Felix Held

About me

I am a doctoral student at the Department of Mathematical Sciences, Chalmers University of Technology and University of Gothenburg, with my advisor Rebecka Jörnsten.

Currently, I am working on data integration methods through joint matrix factorisation, with emphasis on flexible, scalable and interpretable methods. In addition, I started to work on clustering methods in a biological context. Previously, I worked with dynamical models of pharmacological process and parameter estimation in both frequentist and Bayesian settings.

Degrees

• [2018] Licentiate in Advanced Engineering Mathematics from Chalmers University of Technology with work performed at Fraunhofer Chalmers Research Centre for Industrial Mathematics
  • Thesis: Modelling of drug-effect on time-varying biomarkers (pdf)
• [2016] Master of Science in Mathematics from Chalmers University of Technology with work performed at SAFER – Vehicle and Traffic Safety Centre at Chalmers
  • Thesis: Investigation of under-reporting and the consistency of injury severity classifications in Swedish police crash data compared to hospital injury data based on the Swedish Traffic Accident Data Acquisition (STRADA) (pdf)
• [2013] Bachelor of Science in Mathematics with subsidiary subject Physics from University of Würzburg, Germany
  • Thesis: Introduction to the theory of Bergman spaces with emphasis on their dual spaces

Positions

• [Since 2018] Doctoral Student at the University of Gothenburg
• [2016–2018] Project employee at Fraunhofer Chalmers Research Centre for Industrial Mathematics
• [2015] Data Analyst at SAFER – Vehicle and Traffic Safety Centre at Chalmers
• [2015–2016] Consultant at Chalmers teknologkonsulter
• [2010–2011] Software engineer for the Faculty of Physics and Astronomy, University of Würzburg

Teaching

I was responsible for the lectures and course coordination for

• [2021] MSA220/MVE441 Statistical Learning for Big Data at Chalmers/University of Gothenburg (about 130 students, fully digital course)
• [2020] MSA220/MVE440 Statistical Learning for Big Data at Chalmers/University of Gothenburg (about 120 students, fully digital course due to the Covid-19 pandemic)
• [2019] MSA220/MVE440 Statistical Learning for Big Data at Chalmers/University of Gothenburg (about 90 students, Slides)

and did a lot of teaching assistance (e.g. holding exercise classes, correcting submissions) over the years since 2011. Examples of subjects I was involved in are

Mathematical Statistics, Probability Theory, Linear Algebra, and Calculus.

I supervised the following students during their master thesis projects

• [2020] Selma Tabakovic, Co-clustering of tensor data using sparse tensor factorisation
• [2020, co-supervised with Rebecka Jörnsten] Oskar Liew and Per Edvardsson, Deep learning models for data integration and surrogate models for interpretable predictions with applications in integromics and recommender system

Extra-curricular activities

Co-founder and organiser for a workshop on Modelling in Biology and Medicine

• [2020] Workshop held digitally (30+ participants, see recording on YouTube)
• [2019] Workshop held at the Wallenberg Conference Centre in Gothenburg, Sweden (60+ participants)

Member of organising committee for

• [2019] a poster conference for doctoral students at the University of Gothenburg

R package maintainer

• [Since 2020] CMF package (CRAN or GitHub). Original authors: Arto Klami and Lauri Väre
• [Since 2022] mmpca package (CRAN or GitHub). Original author: Jonatan Kallus

Other activities

• [2020-2022] Chair of the PhD Student Council at the Department of Mathematical Sciences, Chalmers University of Technology and University of Gothenburg (GU)
• [2018–2021] Member of the PhD Student Council and Research and Education Committee at the Department of Mathematical Sciences, Chalmers and GU

Publications

Peer-reviewed articles

• Gustafsson J, Held F, Robinson JL, Björnson E, Jörnsten R, Nielsen J (2020) Sources of variation in cell-type RNA-Seq profiles PLoS ONE 15(9):e0239495

• Held F, Hoppe E, Cvijovic M, Jirstrand M, Gabrielsson J (2019) Challenge model of TNF_α turnover at varying LPS and drug provocations. J Pharmacokinet Pharmacodyn 46:223–240

• Held F, Ekstrand C, Cvijovic M, Gabrielsson J, Jirstrand M (2019) Modelling of oscillatory cortisol response in horses using a Bayesian population approach for evaluation of dexamethasone suppression test protocols. J Pharmacokinet Pharmacodyn 46:75–87

• Loryan L, Hoppe E, Hansen K, Held F, Kless A, Linz K, Marossek V, Nolte B, Ratcliffe P, Saunders D, Terlinden R, Wegert A, Welbers A, Will O, Hammarlund-Udenaes M (2017) Quantitative Assessment of Drug Delivery to Tissues and Association with Phospholipidosis: A Case Study with Two Structurally Related Diamines in Development. Mol Pharmaceutics 14(12):4362–4373

Talks & Posters

Invited Talks

• [March 2019] Pharmacokinetic/pharmacodynamic modelling in a Bayesian hierarchical framework. Yearly meeting of the Swedish Society for Medical Statistics, Gothenburg, Sweden
• [July 2018] Bayesian hierarchical model of oscillatory cortisol response during drug intervention. Stan Workshop on Pharmacometrics, INSERM and University Paris Diderot, Paris, France

Research Presentations

• [November 2019] Scalable integration of sparse data sources. Workshop in Data Science, Halden, Norway

Posters

• [June 2019] A challenge model of TNF_α turnover with LPS provocations and drug intervention. PAGE Meeting 2019, Stockholm, Sweden
• [May 2018] Bayesian hierarchical model of oscillatory cortisol response during drug intervention. PAGE Meeting 2018, Montreux, Switzerland