regulatory sequences strength prediction based on AutoML
The design choices underlying machine learning (ML) models present important barriers to entry for many biologists who aim to incorporate ML in their research. Automated machine learning (AutoML) algorithms can address many design challenges that come with applying ML to the life sciences. However, these algorithms are rarely used in systems biology studies because they typically do not explicitly handle biological sequences (e.g., nucleotide, amino acid, or glycan sequences) and cannot be easily compared with other AutoML algorithms.We employed BioAutoMATED,an AutoML platform, demonstrates performance comparable to manually tuned models in predicting gene regulatory sequence strength. Through automated sequence modeling, it provides a convenient pathway for life scientists to integrate machine learning into their research. The study reveals significant sequence features, offering crucial insights into gene regulation. This AutoML-based approach equips researchers with accurate tools, fostering a deeper understanding of gene regulatory sequences. The outcomes hold promise for advancing bioinformatics and biomedical research, unlocking new possibilities in exploring and leveraging the potential mechanisms within gene regulatory sequences.
pip install -r requirements.txt