27828 Chemoinformatics in drug discovery
|Kemoinformatik i lægemiddelforskning|
Point( ECTS )
Taught under open university
|E5B (Wed 13-17)
Scope and form:
|Lectures, computer exercises, mini-projects|
Duration of Course:
Type of assessment:
General course objectives:
The aim of the course is to introduce the participants to various
chemoinformatics methods, to show examples of the use of
chemoinformatics in modern drug research, and to give the
participants practical experience through hands-on chemoinformatics
A student who has met the objectives of the course will be able to:
- Define chemoinformatics and name the main areas of application
within drug discovery.
- Interpret the most important formats used for describing
- Describe the most widely used machine learning tools in
chemoinformatics and the algorithms that they are based on.
- Understand the differences between linear and non-linear
models, supervised and unsupervised machine-learning, clustering
- Argue on how to choose the appropriate computational tools for
a given problem.
- Describe rational work flows for data mining and for preparing
high quality data sets for modeling purposes.
- Interpret the output from and evaluate the performance of a
given computational tool.
- Navigate and extract information from annotated chemical
- Construct and interpret drug-protein interaction networks.
- Plan, carry out and present computer exercises and
mini-projects as team work.
- Be able to evaluate your own work and relevant scientific
- Present projects orally by using MS PowerPoint and by creating
a scientific poster.
Data sets: Extraction of data from a large database, evaluation of
Molecular structures: Graphical representation, 1D, 2D and 3D
molecular structures, pharmacophores.
Molecular descriptors: Generation of descriptors reflecting the
physical and chemical properties of the molecules. Molecular
Properties: Calculation of physical chemical properties such as
solubility and partition coefficients, pharmacological properties
such as absorption and toxicity, and global properties like oral
bioavailability and drug-likeness.
Data analysis: Clustering, classification and regression methods.
Multi-linear regression. self-organizing maps, principal component
analysis, artificial neural networks, decision trees, support
Applications of chemoinformatics in drug research: Chemical
libraries, chemogenomics libraries, virtual screening,
protein-ligand interactions and interaction networks, ligand
activity profiling, quantitative structure-activity relationships
(QSARs), and prediction of ADMET properties (absorption,
distribution, metabolism, elimination and toxicity).
Tools: Internet-based programs, databases, in-house and commercial
The individual, oral exam is based on the poster of the final
mini-project but will also cover other parts of the
Green challenge participation:
Please contact the teacher for information on whether this course
gives the student the opportunity to prepare a project that may
participate in DTU´s Study Conference on sustainability, climate
technology, and the environment (GRØN DYST). More infor
|27 Department of
Registration Sign up:
Last updated: 20. juni, 2014