Home
Software Library
HEMDAG
obogaf-parser
Contribution to ezRun
Contribution to SUSHI
Machine Learning
Identifying biomarkers associated with weight loss using a Bayesian-optimized classifier
Predicting housing prices in California
Predicting biomarker status imputing missing values
Predicting protein localizations with pythorch
Predicting salary and new connections with scikit-learn
Predicting viewer engagement with scikit-learn
Genomics
Identification of breast cancer subtypes
AI tools
A RAG framework for bioinformatics applications
Data Viz
Visualization of Michigan’s temperature records
Visualization of Detroit’s sports teams win percentages
Identification of breast cancer subtypes from bulk RNA-Seq data via a graph-based approach
Author
Marco Notaro
Published
September 18, 2025
Getting data
Exploratory data analysis and preprocessing
Clustering analysis - an in-house approach
Clustering analysis - the Seurat way
Predicting biomarker status imputing missing values