Phenolog Identification Datasets and Supplemental Files

<strong>Project Description</strong> Phenologs are defined as similar phenotypes with hypothesized shared genetic basis. Identifying phenotypes mentioned in literature and predicting their similarity to other phenotypes enables candidate gene prediction in order to discover new genotype to phenotype relationships. In order to calculate the similarity between two phenotype descriptions, the descriptions first need to be converted into a computable format. Computable representations of phenotypes include EQ statements comprised of ontology terms, or embeddings into numerical vectors. These datasets correspond to the code available here. The files here comprise the main pipeline for reproducing results discussed in the corresponding paper and files which contain the pre-computed expected output from running this pipeline. <strong>Files</strong> phenologs_main.zip - Includes data and scripts necessary to reproduce the results discussed in the corresponding paper. See the description in the code repository here for additional details about this pipeline. annotation_files.zip - Includes files that are output during the semantic annotation step of the pipeline. annotation_results.zip - Includes files that summarize the performance of each semantic annotation step and aggregate the annotations. networks.zip - Includes the networks built from the phenotypic description datasets where edges are similarity as assessed by each computational method of representing the descriptions. network_analysis.zip - Includes files specifying the performance of networks built using each method on tasks such as classifying phenotypes and their corresponding genes into functional categories. summary_of_functional_category_similarities.xlsx - Tables summarizing performance of each network in recapitulating curated functional categorizations. <strong>Feedback</strong> Send any feedback, questions, or suggestions to irbraun at iastate dot edu.