Artificial Intelligence in Chemistry: A beginner’s guide towards Data Scientist 0600-EN-AICh

The course is designed for general university students with a background in chemistry and mathematics. It consists of 20 hours of lectures covering the basics of AI, its historical context, key algorithms (e.g., neural networks, decision trees), and its role in modern chemistry. The computational laboratory (40 hours) offers hands-on training in AI tools such as Python, TensorFlow, and cheminformatics libraries. Students will engage in projects such as molecular property prediction, chemical reaction modeling, and exploring datasets for drug discovery. Ethical considerations and limitations of AI in chemistry are also discussed.

Total student workload

Contact hours with teacher: - participation in lectures: 20 hrs - participation in laboratory: 40 hrs Self-study hours: - preparation for lectures/tutorial/laboratory - 20 hrs - preparation for presentations - 10 hrs - completion of a projects - 20 hrs - reading literature - 10 hrs Altogether: 120 hrs

Learning outcomes - knowledge

- Understands the fundamentals of artificial intelligence and its applications in chemistry. - Knows key algorithms and models used in computational chemistry with machine learning, including: linear regression, least square regression, k-nearest neighbours, support vector machines, classification and regression trees and artificial neural networks - Familiar with the ethical implications and challenges of AI in science.

Learning outcomes - skills

- Able to handle and visualize different types of datasets common in Chemistry. - Use Python for AI-driven data analysis in chemistry. - Process data for use in machine learning approaches. - Able to apply AI techniques to solve basic chemical problems. - Identify the suitability of different ML approaches to answer chemical questions based on data. - Use standard ML python pipelines to train models. - Assess the quality of the models and their predictive power. - Recognize different applications of ML in Chemistry.

Learning outcomes - social competencies

- Recognizes the role of AI in advancing chemistry and other sciences. - Demonstrates readiness to explore interdisciplinary approaches integrating AI and chemistry. - Aware of the need for ethical considerations when using AI tools. - Develop interpersonal skills such as communication, cooperation in group and problem-solving abilities

Course coordinators

Saikat Mukherjee

Teaching methods

- informative lecture - laboratories - discussion - presentation of a paper - project work

Observation/demonstration teaching methods

- display
- simulation (simulation games)
- staging

Expository teaching methods

- programmed material
- informative (conventional) lecture
- description
- problem-based lecture
- participatory lecture

Exploratory teaching methods

- laboratory
- practical
- seminar
- presentation of a paper
- brainstorming
- points system
- project work

Online teaching methods

- cooperation-based methods
- exchange and discussion methods
- content-presentation-oriented methods
- evaluative methods
- methods developing reflexive thinking

Prerequisites

General Chemistry General Mathematics No prior knowledge of programming is required

Assessment criteria

Assessment methods:
- seminar: 40 pts
- Project: 40 pts
- class activity: 20 pts

Assessment criteria:

fail- 0 - 49 pts (< 50 %)
satisfactory- 50 - 59 pts (< 60 %)
satisfactory plus- 60 - 65 pts (< 65 %)
good – 66 - 75 pts (< 75 %)
good plus- 76 - 80 pts (< 80 %)
very good- 81 - 100 pts (< 100 %)

Additional information

Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system:

Description of 0600-EN-AICh in USOSweb