CSC - COPENHAGEN SCHOOL OF CHEMOMETRICS

NSCPHD1191 - LPhD191

June 1st July 3rd, 2015

Main responsible: Jos Manuel Amigo

1
Description of the course:
Spectroscopy and Chemometrics (SPECC) group is more than happy to announce the new
edition of the PhD course:

Copenhagen School of Chemometrics - CSC

CSC is a five-week school designed to be an introduction to different key aspects of advanced data
analysis in science. CSC addresses to PhD students/post-docs, associate professors, etc. who want
to acquire or refresh basic knowledge on multivariate data analysis from different disciplines
(Chemistry, Physics, Biology, Geology, Environmental Sciences, etc.). CSC also addresses to
researchers working in industry or research laboratories who want to implement multivariate data
analysis in their daily research environment.

CSC is thought to be an intensive school. Therefore, CSC will be held in five weeks structured in
ten different seminars/workshops where the students will be more than welcome to work with their
own data together with high-qualified teachers.

Targets of CSC:
CSC aims at being a platform for:

- Learning basic and advanced data analysis methods: CSC is specifically designed for
researchers who want to start using data analysis in their routine work.

- Sharing knowledge and interchange ideas between students covering different scientific
backgrounds: One of the key points of CSC is the interaction between the students to discuss
issues and troubleshooting always within the framework of scientific data analysis and
performance. The reports days and the workshop will offer the opportunity to the students to
discuss, share and improve their main issues and initiatives in a professional environment.

2
- Meeting world-wide recognized experts of Multivariate Data Analysis in an open discussion
forum environment: CSC will count on teachers that are well-recognized experts on chemometrics
and multivariate data analysis in their respective fields. This, at the same time, will offer the
possibility of opening new collaborative frameworks between students and teachers.

- Flexibility in the seminars and ECTS credits: The students can chose to attend the seminars
which they consider more relevant for their research. There is no a minimum of seminars that the
student must attend. Also, they will have the opportunity to deepen into any multivariate method in
the WORKSHOP days. In total, attending the whole school, one student can obtain 12 ECTS
credits.

Timetable, topics and lecturers:

The timetable and topics for CSC - 2015 are:

3
All the seminars run from 9 a.m. to 5 p.m. with a lunch break. Organization of the breaks and the
final timetable for each seminar will be under the responsibility of the corresponding teacher.

Lecturers:

1.- LinAl: Dr. Morten A. Rasmusen.

2.- DoE: Dr. Ricardo Leardi.

3.- EXPLORE: Prof. Rasmus Bro.

4.- REGRESS: Dr. Jos Manuel Amigo.

5.- CLASS: Dr. Davide Ballabio.

6.- VarSel: Dr. smund Rinnan.

7.- MCR: Dr. Jos Manuel Amigo.

8.- 3-WAY: Prof. Rasmus Bro.

9.- MSPC: Dr. Frans van den Berg

10.- MetaboMetrics: Prof. Age Smilde and Dr. Frans van der Kloet.

For PhD students:

Each seminar accounts for 1 or 1.5 ECTS (See previous table). All PhD students who want to
obtain the corresponding ECTS credits from the seminars will be obliged:

1) To attend the corresponding seminars.

2) To deliver the corresponding reports (see below). The length, content and the final delivering
date of the reports will be specified by the corresponding lecturer.

4
Detailed description for each seminar:
1.- LinAl. Linear Algebra for Multivariate Data Analysis

Linear Algebra is the basis of the Multivariate Data Analysis. Therefore, it is important to give it a
central position in any school about multivariate data analysis. This seminar will be a clear
introduction to the linear algebra behind the multivariate models that will be presented in the
school.

Previous knowledge needed: None.

Software: Matlab.

2.- DOE. Introduction to Design of Experiments

The basic theory and practice of Design of Experiments and statistical inference is revisited. The
aim is to give a practitioner idea or reminder about the main features and uses of DoE. The seminar
will be based on teaching hours and some guided exercises.

Previous knowledge needed: Basic statistics.

Software: Own software that can be downloaded for free at:

http://gruppochemiometria.it/gruppo-lavoro-r-in-chemiometria.html

3.- EXPLORE

Principal Component Analysis has become the most powerful and versatile tool for analyzing data
tables in Analytical Sciences. Here we present a course to show the main benefits and drawbacks of
PCA when it is used for different kind of analytical data: Spectroscopy, environmental assessment,
experiments performance, chromatography, etc. Moreover, preprocessing of different type of data
will be also addressed in the seminar.

Previous knowledge needed: None.

5
Software: Matlab and/or PLS-Toolbox. A full demo version of PLS-Toolbox can be
downloaded at:

http://www.eigenvector.com/

4.- REGRESS

If PCA is the keystone of pattern recognition methods, PLS is the keystone of multivariate
calibration methods. This seminar will give a general overview of different multivariate calibration
strategies and will focus in Partial Least Squares regression.

Previous knowledge needed: Basic knowledge of PCA and linear algebra.

Software: Matlab and PLS-Toolbox. A full demo version of PLS-Toolbox can be downloaded
at:

http://www.eigenvector.com/

5.- CLASS.

The seminar is focused on the theory and practice of two linear classification tools (SIMCA and
PLS-DA). The seminar will be based on teaching hours with guided exercises and practical sessions
with real cases.

Previous knowledge needed: Basic knowledge of PCA.

Software: Matlab.

6.- VarSel.

This new seminar aims at revisiting the most important variable selection methods for regression
and classification purposes with the aim at improving the performance of the models.

Previous knowledge needed: Basic knowledge of multivariate regression and classification

methods.

6
Software: Matlab.

7.- MCR

In the last years, curve resolution techniques are gaining importance in modeling of different
analytical data types. Especially, Multivariate Curve Resolution has widely demonstrated its
usefulness in kinetic modeling, solving problems in chromatographic data (peak
resolution/deconvolution) and hyperspectral images. This seminar will offer a general overview of
curve resolution methodologies and will focus in multivariate curve resolution applied to different
analytical problems.

Previous knowledge needed: Basic knowledge of PCA.

Software: Matlab and MCR-ALS Toolbox. MCR-ALS Toolbox can be downloaded for free
at: http://www.mcrals.info/

8.- 3-Way

Three-way analysis, covering PARAFAFAC, PARAFAC2 and Tucker3, is the curve resolution
method for three-dimensional and multi-dimensional structures.

Previous knowledge needed: Basic knowledge of PCA.

Software: Matlab and PLS-Toolbox. A full demo version of PLS-Toolbox can be downloaded
at:

http://www.eigenvector.com/

9.- MSPC

Nowadays, there are more and more companies that want to implement fast and reliable
multivariate statistical methods for real-time control of the performance of different processes. In
this seminar, the main Multivariate Statistics Process Control (MSPC) tools will be revisited and
different real examples of how MSPC has been implemented in companies will be shown.

7
Previous knowledge needed: Basic knowledge of PCA, regression methods and linear algebra.

Software: Matlab.

10.- MetaboMetrics

Undoubtedly, metabolomics has become an important tool to address metabolic pathways in

different biological systems. This seminar/workshop aims at offering a general introduction to the
main metabolomics data analysis methods, including preprocessing of metabolomics data.
Moreover, Analysis of variance-Simultaneous Component Analysis (ASCA) and Metabolic
Network Inference will be explained and exemplified.

Previous knowledge needed: Basic knowledge of PCA, regression methods and linear algebra.

Software: Matlab.

8
Location, subscription and fees:
Location: CSC will be held at the department of food sciences of the University Of Copenhagen,
Denmark. The classroom will be the R-437. It is in the fourth floor of the building shown in the
map. The address is Rolighedsvej 30, Frederiksberg C.

Subscription: For joining us, just send an e-mail to Dr. Jos Manuel Amigo ([email protected]) or
Ms. Jeanette Venla Hansen ([email protected]). The e-mail must contain: Full name, position,
university/company, country, which seminars to attend, need of ECTS credits?

Fees: The seminars are free of charge for everybody. NEVERTHELESS, there will be a fee of
2000 Danish Krone for not coming when joining.

9
Important information:
- Read careful the description for each seminar and the needs regarding software. Unless strictly
needed, we will not provide with laptops or software. Therefore, bring your own laptops with the
required software already installed.

- We will provide with office material (notebooks, folders, USB, pens, etc.)

- There will be free WI-FI internet connection.

- We can issue parking permission. But communicate in advance.

- Lunch is not included. Nevertheless, there will be free coffee and refreshment for the coffee
breaks.

10
List of participants:
Student e-mail
Guillermo Grindlay [email protected]
Bhaskar Mitra [email protected]
Mohammed ALAOUI MANSOURI [email protected]
Ren Bjerregaard Madsen [email protected]
Peter Tiainen [email protected]
Robert Frentrup [email protected]
Wenhao Su [email protected]
Helena Marie Lindholm Meng-Lund [email protected]
Chelsi Wicks [email protected]
Flemming Mller [email protected]
Henrik Kragh [email protected]
Yuanyuan Pu [email protected]
Maja Hermann Kamstrup-Nielsen [email protected]
Aissam Eliani [email protected]
Yi Peng [email protected]
Ecem Evrim Celic [email protected]
Manos Poulakis [email protected]
Patz, Dr. Claus-Dieter [email protected]
Helena Marie Lindholm Meng-Lund [email protected]
Siobhn Hennessy [email protected]
Natalia Vazquez [email protected]
Noemi Ayala [email protected]
Alexandra Walsh [email protected]
Kenny, Peter [email protected]
Siewert Hugelier [email protected]
Peinado, Antonio [email protected]
Luciana Oliveira [email protected]
Matero, Sanni [email protected]
Giulia Pratico [email protected]
Ekaitz Martinez [email protected]
Maria Francisca Dias Folque de Gouveia [email protected]
Troels Matias Dalgaard Pedersen [email protected]
Carolina Santos [email protected]
NICOLA CAVALLINI [email protected]
Stine Kreutzmann [email protected]
Lars Christoph Schrbbers [email protected]
Yongqiang [email protected]
Ghazaleh Aliakbarzadeh [email protected]
Daniela Barraza Pinto [email protected]

11
Matheo Baumann [email protected]
Andrea Biereth [email protected]
Pinar Bulut [email protected]
Patrick Kehrer [email protected]
Felix Tapphorn [email protected]
Robert Zehentbauer [email protected]
Anita Lorenz [email protected]
Edwin Ostertag [email protected]
Natalja Genina [email protected]
Alessandro Giraudo [email protected]
Mette Holse [email protected]

12