Courses at KU & SDU
Start with a course.
Instructor-led courses in pharmaceutical data science at the University of Copenhagen and the University of Southern Denmark. Several are open to PhD students and external participants — follow each link for level, dates and enrolment.
Hands-on Introduction to Pharmaceutical Data Science
Graduate School of Health & Medical Sciences · University of Copenhagen
A PhD course introducing pharmaceutical data science in Python. Free for PhD students at Danish universities (except CBS) and NorDoc faculties; others may apply and pay a fee.
AI- & data-driven drug design – An introduction
University of Copenhagen
An introduction to AI- and data-driven approaches to drug design.
Big data, artificial intelligence and machine learning in drug safety
University of Copenhagen · SMIM22002U
Big data, artificial intelligence and machine-learning methods applied to drug safety.
Pharmacoepidemiology, post-authorisation safety studies and real-world data
University of Copenhagen · SMIM25001U
Pharmacoepidemiology, post-authorisation safety studies (PASS) and the use of real-world data.
Medicinal and Biostructural Chemistry
University of Copenhagen · SFAK24001U
Medicinal chemistry and the structural basis of drug–target interactions.
Structure-based Drug Research
University of Copenhagen · SLKKIL112U
Structure-based approaches to drug discovery and research.
Pharmaceutical Modelling
University of Copenhagen · SFAB21002U
Modelling approaches across the pharmaceutical sciences. Open as an elective to BSc and MSc students.
Design and Analysis of Experiments
University of Copenhagen · SFKKIF102U
Statistical design of experiments and analysis of the resulting data. Open as an elective to BSc and MSc students.
Mathematics and statistics for pharmacy
University of Southern Denmark · MM556
A mandatory first-semester course on the BSc in Pharmacy covering the mathematics and statistics pharmacists need.
Instrumental pharmaceutical analysis
University of Southern Denmark · FA507
A mandatory fourth-semester BSc Pharmacy course on instrumental pharmaceutical analysis, with a strong statistics component.
Introduction to Pharmaceutical Molecular Modelling
University of Southern Denmark · FA509
An elective introduction to pharmaceutical molecular modelling — computational and pharmaceutically relevant, if not classic data science.
Chemical and pharmaceutical data science
University of Southern Denmark · FA516
A new BSc elective in chemical and pharmaceutical data science, created by Casper Steinmann and running for the first time in autumn 2026.
Chemical and pharmaceutical data science
University of Southern Denmark · KE561
Data-science methods applied to chemical and pharmaceutical problems.
Application of PBPK Modeling in Pharmaceutics – Biopharmaceutical Data Science
University of Southern Denmark · FA811
An applied, elective MSc summer course on physiologically based pharmacokinetic (PBPK) modelling as a case of pharmaceutical data science.
Where to begin
Two steps to get going.
Pick the language your group uses — Python or R — and follow two steps. Everything else is in the library below, there whenever you want to go deeper.
Getting started
Install the tools and learn the basics from zero. Pick the language your group uses — Python or R. The way of thinking carries over either way.
Python
futurecoder
futurecoder.io
Learn Python from scratch in the browser — it runs your code and gives instant feedback, with nothing to install to begin.
Think Python
Allen B. Downey
A clear introduction to Python for people who have never programmed before. Free online from the author.
Programming with Python (Software Carpentry)
The Carpentries
A hands-on novice Python lesson aimed at researchers — used as the recommended primer for the ULLA AI in Drug Discovery course.
Python Beginner's Guide
Python Software Foundation
The official starting point — how to install Python and where to learn, for both new and experienced programmers.
R
swirl — Learn R, in R
swirlstats
Teaches R inside the R console with hands-on prompts. Pair it with R for Data Science when you want practice rather than reading.
Hands-On Programming with R
Garrett Grolemund
A friendly introduction written for non-programmers, teaching R through small hands-on projects.
R-Ladies Sydney — Basic Basics
R-Ladies Sydney
Get R and RStudio installed and find your way around the IDE. A very gentle start, with short videos.
fasteR — Fast Lane to Learning R
Norm Matloff
A comprehensive single-document introduction to R for new programmers — general programming principles plus R's data types and objects.
R4PhD — Introduction to R and the tidyverse
University of Southern Denmark · O'Neill & Harsted
An open site tied to a hands-on SDU course (run 1–3× a year, also on demand). Assumes no prior data-science experience. 2026 PhD dates: Feb 4–5 and 25–26.
Going further
Once you can write a bit of code, move into data science: wrangling data, making figures, and doing statistics — with reproducible, shareable workflows.
Python
A Whirlwind Tour of Python
Jake VanderPlas
A fast, focused intro for people who already program in some other language and just want the Python they need to read scientific code.
Python Data Science Handbook
Jake VanderPlas
NumPy, pandas, matplotlib, seaborn, and scikit-learn — the canonical reference for the core scientific-Python stack.
Python for Data Analysis (3rd ed.)
Wes McKinney
Written by the creator of pandas. Free to read online; the practical reference for data wrangling once you know basic Python.
Kaggle Learn
Kaggle (Google)
Bite-sized free courses on pandas, ML, computer vision, time series, geospatial. Best as a refresher between bigger commitments.
R
R for Data Science (2nd ed.)
Hadley Wickham, Mine Çetinkaya-Rundel & Garrett Grolemund
The canonical free R + tidyverse book. Best starting point for R if you'll do data wrangling, biostats, or pharmacometrics.
Modern Statistics with R
Måns Thulin
Practical, applied stats with tidyverse syntax. Covers regression, mixed models, survival analysis, and Bayesian methods.
Posit (RStudio) Cheatsheets & Recipes
Posit
One-page printable cheatsheets for ggplot2, dplyr, tidyr, lubridate, and the rest of the tidyverse. The fastest reference once you know the basics.
data.table — Introduction
data.table project
The main features of data.table for fast, memory-efficient data wrangling. Further vignettes cover specific topics in depth.
The full library
Browse everything by topic.
Hand-picked resources grouped by topic — open a section to explore. Mostly free; options that carry a certificate are marked.
Programming foundations
Start here if you've never written code. Pick Python or R based on what your colleagues use.
Python for Everybody
University of Michigan · Charles Severance
The single best on-ramp from no programming to working Python — kind, paced, with auto-graded exercises. Free at py4e.com; same content also available as a paid Coursera Specialization with a certificate.
A Whirlwind Tour of Python
Jake VanderPlas
A fast, focused intro for people who already program in some other language and just want the Python they need to read scientific code.
Real Python (selected free tutorials)
Real Python
Topical, readable Python tutorials. The free articles alone cover most of what you need; the paid track adds video courses.
R for Data Science (2nd ed.)
Hadley Wickham, Mine Çetinkaya-Rundel & Garrett Grolemund
The canonical free R + tidyverse book. Best starting point for R if you'll do data wrangling, biostats, or pharmacometrics.
swirl — Learn R, in R
swirlstats
Teaches R inside the R console with hands-on prompts. Pair it with R for Data Science when you want practice rather than reading.
Posit (RStudio) Cheatsheets & Recipes
Posit
One-page printable cheatsheets for ggplot2, dplyr, tidyr, lubridate, and the rest of the tidyverse. The fastest reference once you know the basics.
Data Science Specialization
Johns Hopkins · Coursera
Long-running R-based specialisation that covers tooling, EDA, regression models, ML, and a capstone. Stackable; audit-free per course.
Applied Data Science with Python Specialization
University of Michigan · Coursera
Pandas, plotting, ML with scikit-learn, text analysis, network analysis. Practical, applied; assumes you know basic Python (do Python for Everybody first).
futurecoder
futurecoder.io
Learn Python from scratch in the browser — it runs your code and gives instant feedback, with nothing to install to begin.
Think Python
Allen B. Downey
A clear introduction to Python for people who have never programmed before. Free online from the author.
Programming with Python (Software Carpentry)
The Carpentries
A hands-on novice Python lesson aimed at researchers — used as the recommended primer for the ULLA AI in Drug Discovery course.
Python for Data Analysis (3rd ed.)
Wes McKinney
Written by the creator of pandas. Free to read online; the practical reference for data wrangling once you know basic Python.
Python Beginner's Guide
Python Software Foundation
The official starting point — how to install Python and where to learn, for both new and experienced programmers.
W3Schools Python Tutorial
W3Schools
A modular, look-it-up reference for Python basics — handy when you just need to remember how to do one small thing.
freeCodeCamp
freeCodeCamp
Free, project-based coding courses you can fit around a busy schedule. Good for building momentum and habit.
fasteR — Fast Lane to Learning R
Norm Matloff
A comprehensive single-document introduction to R for new programmers — general programming principles plus R's data types and objects.
Hands-On Programming with R
Garrett Grolemund
A friendly introduction written for non-programmers, teaching R through small hands-on projects.
R-Ladies Sydney — Basic Basics
R-Ladies Sydney
Get R and RStudio installed and find your way around the IDE. A very gentle start, with short videos.
W3Schools R Tutorial
W3Schools
A modular reference for R basics — nice for quickly looking up how to do a specific thing.
An Introduction to R
R Core Team
The official introduction, straight from the source. A little dry and technical, but authoritative.
data.table — Introduction
data.table project
The main features of data.table for fast, memory-efficient data wrangling. Further vignettes cover specific topics in depth.
Advanced R
Hadley Wickham
Deeper R concepts for experienced programmers — not for beginners, but excellent once you want to understand how R really works.
DataCamp — R courses
DataCamp
Polished interactive courses for R and more. Mostly a paid plan, though the introductory R course has historically been free.
R4PhD — Introduction to R and the tidyverse
University of Southern Denmark · O'Neill & Harsted
An open site tied to a hands-on SDU course (run 1–3× a year, also on demand). Assumes no prior data-science experience. 2026 PhD dates: Feb 4–5 and 25–26.
Statistics & data analysis
Build statistical intuition before reaching for ML. Pharmacy curricula typically cover the basics; these go deeper.
StatQuest with Josh Starmer
Josh Starmer · YouTube
Visual, intuition-first explanations of every statistical and ML concept you're likely to meet — bias-variance, regularisation, PCA, ROC curves, transformers. The friendliest single resource for self-study stats.
Introduction to Statistical Learning (ISLR)
James, Witten, Hastie, Tibshirani
The most-used graduate-level intro to statistical learning. Free PDF, with separate R and Python lab books that walk through the methods on real data.
Statistical Rethinking
Richard McElreath
A complete Bayesian-stats course. The book is paid but the full lecture series, code, and homework are free. The clearest treatment of causal inference + multilevel models you'll find at this level.
Modern Statistics with R
Måns Thulin
Practical, applied stats with tidyverse syntax. Covers regression, mixed models, survival analysis, and Bayesian methods.
3Blue1Brown — Essence of Linear Algebra / Calculus / Probability
Grant Sanderson · YouTube
Animated math explainers with unmatched visual intuition. The 'Essence of' series is the recommended primer before any ML course.
MITx MicroMasters in Statistics & Data Science
MIT · edX
Rigorous graduate-level treatment of probability, stats, ML, and capstone. Audit free; verified track requires payment per course. Stackable into MIT degrees.
Statistical Learning with R / Python
Stanford Online · Hastie & Tibshirani
The video lectures companion to the ISLR book, taught by the authors. Audit free or pay for the verified certificate.
Mathematics for Machine Learning Specialization
Imperial College London · Coursera
Linear algebra, multivariate calculus, and PCA, framed for ML. Bridge between 3Blue1Brown intuition and reading actual ML papers.
Reproducibility & workflow
Git, notebooks, FAIR data. The infrastructure that turns one-off scripts into shareable science.
Pro Git
Scott Chacon & Ben Straub
The official Git book. Free, comprehensive, and stays current with the tool itself.
GitHub Skills
GitHub
Hands-on Git/GitHub exercises run inside real repositories. The fastest way to learn pull requests, code review, and Actions without setting anything up.
Happy Git and GitHub for the useR
Jenny Bryan, the STAT 545 TAs, Jim Hester
Best-in-class onboarding to Git for researchers, especially those using R. Sets up the toolchain step-by-step and explains 'why' not just 'how'.
The Turing Way
The Turing Way community
An open handbook on reproducible, ethical, collaborative data science. Use it as a reference for project structure, FAIR data, and open research practice.
Software & Data Carpentry lessons
The Carpentries
Volunteer-maintained workshop materials covering shell, Git, Python/R, and SQL for researchers. Excellent self-study and even better as the basis for an in-house workshop.
Bioinformatics & Galaxy
For omics, sequencing, registry/structured biological data. Galaxy is point-and-click, the rest are programmatic.
Galaxy Training Network
Galaxy Project · GTN
Hundreds of GUI-driven, runnable tutorials covering RNA-seq, variant calling, proteomics, single-cell, machine learning, and more. The fastest path into bioinformatics for non-coders.
Bioconductor — Course Materials
Bioconductor
Annual workshops and labs from the R/Bioconductor ecosystem. Authoritative for omics analysis in R.
Rosalind — Bioinformatics problems
Rosalind
Project-Euler-style bioinformatics challenges. Great for building Python fluency on biological data without committing to a long course.
Biopython Tutorial & Cookbook
Biopython
Working with sequences, alignments, structures, and biological databases in Python. Complements Galaxy when you need scripted control.
Genomic Data Science Specialization
Johns Hopkins · Coursera
Covers Galaxy, Bioconductor, Python for genomics, statistics, and a capstone. Strong applied bioinformatics path.
National Health Data Science Sandbox
HeaDS · University of Copenhagen
Coordinated at HeaDS (KU). Training modules and a model for building and curating computational resources for research and teaching.
Cheminformatics & drug discovery
Working with molecules, structures, properties, and target prediction in code.
RDKit Cookbook
RDKit
Code recipes for the standard cheminformatics toolkit — SMILES parsing, fingerprints, similarity, structure search, descriptors, conformers.
TeachOpenCADD
Volkamer Lab
A complete computer-aided drug design course as Jupyter notebooks. Covers ligand-based + structure-based design, ADMET, and ML for drug discovery — all reusable as teaching material.
DeepChem Tutorials
DeepChem
Step-by-step notebooks for ML on molecules — featurisation, regression, classification, generative models. Pairs cheminformatics with deep learning.
Machine learning & AI for healthcare
From classical ML (scikit-learn) through deep learning, with a focus on healthcare applications and responsible practice.
Practical Deep Learning for Coders
fast.ai · Jeremy Howard, Rachel Thomas
Top-down deep learning course that has you training real models in week 1 and explaining them in week 7. The 'Deep Learning for Coders' book that accompanies it is also free as Jupyter notebooks.
Hugging Face NLP / LLM Course
Hugging Face
End-to-end course on transformers, fine-tuning, datasets, and evaluation. The standard introduction to modern NLP/LLM tooling.
Made With ML
Goku Mohandas
Goes beyond model training into MLOps — testing, CI/CD, monitoring, and shipping ML systems responsibly. Useful when you need a model to actually run somewhere.
Machine Learning Specialization
DeepLearning.AI · Stanford · Coursera
Andrew Ng's reboot of the classic Coursera ML course. Audit free; pay (~£40/month) for graded assignments and a certificate.
AI for Medicine Specialization
DeepLearning.AI · Coursera
Three courses on diagnosis, prognosis, and treatment with ML — covers medical image segmentation, survival analysis, and causal inference for medicine. Closest 'pharma-flavoured' specialization at this level.
HarvardX Data Science Professional Certificate
Harvard · edX (Rafael Irizarry)
Audit each course for free; pay for the certificate. Covers R, viz, probability, inference, ML, and a capstone. The most-recommended single learning path for stats + ML in R.
AI in Healthcare Specialization
Stanford · Coursera
Stanford School of Medicine's overview of AI in healthcare — from data fundamentals through evaluation and ethics. Most pharma-relevant of the Stanford Coursera offerings.
Microsoft Learn — Machine Learning paths
Microsoft Learn
Free, hands-on learning paths with optional paid Microsoft Certified credentials at the end (Azure Data Scientist Associate is the relevant one). Useful if your org uses Azure.
Kaggle Learn
Kaggle (Google)
Bite-sized free courses on pandas, ML, computer vision, time series, geospatial. Best as a refresher between bigger commitments.
OpenML — open ML data + benchmarks
OpenML
Open repository of curated ML datasets and benchmark results. Useful when you need a teaching dataset that's not the same iris/MNIST as everyone else.
Pharmacometrics & PKPD
Population pharmacokinetic / pharmacodynamic modelling. The dialect of clinical pharmacology and dose-finding.
mrgsolve — User Guide & Vignettes
Metrum Research Group
Open R package for population PK/PD simulation. Vignettes are the de-facto introduction to model-based simulation in R.
Open pharmacometrics teaching materials (Bauer / Mould lectures, NMUsersGroup archives)
Various (NONMEM/PsN/community)
There is no single canonical open pharmacometrics course. The community lives in NMUsers archives, vendor tutorial decks (ICON/NONMEM, Lixoft/Monolix), and conference workshops. Treat this as an entry point — ask a CPDSE pharmacometrician for a curated path.
UCT Pharmacometrics training (PMX Africa)
University of Cape Town · PMX Africa
The University of Cape Town pharmacometrics group's training hub — courses, workshops and a community of practice for learning pharmacometrics.
Data visualisation
Charts that read well in papers, posters, and dashboards. Books and reference sites, mostly free.
Fundamentals of Data Visualization
Claus O. Wilke
Principles-first guide to making honest, readable charts. Tool-agnostic; the principles port to ggplot2, Plotly, matplotlib alike.
ggplot2: Elegant Graphics for Data Analysis (3rd ed.)
Hadley Wickham, Danielle Navarro, Thomas Lin Pedersen
The reference book for ggplot2. Goes deep on the grammar of graphics and the customisation patterns you need for publication-quality figures.
Python Data Science Handbook
Jake VanderPlas
NumPy, pandas, matplotlib, seaborn, and scikit-learn — the canonical reference for the core scientific-Python stack.
Datawrapper Academy
Datawrapper
Tool-agnostic chart-design articles by Lisa Charlotte Muth. Excellent treatment of how to choose a chart type and label it well.
Regulatory, ethics & data governance
GxP, GDPR/HIPAA, fairness, validation. Necessary context for anyone building tools that touch patients.
FDA — Real-World Evidence Program
U.S. Food & Drug Administration
Primary-source FDA guidance on RWE / RWD methodology. The framework most pharma data work eventually has to align to.
EMA — Big Data and Artificial Intelligence
European Medicines Agency
EMA's published reflection papers and the EMA-FDA joint AI principles. The European counterpart to FDA RWE guidance.
FAIRsharing — Standards, Databases, Policies
FAIRsharing.org
Find the right metadata standard, database, or policy for your data. Essential for FAIR-compliant data sharing in life science.
Data protection & information privacy (UCPH)
University of Copenhagen
The University of Copenhagen's information-privacy pages and Data Protection Officer guidance — start here when a project will touch personal data.
Hand-curated and last reviewed 2026-05-08. These are starting points the centre believes in — quality is subjective. Spot a broken link or a better resource? Open an issue or pull request on the website repo.