We have been working on developing solutions to democratize AI, specifically Machine Learning (ML) in biology. So far, our studies have generated solutions that can be applied in the study of biological data, having a high potential to significantly reduce the experience required to use AI/ML pipelines, helping researchers in combating various problems, such as diseases that directly impact people's lives, mainly in low- and middle-income countries, giving biologists and other stakeholders, an opportunity for widespread use of these techniques.

BioAutoML

BioAutoML (a comprehensive suite of solutions) automates the entire ML pipeline, making it fully accessible to non-experts. It comprises two main components, each divided into four modules: (1) Automated Feature Engineering, which covers feature extraction and selection, and (2) Meta-Learning, which focuses on algorithm recommendation and hyperparameter tuning. BioAutoML can automatically extract features from diverse biological datasets, recommend suitable algorithms, and fine-tune them for both binary and multiclass classification tasks. Our solutions operate without the need for specialized human intervention — all that is required is a training dataset to execute a complete ML experiment. BioAutoML lowers the barriers for non-experts to apply advanced ML techniques to biological data, fostering the democratization of AI in the life sciences.

Publications

Our contributions have resulted in awards and published scientific articles, showcasing our commitment to advancing AI in biology - See FAQ.