Can blood reveal the body? Trustworthy AI for tissue gene expression (SHERIFF_E27DTP)
Key details
- Application Deadline
- 30 November 2026 23:59 UK Time
- Location
- Earlham Institute
- Funding Type
- Competition Funded (Home and International)
- Start Date
- 1 October 2027
- Mode of Study
- Full-time
- Programme Type
- PhD
)
Welcome to Norwich
According to the Sunday Times, this city is one of the best places to live in the UK.
Project Description
Primary Supervisor - Dr Rahuman S Malik Sheriffhttps://www.earlham.ac.uk/profile/rahuman-sheriff
A blood sample can be collected repeatedly, but a biopsy from the brain, liver or intestine cannot be. Could the molecular signals in the blood reveal what is happening in other tissues, and tell us when the inference is trustworthy?
This PhD will develop Blood2Tissue, a tissue-conditioned AI modelling framework that predicts tissue-specific gene expression programmes from blood. Existing studies demonstrate feasibility for some genes and tissues, but predictions are often population average, accuracy varies substantially, and current approaches rarely identify which individual predictions can be trusted.
You will build on CHROMATIN, our team’s cross-modal attention framework for imputing missing modalities in multi-omics datasets, and MOCHA, our uncertainty framework with a preprint expected shortly. The aim is not simply to create another blood-to-tissue predictor.
You will benchmark existing methods using GTEx dataset, develop and calibrate Blood2Tissue, and use IBDverse and reference cell atlases to investigate fundamental questions such as why some molecular programmes are blood-visible while others remain tissue-autonomous. Confirmed visits to Ellen McDonagh's Open Targets team at European Bioinformatics Institute (EMBL-EBI) will provide experience connecting reliable molecular signals to genetic and disease evidence. The project will deliver reusable computational methodology and new biological understanding of cross-tissue regulation, with longer-term relevance to Digital Twins of living systems.
Training will span transcriptomics, machine learning, uncertainty quantification, genetics, single-cell genomics, HPC, reproducible software and responsible AI, including supervised use of emerging AI-assisted and agentic tools for coding, benchmarking and workflow automation. The project will be conducted at the Earlham Institute, a world-class BBSRC research centre of excellence in genomics, engineering and computational biology, and AI.
You will join Dr Rahuman Sheriff’s AI integrated Digital Twins Group within Earlham Institute’s data-intensive bioscience environment, with Prof Irene Papatheodorou contributing expertise in cellular genomics and FAIR data. You will join a highly collaborative and supportive research community and have access to training and career development opportunities across the Norwich Research Park through the Norwich Research Park Biosciences Doctoral Training Partnership.
The Norwich Research Park Biosciences Doctoral Training Programme (NRPDTP) is offering fully funded studentships for October 2027 entry. The programme offers postgraduates the opportunity to undertake a 4-year PhD research project whilst enhancing professional development and research skills through a comprehensive training programme. You will join a vibrant community of world-leading researchers. All NRPDTP students undertake a three-month professional internship placement (PIPS) during their study. The placement offers exciting and invaluable work experience designed to enhance professional development. Full support and advice will be provided by our Professional Internship team.
This project has been shortlisted for funding by the NRPDTP. Shortlisted applicants will be interviewed on the 2nd, 3rd and 4th February 2027.
Visit our website for further information on eligibility and how to apply: https://biodtp.norwichresearchpark.ac.uk
Our partners value diverse and inclusive work environments that are positive and supportive. Students are selected for admission without regard to gender, marital or civil partnership status, disability, race, nationality, ethnic origin, religion or belief, sexual orientation, age or social background.
To maximise accessibility and attract students from underrepresented groups to our programme we have introduced bespoke templates for applicant Personal and Research statements which will enable every applicant to fully represent themselves through providing suitable examples and evidence. These forms are on the NRPDTP website and must be used for these sections of the application form.
Entry Requirements
At least UK equivalence Bachelors (Honours) 2:1. English Language requirement (Faculty of Science equivalent: IELTS 6.5 overall, 6 in each category).
Funding
This project is awarded with a 4-year Norwich Research Park Biosciences Doctoral Training Partnership PhD DTP studentship. The studentship includes payment of tuition fees (directly to the University), a stipend to cover living expenses (2026/27 stipend rate: £21,805, and a Research Training Support Grant of £5,000pa for each year of the studentship.
References
Limdi et al. MOCHA - Uncertainty quantification identifies context dependent biology and technical noise (preprint expected shortly) Basu M. et al. Predicting tissue-specific gene expression from whole blood transcriptome. Science Advances 7, eabd6991 (2021). Xu W. et al. Blood-based multi-tissue gene expression inference with Bayesian ridge regression. Bioinformatics 36, 3788-3794 (2020). He G. et al. MTM: a multi-task learning framework to predict individualized tissue gene expression profiles. Bioinformatics 39, btad363 (2023). Laubenbacher, R., Niarakis, A., Helikar, T. et al. Building digital twins of the human immune system: toward a roadmap. npj Digit. Med. 5, 64 (2022).