Nondestructive and multiplex differentiation of pathogenic microorganisms from spoilage microflora on seafood using paper chromogenic array and neural network

Authors: YANG, MANYUN - Cornell University; Luo, Yaguang - Sunny; SHARMA, ARNAV - University Of Connecticut; JIA, ZHEN - University Of Florida; WANG, SHILONG - University Of Massachusetts; WANG, DAYANG - University Of Massachusetts; LIN, SOPHIA - University Of Massachusetts; PEREAULT, WHITNEY - University Of Massachusetts; PUROHIT, SONIA - University Of Massachusetts; GU, TIGNTING - University Of Florida; DILLOW, HYDEN - University Of Massachusetts; LIU, XIAOBO - University Of Massachusetts; YU, HENGYONG - University Of Massachusetts; ZHANG, BOCE - University Of Florida

Submitted to: Food Research International
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/12/2022
Publication Date: 10/17/2022
Citation: Yang, M., Luo, Y., Sharma, A., Jia, Z., Wang, S., Wang, D., Lin, S., Pereault, W., Purohit, S., Gu, T., Dillow, H., Liu, X., Yu, H., Zhang, B. 2022. Nondestructive and multiplex differentiation of pathogenic microorganisms from spoilage microflora on seafood using paper chromogenic array and neural network. Food Research International. https://doi.org/10.1016/j.foodres.2022.112052.
DOI: https://doi.org/10.1016/j.foodres.2022.112052

Interpretive Summary: Technologies enabling the detection of human pathogens without damaging the products is critically needed to ensure food safety. However, the presence of spoilage microorganisms often interferes with the detection accuracy of human pathogens. In this research, we developed and tested a new method using a paper chromogenic array coupled with a machine learning neural network to differentiate human pathogens from other non-pathogenic bacteria on selected food products. We demonstrated that the developed method successfully identified pathogenic microorganisms from other indigenous microorganism with the accuracy reaching 90%-99%. This study benefits food processors with improved technologies for non-destructive detection of human pathogens on food products.

Technical Abstract: Non-destructive detection of foodborne human pathogens is critical to ensuring food safety and public health. Here, we report a new method using a paper chromogenic array coupled with a machine learning neural network (PCA-NN) to detect viable pathogens in the presence of background microflora and spoilage microbe in seafood via volatile organic compounds (VOCs) sensing. Morganella morganii and Shewanella putrefaciens were used as the model pathogen and spoilage bacteria. The study evaluated microbial detection in monoculture and cocktail multiplex detection. The accuracy of PCA-NN detection was first assessed on standard media and later validated on cod and salmon as real seafood models with pathogenic and spoilage bacteria, as well as background microflora. In this study PCA-NN method successfully identified pathogenic microorganisms from indigenous microflora with or without the prevalent spoilage microbe, Shewanella putrefaciens in seafood, with accuracies ranging from 90% to 99%. This approach has the potential to advance smart packaging by achieving nondestructive pathogen surveillance on food without enrichment, incubation, or other sample preparation.