Algorithms in Bioinformatics - #22125

Information for participants

GENERAL SCHEDULE
Lectures will be in the morning from 9.00 - 12.00, and exercises in the afternoon from 13.00 - 17.00.

The morning sessions will consist of lectures and small practical exercises introducing the different algorithms, and the afternoon sessions will consist of programming exercises where the algorithms will be implemented.

Note, that due to the Covid19 situation, this years course will be given in an online version. Further, the theroretical part of the course will in most cases be given as recorded lectures. Recorded lectures are marked as "Recorded" and online sessions as "Online" in the course program. Links to recorded lectures is provide in the program below. The online session will be via Zoom, and links provided on the program next to the session.

The main programming language will be Python (yes, this has been changed compared to earlier years), and all program templates provided in the course will be written in Python. Prior knowlegde of Python programming is NOT required. However, basic programming skills are required to follow the course.

LITERATURE: The course curriculum consists of review paper and selected chapters from Immunological Bioinformatics, Lund et al., MIT Press, 2005. All course material will be made available online during the course. All course material is available either as open access or here Course material.

PROGRAMS AND TOOLS

To do the exercises you must have a Linux/Darwin envirronment on your laptop. See informations on prerequisites on: Tools for SSH and X11.
You must have a Python installation (both Python2 and Python3 can be used), and be able to run "jupyter-notebook".
For help on installing Python and some general links with introduction to Python refer to Peter Wads notes on Course preparation from 36610 - Python and Unix for Bioinformaticians. Note, you do not need Python3 if you already have Python2 installed.
Python for Non-Programmers
Python Numpy Tutorial

Course Programme
Please note that the programme is updated on a regular basis - click the 'refresh' button once in a while to make sure that you have the most updated information

LITERATURE:

The course curriculum consists of review paper and selected chapters from Immunological Bioinformatics, Lund et al., MIT Press, 2005. All course material will be made available online during the course. All course material is available either as open access or here Course material

Friday, 4. June

Introduction to course, UNIX and Python programming crash course 101
Morten Nielsen

BACKGROUND TEXTS

9.00 - 9.20 "Recorded": Introduction to the immune system; Introduction to the immune system (MP4). [PDF] .
9.20 - 9.35 "Recorded": Performance measures; Performance measures (MP4). [PDF] .
9.35 - 9.50: Coffe break
9.50 - 10.00 "Online": Introduction to course; Introduction to course (MP4). [PDF] .
10.00 - 12.00 "Online": Unix crash course; A UNIX/Linux crash course; Information about breakout rooms; Signup sheet for help/questions (add your breakout room number and name)
12.00 - 13.00: Lunch
13.00 - 13.30 "Online": Questions to the mornings lectures and other general questions - Cancelled
13.30 - 17.00 "Recorded": Weight matrix construction (MP4). [PDF]. [PPTX].; Logo Handout; Handout. Estimation of pseudo counts

Monday, 7. June

Weight matrix (PSSM) construction
Morten Nielsen

BACKGROUND TEXTS

Immunological Bioinformatics. MIT Press. Chapter 4.

9.00 - 9.30 "Recorded": Some notes on sequence alignment (MP4) [PDF] .
9.30 - 10.00 "Online": Checking that we all have python and jupyter-notebook installed and running
10.00 - 12.00 "Online": A brief introduction to Python programming and Jupyter-notebooks; Python intro; Signup sheet for help/questions (add your breakout room number and name)
12.00 - 13.00: Lunch
13.00 - 13.30 "Online": Questions to mornings lecture and yesterdays exercise (MP4) (2020 MP4)
13.30 - 17.00 "Online": Implementation of PSSM construction from pre-aligned sequences including pseudo count correction for low counts and sequence clustering; PSSM construction and evaluation; Signup sheet for help/questions (add your breakout room number and name)

Tuesday, 8. June

Sequence alignment, Dynamic programming, and Psi-Blast
Morten Nielsen

BACKGROUND TEXTS
Essentials:

Additionals:

9.00 - 11.00 "Recorded": Blosum matrices (MP4) [PDF]; Sequence alignment (MP4) [PDF] . [PPTX] .; Handout (O3); Handout (O2)
11.00 - 12.00 "Recorded": Blast alignment heuristics, Psi-Blast, and sequence profiles [PDF] . [PPTX] .; Psi-Blast handout.
12.00 - 13.00: Lunch
13.00 - 13.30 "Online": Questions to mornings lectures and yesterdays exercises (MP4) (MP4 2020 class)
13.30 - 17.00 "Online": Implementation of the Smith-Waterman Dynamic programming algorithm; Matrix dumps from alignment programs (to be used for debugging); Signup sheet for help/questions (add your breakout room number and name)

Wednesday, 9. June

Data redundancy reduction algortihms
Optimizations methods
Gibbs sampling
Morten Nielsen

BACKGROUND TEXTS
Essentials:

Additionals:

Simultaneous alignment and clustering of peptide data using a Gibbs sampling approach.Bioinformatics. 2012 Oct 24. [Epub ahead of print]

9.00 - 10.00 "Recorded": Data redundancy reduction algorithms (Hobohm1 and Hobohm2) (MP4). [ PDF]. [ PPTX].
10.00 - 10.45 "Recorded": Optimization procedures - Gradient decent, Monte Carlo; Optimization procedures (MP4) [PDF] [PPTX]; GD handout
10.45 - 11.00: Break
11.00 - 12.00 "Recorded": Gibbs sampling and Gibbs clustering; Gibbs sampling (MP4). [PDF] . [PPTX] .
12.00 - 13.00: Lunch
13.00 - 13.30 "Online": Questions to mornings lectures and yesterdays exercise (MP4) (MP4 2020)
13.30 - 17.00 "Online": Hobohm redundancy reduction algorithms; Implementating of a Gibbs sampling algorithm for prediction of MHC class II binding; Signup sheet for help/questions (add your breakout room number and name)

Thursday, 10. June

Hidden Markov Models
Morten Nielsen

BACKGROUND TEXTS

9.00 - 11.00 "Recorded": Hidden Markov models (with a break around 10.30); Viterbi decoding, Forward/Backward algorithm, Posterior decoding, Baum-Welsh learning; HMM (MP4) [ PDF]. [ PPTX]; Viterbi Handout; Forward Handout
11.00 - 12.00: Profile Hidden Markov Models. "Recorded" (part of the HMM talk above)
12.00 - 13.00: Lunch
13.00 - 13.30: Questions to mornings lecture and yesterdays exercise (MP4) (MP4 2020)
13.30 - 17.00 "Online": Implementation of Viterbi and posterior decoding.; Hidden Markov exercises; Signup sheet for help/questions (add your breakout room number and name)

Friday, 11. June

Cross validation and training of data driven prediction methods. Stabilization matrix method (SMM)
Morten Nielsen

BACKGROUND TEXTS

9.00 - 9.45 "Recorded": Cross validation and training of data driven prediction methods; Cross-validation, overfitting and method evaluation (MP4). [PDF] . [PPTX] .
9.45 - 10.15 "Recorded": Stabilization matrix method (SMM) background; SMM background (MP4). [PDF] . [PPTX] .; SMM handout
10.15 - 10.30: Break
10.30 - 12.00 "Online": Implementing and evaluating SMM algorithms using cross-validation
12.00 - 13.00: Lunch
13.00 - 14.00 "Online": Quiz with questions capturing essential parts of course up to now Quiz; Questions to mornings lecture and yesterdays exercise (MP4) (MP4 2020); Description of potential projects and formation of groups; Project suggestions, and descriptions.; Document for project signup.
14.00 - 17.00: Continuation of exercise; Answers; Signup sheet for help/questions (add your breakout room number and name)

Monday, 14. June

Artificial neural networks. Sequence encoding, feedforward and backpropagation algorithm
Morten Nielsen

BACKGROUND TEXTS

Immunological Bioinformatics. MIT Press. Chapter 4.

Background
Sequence encoding
Feed forward algorithm
Back-propagation and neural network training

9.00 - 10.30 "Recorded": Artificial neural networks Part 1 (MP4). Artificial neural networks Part 2 (MP4). [PDF] . [PPTX] .; Handout; Answers
10.30 - 10.40: Break
10.40 - 12.00 "Recorded": Network training - backpropagation; Training of artificial neural networks (MP4).. [PDF] . [PPTX] .; Handout
12.00 - 13.00: Lunch
13.00 - 13.30 "Online": Questions to mornings lecture and yesterdays exercise (MP4) (MP4 2020)
13.30 - 17.00 "Online": Artificial neural networks (Feedforward and Backpropagation); Signup sheet for help/questions (add your breakout room number and name)

Tuesday, 15. June

An introduction to Deep neural network architectures
Introduction to the project work
Morten Nielsen

BACKGROUND TEXTS

Immunological Bioinformatics. MIT Press. Chapter 4.

9.00 - 9.30 Online: NNAlign, alignment using ANN's [PDF] NNAlign (MP4).
9.30 - 10.00 Online: Trick for ANN training [PDF]. NNtricks (MP4).
10.00 - 12.00 Online: Exercise: Constructing and training Deep ANN methods (Helle Rus Povlsen && Alessandro Montemurro); FNN lecture slides.pdf.; deep_neural_nets slides.pdf.; code.tar.gz.; data.tar.gz.
12.00 - 13.00: Lunch
13.00 - 13.30 Online: Questions to mornings lecture and yesterdays exercise (MP4 2020)
13.30 - 14.00 Online: Selection of projects and formation of project groups Document for project signup.
14.00 -17.00 Online: Exercise: Constructing and training Deep ANN methods (Helle Rus Povlsen && Alessandro Montemurro) cont.

Wednesday 16. - Tuesday 22. June. Project work

No lectures. Project work

Projects must be submitted (in PDF format) via campusnet Tuesday 22. of June 11.59 (Lunch time) at the latest (to give me time to read and evaluate the reports before Wednesday).

Wednesday, 23. June

Project evaluation

Each group has 15 minutes to present their project including 5 minutes for questions. The 5 person group has a little longer and the 1 person group a little shorter.

Thursday, 24. June, Exam

The written exam will be available at the course page at DTU Inside Thursday 24th of June at 8.59, and need to be handed in via DTU Inside Thursday 24th of June before 13.00. The exam is open book, meaning that you can seek information at the internet. You however cannot consult other students taken the exam, and plagiarism is seriously condemned.

Go to

Main Course Page