PhD Position in Data-driven Learning, Optimization and Control of Pharmaceutical Production

Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship commencing 01.03.2021 or as soon as possible thereafter. This PhD position concerns adaptive learning and control of complex stochastic systems, which may only be observed through the stochastic processes they generate. The PhD candidate will work in a team aiming at optimization of pharmaceutical microbial fermentation processes of growth hormone at Novo Nordisk A/S, a leading pharmaceutical company in Denmark. The project is a collaboration between Department of Food Science (FOOD), Department of Computer Science (DIKU) at University of Copenhagen and Novo Nordisk A/S.

In Novo Nordisk Biopharmaceuticals API (active pharmaceutical ingredient) production yield have over the years been improved by optimization projects and systematic problem solving. These approaches include shop floor investigations and the use of control charts to monitor daily operations, as well as basic mathematical modelling of production yields to identify the most influential process parameters. The current optimization strategy relies on historic knowledge and specific individual’s ability to spot interactions and trends. This is a time-consuming and manual procedure, that is highly relying on specific individuals. The project aims to improve process understanding and increase yield using machine learning (ML) approaches. This includes development of new and efficient methods for learning from huge amounts of real-world production data, identification of critical process parameters influencing yield and mapping of the process variability space to gain new insights and establish new production strategies.

The candidate will be working in very close collaboration with the PhD student from UCPH FOOD as the two PhD students will complement each other and work in tandem throughout the project. In addition, close collaboration with the experienced data science team and production chemists at Novo Nordisk A/S is anticipated.

Description of the scientific environment

The University of Copenhagen was founded in 1479 and is the oldest and largest university in Denmark. It is often ranked as the best university in Scandinavia and consistently as one of the top places in Europe. Within computer science, it is ranked number one in the European Union (post-Brexit) by the Shanghai Ranking.

The working language of the university is English, and knowledge of English is also fully sufficient to navigate life in Denmark in general. Denmark routinely scores at the absolute top in rankings of quality of life such as e.g., the OECD Better Life Index http://www.oecdbetterlifeindex.org 

Project description
This PhD position concerns adaptive learning and control of complex stochastic systems, which may only be observed through the stochastic processes they generate. The main goal of this PhD project is to devise an automated data-driven optimization/learning procedure to maximize the production yield and gain valuable insights of such processes. This involves:

   i.  Developing an accurate and robust mathematical, or hybrid/dynamic model of the system, which includes learning dynamics and determining relevant parameters influencing the yield

  ii.  Devising adaptive algorithms to maximize the objective, capable of achieving a near-optimal performance in the long run and of adapting to process variations

To implement these, we plan to use and advance methods from ML, statistics, and control theory. In particular, (i) relies on tools from ML and statistics to learn and identify an accurate reduced-order model. In (ii), we plan to use (deep) reinforcement learning (RL) and online learning combined with adaptive control methods. The project offers a unique opportunity to work with real-world production data, and to develop control strategies to be applied in the API production. 

The project strives at general theoretical results, which are expected to be published in top conferences and journals in ML and control, as well as methodological contributions to publications addressing the applied part of the project.

Principal supervisors are Professor Cristian Igel, Department of Computer Science, igel@di.ku.dk, Assistant Professor Sadegh Talebi, Department of Computer Science, m.shahi@di.ku.dk and Associate Professor Klavs Martin Sørensen, Department of Food Science, Chemometrics & Analytical Technology, kms@food.ku.dk.

Job description

The position is available for a 3-year period and your key tasks as a PhD student at SCIENCE are:

  • To manage and carry through your research project
  • Attend PhD courses
  • Write scientific articles and your PhD thesis
  • Teach and disseminate your research
  • To stay at an external research institution for a few months, preferably abroad
  • Work for the department

Formal requirements
The candidate should have a two-year master’s degree within computer science, electrical engineering, or similar. The candidate must have a solid background in mathematics and ML. Experience with classical and deep RL, time series analysis and control theory are a plus.

In addition, the candidate must have an interest in chemistry/microbiology to gain some basic background, which might be necessary when interacting with production chemists. The candidate will be working in very close collaboration with a PhD student from UCPH FOOD throughout the project. In addition, close collaboration with the experienced data science team and production chemists at Novo Nordisk A/S is anticipated.

Terms of employment

The position is covered by the Memorandum on Job Structure for Academic Staff.

Terms of appointment and payment accord to the agreement between the Ministry of Finance and The Danish Confederation of Professional Associations on Academics in the State.

The starting salary is currently at a minimum DKK 331,125 (approx. €43,750) including annual supplement (+ pension at a minimum DKK 53,811). Negotiation for salary supplement is possible.

Application Procedure

The application, in English, must be submitted electronically by clicking APPLY NOW below.

Please include

  • Cover Letter detailing your motivation and background for applying for the PhD project.
  • CV
  • Diploma and transcripts of records (BSc and MSc)
  • Other information for consideration, e.g. list of publications (if any)
  • 1-3 reference letters (if any)

The University wishes our staff to reflect the diversity of society and thus welcomes applications from all qualified candidates regardless of personal background.

The deadline for applications is 15 December 2020, 23:59 GMT +1.

After the expiry of the deadline for applications, the authorized recruitment manager selects applicants for assessment on the advice of the Interview Committee. Afterwards an assessment committee will be appointed to evaluate the selected applications. The applicants will be notified of the composition of the committee and the final selection of a successful candidate will be made by the Head of Department, based on the recommendations of the assessment committee and the interview committee

The main criterion for selection will be the research potential of the applicant and the above mentioned skills. The successful candidate will then be requested to formally apply for enrolment as a PhD student at the PhD school of Science. You can read more about the recruitment process at https://employment.ku.dk/faculty/recruitment-process/.

Questions

For specific information about the PhD scholarship, please contact the principal supervisor Professor Igel, Department of Computer Science, igel@di.ku.dk,  Direct Phone: (+45) 21849673 or Assistant Professor Sadegh Talebi, Department of Computer Science, m.shahi@di.ku.dk  Direct Phone: (+45) 31539770.

General information about PhD programmes at SCIENCE is available at https://www.science.ku.dk/phd.

APPLY NOW

Part of the International Alliance of Research Universities (IARU), and among Europe’s top-ranking universities, the University of Copenhagen promotes research and teaching of the highest international standard. Rich in tradition and modern in outlook, the University gives students and staff the opportunity to cultivate their talent in an ambitious and informal environment. An effective organisation – with good working conditions and a collaborative work culture – creates the ideal framework for a successful academic career.