@article{RyngajlloChildsLohseetal.2011,
  author    = {Ryngajllo, Malgorzata and Childs, Liam H. and Lohse, Marc and Giorgi, Federico M. and Lude, Anja and Selbig, Joachim and Usadel, Bj{\"o}rn},
  title     = {SLocX predicting subcellular localization of Arabidopsis proteins leveraging gene expression data},
  series = {Frontiers in plant science},
  volume    = {2},
  journal   = {Frontiers in plant science},
  publisher = {Frontiers Research Foundation},
  address   = {Lausanne},
  issn      = {1664-462X},
  doi       = {10.3389/fpls.2011.00043},
  pages     = {19},
  year      = {2011},
  abstract  = {Despite the growing volume of experimentally validated knowledge about the subcellular localization of plant proteins, a well performing in silico prediction tool is still a necessity. Existing tools, which employ information derived from protein sequence alone, offer limited accuracy and/or rely on full sequence availability. We explored whether gene expression profiling data can be harnessed to enhance prediction performance. To achieve this, we trained several support vector machines to predict the subcellular localization of Arabidopsis thaliana proteins using sequence derived information, expression behavior, or a combination of these data and compared their predictive performance through a cross-validation test. We show that gene expression carries information about the subcellular localization not available in sequence information, yielding dramatic benefits for plastid localization prediction, and some notable improvements for other compartments such as the mito-chondrion, the Golgi, and the plasma membrane. Based on these results, we constructed a novel subcellular localization prediction engine, SLocX, combining gene expression profiling data with protein sequence-based information. We then validated the results of this engine using an independent test set of annotated proteins and a transient expression of GFP fusion proteins. Here, we present the prediction framework and a website of predicted localizations for Arabidopsis. The relatively good accuracy of our prediction engine, even in cases where only partial protein sequence is available (e.g., in sequences lacking the N-terminal region), offers a promising opportunity for similar application to non-sequenced or poorly annotated plant species. Although the prediction scope of our method is currently limited by the availability of expression information on the ATH1 array, we believe that the advances in measuring gene expression technology will make our method applicable for all Arabidopsis proteins.},
  language  = {en}
}
@misc{ĆwiekKupczyńskaAltmannArendetal.2016,
  author    = {Ćwiek-Kupczyńska, Hanna and Altmann, Thomas and Arend, Daniel and Arnaud, Elizabeth and Chen, Dijun and Cornut, Guillaume and Fiorani, Fabio and Frohmberg, Wojciech and Junker, Astrid and Klukas, Christian and Lange, Matthias and Mazurek, Cezary and Nafissi, Anahita and Neveu, Pascal and van Oeveren, Jan and Pommier, Cyril and Poorter, Hendrik and Rocca-Serra, Philippe and Sansone, Susanna-Assunta and Scholz, Uwe and van Schriek, Marco and Seren, {\"U}mit and Usadel, Bj{\"o}rn and Weise, Stephan and Kersey, Paul and Krajewski, Paweł},
  title     = {Measures for interoperability of phenotypic data},
  series = {Plant methods},
  journal   = {Plant methods},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-407299},
  pages     = {18},
  year      = {2016},
  abstract  = {Background: Plant phenotypic data shrouds a wealth of information which, when accurately analysed and linked to other data types, brings to light the knowledge about the mechanisms of life. As phenotyping is a field of research comprising manifold, diverse and time ‑consuming experiments, the findings can be fostered by reusing and combin‑ ing existing datasets. Their correct interpretation, and thus replicability, comparability and interoperability, is possible provided that the collected observations are equipped with an adequate set of metadata. So far there have been no common standards governing phenotypic data description, which hampered data exchange and reuse. Results: In this paper we propose the guidelines for proper handling of the information about plant phenotyping experiments, in terms of both the recommended content of the description and its formatting. We provide a docu‑ ment called "Minimum Information About a Plant Phenotyping Experiment", which specifies what information about each experiment should be given, and a Phenotyping Configuration for the ISA ‑Tab format, which allows to practically organise this information within a dataset. We provide examples of ISA ‑Tab ‑formatted phenotypic data, and a general description of a few systems where the recommendations have been implemented. Conclusions: Acceptance of the rules described in this paper by the plant phenotyping community will help to achieve findable, accessible, interoperable and reusable data.},
  language  = {en}
}