|Funding for:||UK Students, EU Students, International Students|
|Funding amount:||£14,777 per annum|
|Placed On:||9th November 2018|
|Closes:||5th December 2018|
PhD Studentship – Combining Statistical Physics with Machine Learning for Drug Discovery - Dr Alpha Lee
Applications are invited for a fully funded PhD studentship in Dr Alpha Lee’s Group on molecular design by combining statistical physics with machine-learning for drug discovery. The studentship has NO nationality restrictions, with an expected start date in October 2019.
The award covers tuition fees (for UK/EU/international students) and provides a tax-free stipend of £14,777 p.a. (index linked).
Fixed-term: The funds for this post are available for 3.5 years in the first instance. The student must complete the programme in this timeframe.
We are looking for candidates interested in developing machine-learning techniques based on statistical physics to accelerate the design-make-test cycle in molecular discovery.
The successful candidate should have a good first degree and a Masters in a relevant quantitative field (e.g. physics, chemistry, mathematics, computer science or statistics). The candidate must be highly motivated, capable of performing independent research and have excellent communication skills with collaborative working skills.
Recent technological advances have made high-throughput experimentation in chemistry possible. The analysis of voluminous and high-dimensional data demandinnovative and novel approaches that integrate data into physical theories.
For accelerating molecular design, deep learning methods will be developed to predict biological activity, making inference on large (potentially noisy and incomplete) pharmacological datasets, refining traditional notions of chemical similarity and pharmacophores to make them statistically powerful. We will develop scalable Bayesian methods for estimating algorithmic uncertainties and drive experiments using machine-learning models. The “make” stage, will require tackling problems of organic synthesis by developing methods that predict organic reactions outcomes using quantum chemical descriptors, graph-based machine-learning and data from high-throughput synthesis studies. This project builds on our previous work on data-driven models for predicting bioactivity and existing industrial collaborations.
The black box of machine-learning will be unveiled by using statistical physics methods such as including explorations of loss function landscape of machine-learning algorithms trained on chemical/reaction data, developing quantitative methodologies to attribute why machine-learning methods arrived at predictions. It is difficult to disentangle and question assumptions that underlie how human scientists reason. A machine-learning algorithm that reaches near-human accuracy, being a mathematical function, can be analysed. We believe this will yield new insights about chemistry and chemical space structure.
Interested candidates are encouraged to make informal enquiries by contacting Dr. Alpha Lee (email@example.com). The successful candidate will be expected to meet the graduate admissions entrance requirements of the University of Cambridge and formally apply for admission at https://www.graduate.study.cam.ac.uk/entry-requirements.
To make an application, follow the procedure outlined on: https://www.graduate.study.cam.ac.uk/how-do-i-apply, selecting ‘PhD Studentship in Physics’ and making sure to mention Dr Alpha Lee and Theory of Condensed Matter Group. Awards maybe made to supplement part-support from other sources. Candidates are encouraged to express their interest for other available awards in the application form in addition to this Studentship and apply to the Winton Scholar programme (https://www.winton.phy.cam.ac.uk/jobs/PhD2019).
IMPORTANT - when submitting the application, you will need to notify Dr Alpha Lee (firstname.lastname@example.org) of your submission.
Deadline for submission of the applications is 5th of December 2018.
Please quote reference KA17344 on your application and in any correspondence about this vacancy.
The University values diversity and is committed to equality of opportunity.
The University has a responsibility to ensure that all employees are eligible to live and work in the UK.
Type / Role: