Natural products are an important source of bioactive compounds discovery. Thesecompounds played a relevantrole onbiotechnologydevelopment, as medicine prototypes, in the fungi and bacteria controland usedas allelochemicals to plant growthinhibition.1,2Due to the importance of natural products, new computational approaches to chemical interpretation of large data sets have been develop, such as molecular networks, which is a molecular mining tool to findmolecular families and substructures in mass spectrometry fragmentation data.3,4Despite these advances, interpreting large-scale, non-targeted metabolomic datasetis still a challenge when reference spectra are not available or when chemical structures need to be assigned.4Thus, in order to improvechemical structural information in a molecular network, the MolNetEnhacer tool (https://ccms-ucsd.github.io/GNPSDocumentation/molnetenhancer/)was implemented on the GNPS platform (Global Natural Products Social Molecular Networking), which accelerates the chemical structural annotation in complex mixtures through the combined use of networks spectral molecular masses, fragmentation patterns and in silicoannotations, providinga more comprehensive chemical overview of spectral data.4This tool is based on the molecular structure similarity (analogs) which generate fragmentation spectra that can be grouped according to the chemical classes presentin the biological sample.4The chemical classesknowledge of secondary metabolites present in an extract increases the ability to supply mechanistic explanations for the biological behavior of the matrix (structure / activity relationship), in addition toenabling a prior analysis of whether the matrix will answer the proposed research hypotsis.3,4Therefore, in this work, the MolNetEnhacer tool was employedto track and identify the chemical classes contained in Diaporthe phaseolorum(Dp)ethyl acetate extract, which has biological potential already described in the literature as bioherbicide, antioxidant, antimicrobial, antifungal, antibactericide, antitumor and larvicide1,5,6,using LC/Q-TOF-MS/MS and the GNPS platform (http://gnps.ucsd.edu).There were identified 109compounds of11 chemical classes in the network using MolNetEnhancer, where molecular families are mainly describedas carboxylic acids and derivatives, fatty acids, flavonoids, homoisoflavonoids, indoles and derivatives, organooxygen compounds, piperidines, prenol lipids, nucleosides of purine, azoles,steroids and derivatives. Based on these results, we conclude that MolNetEnhancer is anuseful tool that greatly helps the researcher allowing prior knowledge of the chemical characteristics of the matrix of interest.