Flexynesis: A deep learning toolkit for bulk multi-omics data integration for precision oncology and beyond.

Area of Science:

• Computational biology
• Bioinformatics
• Precision oncology

Background:

• Precision oncology relies on integrating multimodal molecular data for accurate decision-making.
• Existing deep learning methods for multi-omics integration often lack transparency, modularity, and broad applicability.

Purpose of the Study:

• To introduce Flexynesis, a versatile toolset designed to overcome limitations in current multi-omics integration methods.
• To provide a streamlined and accessible platform for integrating bulk multi-omics data in precision oncology research.

Main Methods:

• Flexynesis offers a standardized interface for data processing, feature selection, hyperparameter tuning, and marker discovery.
• Supports both deep learning architectures and classical supervised machine learning methods.
• Enables single/multi-task training and evaluation for regression, classification, and survival modeling.

Main Results:

• Demonstrates the tool's capability across diverse use-cases in precision oncology.
• Successfully makes deep learning-based bulk multi-omics data integration more accessible.
• Provides a modular and transparent approach to multi-omics data analysis.

Conclusions:

• Flexynesis enhances accessibility and usability of advanced multi-omics integration techniques for clinical and pre-clinical research.
• The toolset empowers researchers with or without deep learning expertise to leverage multimodal data for improved precision oncology outcomes.
• Flexynesis promotes wider adoption of sophisticated computational methods in cancer research.