Predictive Microbiome Risk Management
Next generation genomic techniques monitoring factory wide micro-biome. Machine Learning is used to predict the likelihood of safety or quality concerns.
Predict the likelihood of occurrence of a safety or quality issue in a manufacturing environment.
We use the latest genomic techniques, machine learning and fundamental microbiological growth information to determine the conditions compatible for pathogen or spoiler presence or growth.
Combining the strengths of fundamental microbiology, genomics and machine learning enables the prediction of the likelihood of occurrence of a safety or quality issue. This gives a far greater degree of accuracy and detail than possible from using current traditional microbiological techniques while also benefiting from the insights of domain experts and world-leading academics.
1 – Assessment and Agreement
Initial site screening and service contract
2 – Setting the Frame
Swab-plan tailored to your site, staff training, organisation of kits and shipment
3 – Access to Online Tool
Login to secure site and prepare the process flow map
4 – Collect Swabs and Metadata
Take swabs and record metadata
5 – Logistics
Kit is collected and shipped
6 – Extracting and Sequencing
Anonymous DNA extraction and sequencing in 3rd party lab
7 – Data Processing and Analysis
Converting raw sequence data into meaningful insights
8 – Your Results
Results available for viewing on a secure site
Understand the results and insights we provide
During our long-lasting collaboration with Creme, the team has always demonstrated technical competence and provided rapid feedback in resolving all day to day problems related to the use of the software. Moreover the team have shown that they have the capability of supporting their clients in their efforts to develop new ideas and share their customers’ enthusiasm for achieving important goals.
David Arcella, Researcher, INRAN
It was a pleasure working with Creme Ltd; we truly appreciated the high level of knowledge and professionalism demonstrated by Creme throughout this project.