modelling, casual inference, feature selection
Useful: Understanding of gene regulation and expression, omics data, neural networks and multimodal data

Description: Existing deep learning models are able to predict where a DNA sequence is likely to bind to regulatory proteins. From these models we can get predictions about which DNA bases are most important for regulating binding. These models have been trained on data from single individuals though: the training/validation data sets comprise different regions of the DNA sequence, rather than comparing the same genomic regions across individuals. This project will consider experimental data (specificity histone QTLs) on how genetic variants within DNA sequences affect binding: it will evaluate whether computational models can pay attention to the right genetic variants, and whether this depends on their distance from the binding site. Using the models which are evaluated as best recapitulating experimental data, we will aim to obtain predictions for the effects of Alzheimers-associated genetic variants on cell-type specific histone modifications.

All queries and applications should be sent to datastudygroup at turing.ac.uk<mailto:datastudygroup at turing.ac.uk>.  The deadline for applications is June 14th 2021.

__________________________________
Susan Davies
Coordination Manager, Web Science Institute<https://www.southampton.ac.uk/wsi/index.page?>
University Liaison Manager, The Alan Turing Institute<https://www.southampton.ac.uk/wsi/alan-turing-institute/alan-turing-institute.page>
Room 3041, Building 32
Web Science Institute
University of Southampton
Southampton SO17 1BJ

M 07768 266464

websci21.webscience.org/<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwebsci21.webscience.org%2F&data=04%7C01%7CTuring-Southampton%40ecs.soton.ac.uk%7C49e717b1367947ef2c0a08d92a80ba5b%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637587554624968232%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=1qcO45xA5R6abmPNwiq4xRvw1owDKAguK7RQYf5Oj0o%3D&reserved=0>

[cid:image002.jpg at 01D75C71.F7841F90]

-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ecs.soton.ac.uk/pipermail/turing-southampton/attachments/20210608/f5b7bc44/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 32562 bytes
Desc: image002.jpg
Url : http://mailman.ecs.soton.ac.uk/pipermail/turing-southampton/attachments/20210608/f5b7bc44/attachment-0001.jpg 