SNP Array for Small-Shrimp (Genus Acetes) Origin Determination Using Machine Learning

Area of Science:

• Genomics
• Bioinformatics
• Food Science

Background:

• Accurate seafood origin determination is vital for consumer trust and safety.
• Identifying the origin of Acetes species in salted products presents challenges.
• Existing methods may lack the precision needed for robust authentication.

Purpose of the Study:

• To develop a machine learning-based single-nucleotide polymorphism (SNP) analysis technique for determining the origin of Acetes species.
• To validate the accuracy of SNP genotyping combined with machine learning for seafood authentication.
• To provide a reliable tool for regulatory bodies to combat seafood fraud.

Main Methods:

• Mitochondrial DNA (COI and 16S rRNA) sequencing to identify genetic variations.
• Selection and development of six single-nucleotide polymorphism (SNP) markers from eight candidates.
• Creation of an SNP array for genotyping salted small-shrimp samples.
• Application of a supervised machine learning algorithm for origin classification based on SNP data.

Main Results:

• Mitochondrial DNA analysis revealed significant genetic variations among Acetes species and origins.
• Six validated SNP markers were successfully developed for genotyping.
• Machine learning analysis achieved 100% accuracy in classifying the origin of Acetes species using SNP data.
• The developed SNP array and machine learning model provide a highly accurate method for origin determination.

Conclusions:

• SNP analysis coupled with machine learning offers a powerful and accurate tool for seafood origin determination.
• This method can effectively combat food fraud and ensure the integrity of salted small-shrimp products.
• Future work should involve expanding the dataset to include more species and geographical origins for broader applicability.