PhD fellowship in AI-driven knowledge graphs and network models of plant stress responses

The Department of Plant and Environmental Sciences (PLEN) invites applicants for a PhD fellowship in computational plant biology. The project is financed by the Novo Nordisk Foundation through the Ascending Investigator grant “Accelerating crop resilience with AI-enabled gene function prediction and stress regulatory networks” (NNF26OC0113093). The programme aims to make heat and drought resilience engineering in Nordic crops predictable by converting the plant literature and multi-omics data into evidence-backed predictions of gene function and stress regulation.

Start date is expected to be 1 May 2027 or as soon as possible thereafter.

The project Most plant genes remain functionally uncharacterised, and the knowledge that does exist is scattered across more than 200,000 articles. Our knowledge graph PlantConnectome has shown that large language models can extract this knowledge at scale; this project will build its successor and use it to predict gene function.

You will:

• Fine-tune open large language models (e.g. Llama-class models with QLoRA) on our existing, curated knowledge graph, and use the best checkpoint to extract entities, relationships and supporting evidence from >200,000 open-access plant articles spanning model species and crops
• Build a provenance-aware knowledge graph an order of magnitude larger than PlantConnectome, in which every edge is traceable to the sentence and experiment that supports it
• Predict new gene–GO associations by direct-neighbourhood reasoning (matching LLM-generated entity definitions to GO terms with embeddings and an LLM guardrail) and by path-based link prediction with graph neural networks, evaluated CAFA-style against held-out annotations
• Turn regulatory relationships in the graph into Boolean and related discrete network models of stress signalling, simulate them, and test their predictions against expression data generated in the group
• Distinguish well-supported from over-cited claims, and represent evidence quality and independence explicitly in the graph

The position is computational, but sits in a group that generates its own single-cell stress data and validates predictions in rapeseed, so your predictions will be tested.

Who are we looking for? We are looking for candidates within the field(s) of computational biology, bioinformatics, computer science, physics, mathematics or plant biology with a strong quantitative interest. Experience with natural language processing, large language models, graph databases, network modelling or machine learning is an advantage. An interest in how plants actually work is essential; a formal background in plant biology is not.

What we value Coding experience is welcome but not required at entry – we teach it. What we cannot teach quickly, and therefore select for, is scientific judgment:

• questioning data rather than accepting it – asking what was measured, how, and against which expectation
• noticing anomalies and treating them as information rather than noise
• organising several lines of investigation in parallel and knowing when to stop or redirect one
• connecting computational evidence to a concrete biological question
• changing your mind when the evidence changes

We are equally interested in candidates from biology who want to learn computation and candidates from computer science, physics or engineering who want to learn biology.

Our group and research – and what do we offer? The Mutwil group at PLEN works at the interface of comparative and evolutionary plant biology and AI-driven biological discovery. We build large cross-species gene expression atlases, comparative co-expression networks and knowledge graphs, and we use machine learning and large language models to turn the plant literature and omics archives into testable hypotheses. The group comprises several PhD students, postdocs and master’s students, and maintains a portfolio of widely used community resources under the .plant.tools domain, including PlantConnectome, CoNekt, diurnal.plant.tools and evorepro.plant.tools.

The group is part of the Department of Plant and Environmental Sciences (PLEN), Faculty of Science, University of Copenhagen. We are located on the Frederiksberg Campus in Copenhagen.

We offer creative and stimulating working conditions in a dynamic and international research environment. Our research facilities include modern molecular biology laboratories, plant growth facilities and dedicated high-performance computing and GPU resources.

Principal supervisor is Associate Professor Marek Mutwil, Department of Plant and Environmental Sciences (PLEN), University of Copenhagen. E-mail: mutwil@plen.ku.dk.

The PhD programme A three year full-time study within the framework of the regular PhD programme (5+3 scheme), if you already have an education equivalent to a relevant Danish master’s degree.

Qualifications needed

To be eligible, you must have completed a degree programme equivalent to a Danish master’s degree (180 ECTS/3 FTE BSc + 120 ECTS/2 FTE MSc) related to the subject area of the project, e.g. bioinformatics, computational biology, computer science, physics, mathematics, molecular biology or a related field. For information on the eligibility of completed programmes, see General assessments for specific countries and the Assessment database.

Terms of employment

Employment as a PhD fellow is full time and for a maximum of 3 years. Employment is conditional upon your successful enrolment as a PhD student at the PhD School at the Faculty of Science, University of Copenhagen. This requires submission and acceptance of an application for the specific project formulated by the applicant.

Terms of appointment and payment accord to the agreement between the Danish Ministry of Taxation and the Danish Confederation of Professional Associations on Academics in the State. The position is covered by the Protocol on Job Structure.

You can read more about salary levels in the state sector www.loenoverblik.dk (in Danish).

Responsibilities and tasks

• Carry through an independent research project under supervision
• Complete PhD courses corresponding to approx. 30 ECTS / ½ FTE
• Participate in active research environments, including a stay at another research institution, preferably abroad
• Teaching and knowledge dissemination activities
• Write scientific papers aimed at high-impact journals
• Write and defend a PhD thesis on the basis of your project

We are looking for the following qualifications

• Professional qualifications relevant to the PhD project
• Programming experience (e.g. Python) is an advantage; strong analytical reasoning is essential
• Relevant publications
• Relevant work experience, e.g. with NLP, LLMs, knowledge graphs, network modelling or machine learning
• Other relevant professional activities
• A curious mind-set with a strong interest in turning scientific literature into predictive, testable models
• Good written and spoken English

Application and assessment procedure Your application including all attachments must be in English and submitted electronically by clicking APPLY NOW below.

Please include:

• Motivated letter of application (max. one page), stating your motivation for applying for this specific PhD project
• Written answers to the four questions below (max. 250 words each). You may use AI tools to help draft your answers; please say so if you do. The written answers are a starting point for the interview, where we will explore your reasoning in conversation.
• Curriculum vitae including information about your education, experience, language skills and other skills relevant for the position
• Original diplomas for Bachelor and Master and transcript of records in the original language, including an authorised English translation if issued in another language than English or Danish. If not completed, a certified/signed copy of a recent transcript of records or a written statement from the institution or supervisor is accepted.
• Publication list (if possible)
• Reference letters (if available)

Application questions

1. Research interest. Which biological question would you like to work on in this project, and what evidence would you need to answer it?
2. Reading data. A gene has an expression value of 100 under control conditions, 200 under heat stress, 200 under drought, and 400 under heat and drought combined. What do you conclude, and what would you want to know before concluding it?
3. Working in parallel. You have two weeks, a set of publicly available expression data, and a literature you do not yet know. How would you organise the two weeks, and what would you deliver at the end of each?
4. Changing your mind. Describe a case where you believed something about a project or dataset and evidence made you revise it. What was the evidence?

Application deadline: The deadline for applications is 31 January 2027, 23:59 GMT +1.

We reserve the right not to consider material received after the deadline, and not to consider applications that do not live up to the abovementioned requirements.

The further process After the deadline, a number of applicants will be selected for academic assessment by an unbiased expert assessor. You are notified whether you will be passed for assessment. The assessor will assess the qualifications and experience of the shortlisted applicants with respect to the above-mentioned research area, techniques, skills and other requirements. The assessed applicants will have the opportunity to comment on their assessment. You can read about the recruitment process at http://employment.ku.dk/faculty/recruitment-process/.

Interviews with selected candidates are expected to be held in March 2027.

Questions For specific information about the PhD fellowship, please contact the principal supervisor, Associate Professor Marek Mutwil (mutwil@plen.ku.dk).

General information about PhD study at the Faculty of Science is available at the PhD School’s website: https://www.science.ku.dk/phd/.

The University of Copenhagen wishes to reflect the surrounding community and invites all regardless of personal background to apply for the position