Introduction
The
AILS (Artificial Intelligence for the Life Sciences) course is an
exciting opportunity to explore the cutting-edge applications of machine
learning and deep learning in the field of life sciences. The AILS
course offers an excellent opportunity for participants to gain
practical skills in artificial intelligence techniques applied to the
life sciences. With a focus on hands-on learning and accessible content,
this course promises to equip participants with the necessary tools to
tackle real-world challenges in their respective fields. The course will
take place in Braga from September 4th to 9th, 2023. It is jointly
organized by OmniumAI and NEBIUM - Núcleo de Estudos de Bioinformática
da Universidade do Minho.
Target Audience
AILS
is accessible to non-programmers who have some experience with Python
scripts and Jupyter notebooks, while a short introduction to Python
programming and relevant packages (e.g., pandas) will be provided prior
to the course (online session). Participants are encouraged to bring
their own data, allowing them to apply the learned techniques to
real-world problems they face in their respective fields.
Learning Outcomes
The
course aims to provide participants with state-of-the-art knowledge and
hands-on experience in artificial intelligence applied to the life
sciences. The course will address the following topics:
Basic
data manipulation and analysis in Python
Machine learning core concepts and tools
Basic bioinformatics concepts and tools
Basic omics
data processing and analysis
Machine learning applied to biological sequences and omics
data to predict phenotypes
Basic cheminformatics concepts and tools
Machine learning applied to chemical compounds to predict properties and activity
Deep learning core concepts and tools
Deep learning models for biological and biomedical applications
Generative deep learning models to generate compounds
Throughout
the course, participants will work with a variety of tools and
libraries, including Python scripts and Jupyter notebooks. Participants
will also be introduced to the several Python libraries, essential to
analyze life sciences data and to develop machine learning and deep
learning models.
Practical Applications
The
practical applications of the course are vast, including phenotype
prediction, biomarker discovery, protein classification, prediction of
compound activities and properties, and the generation of novel
compounds.