Phylogenetics Workflows

The dataset presents input/output data of the TGOWLeR framework. TGOWLeR abstracts general patterns from workflow sequences previously extracted from texts. It comprises two modules –a workflow extractor and a pattern miner– both relying on a specific domain ontology.<br>The <em>input</em> of the first module is an RDF/ZIPPED ontology (<b>tgowler_resource_ontologies_PHAGE_1.0.rdf.zip</b>) and a set of un-annotated articles (<em>e.g.</em>, <b>datastore_2018_2019.zip</b>). The proposed pipeline (implemented in GATE 8.1) <em>produces</em> annotated texts (<em>e.g.</em>, <b>annotated_2018_2019.zip</b>) and their corresponding workflows (<em>e.g.</em>, <b>WFMiner_WF_2018_2019.xml</b>).<br>The <em>input</em> of the second module is the serialized ontology ... <br><b>Publications:</b><i>Halioui, Ahmed, et al. "Ontology-based workflow pattern mining: Application to bioinformatics expertise acquisition." Proceedings of the Symposium on Applied Computing. ACM, 2017.</i><br><br><i>Halioui, Ahmed, Petko Valtchev, and Abdoulaye Baniré Diallo. "Bioinformatic Workflow Extraction from Scientific Texts based on Word Sense Disambiguation." IEEE/ACM transactions on computational biology and bioinformatics 15.6 (2018): 1979-1990.</i><br>