@article{HuberRidderVerhoevenetal.2021, author = {Huber, Florian and Ridder, Lars and Verhoeven, Stefan and Spaaks, Jurriaan H. and Diblen, Faruk and Rogers, Simon and van der Hooft, Justin J. J.}, title = {Spec2Vec: Improved mass spectral similarity scoring through learning of structural relationships}, series = {PLOS Computational Biology}, volume = {17}, journal = {PLOS Computational Biology}, number = {2}, publisher = {Cold Spring Harbor Laboratory}, organization = {PLOS}, issn = {1553-7358}, doi = {10.1371/journal.pcbi.1008724}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34687}, year = {2021}, abstract = {Spectral similarity is used as a proxy for structural similarity in many tandem mass spectrometry (MS/MS) based metabolomics analyses such as library matching and molecular networking. Although weaknesses in the relationship between spectral similarity scores and the true structural similarities have been described, little development of alternative scores has been undertaken. Here, we introduce Spec2Vec, a novel spectral similarity score inspired by a natural language processing algorithm-Word2Vec. Spec2Vec learns fragmental relationships within a large set of spectral data to derive abstract spectral embeddings that can be used to assess spectral similarities. Using data derived from GNPS MS/MS libraries including spectra for nearly 13,000 unique molecules, we show how Spec2Vec scores correlate better with structural similarity than cosine-based scores. We demonstrate the advantages of Spec2Vec in library matching and molecular networking. Spec2Vec is computationally more scalable allowing structural analogue searches in large databases within seconds.}, language = {en} } @article{SchornVerhoevenRidderetal.2021, author = {Schorn, Michelle A. and Verhoeven, Stefan and Ridder, Lars and Huber, Florian and Acharya, Deepa D. and Aksenov, Alexander A. and Aleti, Gajender and Moghaddam, Jamshid Amiri and Aron, Allegra T. and Aziz, Saefuddin and Bauermeister, Anelize and Bauman, Katherine D. and Baunach, Martin and Beemelmanns, Christine and Beman, J. Michael and Berlanga-Clavero, Mar{\´i}a Victoria and Blacutt, Alex A. and Bode, Helge B. and Boullie, Anne and Brejnrod, Asker and Bugni, Tim S. and Calteau, Alexandra and Cao, Liu and Carri{\´o}n, V{\´i}ctor J. and Castelo-Branco, Raquel and Chanana, Shaurya and Chase, Alexander B. and Chevrette, Marc G. and Costa-Lotufo, Leticia V. and Crawford, Jason M. and Currie, Cameron R. and Cuypers, Bart and Dang, Tam and de Rond, Tristan and Demko, Alyssa M. and Dittmann, Elke and Du, Chao and Drozd, Christopher and Dujardin, Jean-Claude and Dutton, Rachel J. and Edlund, Anna and Fewer, David P. and Garg, Neha and Gauglitz, Julia M. and Gentry, Emily C. and Gerwick, Lena and Glukhov, Evgenia and Gross, Harald and Gugger, Muriel and Guill{\´e}n Matus, Dulce G. and Helfrich, Eric J. N. and Hempel, Benjamin-Florian and Hur, Jae-Seoun and Iorio, Marianna and Jensen, Paul R. and Kang, Kyo Bin and Kaysser, Leonard and Kelleher, Neil L. and Kim, Chung Sub and Kim, Ki Hyun and Koester, Irina and K{\"o}nig, Gabriele M. and Leao, Tiago and Lee, Seoung Rak and Lee, Yi-Yuan and Li, Xuanji and Little, Jessica C. and Maloney, Katherine N. and M{\"a}nnle, Daniel and Martin H, Christian and McAvoy, Andrew C. and Metcalf, Willam W. and Mohimani, Hosein and Molina-Santiago, Carlos and Moore, Bradley S. and Mullowney, Michael W. and Muskat, Mitchell and Nothias, Louis-F{\´e}lix and O'Neill, Ellis C. and Parkinson, Elizabeth I. and Petras, Daniel and Piel, J{\"o}rn and Pierce, Emily C. and Pires, Karine and Reher, Raphael and Romero, Diego and Roper, M. Caroline and Rust, Michael and Saad, Hamada and Saenz, Carmen and Sanchez, Laura M. and S{\o}rensen, S{\o}ren Johannes and Sosio, Margherita and S{\"u}ssmuth, Roderich D. and Sweeney, Douglas and Tahlan, Kapil and Thomson, Regan J. and Tobias, Nicholas J. and Trindade-Silva, Amaro E. and van Wezel, Gilles P. and Wang, Mingxun and Weldon, Kelly C. and Zhang, Fan and Ziemert, Nadine and Duncan, Katherine R. and Cr{\"u}semann, Max and Rogers, Simon and Dorrestein, Pieter C. and Medema, Marnix H. and van der Hooft, Justin J. J.}, title = {A community resource for paired genomic and metabolomic data mining}, series = {Nature Chemical Biology}, volume = {17}, journal = {Nature Chemical Biology}, number = {4}, publisher = {Nature}, issn = {1552-4469}, doi = {10.1038/s41589-020-00724-z}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34708}, pages = {363 -- 368}, year = {2021}, language = {en} } @article{HuberVerhoevenMeijeretal.2020, author = {Huber, Florian and Verhoeven, Stefan and Meijer, Christiaan and Spreeuw, Hanno and Castilla, Efra{\´i}n and Geng, Cunliang and van der Hooft, Justin J. J. and Rogers, Simon and Belloum, Adam and Diblen, Faruk and Spaaks, Jurriaan H.}, title = {matchms - processing and similarity evaluation of mass spectrometry data}, series = {Journal of Open Source Software}, volume = {5}, journal = {Journal of Open Source Software}, number = {52}, publisher = {Cold Spring Harbor Laboratory}, issn = {2475-9066}, doi = {10.21105/joss.02411}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34856}, pages = {2411}, year = {2020}, language = {en} }