You are here:

99486 - Simulation Methods and Machine Learning in Medicinal Chemistry

Academic Year 2022/2023

                
                        Docente:
                        Matteo Masetti
                    
                        Credits:
                        4
                    
                        SSD:
                        CHIM/08
                    
                        Language:
                        Italian
                    
                        Teaching Mode:
                        Traditional lectures
                        
                            Campus:
                            Bologna
                        
                            Corso:
                            Single cycle degree programme (LMCU) in
                            Chemistry and Pharmaceutical Technologies (cod. 8412)

                                    Course Timetable
                                
from Apr 17, 2023 to May 31, 2023

Learning outcomes

At the end of the course, the student knows the basic aspects of consolidated and emerging computational approaches and methodologies in the pharmaceutical chemistry field. The student is able to address the many problems that characterize the phases of drug discovery and development through the choice of the most appropriate computational tool.

Course contents

Introduzione to the course. Distinction between computer simulation methods and Machine Learning methods.

Computer simulation methods: the potential energy surface and Molecular Dynamics simulation method.

Elements of statistical mechanics in the description of the protein-ligand binding process.

Application of computer simulation methods:
- Prediction of the free energy of protein-ligand binding
- Prediction of protein-ligand binding kinetics
- Study of allosteric and signal transduction mechanisms
- How to tackle “difficult targets” (intrinsically disordered protein, cryptic pockets, …)

Introduction to multiscale modeling.

Machine Learning methods: classes of machine learning methods (supervised and unsupervised learning).

Data struacture in pharmaceutical chemistry. The concept of featurization.

Application of Machine Learning methods:
- Prediction of molecular properties
- De novo design
- Drug repurposing
- Prediction of reactivity and retrosynthetic analysis

Perspectives on the integration of simulation methods and machine learning.

Readings/Bibliography

Scientific articles and reviews suggested by the teacher.

Teaching methods

Lectures accompanied by "case studies" with the aim of showing the practical application, in the real world of academic research and industry, of the methodologies described.

Assessment methods

The learning assessment test consists of oral interviews on the topics covered during the course.

Teaching tools

Slides, scientific publications and other teaching material made available through the Virtual Learning Environment platform.

Office hours

See the website of Matteo Masetti