- Version
- Download 6
- File Size 113.81 KB
- File Count 1
- Create Date November 9, 2023
- Last Updated November 9, 2023
D4.4: Prediction of metabolic pathways of novel microorganisms involved in wastewater treatment (including P-removal/ recovery and sludge digestion) - Executive Summary
GLOMICAVE aims to exploit the information hidden in existing scientific literature and large-scale omics datasets with artificial intelligence (AI) technology to understand genotype-phenotype relationships better. This deliverable will show how the GLOMICAVE approach can achieve this aim using machine learning techniques on meta-genomics, meta-transcriptomics and metabolomics data from two environmental sector use cases.
These use cases address two problems related to wastewater treatment. The first case is concerned with the conversion of waste to biomethane. Such a conversion is performed by anaerobic communities composed of thousands of species in wastewater treatment plant (WWTP) digesters. It is difficult to correlate microbial diversity to biomethane productivity in such complex environments and to identify the most influential microorganisms contributing to process efficiency. The second case is concerned with the improvement of Phosphate removal and recovery from wastewater with Enhanced Biological Phosphorus Removal (EBPR). EBPR is a wastewater treatment technology that uses polyphosphate accumulating organisms (PAOs). These PAOs are all uncultured and can only be investigated by culture-independent methods.
Using machine learning algorithms, GLOMICAVE can identify the microorganisms influencing most the WWTPs' performance when producing biomethane and removing and recovering phosphate from wastewater. This information can help optimize the biomethane production process and the EBPR design.