Proteins and their functional interactions form the backbone of the cellular machinery. Their connectivity network needs to be considered for the full understanding of biological phenomena, but the available information on protein–protein associations is incomplete and exhibits varying levels of annotation granularity and reliability. The STRING database aims to collect, score and integrate all publicly available sources of protein–protein interaction information, and to complement these with computational predictions. Its goal is to achieve a comprehensive and objective global network, including direct (physical) as well as indirect (functional) interactions. The latest version of STRING (11.0) more than doubles the number of organisms it covers, to 5090. The most important new feature is an option to upload entire, genome-wide datasets as input, allowing users to visualize subsets as interaction networks and to perform gene-set enrichment analysis on the entire input. For the enrichment analysis, STRING implements well-known classification systems such as Gene Ontology and KEGG, but also offers additional, new classification systems based on high-throughput text-mining as well as on a hierarchical clustering of the association network itself. The STRING resource is available online at https://string-db.org/.

Medical coding is the task of assigning medical codes to clinical free-text documentation. Healthcare professionals manually assign such codes to track patient diagnoses and treatments. Automated medical coding can considerably alleviate this administrative burden. In this paper, we reproduce, compare, and analyze state-of-the-art automated medical coding machine learning models. We show that several models underperform due to weak configurations, poorly sampled train-test splits, and insufficient evaluation. In previous work, the macro F1 score has been calculated sub-optimally, and our correction doubles it. We contribute a revised model comparison using stratified sampling and identical experimental setups, including hyperparameters and decision boundary tuning. We analyze prediction errors to validate and falsify assumptions of previous works. The analysis confirms that all models struggle with rare codes, while long documents only have a negligible impact. Finally, we present the first comprehensive results on the newly released MIMIC-IV dataset using the reproduced models. We release our code, model parameters, and new MIMIC-III and MIMIC-IV training and evaluation pipelines to accommodate fair future comparisons.

Information extraction by mining the scientific literature is key to uncovering relations between biomedical entities. Most existing approaches based on natural language processing extract relations from single sentence-level co-mentions, ignoring co-occurrence statistics over the whole corpus. Existing approaches counting entity co-occurrences ignore the textual context of each co-occurrence. We propose a novel corpus-wide co-occurrence scoring approach to relation extraction that takes the textual context of each co-mention into account. Our method, called CoCoScore, scores the certainty of stating an association for each sentence that co-mentions two entities. CoCoScore is trained using distant supervision based on a gold-standard set of associations between entities of interest. Instead of requiring a manually annotated training corpus, co-mentions are labeled as positives/negatives according to their presence/absence in the gold standard. We show that CoCoScore outperforms previous approaches in identifying human disease–gene and tissue–gene associations as well as in identifying physical and functional protein–protein associations in different species. CoCoScore is a versatile text mining tool to uncover pairwise associations via co-occurrence mining, within and beyond biomedical applications. CoCoScore is available at: https://github.com/JungeAlexander/cocoscore. Supplementary data are available at Bioinformatics online.

Coffee leaf rust (CLR), caused by the fungal pathogen Hemileia vastatrix, has plagued coffee production worldwide for over 150 years. Hemileia vastatrix produces urediniospores, teliospores, and the sexual basidiospores. Infection of coffee by basidiospores of H. vastatrix has never been reported and thus far, no alternate host, capable of supporting an aecial stage in the disease cycle, has been found. Due to this, some argue that an alternate host of H. vastatrix does not exist. Yet, to date, the plant pathology community has been puzzled by the ability of H. vastatrix to overcome resistance in coffee cultivars despite the apparent lack of sexual reproduction and an aecidial stage. The purpose of this study was to introduce a new method to search for the alternate host(s) of H. vastatrix. To do this, we present the novel hypothetical alternate host ranking (HAHR) method and an automated text mining (ATM) procedure, utilizing comprehensive biogeographical botanical data from the designated sites of interests (Ethiopia, Kenya and Sri Lanka) and plant pathology insights. With the HAHR/ATM methods, we produced prioritized lists of potential alternate hosts plant of coffee leaf rust. This is a first attempt to seek out an alternate plant host of a pathogenic fungus in this manner. The HAHR method showed the highest‐ranking probable alternate host as Psychotria mahonii, Rubus apetalus, and Rhamnus prinoides. The cross‐referenced results by the two methods suggest that plant genera of interest are Croton, Euphorbia, and Rubus. The HAHR and ATM methods may also be applied to other plant–rust interactions that include an unknown alternate host or any other biological system, which rely on data mining of published data.

Information extraction by mining the scientific literature is key to uncovering relations between biomedical entities. Most existing approaches based on natural language processing extract relations from single sentence-level co-mentions, ignoring co-occurrence statistics over the whole corpus. Existing approaches counting entity co-occurrences ignore the textual context of each co-occurrence. We propose a novel corpus-wide co-occurrence scoring approach to relation extraction that takes the textual context of each co-mention into account. Our method, called CoCoScore, scores the certainty of stating an association for each sentence that co-mentions two entities. CoCoScore is trained using distant supervision based on a gold-standard set of associations between entities of interest. Instead of requiring a manually annotated training corpus, co-mentions are labeled as positives/negatives according to their presence/absence in the gold standard. We show that CoCoScore outperforms previous approaches in identifying human disease-gene and tissue-gene associations as well as in identifying physical and functional protein-protein associations in different species. CoCoScore is a versatile text-mining tool to uncover pairwise associations via co-occurrence mining, within and beyond biomedical applications. CoCoScore is available at: https://github.com/JungeAlexander/cocoscore