MOTIVATION: Automatic information extraction from biomedical texts requires machine learning methodology that can recognize biomedical entities, characterize inter-entity relationships, and relate extracted information to specific research topics. Large language models (LLMs) excel in general tasks but perform less reliably in the biomedical domain, where texts are characterized by extensive technical terminology and semantic variations from general literature. There is an unmet need for annotated full-text datasets that can be used to fine-tune language models for significant biomedical applications. Here, we focus on extraction of the complex relationships between genes and diseases. RESULTS: We present BioTriplex, a corpus of 100 full-length biomedical research articles (comprising 604 subsection texts) manually annotated with disease names, genes, and 21 subtypes of disease-gene relationships. We employ BioTriplex to train the LLaMA 3.1 8B language model in gene-disease relation extraction. Our fine-tuned model outperforms zero-shot and few-shot approaches, both within the LLaMA 3.1 architecture and across the larger state-of-the-art LLMs GPT-4 and Claude Sonnet 3.7, and classifies gene-disease relation types with broader scope and greater granularity than previously described. These results validate BioTriplex as a useful full-text data resource and underscore the value of specialized datasets in fine-tuning language models for important biomedical tasks. AVAILABILITY AND IMPLEMENTATION: https://github.com/PanagiotisFytas/BioTriplex.

BACKGROUND: Although there is an enormous number of textual resources in the biomedical domain, currently, manually curated resources cover only a small part of the existing knowledge. The vast majority of these information is in unstructured form which contain nonstandard naming conventions. The task of named entity recognition, which is the identification of entity names from text, is not adequate without a standardization step. Linking each identified entity mention in text to an ontology/dictionary concept is an essential task to make sense of the identified entities. This paper presents an unsupervised approach for the linking of named entities to concepts in an ontology/dictionary. We propose an approach for the normalization of biomedical entities through an ontology/dictionary by using word embeddings to represent semantic spaces, and a syntactic parser to give higher weight to the most informative word in the named entity mentions. RESULTS: We applied the proposed method to two different normalization tasks: the normalization of bacteria biotope entities through the Onto-Biotope ontology and the normalization of adverse drug reaction entities through the Medical Dictionary for Regulatory Activities (MedDRA). The proposed method achieved a precision score of 65.9%, which is 2.9 percentage points above the state-of-the-art result on the BioNLP Shared Task 2016 Bacteria Biotope test data and a macro-averaged precision score of 68.7% on the Text Analysis Conference 2017 Adverse Drug Reaction test data. CONCLUSIONS: The core contribution of this paper is a syntax-based way of combining the individual word vectors to form vectors for the named entity mentions and ontology concepts, which can then be used to measure the similarity between them. The proposed approach is unsupervised and does not require labeled data, making it easily applicable to different domains.

BACKGROUND: Information regarding bacteria biotopes is important for several research areas including health sciences, microbiology, and food processing and preservation. One of the challenges for scientists in these domains is the huge amount of information buried in the text of electronic resources. Developing methods to automatically extract bacteria habitat relations from the text of these electronic resources is crucial for facilitating research in these areas. METHODS: We introduce a linguistically motivated rule-based approach for recognizing and normalizing names of bacteria habitats in biomedical text by using an ontology. Our approach is based on the shallow syntactic analysis of the text that include sentence segmentation, part-of-speech (POS) tagging, partial parsing, and lemmatization. In addition, we propose two methods for identifying bacteria habitat localization relations. The underlying assumption for the first method is that discourse changes with a new paragraph. Therefore, it operates on a paragraph-basis. The second method performs a more fine-grained analysis of the text and operates on a sentence-basis. We also develop a novel anaphora resolution method for bacteria coreferences and incorporate it with the sentence-based relation extraction approach. RESULTS: We participated in the Bacteria Biotope (BB) Task of the BioNLP Shared Task 2013. Our system (Boun) achieved the second best performance with 68% Slot Error Rate (SER) in Sub-task 1 (Entity Detection and Categorization), and ranked third with an F-score of 27% in Sub-task 2 (Localization Event Extraction). This paper reports the system that is implemented for the shared task, including the novel methods developed and the improvements obtained after the official evaluation. The extensions include the expansion of the OntoBiotope ontology using the training set for Sub-task 1, and the novel sentence-based relation extraction method incorporated with anaphora resolution for Sub-task 2. These extensions resulted in promising results for Sub-task 1 with a SER of 68%, and state-of-the-art performance for Sub-task 2 with an F-score of 53%. CONCLUSIONS: Our results show that a linguistically-oriented approach based on the shallow syntactic analysis of the text is as effective as machine learning approaches for the detection and ontology-based normalization of habitat entities. Furthermore, the newly developed sentence-based relation extraction system with the anaphora resolution module significantly outperforms the paragraph-based one, as well as the other systems that participated in the BB Shared Task 2013.

SUMMARY: Knowledge of pathogen-host protein interactions is required to better understand infection mechanisms. The pathogen-host interaction search tool (PHISTO) is a web-accessible platform that provides relevant information about pathogen-host interactions (PHIs). It enables access to the most up-to-date PHI data for all pathogen types for which experimentally verified protein interactions with human are available. The platform also offers integrated tools for visualization of PHI networks, graph-theoretical analysis of targeted human proteins, BLAST search and text mining for detecting missing experimental methods. PHISTO will facilitate PHI studies that provide potential therapeutic targets for infectious diseases. AVAILABILITY: http://www.phisto.org. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.