Experience: Automated Prediction of Experimental Metadata from Scientific Publications

While there exists an abundance of open biomedical data, the lack of high-quality metadata makes it challenging for others to find relevant datasets and to reuse them for another purpose. In particular, metadata are useful to understand the nature and provenance of the data. A common approach to improving the quality of metadata relies on expensive human curation, which itself is time-consuming and also prone to error. Towards improving the quality of metadata, we use scientific publications to automatically predict metadata key:value pairs. For prediction, we use a Convolutional Neural Network (CNN) and a Bidirectional Long-short term memory network (BiLSTM). We focus our attention on the NCBI Disease Corpus, which is used for training the CNN and BiLSTM. We perform two different kinds of experiments with these two architectures: (1) we predict the disease names by using their unique ID in the MeSH ontology and (2) we use the tree structures of MeSH ontology to move up in the hierarchy of these disease terms, which reduces the number of labels. We also perform various multi-label classification techniques for the above-mentioned experiments. We find that in both cases CNN achieves the best results in predicting the superclasses for disease with an accuracy of 83%.

Detecting modifications in proteomics experiments with Param-Medic

Searching tandem mass spectra against a peptide database requires accurate knowledge of various experimental parameters, including machine settings and details of the sample preparation protocol. In some cases, such as in re-analysis of public data sets, this experimental metadata may be missing or inac- curate. We describe a method for automatically inferring the presence of various types of modifications, including stable-isotope and isobaric labeling, tandem mass tags, and phosphorylation, directly from a given set of mass spectra. We demonstrate the sensitivity and specificity of the proposed approach, and we provide open source Python and C++ implementations in a new version of the software tool Param-Medic.