A Hybrid Flux Balance Analysis and Machine Learning Pipeline Elucidates Metabolic Adaptation in Cyanobacteria
Supreeta Vijayakumar, Pattanathu Rahman, Claudio Angione
Abstract
-means clustering, and LASSO regularization to reduce dimensionality and extract key cross-omic features. Our results suggest that combining metabolic modeling with machine learning elucidates mechanisms used by cyanobacteria to cope with fluctuations in light intensity and salinity that cannot be detected using transcriptomics alone. Furthermore, GSMMs introduce critical mechanistic details that improve the performance of omic-based machine learning methods.
Topics & Concepts
Flux balance analysisComputer scienceArtificial intelligenceSystems biologyMachine learningPipeline (software)CyanobacteriaAdaptation (eye)MetabolomicsFlux (metallurgy)Metabolic engineeringBiochemical engineeringComputational biologyBiologyBioinformaticsChemistryEngineeringOrganic chemistryBacteriaBiochemistryGeneticsNeuroscienceEnzymeProgramming languageMicrobial Metabolic Engineering and BioproductionAlgal biology and biofuel productionMetabolomics and Mass Spectrometry Studies