| (*)Students have a deep understanding of how artificial intelligence (AI) and machine learning (ML) methods are applied in life sciences, particularly in areas like drug discovery, pharmacology, toxicology, and bioinformatics. They are able to implement ML techniques to predict drug targets, model molecular interactions, and apply generative models for molecule design, leveraging AI to solve complex problems in life sciences.
|
(*)- Applying Machine Learning Methods in Life Sciences (k5)
Students can implement machine learning models for tasks such as drug target prediction, toxicity assessment, and bioassays, understanding how these techniques are used to analyze biological data.
- Working with Molecular Representations (k5)
Students are able to represent molecules using various techniques (e.g., SMILES strings, molecular fingerprints) to analyze molecular structures and interactions using machine learning algorithms.
- Using QSAR and Chemoinformatics Techniques (k5)
Students can apply quantitative structure-activity relationship (QSAR) models and chemoinformatics tools to predict biological activity and toxicity based on chemical structures.
- Implementing Generative Models for Molecule Design (k5)
Students are capable of designing and training generative models to create new molecular structures and explore chemical space for drug discovery.
- Analyzing Genomic and Transcriptomic Data with Deep Neural Networks (k5)
Students can apply deep learning models to genomic and transcriptomic datasets, using these tools for predictive modeling and analysis in biological research.
|
(*)Students know of AI and machine learning applications in life sciences, covering methods for drug discovery, chemoinformatics, virtual screening, and molecular representations. They have learned about the use of generative models, neural networks for biological data, and machine learning approaches for biological images, focusing on prediction, model interpretability, and real-world applications in bioinformatics and drug design.
|
