@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{MiguelesRowlandsHuberetal.2019, author = {Migueles, Jairo H. and Rowlands, Alex V. and Huber, Florian and Sabia, S{\´e}verine and van Hees, Vincent T.}, title = {GGIR: A Research Community-Driven Open Source R Package for Generating Physical Activity and Sleep Outcomes From Multi-Day Raw Accelerometer Data}, series = {Journal for the Measurement of Physical Behaviour}, volume = {2}, journal = {Journal for the Measurement of Physical Behaviour}, number = {3}, publisher = {Human Kinetics}, issn = {2575-6605}, doi = {10.1123/jmpb.2018-0063}, pages = {188 -- 196}, year = {2019}, language = {en} } @article{BeniddirKangGentaJouveetal.2021, author = {Beniddir, Mehdi A. and Kang, Kyo Bin and Genta-Jouve, Gr{\´e}gory and Huber, Florian and Rogers, Simon and van der Hooft, Justin J. J.}, title = {Advances in decomposing complex metabolite mixtures using substructure- and network-based computational metabolomics approaches}, series = {Natural Product Reports}, volume = {38}, journal = {Natural Product Reports}, number = {11}, publisher = {The Royal Society of Chemistry}, issn = {1460-4752}, doi = {10.1039/D1NP00023C}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34772}, pages = {1967 -- 1993}, year = {2021}, language = {en} } @article{HuberBoireLopezetal.2015, author = {Huber, Florian and Boire, Adeline and L{\´o}pez, Magdalena Preciado and Koenderink, Gijsje H.}, title = {Cytoskeletal crosstalk: when three different personalities team up}, series = {Current Opinion in Cell Biology}, volume = {32}, journal = {Current Opinion in Cell Biology}, publisher = {Elsevier}, issn = {1879-0410}, doi = {10.1016/j.ceb.2014.10.005}, pages = {39 -- 47}, year = {2015}, language = {en} } @article{HuberKaes2011, author = {Huber, Florian and K{\"a}s, Josef}, title = {Self-regulative organization of the cytoskeleton}, series = {Cytoskeleton}, volume = {68}, journal = {Cytoskeleton}, number = {5}, publisher = {Wiley}, issn = {1949-3592}, doi = {10.1002/cm.20509}, pages = {259 -- 265}, year = {2011}, abstract = {Despite its impressive complexity the cytoskeleton succeeds to persistently organize itself and thus the cells' interior. In contrast to classical man-made machines, much of the cellular organization originates from inherent self-assembly and self-organization allowing a high degree of autonomy for various functional units. Recent experimental and theoretical studies revealed numerous examples of cytoskeleton components that arrange and organize in a self-regulative way. In the present review we want to shortly summarize some of the principle mechanisms that are able to inherently trigger and regulate the cytoskeleton organization. Although taken individually most of these regulative principles are rather simple with intuitively predictable consequences, combinations of two or more of these mechanisms can quickly give rise to very complex, unexpected behavior and might even be able to explain the formation of different functional units out of a common pool of available building blocks.}, language = {en} } @article{HuberKaesStuhrmann2008, author = {Huber, Florian and K{\"a}s, Josef and Stuhrmann, Bj{\"o}rn}, title = {Growing actin networks form lamellipodium and lamellum by self-assembly}, series = {Biophysical Journal}, volume = {95}, journal = {Biophysical Journal}, number = {12}, publisher = {Biophysical Society}, issn = {1542-0086}, doi = {10.1529/biophysj.108.134817}, pages = {5508 -- 5523}, year = {2008}, abstract = {Many different cell types are able to migrate by formation of a thin actin-based cytoskeletal extension. Recently, it became evident that this extension consists of two distinct substructures, designated lamellipodium and lamellum, which differ significantly in their kinetic and kinematic properties as well as their biochemical composition. We developed a stochastic two-dimensional computer simulation that includes chemical reaction kinetics, G-actin diffusion, and filament transport to investigate the formation of growing actin networks in migrating cells. Model parameters were chosen based on experimental data or theoretical considerations. In this work, we demonstrate the system's ability to form two distinct networks by self-organization. We found a characteristic transition in mean filament length as well as a distinct maximum in depolymerization flux, both within the first 1-2 microm. The separation into two distinct substructures was found to be extremely robust with respect to initial conditions and variation of model parameters. We quantitatively investigated the complex interplay between ADF/cofilin and tropomyosin and propose a plausible mechanism that leads to spatial separation of, respectively, ADF/cofilin- or tropomyosin-dominated compartments. Tropomyosin was found to play an important role in stabilizing the lamellar actin network. Furthermore, the influence of filament severing and annealing on the network properties is explored, and simulation data are compared to existing experimental data.}, language = {en} } @article{HuberSchnaussRoenickeetal.2013, author = {Huber, Florian and Schnauß, J{\"o}rg and R{\"o}nicke, S. and Rauch, P. and M{\"u}ller, K. and F{\"u}tterer, C. and K{\"a}s, Josef}, title = {Emergent complexity of the cytoskeleton: from single filaments to tissue}, series = {Advances in Physics}, volume = {62}, journal = {Advances in Physics}, number = {1}, publisher = {Taylor \& Francis}, issn = {1460-6976}, doi = {10.1080/00018732.2013.771509}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34812}, pages = {1 -- 112}, year = {2013}, abstract = {Despite their overwhelming complexity, living cells display a high degree of internal mechanical and functional organization which can largely be attributed to the intracellular biopolymer scaffold, the cytoskeleton. Being a very complex system far from thermodynamic equilibrium, the cytoskeleton's ability to organize is at the same time challenging and fascinating. The extensive amounts of frequently interacting cellular building blocks and their inherent multifunctionality permits highly adaptive behavior and obstructs a purely reductionist approach. Nevertheless (and despite the field's relative novelty), the physics approach has already proved to be extremely successful in revealing very fundamental concepts of cytoskeleton organization and behavior. This review aims at introducing the physics of the cytoskeleton ranging from single biopolymer filaments to multicellular organisms. Throughout this wide range of phenomena, the focus is set on the intertwined nature of the different physical scales (levels of complexity) that give rise to numerous emergent properties by means of self-organization or self-assembly.}, language = {en} } @article{HuberStrehleKaes2012, author = {Huber, Florian and Strehle, Dan and Kaes, Josef}, title = {Counterion-induced formation of regular actin bundle networks}, series = {Soft Matter}, volume = {8}, journal = {Soft Matter}, number = {4}, publisher = {Royal Society of Chemistry}, issn = {1744-6848}, pages = {931 -- 936}, year = {2012}, language = {en} } @article{HuberStrehleSchnaussetal.2015, author = {Huber, Florian and Strehle, Dan and Schnauß, J{\"o}rg and K{\"a}s, Josef}, title = {Formation of regularly spaced networks as a general feature of actin bundle condensation by entropic forces}, series = {New Journal of Physics}, volume = {17}, journal = {New Journal of Physics}, number = {4}, publisher = {IOP Publishing}, issn = {1367-2630}, doi = {10.1088/1367-2630/17/4/043029}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34833}, year = {2015}, language = {en} } @article{HubervanderBurgvanderHooftetal.2021, author = {Huber, Florian and van der Burg, Sven and van der Hooft, Justin J. J. and Ridder, Lars}, title = {MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra}, series = {Journal of Cheminformatics}, volume = {13}, journal = {Journal of Cheminformatics}, number = {1}, publisher = {Cold Spring Harbor Laboratory}, issn = {1758-2946}, doi = {10.1186/s13321-021-00558-4}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34847}, pages = {84}, year = {2021}, abstract = {Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model's prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.}, 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} } @article{PreciadoLopezHuberGrigorievetal.2014, author = {Preciado L{\´o}pez, Magdalena and Huber, Florian and Grigoriev, Ilya and Steinmetz, Michel O. and Akhmanova, Anna and Dogterom, Marileen and Koenderink, Gijsje H.}, title = {In vitro reconstitution of dynamic microtubules interacting with actin filament networks}, series = {Methods in Enzymology}, volume = {540}, journal = {Methods in Enzymology}, publisher = {Elsevier}, issn = {1557-7988}, doi = {10.1016/B978-0-12-397924-7.00017-0}, pages = {301 -- 320}, year = {2014}, language = {en} } @article{PreciadoLopezHuberGrigorievetal.2014, author = {Preciado L{\´o}pez, Magdalena and Huber, Florian and Grigoriev, Ilya and Steinmetz, Michel O. and Akhmanova, Anna and Koenderink, Gijsje H. and Dogterom, Marileen}, title = {Actin-microtubule coordination at growing microtubule ends}, series = {Nature Communications}, volume = {5}, journal = {Nature Communications}, publisher = {Springer Nature}, issn = {2041-1723}, doi = {10.1038/ncomms5778}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34878}, pages = {4778}, year = {2014}, abstract = {To power dynamic processes in cells, the actin and microtubule cytoskeletons organize into complex structures. Although it is known that cytoskeletal coordination is vital for cell function, the mechanisms by which cross-linking proteins coordinate actin and microtubule activities remain poorly understood. In particular, it is unknown how the distinct mechanical properties of different actin architectures modulate the outcome of actin-microtubule interactions. To address this question, we engineered the protein TipAct, which links growing microtubule ends via end-binding proteins to actin filaments. We show that growing microtubules can be captured and guided by stiff actin bundles, leading to global actin-microtubule alignment. Conversely, growing microtubule ends can transport, stretch and bundle individual actin filaments, thereby globally defining actin filament organization. Our results provide a physical basis to understand actin-microtubule cross-talk, and reveal that a simple cross-linker can enable a mechanical feedback between actin and microtubule organization that is relevant to diverse biological contexts.}, language = {en} } @article{SiccardiAdamatzkyTuszyńskietal.2020, author = {Siccardi, Stefano and Adamatzky, Andrew and Tuszyński, Jack and Huber, Florian and Schnauß, J{\"o}rg}, title = {Actin networks voltage circuits}, series = {Physical Review E}, volume = {101}, journal = {Physical Review E}, number = {5-1}, publisher = {American Physical Society (APS)}, issn = {2470-0053}, doi = {10.1103/PhysRevE.101.052314}, year = {2020}, language = {en} } @article{SmithGentryStuhrmannetal.2009, author = {Smith, David and Gentry, Brian and Stuhrmann, Bj{\"o}rn and Huber, Florian and Strehle, D. A.N. and Brunner, Claudia and Koch, Daniel and Steinbeck, Matthias and Betz, Timo and K{\"a}s, Josef A.}, title = {The cytoskeleton: An active polymer-based scaffold}, series = {Biophysical Reviews and Letters}, volume = {04}, journal = {Biophysical Reviews and Letters}, issn = {1793-7035}, doi = {10.1142/S1793048009000983}, pages = {179 -- 208}, year = {2009}, language = {en} } @article{StuhrmannHuberKaes2011, author = {Stuhrmann, Bj{\"o}rn and Huber, Florian and K{\"a}s, Josef}, title = {Robust organizational principles of protrusive biopolymer networks in migrating living cells}, series = {Plos One}, volume = {6}, journal = {Plos One}, number = {1}, publisher = {Public Library of Science (PLoS)}, issn = {1932-6203}, doi = {10.1371/journal.pone.0014471}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34901}, year = {2011}, abstract = {Cell migration is associated with the dynamic protrusion of a thin actin-based cytoskeletal extension at the cell front, which has been shown to consist of two different substructures, the leading lamellipodium and the subsequent lamellum. While the formation of the lamellipodium is increasingly well understood, organizational principles underlying the emergence of the lamellum are just beginning to be unraveled. We report here on a 1D mathematical model which describes the reaction-diffusion processes of a polarized actin network in steady state, and reproduces essential characteristics of the lamellipodium-lamellum system. We observe a steep gradient in filament lengths at the protruding edge, a local depolymerization maximum a few microns behind the edge, as well as a differential dominance of the network destabilizer ADF/cofilin and the stabilizer tropomyosin. We identify simple and robust organizational principles giving rise to the derived network characteristics, uncoupled from the specifics of any molecular implementation, and thus plausibly valid across cell types. An analysis of network length dependence on physico-chemical system parameters implies that to limit array treadmilling to cellular dimensions, network growth has to be truncated by mechanisms other than aging-induced depolymerization, e.g., by myosin-associated network dissociation at the transition to the cell body. Our work contributes to the analytical understanding of the cytoskeletal extension's bisection into lamellipodium and lamellum and sheds light on how cells organize their molecular machinery to achieve motility.}, language = {en} } @article{AdamatzkyHuberSchnauss2019, author = {Adamatzky, Andrew and Huber, Florian and Schnauß, J{\"o}rg}, title = {Computing on actin bundles network}, series = {Scientific Reports}, volume = {9}, journal = {Scientific Reports}, number = {1}, publisher = {Springer Nature}, issn = {2045-2322}, doi = {10.1038/s41598-019-51354-y}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34665}, year = {2019}, abstract = {Actin filaments are conductive to ionic currents, mechanical and voltage solitons. These travelling localisations can be utilised to generate computing circuits from actin networks. The propagation of localisations on a single actin filament is experimentally unfeasible to control. Therefore, we consider excitation waves propagating on bundles of actin filaments. In computational experiments with a two-dimensional slice of an actin bundle network we show that by using an arbitrary arrangement of electrodes, it is possible to implement two-inputs-one-output circuits.}, language = {en} } @article{AdamatzkySchnaussHuber2019, author = {Adamatzky, Andrew and Schnauß, J{\"o}rg and Huber, Florian}, title = {Actin droplet machine}, series = {Royal Society Open Science}, volume = {6}, journal = {Royal Society Open Science}, number = {12}, publisher = {Royal Soc. Publ.}, issn = {2054-5703}, doi = {10.1098/rsos.191135}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-34675}, year = {2019}, abstract = {The actin droplet machine is a computer model of a three-dimensional network of actin bundles developed in a droplet of a physiological solution, which implements mappings of sets of binary strings. The actin bundle network is conductive to travelling excitations, i.e. impulses. The machine is interfaced with an arbitrary selected set of k electrodes through which stimuli, binary strings of length k represented by impulses generated on the electrodes, are applied and responses are recorded. The responses are recorded in a form of impulses and then converted to binary strings. The machine's state is a binary string of length k: if there is an impulse recorded on the ith electrode, there is a '1' in the ith position of the string, and '0' otherwise. We present a design of the machine and analyse its state transition graphs. We envisage that actin droplet machines could form an elementary processor of future massive parallel computers made from biopolymers.}, language = {en} } @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}, 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{MullowneyDuncanElsayedetal.2023, author = {Mullowney, Michael W. and Duncan, Katherine R. and Elsayed, Somayah S. and Garg, Neha and van der Hooft, Justin J. J. and Martin, Nathaniel I. and Meijer, David and Terlouw, Barbara R. and Biermann, Friederike and Blin, Kai and Durairaj, Janani and Gorostiola Gonz{\´a}lez, Marina and Helfrich, Eric J. N. and Huber, Florian and Leopold-Messer, Stefan and Rajan, Kohulan and de Rond, Tristan and van Santen, Jeffrey A. and Sorokina, Maria and Balunas, Marcy J. and Beniddir, Mehdi A. and van Bergeijk, Doris A. and Carroll, Laura M. and Clark, Chase M. and Clevert, Djork-Arn{\´e} and Dejong, Chris A. and Du, Chao and Ferrinho, Scarlet and Grisoni, Francesca and Hofstetter, Albert and Jespers, Willem and Kalinina, Olga V. and Kautsar, Satria A. and Kim, Hyunwoo and Leao, Tiago F. and Masschelein, Joleen and Rees, Evan R. and Reher, Raphael and Reker, Daniel and Schwaller, Philippe and Segler, Marwin and Skinnider, Michael A. and Walker, Allison S. and Willighagen, Egon L. and Zdrazil, Barbara and Ziemert, Nadine and Goss, Rebecca J. M. and Guyomard, Pierre and Volkamer, Andrea and Gerwick, William H. and Kim, Hyun Uk and M{\"u}ller, Rolf and van Wezel, Gilles P. and van Westen, Gerard J. P. and Hirsch, Anna K. H. and Linington, Roger G. and Robinson, Serina L. and Medema, Marnix H.}, title = {Artificial intelligence for natural product drug discovery}, series = {Nature Reviews Drug Discovery}, volume = {22}, journal = {Nature Reviews Drug Discovery}, number = {11}, publisher = {Springer Nature}, issn = {1474-1776}, doi = {10.1038/s41573-023-00774-7}, pages = {895 -- 916}, year = {2023}, subject = {Maschinelles Lernen}, 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} } @incollection{AdamatzkyHuberSchnauss2024, author = {Adamatzky, Andrew and Huber, Florian and Schnauß, J{\"o}rg}, title = {Computing on Actin Bundles Network}, series = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing System}, volume = {Wspc Book Series in Unconventional Computing, Vol. 3}, booktitle = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing System}, editor = {Adamatzky, Andrew}, publisher = {WORLD SCIENTIFIC}, isbn = {9789811285066}, issn = {2737-520X}, doi = {10.1142/9789811285073_0013}, pages = {245 -- 261}, year = {2024}, subject = {Actin-Filament}, language = {en} } @incollection{SiccardiAdamatzkyTuszyńskietal.2024, author = {Siccardi, Stefano and Adamatzky, Andrew and Tuszyński, Jack and Huber, Florian and Schnauß, J{\"o}rg}, title = {Actin Networks Voltage Circuits}, series = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing Systems}, volume = {Wspc Book Series in Unconventional Computing, Vol. 3}, booktitle = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing Systems}, editor = {Adamatzky, Andrew}, publisher = {WORLD SCIENTIFIC}, isbn = {9789811285066}, issn = {2737-520X}, doi = {10.1142/9789811285073_0006}, pages = {123 -- 143}, year = {2024}, subject = {Actin-Filament}, language = {en} } @incollection{AdamatzkyHuberSchnauss2024, author = {Adamatzky, Andrew and Huber, Florian and Schnauß, J{\"o}rg}, title = {Actin Droplet Machine}, series = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing Systems}, volume = {Wspc Book Series in Unconventional Computing, Vol. 3}, booktitle = {Actin Computation: Unlocking the Potential of Actin Filaments for Revolutionary Computing Systems}, editor = {Adamatzky, Andrew}, publisher = {WORLD SCIENTIFIC}, isbn = {9789811285066}, issn = {2737-520X}, doi = {10.1142/9789811285073_0014}, pages = {263 -- 284}, year = {2024}, language = {en} } @book{Huber2024, author = {Huber, Florian}, title = {Hands-on Introduction to Data Science with Python}, edition = {v0.21}, publisher = {Zenodo}, doi = {10.5281/zenodo.10074474}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-49548}, pages = {365}, year = {2024}, abstract = {In today's world, data is generated at an unprecedented pace, and our ability to harness it is changing the way we live, work, and even think. Data science, the interdisciplinary field that blends statistics, computer science, and domain-specific knowledge, empowers us to extract insights from this vast ocean of data. As data science becomes increasingly essential across various industries and sectors, there is a growing need for skilled professionals who can make sense of data and transform it into actionable information. This book is designed to give you a very broad and at the same time a very practical hands-on tour through the full spectrum of data science approaches}, subject = {Data Science}, language = {en} } @article{HaberfehlnervandeVenvanderBurgetal.2023, author = {Haberfehlner, Helga and van de Ven, Shankara S. and van der Burg, Sven A. and Huber, Florian and Georgievska, Sonja and Aleo, Ignazio and Harlaar, Jaap and Bonouvri{\´e}, Laura A. and van der Krogt, Marjolein M. and Buizer, Annemieke I.}, title = {Towards automated video-based assessment of dystonia in dyskinetic cerebral palsy: A novel approach using markerless motion tracking and machine learning}, series = {Frontiers in Robotics and AI}, volume = {10}, journal = {Frontiers in Robotics and AI}, publisher = {Frontiers}, issn = {2296-9144}, doi = {10.3389/frobt.2023.1108114}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-40592}, year = {2023}, language = {en} } @article{BittremieuxSchmidHuberetal.2022, author = {Bittremieux, Wout and Schmid, Robin and Huber, Florian and van der Hooft, Justin J. J. and Wang, Mingxun and Dorrestein, Pieter C.}, title = {Comparison of Cosine, Modified Cosine, and Neutral Loss Based Spectrum Alignment For Discovery of Structurally Related Molecules}, series = {Journal of the American Society for Mass Spectrometry}, volume = {33}, journal = {Journal of the American Society for Mass Spectrometry}, number = {9}, publisher = {American Chemical Society (ACS)}, issn = {1044-0305}, doi = {10.1021/jasms.2c00153}, pages = {1733 -- 1744}, year = {2022}, language = {en} } @article{BittremieuxLevitskyPilzetal.2023, author = {Bittremieux, Wout and Levitsky, Lev and Pilz, Matteo and Sachsenberg, Timo and Huber, Florian and Wang, Mingxun and Dorrestein, Pieter C.}, title = {Unified and Standardized Mass Spectrometry Data Processing in Python Using spectrum_utils}, series = {Journal of proteome research}, volume = {22}, journal = {Journal of proteome research}, number = {2}, publisher = {American Chemical Society (ACS)}, issn = {1535-3893}, doi = {10.1021/acs.jproteome.2c00632}, pages = {625 -- 631}, year = {2023}, language = {en} } @article{deJongeMildauMeijeretal.2022, author = {de Jonge, Niek F. and Mildau, Kevin and Meijer, David and Louwen, Joris J. R. and Bueschl, Christoph and Huber, Florian and van der Hooft, Justin J. J.}, title = {Good practices and recommendations for using and benchmarking computational metabolomics metabolite annotation tools}, series = {Metabolomics}, volume = {18}, journal = {Metabolomics}, number = {12}, publisher = {Springer Nature}, issn = {1573-3890}, doi = {10.1007/s11306-022-01963-y}, pages = {22}, year = {2022}, abstract = {Background Untargeted metabolomics approaches based on mass spectrometry obtain comprehensive profiles of complex biological samples. However, on average only 10\% of the molecules can be annotated. This low annotation rate hampers biochemical interpretation and effective comparison of metabolomics studies. Furthermore, de novo structural characterization of mass spectral data remains a complicated and time-intensive process. Recently, the field of computational metabolomics has gained traction and novel methods have started to enable large-scale and reliable metabolite annotation. Molecular networking and machine learning-based in-silico annotation tools have been shown to greatly assist metabolite characterization in diverse fields such as clinical metabolomics and natural product discovery. Aim of review We highlight recent advances in computational metabolite annotation workflows with a special focus on their evaluation and comparison with other tools. Whilst the progress is substantial and promising, we also argue that inconsistencies in benchmarking different tools hamper users from selecting the most appropriate and promising method for their research. We summarize benchmarking strategies of the different tools and outline several recommendations for benchmarking and comparing novel tools. Key scientific concepts of review This review focuses on recent advances in mass spectral library-based and machine learning-supported metabolite annotation workflows. We discuss large-scale library matching and analogue search, the current bloom of mass spectral similarity scores, and how molecular networking has changed the field. In addition, the potentials and challenges of machine learning-supported metabolite annotation workflows are highlighted. Overall, recent developments in computational metabolomics have started to fundamentally change metabolomics workflows, and we expect that as a community we will be able to overcome current method performance ambiguities and annotation bottlenecks.}, subject = {Metabolomik}, language = {en} } @article{deJongeLouwenChekmenevaetal.2023, author = {de Jonge, Niek F. and Louwen, Joris J. R. and Chekmeneva, Elena and Camuzeaux, Stephane and Vermeir, Femke J. and Jansen, Robert S. and Huber, Florian and van der Hooft, Justin J. J.}, title = {MS2Query: reliable and scalable MS2 mass spectra-based analogue search}, series = {Nature Communications}, volume = {14}, journal = {Nature Communications}, publisher = {Springer}, issn = {2041-1723}, doi = {10.1038/s41467-023-37446-4}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-46105}, pages = {12}, year = {2023}, abstract = {Metabolomics-driven discoveries of biological samples remain hampered by the grand challenge of metabolite annotation and identification. Only few metabolites have an annotated spectrum in spectral libraries; hence, searching only for exact library matches generally returns a few hits. An attractive alternative is searching for so-called analogues as a starting point for structural annotations; analogues are library molecules which are not exact matches but display a high chemical similarity. However, current analogue search implementations are not yet very reliable and relatively slow. Here, we present MS2Query, a machine learning-based tool that integrates mass spectral embedding-based chemical similarity predictors (Spec2Vec and MS2Deepscore) as well as detected precursor masses to rank potential analogues and exact matches. Benchmarking MS2Query on reference mass spectra and experimental case studies demonstrate improved reliability and scalability. Thereby, MS2Query offers exciting opportunities to further increase the annotation rate of metabolomics profiles of complex metabolite mixtures and to discover new biology.}, subject = {Metabolomik}, language = {en} } @article{KamiloğluSunBosetal.2024, author = {Kamiloğlu, Roza G. and Sun, Rui and Bos, Patrick and Huber, Florian and Attema, Jisk Jakob and Sauter, Disa A.}, title = {Tickling induces a unique type of spontaneous laughter}, series = {Biology Letters}, volume = {20}, journal = {Biology Letters}, number = {11}, publisher = {The Royal Society}, issn = {1744-957X}, doi = {10.1098/rsbl.2024.0543}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-47446}, year = {2024}, abstract = {Laughing is ubiquitous in human life, yet what causes it and how it sounds is highly variable. Considering this diversity, we sought to test whether there are fundamentally different kinds of laughter. Here, we sampled spontaneous laughs (n = 887) from a wide range of everyday situations (e.g. comedic performances and playful pranks). Machine learning analyses showed that laughs produced during tickling are acoustically distinct from laughs triggered by other kinds of events (verbal jokes, watching something funny or witnessing someone else's misfortune). In a listening experiment (n = 201), participants could accurately identify tickling-induced laughter, validating that such laughter is not only acoustically but also perceptually distinct. A second listening study (n = 210) combined with acoustic analyses indicates that tickling-induced laughter involves less vocal control than laughter produced in other contexts. Together, our results reveal a unique acoustic and perceptual profile of laughter induced by tickling, an evolutionarily ancient play behaviour, distinguishing it clearly from laughter caused by other triggers. This study showcases the power of machine learning in uncovering patterns within complex behavioural phenomena, providing a window into the evolutionary significance of ticking-induced laughter.}, subject = {Lachen}, language = {en} } @article{MildauEhlersMeisenburgetal.2024, author = {Mildau, Kevin and Ehlers, Henry and Meisenburg, Mara and Del Pup, Elena and Koetsier, Robert A. and Torres Ortega, Laura Rosina and de Jonge, Niek F. and Singh, Kumar Saurabh and Ferreira, Dora and Othibeng, Kgalaletso and Tugizimana, Fidele and Huber, Florian and van der Hooft, Justin J. J.}, title = {Effective data visualization strategies in untargeted metabolomics}, series = {Natural Product Reports}, journal = {Natural Product Reports}, publisher = {Royal Society of Chemistry}, issn = {0265-0568}, doi = {10.1039/d4np00039k}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-47596}, pages = {38}, year = {2024}, abstract = {LC-MS/MS-based untargeted metabolomics is a rapidly developing research field spawning increasing numbers of computational metabolomics tools assisting researchers with their complex data processing, analysis, and interpretation tasks. In this article, we review the entire untargeted metabolomics workflow from the perspective of information visualization, visual analytics and visual data integration. Data visualization is a crucial step at every stage of the metabolomics workflow, where it provides core components of data inspection, evaluation, and sharing capabilities. However, due to the large number of available data analysis tools and corresponding visualization components, it is hard for both users and developers to get an overview of what is already available and which tools are suitable for their analysis. In addition, there is little cross-pollination between the fields of data visualization and metabolomics, leaving visual tools to be designed in a secondary and mostly ad hoc fashion. With this review, we aim to bridge the gap between the fields of untargeted metabolomics and data visualization. First, we introduce data visualization to the untargeted metabolomics field as a topic worthy of its own dedicated research, and provide a primer on cutting-edge visualization research into data visualization for both researchers as well as developers active in metabolomics. We extend this primer with a discussion of best practices for data visualization as they have emerged from data visualization studies. Second, we provide a practical roadmap to the visual tool landscape and its use within the untargeted metabolomics field. Here, for several computational analysis stages within the untargeted metabolomics workflow, we provide an overview of commonly used visual strategies with practical examples. In this context, we will also outline promising areas for further research and development. We end the review with a set of recommendations for developers and users on how to make the best use of visualizations for more effective and transparent communication of results.}, subject = {Metabolomik}, language = {en} } @unpublished{deJongeJoasTruongetal.2024, author = {de Jonge, Niek F. and Joas, David and Truong, Lem-Joe and van der Hooft, Justin J.J. and Huber, Florian}, title = {Reliable cross-ion mode chemical similarity prediction between MS2 spectra}, series = {biorxiv}, journal = {biorxiv}, publisher = {Cold Spring Harbor Laboratory}, doi = {10.1101/2024.03.25.586580}, year = {2024}, abstract = {Mass spectrometry is commonly used to characterize metabolites in untargeted metabolomics. This can be done in positive and negative ionization mode, a choice typically guided by the fraction of metabolites a researcher is interested in. During analysis, mass spectral comparisons are widely used to enable annotation through reference libraries and to facilitate data organization through networking. However, until now, such comparisons between mass spectra were restricted to mass spectra of the same ionization mode, as the two modes generally result in very distinct fragmentation spectra. To overcome this barrier, here, we have implemented a machine learning model that can predict chemical similarity between spectra of different ionization modes. Hence, our new MS2DeepScore 2.0 model facilitates the seamless integration of positive and negative ionization mode mass spectra into one analysis pipeline. This creates entirely new options for data exploration, such as mass spectral library searching of negative ion mode spectra in positive ion mode libraries or cross-ionization mode molecular networking. Furthermore, to improve the reliability of predictions and better cope with unseen data, we have implemented a method to estimate the quality of prediction. This will help to avoid false predictions on spectra with low information content or spectra that substantially differ from the training data. We anticipate that the MS2DeepScore 2.0 model will extend our current capabilities in organizing and annotating untargeted metabolomics profiles.}, subject = {Massenspektrometrie}, 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} } @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{HunkeHuberSteffens2025, author = {Hunke, Til and Huber, Florian and Steffens, Jochen}, title = {The Evolution of Song Lyrics: An NLP-Based Analysis of Popular Music in Germany from 1954 to 2022}, series = {Music \& Science}, volume = {8}, journal = {Music \& Science}, publisher = {Sage Publications}, issn = {2059-2043}, doi = {10.1177/20592043251331155}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-52618}, pages = {20}, year = {2025}, abstract = {Music is an indispensable cultural product, reflecting changes in social, psychological, and cultural contexts. This study analyzes the historical evolution of topics and conveyed affect in popular music lyrics in Germany from 1954 to 2022, using LDA-based topic modeling and transformer-based sentiment analysis. These results show that Love \& Relationships is the most referenced topic, with Dreams \& Longings prominent until the mid-1960s and Society \& Status rising from 2017. The sentiment analysis reveals a significant decline in positive sentiment since the mid-1960s, accompanied by increases in negative, ambiguous, and neutral sentiments. These trends may reflect broader societal changes, including shifts in cultural values, rising individualism, and increasing mental health issues. The study highlights the evolving nature of popular music and its reflection of social dynamics.}, subject = {Popmusik}, language = {en} } @article{KokHuberKalischetal.2025, author = {Kok, Maurits and Huber, Florian and Kalisch, Svenja-Marei and Dogterom, Marileen}, title = {EB3-informed dynamics of the microtubule stabilizing cap during stalled growth}, series = {Biophysical Journal}, volume = {124}, journal = {Biophysical Journal}, number = {2}, publisher = {Elsevier}, issn = {1542-0086}, doi = {10.1016/j.bpj.2024.11.3314}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-53164}, pages = {227 -- 244}, year = {2025}, abstract = {Microtubule stability is known to be governed by a stabilizing GTP/GDP-Pi cap, but the exact relation between growth velocity, GTP hydrolysis, and catastrophes remains unclear. We investigate the dynamics of the stabilizing cap through in vitro reconstitution of microtubule dynamics in contact with microfabricated barriers, using the plus-end binding protein GFP-EB3 as a marker for the nucleotide state of the tip. The interaction of growing microtubules with steric objects is known to slow down microtubule growth and accelerate catastrophes. We show that the lifetime distributions of stalled microtubules, as well as the corresponding lifetime distributions of freely growing microtubules, can be fully described with a simple phenomenological 1D model based on noisy microtubule growth and a single EB3-dependent hydrolysis rate. This same model is furthermore capable of explaining both the previously reported mild catastrophe dependence on microtubule growth rates and the catastrophe statistics during tubulin washout experiments.}, subject = {Mikrotubulus}, language = {en} } @unpublished{BushuievBushuievdeJongeetal.2025, author = {Bushuiev, Roman and Bushuiev, Anton and de Jonge, Niek F. and Young, Adamo and Kretschmer, Fleming and Samusevich, Raman and Heirman, Janne and Wang, Fei and Zhang, Luke and D{\"u}hrkop, Kai and Ludwig, Marcus and Haupt, Nils A. and Kalia, Apurva and Brungs, Corinna and Schmid, Robin and Greiner, Russell and Wang, Bo and Wishart, David S. and Liu, Li-Ping and Rousu, Juho and Bittremieux, Wout and R{\"o}st, Hannes and Mak, Tytus D. and Hassoun, Soha and Huber, Florian and van der Hooft, Justin J.J. and Stravs, Michael A. and B{\"o}cker, Sebastian and Sivic, Josef and Pluskal, Tom{\´a}š}, title = {MassSpecGym: A benchmark for the discovery and identification of molecules}, series = {arXiv}, journal = {arXiv}, edition = {v3}, publisher = {arXiv}, doi = {10.48550/arXiv.2410.23326}, pages = {49}, year = {2025}, abstract = {The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym -- the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at this https URL [https://github.com/pluskal-lab/MassSpecGym].}, subject = {Maschinelles Lernen}, language = {en} } @inproceedings{SteffensJoschkoGiangetal.2025, author = {Steffens, Jochen and Joschko, Marcel and Giang, Hien and Huber, Florian}, title = {Using machine learning to identify acoustic fingerprints of concert halls in classical audio recordings [Abstract]}, series = {DAS|DAGA 2025: 51st Annual Meeting on Acoustics, March 17-20, 2025, Copenhagen}, booktitle = {DAS|DAGA 2025: 51st Annual Meeting on Acoustics, March 17-20, 2025, Copenhagen}, publisher = {Deutsche Gesellschaft f{\"u}r Akustik e.V.}, address = {Berlin}, year = {2025}, subject = {Datenanalyse}, language = {en} } @article{deJongeHechtStrobeletal.2024, author = {de Jonge, Niek F. and Hecht, Helge and Strobel, Michael and Wang, Mingxun and van der Hooft, Justin J. J. and Huber, Florian}, title = {Reproducible MS/MS library cleaning pipeline in matchms}, series = {Journal of Cheminformatics}, volume = {16}, journal = {Journal of Cheminformatics}, number = {1}, publisher = {Springer Nature}, issn = {1758-2946}, doi = {10.1186/s13321-024-00878-1}, url = {http://nbn-resolving.de/urn:nbn:de:hbz:due62-opus-46491}, year = {2024}, abstract = {Mass spectral libraries have proven to be essential for mass spectrum annotation, both for library matching and training new machine learning algorithms. A key step in training machine learning models is the availability of high-quality training data. Public libraries of mass spectrometry data that are open to user submission often suffer from limited metadata curation and harmonization. The resulting variability in data quality makes training of machine learning models challenging. Here we present a library cleaning pipeline designed for cleaning tandem mass spectrometry library data. The pipeline is designed with ease of use, flexibility, and reproducibility as leading principles.Scientific contributionThis pipeline will result in cleaner public mass spectral libraries that will improve library searching and the quality of machine-learning training datasets in mass spectrometry. This pipeline builds on previous work by adding new functionality for curating and correcting annotated libraries, by validating structure annotations. Due to the high quality of our software, the reproducibility, and improved logging, we think our new pipeline has the potential to become the standard in the field for cleaning tandem mass spectrometry libraries.}, subject = {Massenspektrometrie}, language = {en} }