PXD059982

PXD059982 is an original dataset announced via ProteomeXchange.

Title	Proteomics coupled machine learning—innovative approach in geographical origin authentication of green Coffea arabica
Description	The geographical authentication of green specialty coffee is an intriguing phenomenon that is not yet fully resolved. As one of few, this study is focused on the authentication of the geographical origin of green specialty coffee beans from well-known harvesting regions in Central America, South America, Africa, and Asia using proteomic profiling coupled with Linear Discriminant Analysis. Out of 1596 proteins, we identified 30 of the most significant target markers for the authentication of the geographical origin of specialty green coffee beans. The prediction performance of the model using leave-one-out cross-validation reached 85.3%, with the lowest accuracy in the prediction rate for Asian samples. Model performance and prediction sensitivity to random states were tested using 5-fold cross-validation. After 20 iterations, the model performance decreased to 84.0%.
HostingRepository	PRIDE
AnnounceDate	2025-10-09
AnnouncementXML	Submission_2025-10-09_14:51:33.118.xml
DigitalObjectIdentifier	https://dx.doi.org/10.6019/PXD059982
ReviewLevel	Peer-reviewed dataset
DatasetOrigin	Original dataset
RepositorySupport	Supported dataset by repository
PrimarySubmitter	Maksym Danchenko
SpeciesList	scientific name: Coffea arabica (Arabian coffee); NCBI TaxID: NEWT:13443;
ModificationList	monohydroxylated residue; iodoacetamide derivatized residue
Instrument	LTQ Orbitrap Elite

Revision	Datetime	Status	ChangeLog Entry
0	2025-01-20 08:57:47	ID requested
⏵ 1	2025-10-09 14:51:33	announced

10.6019/PXD059982;

10.1016/J.FOODCHEM.2025.145784;

submitter keyword: Green coffee, Linear discriminant analysis, Cross-validation, Proteome profiling

Peter Baráth
contact affiliation	Department of Glycobiology, Institute of Chemistry, Slovak Academy of Sciences
contact email	peter.barath@savba.sk
lab head
Maksym Danchenko
contact affiliation	Plant Science and Biodiversity Center SAS
contact email	maxymdan@gmail.com
dataset submitter

Dataset FTP location NOTE: Most web browsers have now discontinued native support for FTP access within the browser window. But you can usually install another FTP app (we recommend FileZilla) and configure your browser to launch the external application when you click on this FTP link. Or otherwise, launch an app that supports FTP (like FileZilla) and use this address: ftp://ftp.pride.ebi.ac.uk/pride/data/archive/2025/10/PXD059982

PRIDE project URI

• PRIDE
  1. PXD059982
     1. Label: PRIDE project
     2. Name: Proteomics coupled machine learning—innovative approach in geographical origin authentication of green Coffea arabica