@article{SzwarcRutzLeeetal.2025, author = {Szwarc, Sarah and Rutz, Adriano and Lee, Kyungha and Mejri, Yassine and Bonnet, Olivier and Hazni, Hazrina and Jagora, Adrien and Mbeng Obame, Rany B. and Noh, Jin Kyoung and Otogo N'Nang, Elvis and Alaribe, Stephenie C. and Awang, Khalijah and Bernadat, Guillaume and Choi, Young Hae and Courdavault, Vincent and Frederich, Michel and Gaslonde, Thomas and Huber, Florian and Kam, Toh-Seok and Low, Yun Yee and Poupon, Erwan and van der Hooft, Justin J. J. and Kang, Kyo Bin and Le Pogam, Pierre and Beniddir, Mehdi A.}, title = {Translating community-wide spectral library into actionable chemical knowledge: a proof of concept with monoterpene indole alkaloids}, series = {Journal of Cheminformatics}, volume = {17}, journal = {Journal of Cheminformatics}, number = {1}, publisher = {Springer Nature}, issn = {1758-2946}, doi = {10.1186/s13321-025-01009-0}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54607}, pages = {15}, year = {2025}, abstract = {With over 3000 representatives, the monoterpene indole alkaloids (MIAs) class is among the most diverse families of plant natural products. The MS/MS spectral space exploration of these complex compounds using chemoinformatic and computational mass spectrometry tools offers a valuable opportunity to extract and share chemical insights from this emblematic family of natural products (NPs). In this work, we first present a substantially updated version of the MIADB, a database now containing 422 MS/MS spectra of MIAs that has been uploaded to the GNPS library versus 172 initial entries. We then introduce an innovative workflow that leverages hundreds of fragmentation spectra to support the FAIRification, extraction and dissemination of chemical knowledge. This workflow aims at the extraction of spectral patterns matching finely defined MIA skeletons. These extracted signatures can then be queried against complex biological extract datasets using MassQL. By applying this strategy to an LC-MS/MS dataset of 75 plant extracts, our results demonstrated the efficiency of this approach in identifying the diversity of MIA skeletons present in the analyzed samples. Additionally, our work enabled the digitization of structural data for diverse MIA skeletons by converting them into machine-readable formats and thereby enhancing their dissemination for the scientific community. Scientific contribution A comprehensive investigation of the monoterpene indole alkaloid chemical space, aiming to highlight skeleton-dependent fragmentation similarity trends and to generate valuable spectrometric signatures that could be used as queries.}, subject = {Computational chemistry}, language = {en} } @unpublished{HuberPollmann2025, author = {Huber, Florian and Pollmann, Julian}, title = {Count your bits: more subtle similarity measures using larger radius count vectors}, publisher = {bioRXiv}, doi = {10.1101/2025.06.16.659994}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54632}, pages = {29}, year = {2025}, abstract = {Quantifying molecular similarity is a cornerstone of cheminformatics, underpinning applications from virtual screening to chemical space visualization. A wide range of molecular fingerprints and similarity metrics, most notably Tanimoto scores, are employed, but their effectiveness is highly context-dependent. In this study, we systematically evaluate several 2D fingerprint types, including circular, path-based, and distance-encoded variants, using both binary and count representations. We highlight the consequences of fingerprint choice, vector folding, and similarity metric selection, revealing critical issues such as fingerprint duplication, mass dependent score biases, and high bit collision rates. Sparse and count-based fingerprints consistently outperform fixed-size binary vectors in preserving structural distinctions. Furthermore, we introduce percentile-based normalization, propose inverse-document-frequency (IDF) weighting, and benchmark all methods against graph-based MCES similarities. Our results offer practical guidance for selecting molecular similarity measures, emphasizing the need for conscious, task-aware fingerprinting choices in large-scale chemical analyses.}, subject = {Computational chemistry}, language = {en} } @article{GaudryHuberNothiasetal.2022, author = {Gaudry, Arnaud and Huber, Florian and Nothias, Louis-F{\´e}lix and Cretton, Sylvian and Kaiser, Marcel and Wolfender, Jean-Luc and Allard, Pierre-Marie}, title = {MEMO: Mass Spectrometry-Based Sample Vectorization to Explore Chemodiverse Datasets}, series = {Frontiers in Bioinformatics}, volume = {2}, journal = {Frontiers in Bioinformatics}, publisher = {Frontiers}, issn = {2673-7647}, doi = {10.3389/fbinf.2022.842964}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-54660}, pages = {13}, year = {2022}, abstract = {In natural products research, chemodiverse extracts coming from multiple organisms are explored for novel bioactive molecules, sometimes over extended periods. Samples are usually analyzed by liquid chromatography coupled with fragmentation mass spectrometry to acquire informative mass spectral ensembles. Such data is then exploited to establish relationships among analytes or samples (e.g., via molecular networking) and annotate metabolites. However, the comparison of samples profiled in different batches is challenging with current metabolomics methods since the experimental variation—changes in chromatographical or mass spectrometric conditions - hinders the direct comparison of the profiled samples. Here we introduce MEMO—MS2 BasEd SaMple VectOrization—a method allowing to cluster large amounts of chemodiverse samples based on their LC-MS/MS profiles in a retention time agnostic manner. This method is particularly suited for heterogeneous and chemodiverse sample sets. MEMO demonstrated similar clustering performance as state-of-the-art metrics considering fragmentation spectra. More importantly, such performance was achieved without the requirement of a prior feature alignment step and in a significantly shorter computational time. MEMO thus allows the comparison of vast ensembles of samples, even when analyzed over long periods of time, and on different chromatographic or mass spectrometry platforms. This new addition to the computational metabolomics toolbox should drastically expand the scope of large-scale comparative analysis.}, subject = {Computational chemistry}, language = {en} } @inproceedings{GaudryHuberFlueckigeretal.2022, author = {Gaudry, Arnaud and Huber, Florian and Fl{\"u}ckiger, Julien and Quir{\´o}s, L and Rutz, Adriano and Kaiser, M and Grondin, A and Marcourt, Laurence and Ferreira Queiroz, E and Wolfender, Jean-Luc and Allard, Pierre-Marie}, title = {Short Lecture "Mass spectrometry-based sample vectorization for exploration of large chemodiverse datasets and efficient identification of new antiparasitic compounds"}, series = {Planta Medica}, volume = {88}, booktitle = {Planta Medica}, number = {15}, publisher = {Thieme}, issn = {1439-0221}, doi = {10.1055/s-0042-1758983}, year = {2022}, subject = {Massenspektrometrie}, language = {en} }