Kinbiont

Kinbiont integrates dynamic models and machine learning to analyze microbial kinetics data, generate hypotheses, and accelerate discovery in microbiology.

Key Features:

• Data Preprocessing: Facilitates preparation of microbial growth datasets for downstream analysis.
• Model-Based Parameter Inference: Supports both user-defined differential equation systems and hard-coded growth models for parameter inference from microbial kinetics data.
• Explainable Machine Learning: Maps experimental conditions directly to inferred biological parameters to generate interpretable and testable hypotheses.

Scientific Applications:

• Diauxic Growth Analysis: Analyzes diauxic growth curves to characterize microbial responses to multiple nutrient sources.
• Bioproduction Optimization: Quantifies microbial kinetics in ethanol bioproduction processes.
• Phage-Bacteria Interaction Studies: Characterizes dynamics of phage-bacteria interactions through kinetic modeling.
• Nutrient Limitation Studies: Identifies mathematical relationships underlying microbial responses to nutrient limitation, as demonstrated by revisiting Monod's classical experiment.
• Antibiotic Response Profiling: Performs growth inhibition assays to quantify microbial responses to ribosome-targeting antibiotics.
• Ecotoxicological Screening: Reveals growth-phase-specific sensitivities to environmental stressors in large-scale screens.

Methodology:

Kinbiont consists of three sequential yet independent modules: (1) data preprocessing, (2) model-based parameter inference with both user-defined differential equation systems and hard-coded growth models, and (3) explainable machine learning analyses to map experimental conditions directly to inferred biological parameters.