Teaching Plan Information

1. Course details

1.1. Content area

MULTISCALE, MACHINE LEARNING AND QSAR METHODS APPLIED TO BIOMOLECULES

1.2. Course nature

Optional

1.3. Course level

Máster (EQF/MECU 7)

1.4. Year of study

2

1.5. Semester

Second semester

1.6. ECTS Credit allotment

6.0

1.7. Language of instruction

English. 

1.8. Prerequisites

There not prerequisites. 

1.9. Recommendations

No applicable. 

1.10. Minimum attendance requirement

Attendance is mandatory. 

1.11. Subject coordinator

Noelia Faginas Lago (University of Perugia). 

1.12. Competences and learning outcomes

1.12.1. Competences

BASIC AND GENERAL

CG01 - Students are able to promote, in academic and professional contexts, technological and scientific progress within a society based on knowledge and respect for: a) fundamental rights and equal opportunities between men and women, b) the principles of equal opportunities and universal accessibility for people with disabilities and c) the values of a culture of peace and democratic values.

CG04 - Students develop critical thinking and reasoning and know how to communicate them in an egalitarian and non-sexist way both orally and in writing, in their own language and in a foreign language.

CB7 - Students are able to apply their acquired knowledge and problem-solving skills in new or unfamiliar environments within broader (or multidisciplinary) contexts related to their field of study.

CB10 - That students possess the learning skills that will enable them to continue studying in a largely self-directed or autonomous manner.

TRANSVERSALS

CT02 - The student is organised in his/her work, demonstrating that he/she knows how to manage the time and resources available to him/her.

CT09 - Ability to obtain, select, elaborate and process information from different sources with objective criteria, prioritising them according to their quality and relevance.

CT10 - Predict and control the evolution of complex situations through the development of new and innovative work methodologies adapted to the scientific/research and professional field.

CT11 - Identify and rigorously select the appropriate methodology to formulate hypotheses, define problems and design work strategies specific to research with an emphasis on ethical commitment.

SPECIFIC

SC13 - Students are able to handle the most common programming techniques in physics and chemistry and are familiar with the essential calculation tools in these areas.

SC16 - The student is able to discern between the different existing methods and how to select the most appropriate one for each problem.

SC19 - The student is familiar with the computational techniques that, based on molecular mechanics and dynamics, are the basis for the design of molecules of interest in fields such as pharmacology, petrochemistry, etc.

1.12.2. Learning outcomes

not applicable. 

1.12.3. Course objectives

The aim of this course is to provide students with the basic knowledge of machine learning techniques and QSAR (Quantitative Structure-Activity Relationship) methods applied to small and large molecular systems, such as simple reagents or biomolecules. Machine Learning (ML) allows teams to solve problems by learning from data. In recent years ML has been increasingly applied to a wide variety of chemical challenges, from improving computational chemistry to drug and material design and even synthesis planning. This course aims to introduce this rapidly growing reality.

1.13. Course contents

1. Introduction to Cloud Computing.

2. Virtualisation and container architectures.

3. Big Data management services and automatic deployments.

4. Binary classification of proteins using Machine learning approach.

5. Multiscale modelling of biochemical processes.

6. High-throughput molecular dynamics: theory and applications.

7. Introduction to deep learning and Tensorflow.

8. Multiscale molecular dynamics of biomolecules.

9. Machine learning possibilities.

10. QSAR methods applied to biomolecules.

1.14. Course bibliography

Combined Quantum Mechanics/Molecular Mechanics (QM/MM) Methods in Computational Enzymology M.W. van der Kamp and A. J. Mulholland Biochemistry 2013.

QM/MM Methods for Biomolecular Systems H. M. Senn and W. Thiel (2009), QM/MM Methods for Biomolecular Systems. Angewandte Chemie Int. Ed. 2009. 

A Hybrid Potential Reaction Path and Free Energy Study of the Chorismate Mutase Reaction S. Martí, J. A., V. Moliner, E. Silla, I. Tuñón, J. Bertrán, and M. J. Field Journal of the American Chemical Society 2001.

2. Teaching-and-learning methodologies and student workload

2.1. Contact hours

2.2. List of training activities

3. Evaluation procedures and weight of components in the final grade

3.1. Regular assessment

The final mark for the course will be based on: 20% final exam of the course and 80% corresponding to the delivery of a report of exercises proposed by the professor.

3.1.1. List of evaluation activities

3.2. Resit

The evaluation will be based on the delivery of a report with the proposed exercises.

3.2.1. List of evaluation activities

4. Proposed workplan

The course will be organized by University of Perugia.