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.

The main programming language will be Python and all program templates provided in the course will be written in Python. Prior detailed knowlegde of Python programming is strongly encouraged but NOT required. However, basic programming skills are required to follow the course.

PROGRAMS AND TOOLS


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:

O Thursday, 6. June

Introduction to course. PSSM construction from pre-aligned sequences including pseudo count. Python recap
Morten Nielsen

  • BACKGROUND TEXTS Essentials: Additionals:
    9.00 - 9.15
    Introduction to course
    Introduction to course [PDF] (MP4).
    9.15 - 9.30
    Introduction to the immune system [PDF] (MP4).
    9.30 - 11.20 (coffee break included)
    Weight matrix construction[PDF]. [PPTX] Weight matrix construction (MP4).
    Logo Handout
    Answers
    Handout. Estimation of pseudo counts
    Answer
    11.20 - 12.00
    Questions to the mornings lectures and other general issues
    Checking that we all have python and jupyter-notebook installed and running
    12.00 - 13.00
    Lunch
    13.00 - 13.30
    Some notes on sequence alignment [PDF] (MP4)
    13.30 - 17.00
    A brief introduction to Python programming and Jupyter-notebooks
    Python intro
    Python Answers
    Implementation of PSSM construction from pre-aligned sequences including pseudo count correction for low counts and sequence clustering
    PSSM construction and evaluation
    PSSM answers


    O Friday, 7. June

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

    BACKGROUND TEXTS
    Essentials: Additionals:
    9.00 - 9.30
    Questions to yesterdays lectures and exercises
    9.30 - 11.00
    Blosum matrices [PDF] (MP4)
    Sequence alignment [PDF] . [PPTX] . (MP4)
    Handout (O3)
    Handout (O2)
    Handout answers
    11.00 - 12.00
    Blast alignment heuristics, Psi-Blast, and sequence profiles [PDF] . [PPTX] .
    Psi-Blast handout.
    12.00 - 13.00
    Lunch
    13.00 - 17.00
    Implementation of the Smith-Waterman Dynamic programming algorithm
    Matrix dumps from alignment programs (to be used for debugging)
    Answers to sequence alignment exercise

    O Monday, 10. June.
    Optimizations methods
    Cross validation and training of data driven prediction methods
    Stabilization matrix method (SMM)
    Morten Nielsen

    BACKGROUND TEXTS - Optimization methods, Stabilization matrix method (SMM)
    Essentials: Additionals:
    9.00 - 9.30
    Questions to yesterdays lectures and exercises
    9.30 - 10.00
    Optimization procedures - Gradient decent, Monte Carlo
    Optimization procedures [PDF] [PPTX] (MP4)
    GD handout
    10.00 - 10.15
    Break
    10.15 - 10.30
    Cross validation and training of data driven prediction methods
    [PDF] . [PPTX] . [MP4].
    10.30 - 11.00
    Stabilization matrix method (SMM) background
    [PDF] . [PPTX] . [MP4].
    SMM handout
    11.00 - 12.00
    SMM exercise
    Implementing and evaluating SMM algorithms using cross-validation
    12.00 - 13.00
    Lunch
    13.00 - 17.00 SMM exercise continued
    SMM exercise - continued
    Answers

    O Tuesday, 11. June
    Hidden Markov Models
    Morten Nielsen

  • BACKGROUND TEXTS
    9.00 - 9.30
    Questions to yesterdays lectures and exercises
    9.30 - 12.00 (with a break somewhere)
    Hidden Markov models
    Viterbi decoding, Forward/Backward algorithm, Posterior decoding, Baum-Welsh learning
    Profile Hidden Markov Models (see Hidden Markov model slides from yesterday)
    [PDF]. [PPTX] HMM (MP4)
    Viterbi Handout
    Answers
    Forward Handout
    12.00 - 13.00
    Lunch
    13.00 - 17.00
    Implementation of Viterbi and posterior decoding.
    Hidden Markov exercises
    Answer to Hidden Markov exercises

    O Wednesday, 12. June
    Artificial neural networks. Sequence encoding, feedforward and backpropagation algorithm
    Morten Nielsen

  • BACKGROUND TEXTS Topics
    9.00 - 9.30
    Questions to yesterdays lectures and exercises
    9.30 - 10.30
    Artificial neural networks[PDF] . [PPTX] . Artificial neural networks Part 1 (MP4). Artificial neural networks Part 2 (MP4).
    Handout
    Answers
    10.30 - 10.40
    Break
    10.40 - 12.00
    Network training - backpropagation
    Training of artificial neural networks [PDF] . [PPTX] . (MP4)..
    Handout
    12.00 - 13.00
    Lunch
    13.00 - 17.00
    Artificial neural networks (Feedforward and Backpropagation)
    ANN answers

    O Thursday, 13. June
    An introduction to Deep neural network architectures
    Morten Nielsen

  • BACKGROUND TEXTS
    9.00 - 9.30
    Questions to yesterdays lectures and exercises
    Quiz with questions capturing essential parts of course up to now Quiz. We will go over the answers to the quiz tomorrow morning.
    9.30 - 10.00
    Trick for ANN training [PDF].
    10.00 - 10.30
    NNAlign, alignment using ANN's [PDF]
    10.30 - 11.00
    Deep Learning using FFNN and CNNs (PPTX) [PDF]
    11.00 - 12.00
    Exercise: Constructing and training Deep ANN methods (Yat-Tsai Richie Wan && Sebastian Nymann Deleuran)
    NNdeep exercise
    12.00 - 13.00
    Lunch
    13.00 -17.00
    Exercise: Constructing and training Deep ANN methods (Yat-Tsai Richie Wan && Sebastian Nymann Deleuran) cont.
    NNdeep exercise
    Answer Deep FFNN


    O Friday, 14. June
    Deep neural network architectures continued
    Morten Nielsen

    9.00 - 9.30
    Answers to Quiz
    9.30 - 9.45
    What goes on inside a CNN? (Morten Nielsen) [PDF]
    9.45 - 10.15
    Description of potential projects and formation of groups
    Project suggestions, and descriptions.
    Document for project signup.
    10.15 - 10.30
    Questions to yesterdays lectures and exercises
    10.30 - 12.00
    Constructing and training Deep ANN methods (Yat-Tsai Richie Wan && Sebastian Nymann Deleuran) NNdeep exercise - CNNs
    NNdeep exercise - Part II
    12.00 - 13.00
    Lunch
    13.00 - 16.00
    Exercise Part II continued

    O Monday, 17. June
    Data redundancy reduction algortihms
    Last words in Deep neural network architectures
    Introduction to the project work
    Morten Nielsen

  • BACKGROUND TEXTS - Data redundancy reduction
    9.00 - 9.15
    Questions to yesterdays lectures and exercises
    9.15- 9.45
    Data redundancy reduction algorithms (Hobohm1 and Hobohm2) [PDF]. [PPTX]. (MP4).
    9.45 - 12.00
    Hobohm redundancy reduction algorithms
    Answers to Hobohm programming exercise
    12.00 - 13.00
    Lunch
    13.00 - 13.30
    Answers to Fridays CNN and todays Hobohm exercises
    13.30 - 13.45
    Doing things in C - A few examples: Alignment and ANN training
    Some code examples
    13.45 - 14.30
    Selection of projects, formation of project groups and start of project work Document for project signup.
    NOTE, EACH GROUP MUST SENT AN EMAIL TO MORTEN (morni@dtu.dk) WITH THE PROJECT TITLE, GROUP MEMBERS (NAME AND ID), A BRIEF PROJECT OUTLINE, AND A DESRIPTION OF THE PROJECT DATA AND HOW THESE ARE LOCATED BEFORE TUESDAY JUNE 18TH, 11.59 AM.
    14.30 - 17.00
    Work on project (on your own)

    O Tuesday 18. - Monday 24. June. Project work
    No lectures. Project work
    Projects must be submitted (in PDF format) via DTU Learn Monday 24. of June 11.59 AM (just before lunch)

    O Tuesday, 25. June, Exam

    The written exam will be available at the course page Tuesday 25th of June at 9.59, and needs to be handed in via DTU Learn Tuesday 25th of June before 12.00. The exam is open book, meaning that you can seek information at the internet.

    It is allowed to use generative AI (e.g., chatGPT) but please note:

    You however cannot consult anyone, and plagiarism is seriously condemned. The exam will take place in the usual class room in building 210.
    exam.ipynb (NoteBook)
    exam.html (HTML)


    O Wednesday 26. June

    Project evaluation

    Each group has 10 minutes to present their project followed by 5 minutes for questions. Note, only the group will be present for the presentation of the individual projects. The project presentations will take place in the usual class room in building 210.

    Wednesday 26st of June, 8.30 - 12.00
    
    8.30 - 8.50
    Group 1
    Christian Christensen (s223096), Mikkel Piester Hansen (s223105)
    Peptide MHC binding predictions using artificial neural networks with different sequence encoding schemes
    
    8.50 - 9.10
    Group 2
    Jiawen We (s222372), Magnus Harthimmer (s233426), Rune Daucke (PhD)
    Implementation of HMM Baum-Welch algorithm
    
    9.10 - 9.30
    Group 3
    Matilde Uth (s195796), Jacqueline Printz (s194377), Christina Christiansen (s223094)
    Comparative study of PSSM, ANN, SMM for peptide MHC binding
    
    9.30 - 9.50
    Group 4
    Paula Gomez-Plana Rodriguez (s233165), Maria Gabriela Frascella Bracho (s233113), Eirini Giannakopoulou (s230204), Amanda Jimenez (s233150)
    Comparative study of PSSM, ANN, SMM for peptide MHC binding
    
    9.50 - 10.00
    Break
    
    10.00 - 10.20
    Group 5
    Johanne Lund (s233246), Luisa Weisch (s233028), Eleni Tseperi (s240066)
    Comparative study of PSSM, ANN, SMM for peptide MHC binding
    
    10.20 - 10.40
    Group 6
    Anton Wang Strandberg (s183220), Ona Saulianskaite (s232958), Johan von Staffeldt (s225001)
    Tools for ANN training (FFNN + CNN)
    
    10.40 - 11.00
    Group 7
    Emilie Sofie Engdal (s194360), Sarah Rosenberg (s194689), Asger Bjoern Larsen (s204306), Saxe i Dali Wagner (s204559)
    Implementation of regularization in ANN training
    
    11.00 - 11.20
    Group 8
    Lea Eschen Skytthe (s203531), Trine Soegaard (s204655), William Hagedorn-Rasmussen (s194545)
    Peptide MHC binding predictions using artificial neural networks with different sequence encoding schemes
    
    11.20 - 11.40
    Group 9
    Anas Majed El-Youssef (s233381), Xavier Vinas Margalef (s233532), Max Edin (maxed@dtu.dk)
    Method evaluation using crossvalidation
    
    11.40 - 12.00
    Group 10
    Peptide MHC binding predictions using artificial neural networks with different sequence encoding schemes
    Balint Norbert, s204668,Rebecca Hjermind Millum, s215024, Grinos (phd)
    

    Go to