Research output: Contribution to journal › Article › peer-review
NPOmix: a machine learning classifier to connect mass spectrometry fragmentation data to biosynthetic gene clusters. / Leão, Tiago F.; Wang, Mingxun; da Silva, Ricardo; Gurevich, Alexey ; Bauermeister, Anelize; Gomes, Paulo Wender P.; Brejnrod, Asker; Glukhov, Evgenia; Aron, Allegra T.; Louwen, Joris J. R.; Kim, Hyun Woo; Reher, Raphael; Fiore, Marli F.; van der Hooft, Justin J.J.; Gerwick, Lena; Gerwick, William H.; Bandeira, Nuno; Dorrestein, Pieter C.
In: PNAS Nexus, 26.11.2022.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - NPOmix: a machine learning classifier to connect mass spectrometry fragmentation data to biosynthetic gene clusters
AU - Leão, Tiago F.
AU - Wang, Mingxun
AU - da Silva, Ricardo
AU - Gurevich, Alexey
AU - Bauermeister, Anelize
AU - Gomes, Paulo Wender P.
AU - Brejnrod, Asker
AU - Glukhov, Evgenia
AU - Aron, Allegra T.
AU - Louwen, Joris J. R.
AU - Kim, Hyun Woo
AU - Reher, Raphael
AU - Fiore, Marli F.
AU - van der Hooft, Justin J.J.
AU - Gerwick, Lena
AU - Gerwick, William H.
AU - Bandeira, Nuno
AU - Dorrestein, Pieter C.
N1 - Tiago F Leão, Mingxun Wang, Ricardo da Silva, Alexey Gurevich, Anelize Bauermeister, Paulo Wender P Gomes, Asker Brejnrod, Evgenia Glukhov, Allegra T Aron, Joris J R Louwen, Hyun Woo Kim, Raphael Reher, Marli F Fiore, Justin J J van der Hooft, Lena Gerwick, William H Gerwick, Nuno Bandeira, Pieter C Dorrestein, NPOmix: a machine learning classifier to connect mass spectrometry fragmentation data to biosynthetic gene clusters, PNAS Nexus, 2022;, pgac257, https://doi.org/10.1093/pnasnexus/pgac257
PY - 2022/11/26
Y1 - 2022/11/26
N2 - Microbial specialized metabolites are an important source of and inspiration for many pharmaceutical, biotechnological products and play key roles in ecological processes. Untargeted metabolomics using liquid chromatography coupled with tandem mass spectrometry is an efficient technique to access metabolites from fractions and even environmental crude extracts. Nevertheless, metabolomics is limited in predicting structures or bioactivities for cryptic metabolites. Efficiently linking the biosynthetic potential inferred from (meta)genomics to the specialized metabolome would accelerate drug discovery programs by allowing metabolomics to make use of genetic predictions. Here, we present a k-nearest neighbor classifier to systematically connect mass spectrometry fragmentation spectra to their corresponding biosynthetic gene clusters (independent of their chemical class). Our new pattern-based genome mining pipeline links biosynthetic genes to metabolites that they encode for, as detected via mass spectrometry from bacterial cultures or environmental microbiomes. Using paired datasets that include validated genes-mass spectral links from the Paired omics Data Platform, we demonstrate this approach by automatically linking 18 previously known mass spectra to their corresponding previously experimentally validated biosynthetic genes (e.g., via nuclear magnetic resonance or genetic engineering). We illustrated a computational example of how to combine NPOmix with MassQL for mining siderophores that can be reproduced by NPOmix users. We conclude that NPOmix minimizes the need for culturing (it worked well on microbiomes) and facilitates specialized metabolite prioritization based on integrative omics mining.
AB - Microbial specialized metabolites are an important source of and inspiration for many pharmaceutical, biotechnological products and play key roles in ecological processes. Untargeted metabolomics using liquid chromatography coupled with tandem mass spectrometry is an efficient technique to access metabolites from fractions and even environmental crude extracts. Nevertheless, metabolomics is limited in predicting structures or bioactivities for cryptic metabolites. Efficiently linking the biosynthetic potential inferred from (meta)genomics to the specialized metabolome would accelerate drug discovery programs by allowing metabolomics to make use of genetic predictions. Here, we present a k-nearest neighbor classifier to systematically connect mass spectrometry fragmentation spectra to their corresponding biosynthetic gene clusters (independent of their chemical class). Our new pattern-based genome mining pipeline links biosynthetic genes to metabolites that they encode for, as detected via mass spectrometry from bacterial cultures or environmental microbiomes. Using paired datasets that include validated genes-mass spectral links from the Paired omics Data Platform, we demonstrate this approach by automatically linking 18 previously known mass spectra to their corresponding previously experimentally validated biosynthetic genes (e.g., via nuclear magnetic resonance or genetic engineering). We illustrated a computational example of how to combine NPOmix with MassQL for mining siderophores that can be reproduced by NPOmix users. We conclude that NPOmix minimizes the need for culturing (it worked well on microbiomes) and facilitates specialized metabolite prioritization based on integrative omics mining.
KW - genomics
KW - mass spectrometry
KW - machine learning
KW - Specialized metabolites
KW - biosynthetic gene clusters
UR - https://www.biorxiv.org/content/10.1101/2021.10.05.463235v2.article-info
M3 - Article
JO - PNAS Nexus
JF - PNAS Nexus
SN - 2752-6542
M1 - pgac257
ER -
ID: 100483223