University of Hong Kong Featured PhD Programmes
University of Southampton Featured PhD Programmes
University College London Featured PhD Programmes

EASTBIO How much information is in 30ml of milk? – Implementation of artificial intelligence methods for the prediction of novel phenotypes from milk mid infrared spectral data

PHD Opportunities

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
Dr S Denholm , Prof Mike Coffey No more applications being accepted Competition Funded PhD Project (Students Worldwide)

About the Project

Artificial intelligence (AI) and machine learning are not new, however, advances in computer technology and the use of increasingly huge datasets have ignited a boom in deep learning – a sub-branch of machine learning. Deep learning is a technique that imitates the workings of the human brain to process data and identify patterns for use in decision making. This emerging and innovative methodology is only just beginning to be adopted in agriculture.

Infrared spectroscopy is a routine analytical technique used internationally in chemical laboratories to identify compounds in an unknown sample. Analysis is based on different wavelengths of light-energy absorbed by chemical bonds, resulting in a chemical fingerprint. Mid infrared (MIR) spectroscopy is routinely carried out in the dairy industry; farmers pay for this service to measure the effects of management interventions and to ensure milk composition is optimal for their commercial conditions. Spectral data can be used in national genetic evaluations and to predict many different phenotypes due to the chemical imprint left in the milk by a biological process in the cow. This method of prediction is valuable as an efficient low-cost tool for rapid measurement of economically important phenotypes – all this information from only 30ml of milk (per cow)! We have demonstrated that deep and machine learning can be implemented to routinely, automatically, and more importantly non-invasively predict such phenotypes, delivering key insights to farmers and informing management decisions. Recently our group has been the first in the world to have success in implementing such techniques to predict predictions of bovine tuberculosis and pregnancy status in dairy cows (Denholm et al., 2020; Brand et al., 2020).

This studentship will provide training in novel techniques such as deep learning, scientific programming and data handling. Training will be delivered via specialised courses (NVIDIA Deep Learning Institute) and from experts at SRUC and EGENES. Working with NMR staff will provide experience in the commercial milk recording sector will be encouraged. Deep-learning tasks require large volumes of data and computing resource and this studentship will provide access to both. Existing spectral data accumulated by SRUC are available with a new data from over 4000 farms arriving daily. The student will also have access to SRUC’s personal supercomputer (NVIDIA DGX Station) with computational power supplied by 4 NVIDIA Tesla-v100 GPUs. This studentship will provide the opportunity to be trained in a bleeding edge area of research and develop knowledge and skills much sough-after by industry and academia alike; all while interacting with other scientists in a leading research environment. SRUC’s new partnership with NVIDIA means further training opportunities from experts in the fields of AI, high performance computing and data science.

This interdisciplinary studentship will combine genetic, computational, mathematical and chemical expertise to produce deep learning models for the prediction of novel phenotypes from MIR spectra. Specifically, analyses will attempt to explain the relationship between MIR and phenotype at the biological and chemical level. Finally breeding values will be produced using the phenotypes generated and validated against EBVs from animals with known phenotypes.

Applicants should download the required forms from and send the following documents to [Email Address Removed]:
a. EASTBIO Application Form
b. EASTBIO DTP Equality Form
c. CV
d. Academic transcripts (a minimum of an upper second class or first class honours degree or equivalent is required for PhD study
e. Two references should be provided by the deadline using the EASTBIO reference form ( Please advise your referees to return the reference form to [Email Address Removed].
f. If you are nominated by the supervisor(s) of the EASTBIO PhD project you wish to apply for, they will provide a Supervisor Support Statement.

Funding Notes

This 4 year PhD project is part of a competition funded by EASTBIO BBSRC Doctoral Training Partnership This opportunity is open to UK and International students and provides funding to cover stipend and UK level tuition (Please state if your institution will provide funding to cover the difference in fees). Please refer to UKRI website and Annex B of the UKRI Training Grant Terms and Conditions for full eligibility criteria.


Two references should be provided by the deadline using the EASTBIO reference form ( Please advise your referees to return the reference form to
Search Suggestions

Search Suggestions

Based on your current searches we recommend the following search filters.

FindAPhD. Copyright 2005-2021
All rights reserved.