Data Science in Chemistry

Large Language Models, Chemometrics, Predictive and Generative Design with Jupyter
2. Completely Revised and Extended Auflage 2026
ISBN: 978-3-11-153743-6
Verlag: De Gruyter

Buch, Englisch, 594 Seiten, Format (B × H): 170 mm x 240 mm, Gewicht: 500 g

Reihe: De Gruyter Textbook

Data science has become a core discipline of modern chemistry. With the rapid growth of available data, the fourth paradigm of science has taken shape, built on three pillars: computer science, mathematics, and the specialist domain ‘chemistry’. This book shows how to put data science to work: learn how to use Python, cheminformatics, and machine learning to gain new insight from their data. find use cases from pharma and chemistry and learn how their methods apply to the domain.

Data science itself is moving on. Large language models are changing not only the tools but also the way chemists look at their data and their work. The second edition follows this shift: it adds a new chapter on , covering foundation models, prompt engineering, retrieval-augmented generation, fine-tuning, and , and a catalog of design patterns for data science in chemistry.

Autoren/Hrsg.

Gressling, Thorsten

Fachgebiete

• Naturwissenschaften Chemie Chemie Allgemein Chemometrik, Chemoinformatik

Über Autor(innen)

Thorsten Gressling

received his Ph.D. in Chemistry and Computer Science from the University of Kiel and has worked at the frontier of both fields for three decades. He served as AI Transformation Lead at Bayer, where he was named a Bayer Science Fellow, and has carried out projects for leading pharmaceutical and chemical companies. He teaches AI in Chemistry, Cheminformatics, and Lab Informatics at Humboldt-Universität zu Berlin. He is the founder of paramus.ai, an agent-first chemical intelligence platform connecting cheminformatics, the workbench, and the autonomous laboratory.