NKEB22002U Machine Learning and Molecules (MLmol)

Volume 2022/2023

Students write their own neural network code from scratch using Python and use it to predict chemical properties of molecules. The performance is compared to standard machine learning packages such as scikit-learn, Keras, and DeepChem.


Learning Outcome

Basic principles behind Python programming, machine learning, and cheminformatics. Classification and regression using neural networks. Activation functions, back propagation using gradient descent, Overfitting, regularisation, hyperparameter optimisation, and training/validation/test sets.  SMILES strings, molecular fingerprints, and graph convolution as applied to molecules.

Data manipulation and visualisation using Pandas, numpy, and Matplotlib/Seaborn. Manipulation of chemical data using RDKit. Use of scikit-learn, Keras, and DeepChem. 

Prediction of chemical properties using machine learning. Critical evaluation of machine learning models.

See Absalon for a list of course literature

First year organic chemistry and mathematics
Videolectures and classroom discussion
  • Category
  • Hours
  • Class Instruction
  • 12
  • Preparation
  • 93,5
  • E-Learning
  • 50
  • Project work
  • 50
  • Exam
  • 0,5
  • Total
  • 206,0
Continuous feedback during the course
Feedback by final exam (In addition to the grade)
7,5 ECTS
Type of assessment
Oral examination, 30 min
Type of assessment details
In the event of timely submission, a final 30-minute individual oral examination is held during the block's examination period without preparation based on the project report. The exam begins with a 10-20 minute presentation from the examinee, after which the internal assessors ask questions in the project area.
Exam registration requirements

Three out of three assignments have to be approved; b) the report of the individual project has to be submitted by the end of the 8th week of the block"

All aids allowed
Marking scale
passed/not passed
Censorship form
No external censorship
Several internal examiners

Same as ordinary exam. The same report, possibly improved based on feedback, can be used for the oral re-exam.

Criteria for exam assesment

See Learning Outcome