Large Language Models and Genomics for Summarizing the Role of microRNA in Regulating mRNA Expression.

microRNA (miRNA)-messenger RNA (mRNA or gene) interactions are pivotal in various biological processes, including the regulation of gene expression, cellular differentiation, proliferation, apoptosis, and development, as well as the maintenance of cellular homeostasis and pathogenesis of numerous diseases, such as cancer, cardiovascular diseases, neurological disorders, and metabolic conditions. Understanding the mechanisms of miRNA-mRNA interactions can provide insights into disease mechanisms and potential therapeutic targets. However, extracting these interactions efficiently from a huge collection of published articles in PubMed is challenging. In the current study, we annotated a miRNA-mRNA Interaction Corpus (MMIC) and used it for evaluating the performance of a variety of machine learning (ML) models, deep learning-based transformer (DLT) models, and large language models (LLMs) in extracting the miRNA-mRNA interactions mentioned in PubMed. We used the genomics approaches for validating the extracted miRNA-mRNA interactions. Among the ML, DLT, and LLM models, PubMedBERT showed the highest precision, recall, and F-score, with all equal to 0.783. Among the LLM models, the performance of Llama-2 is better when compared to others. Llama 2 achieved 0.56 precision, 0.86 recall, and 0.68 F-score in a zero-shot experiment and 0.56 precision, 0.87 recall, and 0.68 F-score in a three-shot experiment. Our study shows that Llama 2 achieves better recall than ML and DLT models and leaves space for further improvement in terms of precision and F-score.

A High-Quality Blue Whale Genome, Segmental Duplications, and Historical Demography.

The blue whale, Balaenoptera musculus, is the largest animal known to have ever existed, making it an important case study in longevity and resistance to cancer. To further this and other blue whale-related research, we report a reference-quality, long-read-based genome assembly of this fascinating species. We assembled the genome from PacBio long reads and utilized Illumina/10×, optical maps, and Hi-C data for scaffolding, polishing, and manual curation. We also provided long read RNA-seq data to facilitate the annotation of the assembly by NCBI and Ensembl. Additionally, we annotated both haplotypes using TOGA and measured the genome size by flow cytometry. We then compared the blue whale genome with other cetaceans and artiodactyls, including vaquita (Phocoena sinus), the world's smallest cetacean, to investigate blue whale's unique biological traits. We found a dramatic amplification of several genes in the blue whale genome resulting from a recent burst in segmental duplications, though the possible connection between this amplification and giant body size requires further study. We also discovered sites in the insulin-like growth factor-1 gene correlated with body size in cetaceans. Finally, using our assembly to examine the heterozygosity and historical demography of Pacific and Atlantic blue whale populations, we found that the genomes of both populations are highly heterozygous and that their genetic isolation dates to the last interglacial period. Taken together, these results indicate how a high-quality, annotated blue whale genome will serve as an important resource for biology, evolution, and conservation research.

Serial KinderMiner (SKiM) discovers and annotates biomedical knowledge using co-occurrence and transformer models.

BACKGROUND: The PubMed archive contains more than 34 million articles; consequently, it is becoming increasingly difficult for a biomedical researcher to keep up-to-date with different knowledge domains. Computationally efficient and interpretable tools are needed to help researchers find and understand associations between biomedical concepts. The goal of literature-based discovery (LBD) is to connect concepts in isolated literature domains that would normally go undiscovered. This usually takes the form of an A-B-C relationship, where A and C terms are linked through a B term intermediate. Here we describe Serial KinderMiner (SKiM), an LBD algorithm for finding statistically significant links between an A term and one or more C terms through some B term intermediate(s). The development of SKiM is motivated by the observation that there are only a few LBD tools that provide a functional web interface, and that the available tools are limited in one or more of the following ways: (1) they identify a relationship but not the type of relationship, (2) they do not allow the user to provide their own lists of B or C terms, hindering flexibility, (3) they do not allow for querying thousands of C terms (which is crucial if, for instance, the user wants to query connections between a disease and the thousands of available drugs), or (4) they are specific for a particular biomedical domain (such as cancer). We provide an open-source tool and web interface that improves on all of these issues. RESULTS: We demonstrate SKiM's ability to discover useful A-B-C linkages in three control experiments: classic LBD discoveries, drug repurposing, and finding associations related to cancer. Furthermore, we supplement SKiM with a knowledge graph built with transformer machine-learning models to aid in interpreting the relationships between terms found by SKiM. Finally, we provide a simple and intuitive open-source web interface ( https://skim.morgridge.org ) with comprehensive lists of drugs, diseases, phenotypes, and symptoms so that anyone can easily perform SKiM searches. CONCLUSIONS: SKiM is a simple algorithm that can perform LBD searches to discover relationships between arbitrary user-defined concepts. SKiM is generalized for any domain, can perform searches with many thousands of C term concepts, and moves beyond the simple identification of an existence of a relationship; many relationships are given relationship type labels from our knowledge graph.

Serial KinderMiner (SKiM) Discovers and Annotates Biomedical Knowledge Using Co-Occurrence and Transformer Models.

Background: The PubMed database contains more than 34 million articles; consequently, it is becoming increasingly difficult for a biomedical researcher to keep up-to-date with different knowledge domains. Computationally efficient and interpretable tools are needed to help researchers find and understand associations between biomedical concepts. The goal of literature-based discovery (LBD) is to connect concepts in isolated literature domains that would normally go undiscovered. This usually takes the form of an A-B-C relationship, where A and C terms are linked through a B term intermediate. Here we describe Serial KinderMiner (SKiM), an LBD algorithm for finding statistically significant links between an A term and one or more C terms through some B term intermediate(s). The development of SKiM is motivated by the the observation that there are only a few LBD tools that provide a functional web interface, and that the available tools are limited in one or more of the following ways: 1) they identify a relationship but not the type of relationship, 2) they do not allow the user to provide their own lists of B or C terms, hindering flexibility, 3) they do not allow for querying thousands of C terms (which is crucial if, for instance, the user wants to query connections between a disease and the thousands of available drugs), or 4) they are specific for a particular biomedical domain (such as cancer). We provide an open-source tool and web interface that improves on all of these issues. Results: We demonstrate SKiM's ability to discover useful A-B-C linkages in three control experiments: classic LBD discoveries, drug repurposing, and finding associations related to cancer. Furthermore, we supplement SKiM with a knowledge graph built with transformer machine-learning models to aid in interpreting the relationships between terms found by SKiM. Finally, we provide a simple and intuitive open-source web interface ( https://skim.morgridge.org ) with comprehensive lists of drugs, diseases, phenotypes, and symptoms so that anyone can easily perform SKiM searches. Conclusions: SKiM is a simple algorithm that can perform LBD searches to discover relationships between arbitrary user-defined concepts. SKiM is generalized for any domain, can perform searches with many thousands of C term concepts, and moves beyond the simple identification of an existence of a relationship; many relationships are given relationship type labels from our knowledge graph.

A Text Mining Protocol for Extracting Drug-Drug Interaction and Adverse Drug Reactions Specific to Patient Population, Pharmacokinetics, Pharmacodynamics, and Disease.

Drug-drug interactions (DDIs) and adverse drug reactions (ADR) are experienced by many patients, especially by elderly population due to their multiple comorbidities and polypharmacy. Databases such as PubMed contain hundreds of abstracts with DDI and ADR information. PubMed is being updated every day with thousands of abstracts. Therefore, manually retrieving the data and extracting the relevant information is tedious task. Hence, automated text mining approaches are required to retrieve DDI and ADR information from PubMed. Recently we developed a hybrid approach for predicting DDI and ADR information from PubMed. There are many other existing approaches for retrieving DDI and ADR information from PubMed. However, none of the approaches are meant for retrieving DDI and ADR specific to patient population, gender, pharmacokinetics, and pharmacodynamics. Here, we present a text mining protocol which is based on our recent work for retrieving DDI and ADR information specific to patient population, gender, pharmacokinetics, and pharmacodynamics from PubMed.

Integrative Approach to Reveal Cell Type Specificity and Gene Candidates for Psoriatic Arthritis Outside the MHC.

We recently conducted a large association analysis to compare the genetic profiles between patients with psoriatic arthritis (PsA) and cutaneous-only psoriasis (PsC). Despite including over 7,000 genotyped patients, only the MHC achieved genome-wide significance. In this study, we hypothesized that appropriate epigenomic elements (H3K27ac marks for active enhancers) can guide us to reveal valuable information about the loci with suggestive evidence of association. Our aim is to investigate these loci and explore how they may lead to the development of PsA. We evaluated this potential by investigating the genes connected with these loci from the perspective of pharmacogenomics and gene expression. We illustrated that markers with suggestive evidence of association outside the MHC region are enriched in H3K27ac marks for osteoblast and chondrogenic differentiated cells; using pharmacogenomics resources, we showed that genes near these markers are targeted by existing drugs used to treat psoriatic arthritis. Significantly, six of the ten suggestive significant loci overlapping the regulatory elements encompass genes differentially expressed (FDR < 5%) in differentiated osteoblasts, including genes participating in the Wnt signaling such as RUNX1, FUT8, and CTNNAL1. Our approach shows that epigenomic information can be used as cost-effective approach to enhance the inferences for GWAS results, especially in situations when few genome-wide significant loci are available. Our results also point the way to more directed investigations comparing the genetics of PsA and PsC.

Genetic signature to provide robust risk assessment of psoriatic arthritis development in psoriasis patients.

Psoriatic arthritis (PsA) is a complex chronic musculoskeletal condition that occurs in ~30% of psoriasis patients. Currently, no systematic strategy is available that utilizes the differences in genetic architecture between PsA and cutaneous-only psoriasis (PsC) to assess PsA risk before symptoms appear. Here, we introduce a computational pipeline for predicting PsA among psoriasis patients using data from six cohorts with >7000 genotyped PsA and PsC patients. We identify 9 new loci for psoriasis or its subtypes and achieve 0.82 area under the receiver operator curve in distinguishing PsA vs. PsC when using 200 genetic markers. Among the top 5% of our PsA prediction we achieve >90% precision with 100% specificity and 16% recall for predicting PsA among psoriatic patients, using conditional inference forest or shrinkage discriminant analysis. Combining statistical and machine-learning techniques, we show that the underlying genetic differences between psoriasis subtypes can be used for individualized subtype risk assessment.

Atypical presentation of gastrointestinal stromal tumours-a case report.

Gastrointestinal stromal tumors (GISTs) are benign mesenchymal tumors of the gastrointestinal tract (GIT). Their clinical presentations are variable. We report a case of a 31-year-old man who presented with pain in the abdomen and vomiting. CT abdomen revealed a large exophytic mass in the epigastrium with enhancement pattern similar to hemangioma. No relationship of the mass could be made out with the adjacent structures on CT, histopathology proved it to be a GIST.