LACDR PhD Portal

Scientific computing for Drug Discovery in Python and/or R

Data analysis with Python and R are rapidly becoming essential skills for modern scientists. Therefore, we are offering courses to develop your scientific computing skills. Those courses are optional for LACDR PhD candidates.

The following courses are offered:
• basic scientific programming in Python and/or R
• applied scientific computing for drug discovery in Python and/or R

Course basic scientific programming in Python and/or R

Learning goals basic course

After following this course you will be able to use R and Python in your basic data manipulation and visualization tasks. You will be able to reformat data as needed, calculate summary statistics and you will be able to visualize results in publication ready graphs. Moreover, you will learn the basic structure of the language in such a way that it will become easier to follow more advanced topics such as Bioconductor or more advanced applications.

Course program

During this course the following subjects will be treated:

• R and python syntax
• R and python data structures
• R and python objects, methods and functions
• reading and writing of data files
• data processing such as reshaping and aggregation
• making publication ready graphs

Course applied scientific computing for drug discovery in Python and/or R

Learning goals applied course

• Machine learning in Python

• The student will be able to train machine learning models in Python (on cheminformatics data)
• The student will have hands on experience with the most commonly applied machine learning models (random forests and support vector machines)
• The student will learn procedures to create training and test sets that can estimate model performance on unseen data.

• Linear (mixed) models for inferential statistics with R

• The student will be able to explain the mathematical principles of linear models to obtain inferential statistics such as an ANOVA.
• The student will be able to decide when to use a linear model and when to use a mixed model depending on the data structure.
• The student can apply basic linear (mixed) models in R and correctly interpret the results.
• The student will have sufficient knowledge to understand the limitations of linear models and know about alternatives such as Generalized Additive Models.                     

• Pharmacokinetic modeling and dose-response modeling with R

• • The student will be able to perform regression analysis and obtain meaningful derived summary measures.
  • The students can make predictions based on linear models and mixed effects models.

Course program

During this course the following subjects will be treated:

• Machine learning in Python
• Statistical inference in R with linear (mixed) models
• Pharmacokinetic modeling in R
• Dose response analysis in R

Credits - application

The course basic scientific programming in Python and/or R will give you 48 education hours, of which 32 contact hours (1,7 EC points) in total. The course applied scientific computing for drug discovery in Python and/or R will give you 42 education hours, of which 24 contact hours (1,5 EC points).

As well as the basic course as the applied course will be given once a year. All PhD candidates will receive a notification, when the registration will be opened. It is possible to follow only the modules for Python or the modules for R.