Data science in Chemistry

Course goals

At the end of the course the student will:
• Understand the fundamentals of data science.
• Understands error propagation.
• Understands methods for regression.
• Understands methods for classification.
• Knows methods for data visualization.
• Knows basic methods used in chemometrics and machine learning.
• Have a broad enough overview over these methods to select and, after further specialization, apply them to suitable data science problems in chemistry.
 

Content

Self-assessment intake quiz:
An online quiz will be provided to the students at the start of the course, so they can self-assess their prior knowledge concerning the topics addressed in the course. This quiz is intended both as a selfassessment tool for the students and as a way for the lecturers to judge whether adjustments in the program are needed to tailor it to the background of most participants and to identify whether additional study material is needed.
The intake exam will be prepared via MS forms and will remain open to enrolled students from Monday September 1, 2025, 9 a.m., to Sunday September 7, 2025, 6 p.m. During this period, students will be able to take the test at a time of their own convenience. There is no time limit to complete the quiz, but it can be done only once.
The intake quiz is compulsory but will not be graded. However, by participating in the intake exam the student becomes eligible to receive one bonus point for the final exam. The bonus point will be added to the grade obtained by the student in the final exam, but only if she/he correctly answers the
specific bonus point question in the respective final exam (i.e., their maximum grade is 10 + bonus). The bonus question will be taken from the intake exam (but not be marked as such). Students who did not participate in the intake exam will not be entitled to the bonus point, even if they correctly
answer the bonus question (i.e., their maximum score is 10).

Brief course content
Data science is an interdisciplinary field that uses statistics, algorithms, scientific computing, and scientific methods, to extract or extrapolate knowledge and insights from structured or unstructured and potentially noisy data. Data science is related to data mining and big data.
Definition: “Data science is performed to analyze, understand, and extract actual phenomena in data. The challenge is to identify unique patterns and variables.” [1]
Because the goal in data science is to understand and extract insights, it is a multidisciplinary field that combines concepts from computer science, statistics, machine learning, and data analysis with domain knowledge. Here, the domain we focus on is chemistry.
The two main questions in data science are “What can we learn from this data?” and “What actions can we take, once we find whatever it is we are looking for?” [1]. To answer these questions, we first need to understand and prepare the data, and then we typically face two main types of problems:
– Classification, which means assigning something to a discrete set of possibilities, and
– Regression, which means predicting a numerical value.
Additionally, we need to inspect (check uncertainties) and communicate results and findings, which encompasses the field of data visualization.

This course will provide basic understanding of the fundamentals of data science, with a focus on applications in chemistry, especially analytical chemistry. The aim of the course is to provide students with the knowledge and skills to understand the working principles of modern data science. The content taught will enable them to choose and further investigate methods and techniques that are best suited to understand, manage, process, and extract knowledge from data acquired or generated in a chemistry context.
Specific topic that will be covered:
• What is Data and what is Data Science?
• Data curation, the FAIR principle, and Big Data
• Propagation of uncertainty
• Regression
• Classification
• Visualization
• Chemometrics and machine learning

Reference:
[1] Data Science in Chemistry, Thorsten Gressling, Walter de Gruyter GmbH, Berlin/Boston, 2021,
ISBN 978-3-11-062939-2.