生物機器學習

Machine Learning in Computational Biology

學期

113-1

學分

3 學分

當期課號

430108

永久課號

BTBI30044

開課單位

生物資訊及系統生物研究所

授課教師

李宗夷

校區

博愛

類別

選修

上課時間表

節	週二
7 15:30–16:20	生物機器學習 BI301 3 節連堂
8 16:30–17:20
9 17:30–18:20

* 根據陽明交大上課時間表所列

概述

In this course, students will learning and explore the intersection of molecular biology and machine learning, uncovering the tremendous potential for solving complex biological problems using state-of-the-art computational techniques. The goal of this course is to provide you with a comprehensive understanding of how machine learning can be applied to biological data, enabling breakthroughs in fields such as genomics, proteomics, drug discovery, and biomedical research. A wide range of topics are covered in this course, including: 1. Introduction to Machine Learning: We will start with the fundamentals of machine learning, covering supervised and unsupervised learning techniques, model evaluation, and data preprocessing. 2. Biological Data Types: Understanding the unique characteristics of biological data is essential for effective analysis. We will explore diverse data types, including genomic sequences, gene expression data, protein structures, and biological networks. 3. Feature Extraction and Dimensionality Reduction: With the high dimensionality of biological data, feature extraction and dimensionality reduction techniques play a vital role in reducing complexity and extracting meaningful information. We will study various methods such as principal component analysis (PCA), t-SNE, and feature selection algorithms. 4. Predictive Modeling in Genomics: Genomic data holds enormous potential for personalized medicine and understanding disease mechanisms. We will explore how machine learning algorithms can be used to predict gene functions, identify disease-associated genetic variants, and construct gene regulatory networks. 5. Drug Discovery and Pharmacogenomics: Machine learning has the potential to accelerate drug discovery processes and facilitate precision medicine. We will investigate how computational models can aid in virtual screening, drug target identification, and predicting drug response based on genomic information. 6. Deep Learning in Bioinformatics: Deep learning architectures, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have shown remarkable performance in various biological applications. We will examine how these models can be applied to tasks like image analysis, protein structure prediction, and genomics. Throughout the course, you will have the opportunity to work on hands-on projects and gain practical experience in applying machine learning techniques to real biological datasets. By the end, you will have a solid foundation in biological machine learning and be equipped to contribute to this rapidly evolving field.

先修科目

Programming / Bioinformatics / Computational Biology

教學方式

Lectures, Discussion and Hands-on Practice

評分方式

Assignments (40%) + Presentation(20%) + Final Project Report (40%)

週次計畫

週次	主題
第 1 週	Course Introduction and Biological Data
第 2 週	Data Preparation and Preprocessing
第 3 週	Mid-Autumn Festival (中秋節)
第 4 週	Features Encoding and Investigation - One Hot Encoding, Amino Acid Composition, Amino Acid Pair Composition, Positional Weight Matrix, CKSAAP, PSSM, Sequence Motifs
第 5 週	Model Construction and Performance Evaluation
第 6 週	Supervised Machine Learning Methods I - Profile Hidden Markov Models
第 7 週	Supervised Machine Learning Methods II - Decision Tree, Random Forest, Basian Network
第 8 週	Midterm Review ( Self-study )
第 9 週	Supervised Machine Learning Methods III - Linear Regression, Support Vector Machine, Neural Networks
第 10 週	Unsupervised Machine Learning Methods I - Hierarchical and non-Hierarchical Clustering methods
第 11 週	Unsupervised Machine Learning Methods II - Association Rule and Maximal Dependence Decomposition
第 12 週	Unsupervised Machine Learning Methods III - Dimensionality Reduction and Principal Component Analysis (PCA)
第 13 週	Deep Learning Methods - Convolutional Neural Networks (CNNs), Transformer and Generative Learning
第 14 週	Final Project - Oral Presentation
第 15 週	Final Project - Oral Presentation
第 16 週	Final Project - Independent Testing

教科書

1. Ethem Alpaydin,“Introduction to Machine Learning", The MIT Press, 3rd edition, 2014 2. S. Mitra, S. Datta, T. Perkins and G. Michailidis, "Introduction to Machine Learning and Bioinformatics", New York: Chapman & Hall/CRC Press, ISBN 978-1584886822, 2008. 3. Kai Hwang and Min Chen,“Big-Data Analytics for Cloud, IoT and Cognitive Computing”, WILEY, First edition.

Office Hours

地點: Room 317, BioICT Building, Poai Campus
時間: Wednesdays 14:00 - 17:30
聯絡方式: leetzongyi@nycu.edu.tw / 03-5712121 #56947