Agentic AI for Integrative Multi-Omics Research in Cancer The University of Manchester in United Kingdom

This PhD opportunity at The University of Manchester invites applications from motivated candidates eager to advance research at the intersection of artificial intelligence and cancer biology. The project, 'Agentic AI for Integrative Multi-Omics Research in Cancer,' aims to develop novel Agentic AI frameworks to tackle the integration and interpretation of complex multi-omics data in oncology. Cancer is characterized by intricate genomic, transcriptomic, proteomic, and metabolomic alterations, and while high-throughput technologies have enabled comprehensive profiling, a holistic understanding of these molecular layers remains a challenge. Traditional computational methods often fall short in handling the scale and heterogeneity of such data, limiting insights into tumour progression and therapeutic resistance.

The research will move beyond conventional machine learning, focusing on building sophisticated AI agents capable of autonomous exploration of vast multi-omics datasets. These agents will formulate and test hypotheses, collaborate to construct coherent models of cancer biology, and emulate aspects of the scientific discovery process. The ultimate goal is to identify novel diagnostic biomarkers, pinpoint key molecular pathways for therapeutic intervention, and provide a deeper, systems-level understanding of cancer.

Project methodology includes designing a multi-agent AI system using state-of-the-art deep learning, reinforcement learning, and large language models. Each agent will specialize in processing specific data types, such as genomics or proteomics, and will be grounded in biological knowledge by integrating public databases like TCGA, Gene Ontology, and KEGG pathways. The collaborative reasoning framework will enable agents to communicate findings, debate evidence, and generate testable hypotheses about cancer mechanisms. Hypotheses will be validated using bioinformatics pipelines and, where appropriate, through collaboration with biomedical partners for experimental verification. Emphasis is placed on interpretable models, ensuring transparency and mechanistic plausibility.

Applicants should have a strong background in computer science, bioinformatics, computational biology, or related fields. Essential qualifications include a first-class or upper-second-class undergraduate degree, proficiency in Python and machine learning libraries, and a solid understanding of large language models and Agentic AI. Knowledge of molecular biology, genomics, or cancer biology is advantageous. Candidates should demonstrate interest in AI, particularly in multi-agent systems, reinforcement learning, or LLMs, and possess excellent analytical and problem-solving skills.

The position is funded for 3.5 years, with excellent candidates nominated for competence-based funding. The University of Manchester offers a range of scholarships, studentships, and awards to support both UK and overseas postgraduate researchers. The start date is October 2026, and the application deadline is April 1, 2026. Flexible study arrangements, including part-time options, may be considered depending on the project and funding.

To apply, candidates are strongly encouraged to contact the supervisor, Dr. Jingyuan Sun ([email protected]), before submitting their application. Applications must be made online, specifying the project title and supervisor, and include all required documents: transcripts, CV, referee contact details, and English language certificate if applicable. Incomplete applications will not be considered. For further information or questions, contact the admissions team at [email protected].

The University of Manchester is committed to equality, diversity, and inclusion, actively encouraging applicants from diverse backgrounds and career paths. Flexible study arrangements and support for those returning from career breaks are available.