IRNASUS   26003
INSTITUTO DE INVESTIGACIONES EN RECURSOS NATURALES Y SUSTENTABILIDAD JOSE SANCHEZ LABRADOR S.J.
Unidad Ejecutora - UE
artículos
Título:
Algorithmic Learning for Auto-deconvolution and Molecular Networking of GC-MS Data
Autor/es:
ALEXANDER AKSENOV; ANDREA SMANIA; PIETER C. DORRESTEIN; ANDREA ALBARRACÍN ORIO; ET AL.; ET AL.; DANIEL PETRAS; KIRILL VESELKOV
Revista:
NATURE BIOTECHNOLOGY
Editorial:
NATURE PUBLISHING GROUP
Referencias:
Lugar: Londres; Año: 2020
ISSN:
1087-0156
Resumen:
A machine learning workflow was engineered to enable the community to store, process, share, annotate, compare, and perform molecular networking of GC-MS data within the Global Natural Product Social (GNPS) Molecular Networking analysis platform. The workflow performs auto-deconvolution of compound fragmentation patterns via unsupervised non-negative matrix factorization, using a Fast Fourier Transform-based strategy to overcome scalability limitations and quantifies the reproducibility of fragmentation patterns across samples using a ?balance score?.