@article{DaiFuellgrabePfeufferetal., author = {Dai, Chengxin and F{\"u}llgrabe, Anja and Pfeuffer, Julianus and Solovyeva, Elizaveta M. and Deng, Jingwen and Moreno, Pablo and Kamatchinathan, Selvakumar and Kundu, Deepti Jaiswal and George, Nancy and Fexovy, Silvie and Gr{\"u}ning, Bj{\"o}rn and F{\"o}ll, Melanie Christine and Griss, Johannes and Vaudel, Marc and Audain, Enrique and Locard-Paulet, Marie and Turewicz, Michael and Eisenacher, Martin and Uszkoreit, Julian and Van Den Bossche, Tim and Schw{\"a}mmle, Veit and Webel, Henry and Schulze, Stefan and Bouyssi{\´e}, David and Jayaram, Savita and Duggineni, Vinay Kumar and Samaras, Patroklos and Wilhelm, Mathias and Choi, Meena and Wang, Mingxun and Kohlbacher, Oliver and Brazma, Alvis and Papatheodorou, Irene and Bandeira, Nuno and Deutsch, Eric W. and Vizca{\´i}no, Juan Antonio and Bai, Mingze and Sachsenberg, Timo and Levitsky, Lev I. and Perez-Riverol, Yasset}, title = {A proteomics sample metadata representation for multiomics integration and big data analysis}, series = {Nature Communications}, volume = {12}, journal = {Nature Communications}, number = {5854}, doi = {https://doi.org/10.1038/s41467-021-26111-3}, abstract = {The amount of public proteomics data is rapidly increasing but there is no standardized format to describe the sample metadata and their relationship with the dataset files in a way that fully supports their understanding or reanalysis. Here we propose to develop the transcriptomics data format MAGE-TAB into a standard representation for proteomics sample metadata. We implement MAGE-TAB-Proteomics in a crowdsourcing project to manually curate over 200 public datasets. We also describe tools and libraries to validate and submit sample metadata-related information to the PRIDE repository. We expect that these developments will improve the reproducibility and facilitate the reanalysis and integration of public proteomics datasets.}, language = {en} } @article{KontouWalterAlkaetal., author = {Kontou, Eftychia E. and Walter, Axel and Alka, Oliver and Pfeuffer, Julianus and Sachsenberg, Timo and Mohite, Omkar and Nuhamunanda, Matin and Kohlbacher, Oliver and Weber, Tilmann}, title = {UmetaFlow: An untargeted metabolomics workflow for high-throughput data processing and analysis}, series = {Journal of Cheminformatics}, volume = {15}, journal = {Journal of Cheminformatics}, doi = {10.1186/s13321-023-00724-w}, abstract = {Metabolomics experiments generate highly complex datasets, which are time and work-intensive, sometimes even error-prone if inspected manually. Therefore, new methods for automated, fast, reproducible, and accurate data processing and dereplication are required. Here, we present UmetaFlow, a computational workflow for untargeted metabolomics that combines algorithms for data pre-processing, spectral matching, molecular formula and structural predictions, and an integration to the GNPS workflows Feature-Based Molecular Networking and Ion Identity Molecular Networking for downstream analysis. UmetaFlow is implemented as a Snakemake workflow, making it easy to use, scalable, and reproducible. For more interactive computing, visualization, as well as development, the workflow is also implemented in Jupyter notebooks using the Python programming language and a set of Python bindings to the OpenMS algorithms (pyOpenMS). Finally, UmetaFlow is also offered as a web-based Graphical User Interface for parameter optimization and processing of smaller-sized datasets. UmetaFlow was validated with in-house LC-MS/MS datasets of actinomycetes producing known secondary metabolites, as well as commercial standards, and it detected all expected features and accurately annotated 76\% of the molecular formulas and 65\% of the structures. As a more generic validation, the publicly available MTBLS733 and MTBLS736 datasets were used for benchmarking, and UmetaFlow detected more than 90\% of all ground truth features and performed exceptionally well in quantification and discriminating marker selection.}, language = {en} }