Protein Prediction II for Computer Scientists

What it is about

You will learn methods for predicting protein functions from sequence and structure information, as well as approaches for predicting interactions, subcellular localization, and effects of individual amino acid variants. By the end, you will be able to critically evaluate ML/AI-based prediction methods, design your own solutions, and implement them in pseudocode or programs.

What you will be able to do

Understand key aspects of protein function prediction
Handle limited and noisy data
Avoid overfitting and data leakage
Evaluate and critically analyze published methods
Develop and present your own prediction methods (group work)
Communicate with researchers from other disciplines about requirements and limitations of AI solutions

What the module consists of

LectureConveying the theoretical background and overview of methods
Exercises/Project workProgramming and development of a novel prediction method; group project with presentation

Teaching method

Lectures (incl. Q&A)Explain the theoretical background, interactive discussions
Whiteboard presentationsDeepening and interactive work on details
Exercises with project workPractical application, implementation and presentation of own solutions
Recordings and slidesReview and reference material

What you should already know

Protein Prediction 1 for Computer Scientistsrecommended
Bachelor in Computer Science or related fields and practical experience with ML/AIrecommended

Assessment

oral examinationgroup projectpresentation

Oral examination at the end of the semester: 20 minutes (individual) or 60 minutes (group). Questions come exclusively from lectures and project work. Students who contribute substantially to a successful project may receive a grade bonus of 0.3 upon passing the exam.

Reading list

AM Lesk - Overview zur Proteinfunktion (Buch, 2004)
B Rost et al. - Review zur Vorhersage von Proteinfunktionen (Cellular and Molecular Life Sciences, 2003)
T Goldberg et al. - Ort/Lokalisierung (Bioinformatics, 2012)
H Stark et al. - Ort/Lokalisierung (Bioinform Adv, 2021)
Y Ofran & B Rost - Interaktionen (J Mol Biol, 2003)
M Littmann et al. - Interaktionen (Scientific Reports, 2021)
T Hamp und B Rost - Interaktionen (Bioinformatics, 2015)
Y Bromberg & B Rost - Auswirkung von Varianten (Nucleic Acids Research, 2007)
C Marquet, J Schlensok, M Abakarova, B Rost und E Laine - Auswirkung von Varianten (Bioinformatics, 2024)

Dates

ExerciseExercises for Protein Prediction II for Computer Scientists (IN2291)

Mon10:00–12:00
01.09.034, Seminarraum (5609.01.034)
14× · 19.10.–01.02.
- 19.10.
- 26.10.
- 02.11.
- 09.11.
- 16.11.
- 23.11.
- 30.11.
- 07.12.
- 14.12.
- 21.12.
- 11.01.
- 18.01.
- 25.01.
- 01.02.

LectureProtein Prediction II for Computer Scientists (IN2291)2 groups to choose from

ATue14:00–16:00
00.13.009A, Seminarraum (5613.EG.009A)
15× · 13.10.–02.02.
- 13.10.
- 20.10.
- 27.10.
- 03.11.
- 10.11.
- 17.11.
- 24.11.
- 01.12.
- 08.12.
- 15.12.
- 22.12.
- 12.01.
- 19.01.
- 26.01.
- 02.02.
BThu12:00–14:00
00.13.009A, Seminarraum (5613.EG.009A)
14× · 15.10.–04.02.
- 15.10.
- 22.10.
- 29.10.
- 05.11.
- 12.11.
- 19.11.
- 26.11.
- 10.12.
- 17.12.
- 07.01.
- 14.01.
- 21.01.
- 28.01.
- 04.02.

From the current semester, not binding. You attend one of several groups; the timetable automatically suggests the one with the fewest clashes.

Filters