Auto-deconvolution and molecular networking of gas chromatography-mass spectrometry data.
Alexander A AksenovIvan LaponogovZheng ZhangSophie L F DoranIlaria BelluomoDennis VeselkovWout BittremieuxLouis-Felix NothiasMélissa Nothias-EspositoKatherine N MaloneyBiswapriya B MisraAlexey V MelnikAleksandr SmirnovXiuxia DuKenneth L JonesKathleen DorresteinMorgan PanitchpakdiMadeleine ErnstJustin Johan Jozias van der HooftMabel GonzalezChiara CarazzoneAdolfo AmézquitaChris CallewaertJames T MortonRobert A QuinnAmina BouslimaniAndrea Albarracín OrioDaniel PetrasAndrea M SmaniaSneha P CouvillionMeagan C BurnetCarrie D NicoraErika M ZinkThomas O MetzViatcheslav ArtaevElizabeth Humston-FulmerRachel GregorMichael M MeijlerItzhak MizrahiStav EyalBrooke AndersonRachel DuttonRaphaël LuganPauline Le BoulchYann GuittonStephanie PrevostAudrey PoirierGaud DervillyAbdoulaye Zié KonéAaron FaitNoga Sikron PersiChao SongKelem GashuRoxana CorasMonica GumaJulia ManassonJose U ScherDinesh Kumar BarupalSaleh AlseekhAlisdair Robert FernieReza MirnezamiVasilis VasiliouRobin SchmidRoman S BorisovLarisa N KulikovaRob KnightMingxun WangGeorge B HannaPieter C DorresteinKirill VeselkovPublished in: Nature biotechnology (2020)
We engineered a machine learning approach, MSHub, to enable auto-deconvolution of gas chromatography-mass spectrometry (GC-MS) data. We then designed workflows 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. MSHub/GNPS performs auto-deconvolution of compound fragmentation patterns via unsupervised non-negative matrix factorization and quantifies the reproducibility of fragmentation patterns across samples.