Entry requirements

150 credits, including 120 credits from courses in biomedicine, pharmaceutical sciences and/or natural sciences/engineering. Proficiency in English equivalent to the Swedish upper secondary course English 6.

Learning outcomes

After course completion, the student should be able to:

- explain and use basic concepts and methods in statistics

- explain and use standard regression methods and methods for estimating model parameters

- describe and use methods for exploratory and predictive multivariate data analysis

- describe and apply basic concepts of model evaluation

- describe and use basic statistical experimental design methods

- apply these methods to typical drug discovery/development scenarios, such as the analysis of genomic, proteomic, chemical and biological data, the modelling of relationships between chemical structures of drug molecules and their physical, biological and pharmacological properties, and the modelling of drug effects using preclinical and clinical data.

- analyse, assess and present the results of statistical data analyses

Content

The course covers the use of statistical methods to analyse and model chemical and biological data in drug discovery and development. The course illustrates general concepts of the differant methodologies discussed, their applicability to specific types of problems encountered in the development of new drugs, and their practical use. Focus lies on applications in drug discovery and development, including: informatics applied to genomic, proteomic, chemical and biological data, structure-property relationship modelling, and model-based preclinical and clinical pharmaceutical research. By applying the methods discussed to relevant cases, the students will gain hands-on experience in several statistical methods and software.

The course contents include, for example:

- basic statistical concepts, such as distributions (continuous/discrete), location/dispersion/shape, hypothesis testing, ANOVA, Bayesian statistics, prior/posterior probabilties

- regression methods and methods for estimating model parameters (e.g., linear/multiple linear/non-linear/robust regression, maximum likelihood estimation)

- multivariate data analysis (e.g., principal components analysis, cluster analysis, partial least squares projection, support vector machines, decision trees)

- model evaluation (e.g., cross-validation, boot-strapping, permutation analysis)

- statistical experimental design (e.g., factorial design, D-optimal design)

After course completion, the students should be knowledgeable in the general concepts and standard methods in multivariate data analysis, experimental design, parameter estimation, and the evaluation of model fit, and be able to apply these to typical drug discovery/development questions.

Instruction

Teaching is a mixture of lectures, computer exercises and group exercises. Compulsory sections: computer exercises, group exercises, and student presentations.

The course is given in English.

Assessment

Examination will take place at the end of the course, and comprises an oral group-based presentation of a project (3 credits) and an individual written project report (4.5 credits). Passing the course requires approved examination of the compulsory sections. 

If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the University's disability coordinator.

Other directives

This course substitutes and corresponds to 3FG890, Preclinical and Clinical Data Analysis in Predictive Drug Discovery/Development.