@article{Rajan2022,

title = {Performance of chemical structure string representations for chemical image recognition using transformers},

author = {Kohulan Rajan and Christoph Steinbeck and Achim Zielesny},

url = {http://dx.doi.org/10.1039/D1DD00013F},

doi = {10.1039/D1DD00013F},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

journal = {Digital Discovery},

pages = {-},

publisher = {RSC},

abstract = {The use of molecular string representations for deep learning in chemistry has been steadily increasing in recent years. The complexity of existing string representations, and the difficulty in creating meaningful tokens from them, lead to the development of new string representations for chemical structures. In this study, the translation of chemical structure depictions in the form of bitmap images to corresponding molecular string representations was examined. An analysis of the recently developed DeepSMILES and SELFIES representations in comparison with the most commonly used SMILES representation is presented where the ability to translate image features into string representations with transformer models was specifically tested. The SMILES representation exhibits the best overall performance whereas SELFIES guarantee valid chemical structures. DeepSMILES perform in between SMILES and SELFIES, InChIs are not appropriate for the learning task. All investigations were performed using publicly available datasets and the code used to train and evaluate the models has been made available to the public.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_111931255,

title = {Surge: a fast open-source chemical graph generator},

author = {Christoph Steinbeck and Brendan D. McKay and Mehmet Aziz Yirik and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-022-00604-9},

doi = {10.1186/s13321-022-00604-9},

year  = {2022},

date = {2022-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:35681226,

title = {DECIMER-hand-drawn molecule images dataset.},

author = {Brinkhaus HO and Zielesny A and Steinbeck C and Rajan K},

doi = {10.1186/s13321-022-00620-9},

year  = {2022},

date = {2022-01-01},

journal = {Journal of cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:35668480,

title = {RanDepict: Random chemical structure depiction generator.},

author = {Brinkhaus HO and Rajan K and Zielesny A and Steinbeck C},

doi = {10.1186/s13321-022-00609-4},

year  = {2022},

date = {2022-01-01},

journal = {Journal of cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_114466081,

title = {Notes on the Treatment of Charged Particles for Studying Cyclotide/Membrane Interactions with Dissipative Particle Dynamics},

author = {Christoph Steinbeck and Felix Bänsch and Christoph Steinbeck and Achim Zielesny},

url = {http://doi.org/10.3390/membranes12060619},

doi = {10.3390/membranes12060619},

year  = {2022},

date = {2022-01-01},

journal = {Membranes},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:35616633,

title = {The LOTUS initiative for open knowledge management in natural products research.},

author = {Rutz A and Sorokina M and Galgonek J and Mietchen D and Willighagen E and Gaudry A and Graham JG and Stephan R and Page R and Vondrášek J and Steinbeck C and Pauli GF and Wolfender JL and Allard PM},

doi = {10.7554/elife.70780},

year  = {2022},

date = {2022-01-01},

journal = {eLife},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:35242913,

title = {Draft genome assembly and sequencing dataset of the marine diatom \textit{Skeletonema} cf. \textit{costatum} RCC75.},

author = {Sorokina M and Barth E and Zulfiqar M and Kwantes M and Pohnert G and Steinbeck C},

doi = {10.1016/j.dib.2022.107931},

year  = {2022},

date = {2022-01-01},

journal = {Data in brief},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Yirik_2021,

title = {MAYGEN - an Open-Source Chemical Structure Generator for Constitutional Isomers Based on the Orderly Generation Principle},

author = {Mehmet Aziz Yirik and Maria Sorokina and Christoph Steinbeck},

url = {https://doi.org/10.26434%2Fchemrxiv.14497959},

doi = {10.26434/chemrxiv.14497959},

year  = {2021},

date = {2021-04-01},

publisher = {American Chemical Society (ACS)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schaub_2021,

title = {Description and Analysis of Glycosidic Residues in the Largest Open Natural Products Database},

author = {Jonas Schaub and Achim Zielesny and Christoph Steinbeck and Maria Sorokina},

url = {https://doi.org/10.3390%2Fbiom11040486},

doi = {10.3390/biom11040486},

year  = {2021},

date = {2021-03-01},

journal = {Biomolecules},

volume = {11},

number = {4},

pages = {486},

publisher = {MDPI AG},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_86548226,

title = {COCONUT online: Collection of Open Natural Products database},

author = {Christoph Steinbeck and Maria Sorokina and Peter Merseburger and Kohulan Rajan and Mehmet Aziz Yirik and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-020-00478-9},

doi = {10.1186/s13321-020-00478-9},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_90179013,

title = {DECIMER-Segmentation: Automated extraction of chemical structure depictions from scientific literature},

author = {Christoph Steinbeck and Kohulan Rajan and Henning Otto Brinkhaus and Maria Sorokina and Achim Zielesny and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-021-00496-1},

doi = {10.1186/s13321-021-00496-1},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_92883418,

title = {STOUT: SMILES to IUPAC names using neural machine translation},

author = {Christoph Steinbeck and Kohulan Rajan and Achim Zielesny and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-021-00512-4},

doi = {10.1186/s13321-021-00512-4},

year  = {2021},

date = {2021-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:33526050,

title = {Molecule Set Comparator (MSC): a CDK-based open rich-client tool for molecule set similarity evaluations.},

author = {Rajan K and Hein JM and Steinbeck C and Zielesny A},

doi = {10.1186/s13321-021-00485-4},

year  = {2021},

date = {2021-01-01},

journal = {Journal of cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_86287117,

title = {Chemical graph generators},

author = {Christoph Steinbeck and Mehmet Aziz Yirik and Daniel Mietchen and Christoph Steinbeck},

url = {http://doi.org/10.1371/journal.pcbi.1008504},

doi = {10.1371/journal.pcbi.1008504},

year  = {2021},

date = {2021-01-01},

journal = {PLOS Computational Biology},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Rajan_2020b,

title = {DECIMER: towards deep learning for chemical image recognition},

author = {Kohulan Rajan and Achim Zielesny and Christoph Steinbeck},

url = {https://doi.org/10.1186%2Fs13321-020-00469-w},

doi = {10.1186/s13321-020-00469-w},

year  = {2020},

date = {2020-10-01},

journal = {Journal of Cheminformatics},

volume = {12},

number = {1},

publisher = {Springer Science and Business Media LLC},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck:bi,

title = {NFDI4Chem - Towards a National Research Data Infrastructure for Chemistry in Germany},

author = {Christoph Steinbeck and Oliver Koepler and Felix Bach and Sonja Herres-Pawlis and Nicole Jung and Johannes Liermann and Steffen Neumann and Matthias Razum and Carsten Baldauf and Frank Biedermann and Thomas Bocklitz and Franziska Boehm and Frank Broda and Paul Czodrowski and Thomas Engel and Martin Hicks and Stefan Kast and Carsten Kettner and Wolfram Koch and Giacomo Lanza and Andreas Link and Ricardo Mata and Wolfgang Nagel and Andrea Porzel and Nils Schlörer and Tobias Schulze and Hans-Georg Weinig and Wolfgang Wenzel and Ludger Wessjohann and Stefan Wulle},

url = {https://riojournal.com/article/55852/},

doi = {10.3897/rio.6.e55852},

year  = {2020},

date = {2020-06-26},

journal = {Research Ideas and Outcomes},

volume = {6},

pages = {e55852},

publisher = {Pensoft Publishers},

abstract = {The vision of NFDI4Chem is the digitalisation of all key steps in chemical research to support scientists in their efforts to collect, store, process, analyse, disclose and re-use research data. Measures to promote Open Science and Research Data Management (RDM) in agreement with the FAIR data principles are fundamental aims of NFDI4Chem to serve the chemistry community with a holistic concept for access to research data. To this end, the overarching objective is the development and maintenance of a national research data infrastructure for the research domain of chemistry in Germany, and to enable innovative and easy to use services and novel scientific approaches based on re-use of research data. NFDI4Chem intends to represent all disciplines of chemistry in academia. We aim to collaborate closely with thematically related consortia. In the initial phase, NFDI4Chem focuses on data related to molecules and reactions including data for their experimental and theoretical characterisation.This overarching goal is achieved by working towards a number of key objectives:Key Objective 1: Establish a virtual environment of federated repositories for storing, disclosing, searching and re-using research data across distributed data sources. Connect existing data repositories and, based on a requirements analysis, establish domain-specific research data repositories for the national research community, and link them to international repositories.Key Objective 2: Initiate international community processes to establish minimum information (MI) standards for data and machine-readable metadata as well as open data standards in key areas of chemistry. Identify and recommend open data standards in key areas of chemistry, in order to support the FAIR principles for research data. Finally, develop standards, if there is a lack.Key Objective 3: Foster cultural and digital change towards Smart Laboratory Environments by promoting the use of digital tools in all stages of research and promote subsequent Research Data Management (RDM) at all levels of academia, beginning in undergraduate studies curricula.Key Objective 4: Engage with the chemistry community in Germany through a wide range of measures to create awareness for and foster the adoption of FAIR data management. Initiate processes to integrate RDM and data science into curricula. Offer a wide range of training opportunities for researchers.Key Objective 5: Explore synergies with other consortia and promote cross-cutting development within the NFDI.Key Objective 6: Provide a legally reliable framework of policies and guidelines for FAIR and open RDM.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sorokina_2020,

title = {Review on natural products databases: where to find data in 2020},

author = {Maria Sorokina and Christoph Steinbeck},

url = {https://doi.org/10.1186%2Fs13321-020-00424-9},

doi = {10.1186/s13321-020-00424-9},

year  = {2020},

date = {2020-04-01},

journal = {Journal of Cheminformatics},

volume = {12},

number = {1},

publisher = {Springer Science and Business Media LLC},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Steinbeck_2020,

title = {Meet the Editors-in-Chief},

author = {Christoph Steinbeck and Paul Trevorrow},

url = {https://doi.org/10.1002%2Fansa.20190010},

doi = {10.1002/ansa.20190010},

year  = {2020},

date = {2020-03-01},

journal = {Analytical Science Advances},

publisher = {Wiley},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Sorokina:2020cl,

title = {Review on natural products databases: where to find data in 2020},

author = {Maria Sorokina and Christoph Steinbeck},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-020-00424-9},

doi = {10.1186/s13321-020-00424-9},

year  = {2020},

date = {2020-01-01},

journal = {Journal of cheminformatics},

volume = {12},

number = {1},

pages = {1--51},

publisher = {BioMed Central},

abstract = {Natural products (NPs) have been the centre of attention of the scientific community in the last decencies and the interest around them continues to grow incessantly. As a consequence, in the last 20 years, there was a rapid multiplication of various databases and collections as generalistic or thematic resources for NP information. In this review, we establish a complete overview of these resources, and the numbers are overwhelming: over 120 different NP databases and collections were published and re-used since 2000. 98 of them are still somehow accessible and only 50 are open access. The latter include not only databases but also big collections of NPs published as supplementary material in scientific publications and collections that were backed up in the ZINC database for commercially-available compounds. Some databases, even published relatively recently are already not accessible anymore, which leads to a dramatic loss of data on NPs. The data sources are presented in this manuscript, together with the comparison of the content of open ones. With this review, we also compiled the open-access natural compounds in one single dataset a COlleCtion of Open NatUral producTs (COCONUT), which is available on Zenodo and contains structures and sparse annotations for over 400,000 non-redundant NPs, which makes it the biggest open collection of NPs available to this date.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:32193935,

title = {Gene Cluster Activation in a Bacterial Symbiont Leads to Halogenated Angucyclic Maduralactomycins and Spirocyclic Actinospirols.},

author = {Guo H and Schwitalla JW and Benndorf R and Baunach M and Steinbeck C and Görls H and Beer de ZW and Regestein L and Beemelmanns C},

doi = {10.1021/acs.orglett.0c00601},

year  = {2020},

date = {2020-01-01},

journal = {Organic letters},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_81571333b,

title = {A review of optical chemical structure recognition tools},

author = {Christoph Steinbeck and Kohulan Rajan and Henning Otto Brinkhaus and Achim Zielesny and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-020-00465-0},

doi = {10.1186/s13321-020-00465-0},

year  = {2020},

date = {2020-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_81571333c,

title = {A review of optical chemical structure recognition tools},

author = {Christoph Steinbeck and Kohulan Rajan and Henning Otto Brinkhaus and Achim Zielesny and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-020-00465-0},

doi = {10.1186/s13321-020-00465-0},

year  = {2020},

date = {2020-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck_81571333b,

title = {A review of optical chemical structure recognition tools},

author = {Christoph Steinbeck and Kohulan Rajan and Henning Otto Brinkhaus and Achim Zielesny and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-020-00465-0},

doi = {10.1186/s13321-020-00465-0},

year  = {2020},

date = {2020-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:33271569,

title = {Metabolomics - the stethoscope for the 21st century.},

author = {Ashrafian H and Sounderajah V and Glen R and Ebbels T and Blaise BJ and Kalra D and Kultima K and Spjuth O and Tenori L and Salek R and Kale N and Haug K and Schober D and Rocca-Serra P and Cascante M},

doi = {10.1159/000513545},

year  = {2020},

date = {2020-01-01},

journal = {Medical principles and practice : international journal of the Kuwait University, Health Science Centre},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Helfrich_2019,

title = {Automated structure prediction of trans-acyltransferase polyketide synthase products},

author = {Eric J N Helfrich and Reiko Ueoka and Alon Dolev and Michael Rust and Roy A Meoded and Agneya Bhushan and Gianmaria Califano and Rodrigo Costa and Muriel Gugger and Christoph Steinbeck and Pablo Moreno and Jörn Piel},

url = {https://doi.org/10.1038%2Fs41589-019-0313-7},

doi = {10.1038/s41589-019-0313-7},

year  = {2019},

date = {2019-07-01},

journal = {Nature Chemical Biology},

publisher = {Springer Science and Business Media LLC},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{publ2001984494,

title = {Interoperable and scalable data analysis with microservices: Applications in Metabolomics.},

author = {P Emami Khoonsari and P Moreno and S Bergmann and J Burman and M Capuccini and M Carone and M Cascante and P de Atauri and C Foguet and A Gonzalez-Beltran and T Hankemeier and K Haug and S He and S Herman and D Johnson and A Larsson and N Kale and K Peters and S Neumann and P Rocca-Serra and L Pireddu and R Rueedi and P Roger and N Sadawi and C Ruttkies and SA Sansone and RM Salek and V Selivanov and D Schober and EA Thévenot and M van Vliet and G Zanetti and C Steinbeck and K Kultima and O Spjuth},

doi = {10.1093/bioinformatics/btz160},

year  = {2019},

date = {2019-01-01},

address = {Oxford},

abstract = {The PhenoMeNal consortium maintains a web portal (https://portal.phenomenal-h2020.eu) providing a GUI for launching the virtual research environment. The GitHub repository https://github.com/phnmnl/ hosts the source code of all projects. 

Supplementary data are available at Bioinformatics online. 

Developing a robust and performant data analysis workflow that integrates all necessary components whilst still being able to scale over multiple compute nodes is a challenging task. We introduce a generic method based on the microservice architecture, where software tools are encapsulated as Docker containers that can be connected into scientific workflows and executed using the Kubernetes container orchestrator. 

We developed a virtual research environment which facilitates rapid integration of new tools and developing scalable and interoperable workflows for performing metabolomics data analysis. The environment can be launched on-demand on cloud resources and desktop computers. IT-expertise requirements on the user side are kept to a minimum, and workflows can be re-used effortlessly by any novice user. We validate our method in the field of metabolomics on two mass spectrometry, one nuclear magnetic resonance spectroscopy and one fluxomics study. We showed that the method scales dynamically with increasing availability of computational resources. We demonstrated that the method facilitates interoperability using integration of the major software suites resulting in a turn-key workflow encompassing all steps for mass-spectrometry-based metabolomics including preprocessing, statistics, and identification. Microservices is a generic methodology that can serve any scientific discipline and opens up for new types of large-scale integrative science. 

AVAILABILITY AND IMPLEMENTATION 

SUPPLEMENTARY INFORMATION 

MOTIVATION 

RESULTS},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Fritsch:2019dt,

title = {ErtlFunctionalGroupsFinder: automated rule-based functional group detection with the Chemistry Development Kit (CDK)},

author = {Sebastian Fritsch and Stefan Neumann and Jonas Schaub and Christoph Steinbeck and Achim Zielesny},

url = {https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0361-8},

doi = {10.1186/s13321-019-0361-8},

year  = {2019},

date = {2019-01-01},

journal = {Journal of cheminformatics},

volume = {11},

number = {1},

pages = {37},

publisher = {BioMed Central},

abstract = {The Ertl algorithm for automated functional groups (FG) detection and extraction of organic molecules is implemented on the basis of the Chemistry Development Kit (CDK). A distinct impact of the chosen CDK aromaticity model is demonstrated by an FG analysis of the ChEMBL database compounds. The average performance of less than a millisecond for a single-molecule FG extraction allows for fast processing of even large compound databases.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Christoph_Steinbeck60376927,

title = {NaPLeS: a natural products likeness scorer—web application and database},

author = {Christoph Steinbeck and Maria Sorokina and Christoph Steinbeck},

url = {http://doi.org/10.1186/s13321-019-0378-z},

doi = {10.1186/s13321-019-0378-z},

year  = {2019},

date = {2019-01-01},

journal = {Journal of Cheminformatics},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:31313429b,

title = {NFDI4Chem: Shaping a Digital and Cultural Change in Chemistry.},

author = {Herres-Pawlis S and Koepler O and Steinbeck C},

doi = {10.1002/anie.201907260},

year  = {2019},

date = {2019-01-01},

journal = {Angewandte Chemie (International ed. in English)},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Pupier:2018jo,

title = {NMReDATA, a standard to report the NMR assignment and parameters of organic compounds},

author = {Marion Pupier and Jean Marc Nuzillard and Julien Wist and Nils E Schlörer and Stefan Kuhn and Mate Erdelyi and Christoph Steinbeck and Antony J Williams and Craig Butts and Tim D W Claridge and Bozhana Mikhova and Wolfgang Robien and Hesam Dashti and Hamid R Eghbalnia and Christophe Far{`e}s and Christian Adam and Kessler Pavel and Fabrice Moriaud and Mikhail Elyashberg and Dimitris Argyropoulos and Manuel Pérez and Patrick Giraudeau and Roberto R Gil and Paul Trevorrow and Damien Jeannerat},

url = {https://onlinelibrary.wiley.com/doi/full/10.1002/mrc.4737},

doi = {10.1002/mrc.4737},

year  = {2018},

date = {2018-01-01},

journal = {Magnetic Resonance in Chemistry},

publisher = {Wiley-Blackwell},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ritter:2018bd,

title = {In vivo and in vitro identification of Z-BOX C – a new bilirubin oxidation end product},

author = {Marcel Ritter and Sandesh Neupane and Raphael A Seidel and Christoph Steinbeck and Georg Pohnert},

url = {http://pubs.rsc.org/en/content/articlehtml/2018/ob/c8ob00164b},

doi = {10.1039/C8OB00164B},

year  = {2018},

date = {2018-01-01},

journal = {Organic & Biomolecular Chemistry},

volume = {6},

pages = {967},

publisher = {The Royal Society of Chemistry},

abstract = {A new bilirubin oxidation end product (BOX) was isolated and characterized. The formation of the so-called Z-BOX C proceeds from bilirubin via propentdyopents as intermediates. This BOX was detected in pathological human bile samples using liquid chromatography/mass spectrometry and has potential relevance for liver dysfunction and cerebral vasospasms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peters:2018cv,

title = {Current Challenges in Plant Eco-Metabolomics},

author = {Kristian Peters and Anja Worrich and Alexander Weinhold and Oliver Alka and Gerd Balcke and Claudia Birkemeyer and Helge Bruelheide and Onno Calf and Sophie Dietz and Kai Dührkop and Emmanuel Gaquerel and Uwe Heinig and Marlen Kücklich and Mirka Macel and Caroline Müller and Yvonne Poeschl and Georg Pohnert and Christian Ristok and Victor Rodr{'i}guez and Christoph Ruttkies and Meredith Schuman and Rabea Schweiger and Nir Shahaf and Christoph Steinbeck and Maria Tortosa and Hendrik Treutler and Nico Ueberschaar and Pablo Velasco and Brigitte Weiß and Anja Widdig and Steffen Neumann and Nicole Dam},

url = {http://www.mdpi.com/1422-0067/19/5/1385/htm},

doi = {10.3390/ijms19051385},

year  = {2018},

date = {2018-01-01},

journal = {International Journal of Molecular Sciences},

volume = {19},

number = {5},

pages = {1385},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {The relatively new research discipline of Eco-Metabolomics is the application of metabolomics techniques to ecology with the aim to characterise biochemical interactions of organisms across different spatial and temporal scales. Metabolomics is an untargeted biochemical approach to measure many thousands of metabolites in different species, including plants and animals. Changes in metabolite concentrations can provide mechanistic evidence for biochemical processes that are relevant at ecological scales. These include physiological, phenotypic and morphological responses of plants and communities to environmental changes and also interactions with other organisms. Traditionally, research in biochemistry and ecology comes from two different directions and is performed at distinct spatiotemporal scales. Biochemical studies most often focus on intrinsic processes in individuals at physiological and cellular scales. Generally, they take a bottom-up approach scaling up cellular processes from spatiotemporally fine to coarser scales. Ecological studies usually focus on extrinsic processes acting upon organisms at population and community scales and typically study top-down and bottom-up processes in combination. Eco-Metabolomics is a transdisciplinary research discipline that links biochemistry and ecology and connects the distinct spatiotemporal scales. In this review, we focus on approaches to study chemical and biochemical interactions of plants at various ecological levels, mainly plant-organismal interactions, and discuss related examples from other domains. We present recent developments and highlight advancements in Eco-Metabolomics over the last decade from various angles. We further address the five key challenges: (1) complex experimental designs and large variation of metabolite profiles; (2) feature extraction; (3) metabolite identification; (4) statistical analyses; and (5) bioinformatics software tools and workflows. The presented solutions to these challenges will advance connecting the distinct spatiotemporal scales and bridging biochemistry and ecology.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Guo:2018ge,

title = {Expanding the Rubterolone Family - Intrinsic Reactivity and Directed Diversification of PKS-derived Pyrans},

author = {Huijuan Guo and Rene Benndorf and Stefanie König and Daniel Leichnitz and Christiane Weigel and Gundela Peschel and Patrick Berthel and Marcel Kaiser and Christoph Steinbeck and Oliver Werz and Michael Poulsen and Christine Beemelmanns},

url = {https://onlinelibrary.wiley.com/doi/full/10.1002/chem.201802066},

doi = {10.1002/chem.201802066},

year  = {2018},

date = {2018-01-01},

journal = {Chemistry – A European Journal},

publisher = {Wiley-Blackwell},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{McAlpine:2018ee,

title = {The value of universally available raw NMR data for transparency, reproducibility, and integrity in natural product research},

author = {James B McAlpine and Shao-Nong Chen and Andrei Kutateladze and John B MacMillan and Giovanni Appendino and Andersson Barison and Mehdi A Beniddir and Maique W Biavatti and Stefan Bluml and Asmaa Boufridi and Mark S Butler and Robert J Capon and Young H Choi and David Coppage and Phillip Crews and Michael T Crimmins and Marie Csete and Pradeep Dewapriya and Joseph M Egan and Mary J Garson and Grégory Genta-Jouve and William H Gerwick and Harald Gross and Mary Kay Harper and Precilia Hermanto and James M Hook and Luke Hunter and Damien Jeannerat and Nai-Yun Ji and Tyler A Johnson and David G I Kingston and Hiroyuki Koshino and Hsiau-Wei Lee and Guy Lewin and Jie Li and Roger G Linington and Miaomiao Liu and Kerry L McPhail and Tadeusz F Molinski and Bradley S Moore and Joo-Won Nam and Ram P Neupane and Matthias Niemitz and Jean Marc Nuzillard and Nicholas H Oberlies and Fernanda M M Ocampos and Guohui Pan and Ronald J Quinn and Sai D Reddy and Jean-Hugues Renault and José Rivera-Chávez and Wolfgang Robien and Carla M Saunders and Thomas J Schmidt and Christoph Seger and Ben Shen and Christoph Steinbeck and Hermann Stuppner and Sonja Sturm and Orazio Taglialatela-Scafati and Dean J Tantillo and Robert Verpoorte and Bin-Gui Wang and Craig M Williams and Philip G Williams and Julien Wist and Jian-Min Yue and Chen Zhang and Zhengren Xu and Charlotte Simmler and David C Lankin and Jonathan Bisson and Guido F Pauli},

url = {https://pubs.rsc.org/en/content/articlehtml/2018/np/c7np00064b},

doi = {10.1039/C7NP00064B},

year  = {2018},

date = {2018-01-01},

journal = {Natural Product Reports},

volume = {33},

pages = {1028},

publisher = {The Royal Society of Chemistry},

abstract = {Covering: up to 2018With contributions from the global natural product (NP) research community, and continuing the Raw Data Initiative, this review collects a comprehensive demonstration of the immense scientific value of disseminating raw nuclear magnetic resonance (NMR) data, independently of, and in parallel with, classical publishing outlets. A comprehensive compilation of historic to present-day cases as well as contemporary and future applications show that addressing the urgent need for a repository of publicly accessible raw NMR data has the potential to transform natural products (NPs) and associated fields of chemical and biomedical research. The call for advancing open sharing mechanisms for raw data is intended to enhance the transparency of experimental protocols, augment the reproducibility of reported outcomes, including biological studies, become a regular component of responsible research, and thereby enrich the integrity of NP research and related fields.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Peters:2018dt,

title = {PhenoMeNal: Processing and analysis of Metabolomics data in the Cloud},

author = {Kristian Peters and James Bradbury and Sven Bergmann and Marco Capuccini and Marta Cascante and Pedro de Atauri and Tim Ebbels and Carles Foguet and Robert Glen and Alejandra González-Beltrán and Evangelos Handakas and Thomas Hankemeier and Stephanie Herman and Kenneth Haug and Petr Holub and Massimiliano Izzo and Daniel Jacob and David Johnson and Fabien Jourdan and Namrata Kale and Ibrahim Karaman and Bita Khalili and Payam Emami Khoonsari and Kim Kultima and Samuel Lampa and Anders Larsson and Pablo Moreno and Steffen Neumann and Jon Ander Novella and Claire O'Donovan and Jake TM Pearce and Alina Peluso and Luca Pireddu and Marco Enrico Piras and Michelle AC Reed and Philippe Rocca-Serra and Pierrick Roger and Antonio Rosato and Rico Rueedi and Christoph Ruttkies and Noureddin Sadawi and Reza Salek and Susanna-Assunta Sansone and Vitaly Selivanov and Ola Spjuth and Daniel Schober and Etienne A Thévenot and Mattia Tomasoni and Merlijn van Rijswijk and Michael van Vliet and Mark Viant and Ralf Weber and Gianluigi Zanetti and Christoph Steinbeck},

url = {http://biorxiv.org/lookup/doi/10.1101/409151},

doi = {10.1101/409151},

year  = {2018},

date = {2018-01-01},

journal = {bioRxiv},

pages = {409151},

publisher = {Cold Spring Harbor Laboratory},

abstract = {
Background: Metabolomics is the comprehensive study of a multitude of small molecules to gain insight into an organism9s metabolism. The research field is dynamic and expanding with applications across biomedical, biotechnological and many other applied biological domains. Its computationally-intensive nature has driven requirements for open data formats, data repositories and data analysis tools. However, the rapid progress has resulted in a mosaic of independent, and sometimes incompatible, analysis methods that are difficult to connect into a useful and complete data analysis solution. Findings: The PhenoMeNal (Phenome and Metabolome aNalysis) e-infrastructure provides a complete, workflow-oriented, interoperable metabolomics data analysis solution for a modern infrastructure-as-a-service (IaaS) cloud platform. PhenoMeNal seamlessly integrates a wide array of existing open source tools which are tested and packaged as Docker containers through the project9s continuous integration process and deployed based on a kubernetes orchestration framework. It also provides a number of standardized, automated and published analysis workflows in the user interfaces Galaxy, Jupyter, Luigi and Pachyderm. Conclusions: PhenoMeNal constitutes a keystone solution in cloud infrastructures available for metabolomics. It provides scientists with a ready-to-use, workflow-driven, reproducible and shareable data analysis platform harmonizing the software installation and configuration through user-friendly web interfaces. The deployed cloud environments can be dynamically scaled to enable large-scale analyses which are interfaced through standard data formats, versioned, and have been tested for reproducibility and interoperability. The flexible implementation of PhenoMeNal allows easy adaptation of the infrastructure to other application areas and 9omics research domains.
},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PMID:30535405,

title = {PhenoMeNal: Processing and analysis of Metabolomics data in the Cloud.},

author = {Peters K and Bradbury J and Bergmann S and Capuccini M and Cascante M and Atauri de P and Ebbels TMD and Foguet C and Glen R and Gonzalez-Beltran A and Günther UL and Handakas E and Steinbeck C},

doi = {10.1093/gigascience/giy149},

year  = {2018},

date = {2018-01-01},

journal = {GigaScience},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017cr,

title = {A decade after the metabolomics standards initiative it's time for a revision},

author = {Rachel A Spicer and Reza Salek and Christoph Steinbeck},

url = {http://www.nature.com/articles/sdata2017138},

doi = {10.1038/sdata.2017.138},

year  = {2017},

date = {2017-09-01},

journal = {Scientific Data},

volume = {4},

pages = {sdata2017138},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{vanRijswijk:2017jk,

title = {The future of metabolomics in ELIXIR},

author = {Merlijn van Rijswijk and Charlie Beirnaert and Christophe Caron and Marta Cascante and Victoria Dominguez and Warwick B Dunn and Timothy M D Ebbels and Franck Giacomoni and Alejandra González-Beltrán and Thomas Hankemeier and Kenneth Haug and Jose L Izquierdo-Garcia and Rafael C Jiménez and Fabien Jourdan and Namrata Kale and Maria I Klapa and Oliver Kohlbacher and Kairi Koort and Kim Kultima and Gildas Le Corguillé and Nicholas K Moschonas and Steffen Neumann and Claire O'Donovan and Martin Reczko and Philippe Rocca-Serra and Antonio Rosato and Reza M Salek and Susanna-Assunta Sansone and Venkata Satagopam and Daniel Schober and Ruth Shimmo and Rachel A Spicer and Ola Spjuth and Etienne A Thévenot and Mark R Viant and Ralf J M Weber and Egon L Willighagen and Gianluigi Zanetti and Christoph Steinbeck},

url = {https://f1000research.com/articles/6-1649/v1},

doi = {10.12688/f1000research.12342.1},

year  = {2017},

date = {2017-09-01},

journal = {F1000Research},

volume = {6},

pages = {1649},

abstract = {Read the latest article version by Merlijn van Rijswijk, Charlie Beirnaert, Christophe Caron, Marta Cascante, Victoria Dominguez, Warwick B. Dunn, Timothy M. D. Ebbels, Franck Giacomoni, Alejandra Gonzalez-Beltran, Thomas Hankemeier, Kenneth Haug, Jose L. Izquierdo-Garcia, Rafael C. Jimenez, Fabien Jourdan, Namrata Kale, Maria I. Klapa, Oliver Kohlbacher, Kairi Koort, Kim Kultima, Gildas Le Corguillé, Nicholas K. Moschonas, Steffen Neumann, Claire OtextquoterightDonovan, Martin Reczko, Philippe Rocca-Serra, Antonio Rosato, Reza M. Salek, Susanna-Assunta Sansone, Venkata Satagopam, Daniel Schober, Ruth Shimmo, Rachel A. Spicer, Ola Spjuth, Etienne A. Thévenot, Mark R. Viant, Ralf J. M. Weber, Egon L. Willighagen, Gianluigi Zanetti, Christoph Steinbeck, at F1000Research.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017jc,

title = {Navigating freely-available software tools for metabolomics analysis},

author = {Spicer, Rachel and Salek, Reza M and Moreno, Pablo and Cañueto, Daniel and Steinbeck, Christoph},

url = {https://link.springer.com/article/10.1007/s11306-017-1242-7},

doi = {10.1007/s11306-017-1242-7},

year  = {2017},

date = {2017-08-01},

journal = {Metabolomics},

volume = {13},

number = {9},

pages = {106},

publisher = {Springer US},

abstract = {The field of metabolomics has expanded greatly over the past two decades, both as an experimental science with applications in many areas, as well as in regards to data standards and bioinformatics so},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PerezRiverol:2017ek,

title = {Discovering and linking public omics data sets using the Omics Discovery Index},

author = {Pèrez-Riverol, Yasset and Bai, Mingze and da Veiga Leprevost, Felipe and Squizzato, Silvano and Park, Young Mi and Haug, Kenneth and Carroll, Adam J and Spalding, Dylan and Paschall, Justin and Wang, Mingxun and Del-Toro, Noemi and Ternent, Tobias and Zhang, Peng and Buso, Nicola and Bandeira, Nuno and Deutsch, Eric W and Campbell, David S and Beavis, Ronald C and Salek, Reza M and Sarkans, Ugis and Petryszak, Robert and Keays, Maria and Fahy, Eoin and Sud, Manish and Subramaniam, Shankar and Barbera, Ariana and Jim{'e}nez, Rafael C and Nesvizhskii, Alexey I and Sansone, Susanna-Assunta and Steinbeck, Christoph and Lopez, Rodrigo and Vizca{'i}no, Juan A and Ping, Peipei and Hermjakob, Henning},

url = {http://www.nature.com/doifinder/10.1038/nbt.3790},

doi = {10.1038/nbt.3790},

year  = {2017},

date = {2017-05-01},

journal = {Nature Biotechnology},

volume = {35},

number = {5},

pages = {406--409},

publisher = {Nature Research},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Haug:2017cb,

title = {Global open data management in metabolomics.},

author = {Haug, Kenneth and Salek, Reza M and Steinbeck, Christoph},

url = {http://linkinghub.elsevier.com/retrieve/pii/S1367593116302083},

doi = {10.1016/j.cbpa.2016.12.024},

year  = {2017},

date = {2017-02-01},

journal = {Current Opinion in Chemical Biology},

volume = {36},

pages = {58--63},

abstract = {Chemical Biology employs chemical synthesis, analytical chemistry and other tools to study biological systems. Recent advances in both molecular biology such as next generation sequencing (NGS) have led to unprecedented insights towards the evolution of organisms' biochemical repertoires. Because of the specific data sharing culture in Genomics, genomes from all kingdoms of life become readily available for further analysis by other researchers. While the genome expresses the potential of an organism to adapt to external influences, the Metabolome presents a molecular phenotype that allows us to asses the external influences under which an organism exists and develops in a dynamic way. Steady advancements in instrumentation towards high-throughput and highresolution methods have led to a revival of analytical chemistry methods for the measurement and analysis of the metabolome of organisms. This steady growth of metabolomics as a field is leading to a similar accumulation of big data across laboratories worldwide as can be observed in all of the other omics areas. This calls for the development of methods and technologies for handling and dealing with such large datasets, for efficiently distributing them and for enabling re-analysis. Here we describe the recently emerging ecosystem of global open-access databases and data exchange efforts between them, as well as the foundations and obstacles that enable or prevent the data sharing and reanalysis of this data.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Larralde:2017di,

title = {mzML2ISA & nmrML2ISA: generating enriched ISA-Tab metadata files from metabolomics XML data.},

author = {Larralde, Martin and Lawson, Thomas N and Weber, Ralf J M and Moreno, Pablo and Haug, Kenneth and Rocca-Serra, Philippe and Viant, Mark R and Steinbeck, Christoph and Salek, Reza M},

url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btx169},

doi = {10.1093/bioinformatics/btx169},

year  = {2017},

date = {2017-01-01},

journal = {Bioinformatics},

abstract = {Summary:Submission to the MetaboLights repository for metabolomics data currently places the burden of reporting instrument and acquisition parameters in ISA-Tab format on users, who have to do it manually, a process that is time consuming and prone to user input error. Since the large majority of these parameters are embedded in instrument raw data files, an opportunity exists to capture this metadata more accurately. Here we report a set of Python packages that can automatically generate ISA-Tab metadata file stubs from raw XML metabolomics data files. The parsing packages are separated into mzML2ISA (encompassing mzML and imzML formats) and nmrML2ISA (nmrML format only). Overall, the use of mzML2ISA & nmrML2ISA reduces the time needed to capture metadata substantially (capturing 90% of metadata on assay and sample levels), is much less prone to user input errors, improves compliance with minimum information reporting guidelines and facilitates more finely grained data exploration and querying of datasets. 

 

Availability and Implementation:mzML2ISA & nmrML2ISA are available under version 3 of the GNU General Public Licence at https://github.com/ISA-tools . Documentation is available from http://2isa.readthedocs.io/en/latest/ . 

 Contact:reza.salek@ebi.ac.uk or isatools@googlegroups.com. 

 

Supplementary information:Supplementary data are available at Bioinformatics online.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Willighagen:2017ge,

title = {The Chemistry Development Kit (CDK) v2.0: atom typing, depiction, molecular formulas, and substructure searching},

author = {Willighagen, Egon L and Mayfield, John W and Alvarsson, Jonathan and Berg, Arvid and Carlsson, Lars and Jeliazkova, Nina and Kuhn, Stefan and Pluskal, Tomás and Rojas-Chertó, Miquel and Spjuth, Ola and Torrance, Gilleain and Evelo, Chris T and Guha, Rajarshi and Steinbeck, Christoph},

url = {https://jcheminf.springeropen.com/articles/10.1186/s13321-017-0220-4},

doi = {10.1186/s13321-017-0220-4},

year  = {2017},

date = {2017-01-01},

journal = {Journal of cheminformatics},

volume = {9},

number = {1},

pages = {33},

publisher = {Springer International Publishing},

abstract = {The Chemistry Development Kit (CDK) is a widely used open source cheminformatics toolkit, providing data structures to represent chemical concepts along with methods to manipulate such structures and perform computations on them. The library implements a wide variety of cheminformatics algorithms ranging from chemical structure canonicalization to molecular descriptor calculations and pharmacophore perception. It is used in drug discovery, metabolomics, and toxicology. Over the last 10~years, the code base has grown significantly, however, resulting in many complex interdependencies among components and poor performance of many algorithms. We report improvements to the CDK v2.0 since the v1.2 release series, specifically addressing the increased functional complexity and poor performance. We first summarize the addition of new functionality, such atom typing and molecular formula handling, and improvement to existing functionality that has led to significantly better performance for substructure searching, molecular fingerprints, and rendering of molecules. Second, we outline how the CDK has evolved with respect to quality control and the approaches we have adopted to ensure stability, including a code review mechanism. This paper highlights our continued efforts to provide a community driven, open source cheminformatics library, and shows that such collaborative projects can thrive over extended periods of time, resulting in a high-quality and performant library. By taking advantage of community support and contributions, we show that an open source cheminformatics project can act as a peer reviewed publishing platform for scientific computing software.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Weber:2017fga,

title = {Computational tools and workflows in metabolomics: An international survey highlights the opportunity for harmonisation through Galaxy.},

author = {Weber, Ralf J M and Lawson, Thomas N and Salek, Reza M and Ebbels, Timothy M D and Glen, Robert C and Goodacre, Royston and Griffin, Julian L and Haug, Kenneth and Koulman, Albert and Moreno, Pablo and Ralser, Markus and Steinbeck, Christoph and Dunn, Warwick B and Viant, Mark R},

url = {http://link.springer.com/10.1007/s11306-016-1147-x},

doi = {10.1007/s11306-016-1147-x},

year  = {2017},

date = {2017-01-01},

journal = {Metabolomics},

volume = {13},

number = {2},

pages = {12},

publisher = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Salek:2017ex,

title = {Automated Assembly of Species Metabolomes through Data Submission into a Public Repository},

author = {Reza M Salek and Pablo Conesa and Keeva Cochrane and Kenneth Haug and Mark Williams and Namrata Kale and Pablo Moreno and Kalai Jayaseelan and Jose Ramon Macias and Venkata Chandrasekhar Nainala and Robert D Hall and Laura K Reed and Mark R Viant and Claire O'Donovan and Christoph Steinbeck},

url = {https://academic.oup.com/gigascience/article-lookup/doi/10.1093/gigascience/gix062},

doi = {10.1093/gigascience/gix062},

year  = {2017},

date = {2017-01-01},

journal = {GigaScience},

abstract = {Following similar global efforts to exchange genomic and other biomedical data, global databases in metabolomics have now been established. MetaboLights, the first general purpose, publically available, cross-species, cross-application database in metabolomics, has become the fastest growing data repository at the European Bioinformatics Institute in terms of data volume. Here we present the automated assembly of species metabolomes in MetaboLights, a crucial reference for chemical biology, which is growing through user submissions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Spicer:2017gy,

title = {Compliance with minimum information guidelines in public metabolomics repositories},

author = {Rachel A Spicer and Reza Salek and Christoph Steinbeck},

url = {http://www.nature.com/articles/sdata2017137},

doi = {10.1038/sdata.2017.137},

year  = {2017},

date = {2017-01-01},

journal = {Scientific Data},

volume = {4},

pages = {sdata2017137},

publisher = {Nature Publishing Group},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Schober:2017gg,

title = {nmrML: A Community Supported Open Data Standard for the Description, Storage, and Exchange of NMR Data},

author = {Daniel Schober and Daniel Jacob and Michael Wilson and Joseph A Cruz and Ana Marcu and Jason R Grant and Annick Moing and Catherine Deborde and Luis F de Figueiredo and Kenneth Haug and Philippe Rocca-Serra and John Easton and Timothy M D Ebbels and Jie Hao and Christian Ludwig and Ulrich L Günther and Antonio Rosato and Matthias S Klein and Ian A Lewis and Claudio Luchinat and Andrew R Jones and Arturas Grauslys and Martin Larralde and Masashi Yokochi and Naohiro Kobayashi and Andrea Porzel and Julian L Griffin and Mark R Viant and David S Wishart and Christoph Steinbeck and Reza M Salek and Steffen Neumann},

url = {http://pubs.acs.org/doi/10.1021/acs.analchem.7b02795},

doi = {10.1021/acs.analchem.7b02795},

year  = {2017},

date = {2017-01-01},

journal = {Analytical Chemistry},

volume = {90},

number = {1},

pages = {649--656},

publisher = {American Chemical Society},

abstract = {NMR is a widely used analytical technique with a growing number of repositories available. As a result, demands for a vendor-agnostic, open data format for long-term archiving of NMR data have emerged with the aim to ease and encourage sharing, comparison, and reuse of NMR data. Here we present nmrML, an open XML-based exchange and storage format for NMR spectral data. The nmrML format is intended to be fully compatible with existing NMR data for chemical, biochemical, and metabolomics experiments. nmrML can capture raw NMR data, spectral data acquisition parameters, and where available spectral metadata, such as chemical structures associated with spectral assignments. The nmrML format is compatible with pure-compound NMR data for reference spectral libraries as well as NMR data from complex biomixtures, i.e., metabolomics experiments. To facilitate format conversions, we provide nmrML converters for Bruker, JEOL and Agilent/Varian vendor formats. In addition, easy-to-use Web-based spectral viewing, proc...},

keywords = {},

pubstate = {published},

tppubtype = {article}

}