Statistical Learning for Genetics and Biology
This course provides an introduction to statistical and computational methods for modern genetics and biological research. It begins with fundamental concepts in statistical learning and statistical genetics, and then introduces their applications to genetic association, quantitative trait analysis, and high-dimensional biological data.A particular focus is placed on personalized quantitative genetics, where statistical models are used to characterize individual-specific genetic effects, genetic interactions, and dynamic biological processes. The course also covers the foundations of machine learning and deep learning, including commonly used algorithms, model evaluation, and interpretation.The final part of the course introduces recent developments in AI for biological science, with examples from genomics, transcriptomics, phenomics, systems biology, and related areas. Through lectures, methodological discussions, and selected research papers, students will learn how statistical modeling, machine learning, and artificial intelligence can be integrated to address complex problems in contemporary biological research.
Lecturer
Date
22nd September ~ 16th December, 2026
Location
| Weekday | Time | Venue | Online | ID | Password |
|---|---|---|---|---|---|
| Tuesday | 13:30 - 16:55 | A3-4-101 | ZOOM 05 | 293 812 9202 | BIMSA |
Syllabus
1. Statistical Foundations and Statistical Learning
Probability, statistical inference, regression, and model selection
Fundamentals of statistical learning
Model evaluation, regularization, and high-dimensional data analysis
2. Statistical Methods in Genetics
Basic concepts of quantitative and population genetics
Genetic association and genome-wide association studies
Mixed models and genetic variance components
Genotype–phenotype mapping and genomic prediction
3. Personalized Quantitative Genetics
From population-level to individual-specific genetic effects
Genetic interactions and complex genotype–phenotype relationships
Dynamic and functional quantitative traits
Network-based and individualized genetic modeling
4. Machine Learning and Deep Learning Fundamentals
Decision trees, random forests, boosting, and ensemble learning
Neural networks and deep learning fundamentals
Representation learning for high-dimensional biological data
Model interpretation and explainable AI
5. AI for Biological Science
AI applications in genomics and transcriptomics
AI for phenomics and biological time-series data
Biological network modeling and systems biology
Integrating statistical models, machine learning, and biological knowledge
Recent advances and selected case studies in AI-driven biological research
Probability, statistical inference, regression, and model selection
Fundamentals of statistical learning
Model evaluation, regularization, and high-dimensional data analysis
2. Statistical Methods in Genetics
Basic concepts of quantitative and population genetics
Genetic association and genome-wide association studies
Mixed models and genetic variance components
Genotype–phenotype mapping and genomic prediction
3. Personalized Quantitative Genetics
From population-level to individual-specific genetic effects
Genetic interactions and complex genotype–phenotype relationships
Dynamic and functional quantitative traits
Network-based and individualized genetic modeling
4. Machine Learning and Deep Learning Fundamentals
Decision trees, random forests, boosting, and ensemble learning
Neural networks and deep learning fundamentals
Representation learning for high-dimensional biological data
Model interpretation and explainable AI
5. AI for Biological Science
AI applications in genomics and transcriptomics
AI for phenomics and biological time-series data
Biological network modeling and systems biology
Integrating statistical models, machine learning, and biological knowledge
Recent advances and selected case studies in AI-driven biological research
Audience
Undergraduate
, Graduate
, Postdoc
Video Public
No
Notes Public
No
Language
Chinese
Lecturer Intro
杨登程博士，北京雁栖湖应用数学研究院助理研究员。主要研究方向为计算生物学与生物信息学，主要包括复杂系统的建模与分析，全基因组互作网络、连锁不平衡估计等统计方法的开发，并开展结合机器学习与深度学习的基因组预测方法研究，同时在林木智慧育种等领域开展应用研究。相关成果发表于 Nature Communications、Physics Reports 等国际期刊。