P000154, Praktisk maskininlärning i life science med R, 5.0 Hp
Skriv ut kursplan

Kursplan

Fastställd av: Galia Zamaratskaia and Ali Moazzami, 2025-10-21
Giltig från och med :

Nivå

Forskarnivå

Ämne

Matematisk statistik, Biologi

Betygsskala

Kraven för kursens olika betygsgrader framgår av betygskriterier, som ska finnas tillgängliga senast vid kursstart.

Kursspråk

Engelska

Behörighetskrav

Mål

Course Objectives

This course provides a hands-on approach to machine learning in life sciences, focusing on the practical application of key algorithms using R. Students will gain basic knowledge of supervised and unsupervised models and learn how to apply, evaluate, and interpret these models in real-world biological datasets.

Learning Outcomes

By the end of this course, students will be able to:

• Explain the workflow of supervised and unsupervised machine learning for life‑science data
• Implement decision trees, random forests, SVMs, clustering, PCA, and simple ANNs in R
• Evaluate and tune models (resampling, hyperparameters, performance metrics)
• Interpret results for scientific reporting in agricultural, biological, and medical contexts
• Communicate findings via a short, structured project presentation

Innehåll

Teaching & Assessment Strategy

• Synchronous sessions: 2 per week (Lecture/Discussion and Lab), ~1.5–2 h each
• Assessment: One combined assignment (supervised + unsupervised) and one final project presentation
• Short pre-class video/readings for theory; live time is used for Q&A and hands‑on labs

Delivery: Online (Zoom)

Examinationsformer

**Pass criteria:** Submission quality, code correctness/reproducibility, methodological justification, and clarity of interpretation.

Ansvarig institution eller motsvarande

Institutionen för molekylära vetenskaper

Kompletterande uppgifter