@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{BaiDengDaietal.2023, author = {Bai, Mingze and Deng, Jingwen and Dai, Chengxin and Pfeuffer, Julianus and Sachsenberg, Timo and Perez-Riverol, Yasset}, title = {LFQ-Based Peptide and Protein Intensity Differential Expression Analysis}, series = {J. Proteome Res.}, volume = {22}, journal = {J. Proteome Res.}, number = {6}, publisher = {American Chemical Society}, doi = {10.1021/acs.jproteome.2c00812}, pages = {2114 -- 2123}, year = {2023}, abstract = {Testing for significant differences in quantities at the protein level is a common goal of many LFQ-based mass spectrometry proteomics experiments. Starting from a table of protein and/or peptide quantities from a given proteomics quantification software, many tools and R packages exist to perform the final tasks of imputation, summarization, normalization, and statistical testing. To evaluate the effects of packages and settings in their substeps on the final list of significant proteins, we studied several packages on three public data sets with known expected protein fold changes. We found that the results between packages and even across different parameters of the same package can vary significantly. In addition to usability aspects and feature/compatibility lists of different packages, this paper highlights sensitivity and specificity trade-offs that come with specific packages and settings.}, language = {en} }