Search

Understanding complex biological pathways, including gene–gene interactions and gene regulatory networks, is critical for exploring disease mechanisms and drug development. Manual literature curation of biological pathways cannot keep up with the exponential growth of new discoveries in the literature. Large‐scale language models (LLMs) trained on extensive text corpora contain rich biological information, and they can be mined as a biological knowledge graph. This study assesses 21 LLMs, including both application programming interface (API)‐based models and open‐source models in their capacities of retrieving biological knowledge. The evaluation focuses on predicting gene regulatory relations (activation, inhibition, and phosphorylation) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway components. Results indicated a significant disparity in model performance. API‐based models GPT‐4 and Claude‐Pro showed superior performance, with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction, and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction, respectively. Open‐source models lagged behind their API‐based counterparts, whereas Falcon‐180b and llama2‐7b had the highest F1 scores of 0.2787 and 0.1923 in gene regulatory relations, respectively. The KEGG pathway recognition had a Jaccard similarity index of 0.2237 for Falcon‐180b and 0.2207 for llama2‐7b. Our study suggests that LLMs are informative in gene network analysis and pathway mapping, but their effectiveness varies, necessitating careful model selection. This work also provides a case study and insight into using LLMs das knowledge graphs. Our code is publicly available at the website of GitHub (Muh‐aza). [ABSTRACT FROM AUTHOR]

Abstract The supervised machine learning method is often used for biomedical relationship extraction. The disadvantage is that it requires much time and money to manually establish an annotated dataset. Based on distant supervision, the knowledge base is combined with the corpus, thus, the training corpus can be automatically annotated. As many biomedical databases provide knowledge bases for study with a limited number of annotated corpora, this method is practical in biomedicine. The clinical significance of each patient’s genetic makeup can be understood based on the healthcare provider’s genetic database. Unfortunately, the lack of previous biomedical relationship extraction studies focuses on gene–gene interaction. The main purpose of this study is to develop extraction methods for gene–gene interactions that can help explain the heritability of human complex diseases. This study referred to the information on gene–gene interactions in the KEGG PATHWAY database, the abstracts in PubMed were adopted to generate the training sample set, and the graph kernel method was adopted to extract gene–gene interactions. The best assessment result was an F1-score of 0.79. Our developed distant supervision method automatically finds sentences through the corpus without manual labeling for extracting gene–gene interactions, which can effectively reduce the time cost for manual annotation data; moreover, the relationship extraction method based on a graph kernel can be successfully applied to extract gene–gene interactions. In this way, the results of this study are expected to help achieve precision medicine.

The supervised machine learning method is often used for biomedical relationship extraction. The disadvantage is that it requires much time and money to manually establish an annotated dataset. Based on distant supervision, the knowledge base is combined with the corpus, thus, the training corpus can be automatically annotated. As many biomedical databases provide knowledge bases for study with a limited number of annotated corpora, this method is practical in biomedicine. The clinical significance of each patient's genetic makeup can be understood based on the healthcare provider's genetic database. Unfortunately, the lack of previous biomedical relationship extraction studies focuses on gene–gene interaction. The main purpose of this study is to develop extraction methods for gene–gene interactions that can help explain the heritability of human complex diseases. This study referred to the information on gene–gene interactions in the KEGG PATHWAY database, the abstracts in PubMed were adopted to generate the training sample set, and the graph kernel method was adopted to extract gene–gene interactions. The best assessment result was an F1-score of 0.79. Our developed distant supervision method automatically finds sentences through the corpus without manual labeling for extracting gene–gene interactions, which can effectively reduce the time cost for manual annotation data; moreover, the relationship extraction method based on a graph kernel can be successfully applied to extract gene–gene interactions. In this way, the results of this study are expected to help achieve precision medicine. [ABSTRACT FROM AUTHOR]

Biomedical-named entity recognition (Bio-NER) is a key task of biomedical natural language processing, which is performed on biomedical documents containing professional literature and electronic health records. It involves the identification and categorisation of the named entities that are presented in a text document. Bio-NER plays a crucial role in diverse fields, such as text summarisation, relation extraction, and question answering. However, the data imbalance issue is a significant challenge in Bio-NER, which adversely impacts its performance. Many undersampling methods are employed to overcome this issue. However, they eliminate relevant information during the process, which leads to the degradation of the performance of Bio-NER. To deal with this problem, we propose an undersampling method based on preprocessing and sentence filtering (USPSF). The proposed method preserves relevant data effectively during the process. The effectiveness of the proposed method is analysed on the NCBI disease dataset, CHEMDNER and CDR chemical datasets. The performance of the proposed method is evaluated against the existing methods for Bio-NER. Experimental results show that the proposed method outperforms the competitive methods with respect to the F1 score, showcasing their efficacy in improving Bio-NER performance. [ABSTRACT FROM AUTHOR]

Diabetic kidney disease (DKD) is the leading cause of end-stage renal disease worldwide. This study's goal was to identify the signaling drivers and pathways that modulate glomerular endothelial dysfunction in DKD via artificial intelligence-enabled literature-based discovery. Cross-domain text mining of 33+ million PubMed articles was performed with SemNet 2.0 to identify and rank multi-scalar and multi-factorial pathophysiological concepts related to DKD. A set of identified relevant genes and proteins that regulate different pathological events associated with DKD were analyzed and ranked using normalized mean HeteSim scores. High-ranking genes and proteins intersected three domains—DKD, the immune response, and glomerular endothelial cells. The top 10% of ranked concepts were mapped to the following biological functions: angiogenesis, apoptotic processes, cell adhesion, chemotaxis, growth factor signaling, vascular permeability, the nitric oxide response, oxidative stress, the cytokine response, macrophage signaling, NF κ B factor activity, the TLR pathway, glucose metabolism, the inflammatory response, the ERK/MAPK signaling response, the JAK/STAT pathway, the T-cell-mediated response, the WNT/ β -catenin pathway, the renin–angiotensin system, and NADPH oxidase activity. High-ranking genes and proteins were used to generate a protein–protein interaction network. The study results prioritized interactions or molecules involved in dysregulated signaling in DKD, which can be further assessed through biochemical network models or experiments. [ABSTRACT FROM AUTHOR]

Identifying relationships between biomedical entities from unstructured biomedical text is a challenging task. SnorkelPlus has been proposed to provide the flexibility to extract these biomedical relations without any human effort. Our proposed model, SnorkelPlus, is aimed at finding connections between gene and disease entities. We achieved three objectives: (i) extract only gene and disease articles from NCBI's, PubMed or PubMed central database, (ii) define reusable label functions and (iii) ensure label function accuracy using generative and discriminative models. We utilized deep learning methods to achieve label training data and achieved an AUROC of 85.60% for the generated gene and disease corpus from PubMed articles. Snorkel achieved an AUPR of 45.73%, which is +2.3% higher than the baseline model. We created a gene–disease relation database using SnorkelPlus from approximately 29 million scientific abstracts without involving annotated training datasets. Furthermore, we demonstrated the generalizability of our proposed application on abstracts of PubMed articles enriched with different gene and disease relations. In the future, we plan to design a graphical database using Neo4j. [ABSTRACT FROM AUTHOR]

Biomedical knowledge graphs (KGs) hold valuable information regarding biomedical entities such as genes, diseases, biological processes, and drugs. KGs have been successfully employed in challenging biomedical areas such as the identification of pathophysiology mechanisms or drug repurposing. The creation of high-quality KGs typically requires labor-intensive multi-database integration or substantial human expert curation, both of which take time and contribute to the workload of data processing and annotation. Therefore, the use of automatic systems for KG building and maintenance is a prerequisite for the wide uptake and utilization of KGs. Technologies supporting the automated generation and updating of KGs typically make use of Natural Language Processing (NLP), which is optimized for extracting implicit triples described in relevant biomedical text sources. At the core of this challenge is how to improve the accuracy and coverage of the information extraction module by utilizing different models and tools. The emergence of pre-trained large language models (LLMs), such as ChatGPT which has grown in popularity dramatically, has revolutionized the field of NLP, making them a potential candidate to be used in text-based graph creation as well. So far, no previous work has investigated the power of LLMs on the generation of cause-and-effect networks and KGs encoded in Biological Expression Language (BEL). In this paper, we present initial studies towards one-shot BEL relation extraction using two different versions of the Generative Pre-trained Transformer (GPT) models and evaluate its performance by comparing the extracted results to a highly accurate, manually curated BEL KG curated by domain experts.

Abstract 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.

Background: Biomedical knowledge graphs (KG) have become crucial for describing biological findings in a structured manner. To keep up with the constantly changing flow of knowledge, their embedded information must be regularly updated with the latest findings. Natural language processing (NLP) has created new possibilities for automating this upkeep by facilitating information extraction from free text. However, due to annotated and labeled biomedical data limitations, the development of completely autonomous information extraction systems remains a substantial scientific and technological hurdle. This study aims to explore methodologies best suited to support the automatic extraction of causal relationships from biomedical literature with the aim of regular and rapid updating of disease-specific pathophysiology mechanism KGs. Methods: Our proposed approach first searches and retrieves PubMed abstracts using the desired terms and keywords. The extension corpora are then passed through the NLP pipeline for automatic information extraction. We then identify triples representing cause-and-effect relationships and encode this content using the Biological Expression Language (BEL). Finally, domain experts perform an analysis of the completeness, relevance, accuracy, and novelty of the extracted triples. Results: In our test scenario, which is focused on the KG regarding the phosphorylation of the Tau protein, our pipeline successfully contributed novel data, which was then subsequently used to update the KG leading to the identification of six additional upstream regulators of Tau phosphorylation. Conclusion: Here, it is demonstrated that the NLP-based workflow we created is capable of rapidly updating pathophysiology mechanism graphs. As a result, production-scale, semi-automated updating of pre-existing, curated mechanism graphs is enabled.

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. [ABSTRACT FROM AUTHOR]

Syndrome differentiation and treatment is the basic principle of traditional Chinese medicine (TCM) to recognize and treat diseases. Accurate syndrome differentiation can provide a reliable basis for treatment, therefore, establishing a scientific intelligent syndrome differentiation method is of great significance to the modernization of TCM. With the development of biomdical text mining technology, TCM has entered the era of intelligence that based on data, and model training increasingly relies on the large-scale labeled data. However, it is difficult to form a large standard data set in the field of TCM due to the low degree of standardization of TCM data collection and the privacy protection of patients' medical records. To solve the above problem, a multi-label deep forest model based on an improved multi-label ReliefF feature selection algorithm, ML-PRDF, is proposed to enhance the representativeness of features within the model, express the original information with fewer features, and achieve optimal classification accuracy, while alleviating the problem of high data processing cost of deep forest models and achieving effective TCM discriminative analysis under small samples. The results show that the proposed model finally outperforms other multi-label classification models in terms of multi-label evaluation criteria, and has higher accuracy in the TCM syndrome differentiation problem compared with the traditional multi-label deep forest, and the comparative study shows that the use of PCC-MLRF algorithm for feature selection can better select representative features. [ABSTRACT FROM AUTHOR]

In the biomedical field due to tremendous medical research, every year the medical papers generated is very huge. In order to process these tremendous amounts of textual data, the information retrieval techniques are combined with machine learning methods like natural language processing (NLP) for finding the useful insights in data for NLP tasks. In this work, we have addressed the challenges involved in existing NLP techniques like Word2Vec, Doc2Vec, and Biosent2Vec and followed by the traditional classification of articles with Concept2Vec and random forest classification. Concept vector techniques are emerging methods in NLP and in information retrieval systems. Pretrained concept encoders are available in Machine learning, whereas no such exists in biomedical domain. In this paper a proposal on Concept2Vec trained from biomedical text is highlighted. Our work accurately emphasizes on the quality of semantics defined between the medical terms, which can help the medical practitioners in taking errorless decisions. In this work 20 thousand biomedical documents are considered for Concept2Vec embeddings and the proposed approach have shown best concept similarity in terms of relevant measures compared with existing approaches such as Word2Vec, global vectors (GloVe), fastText, and BioSentVec, bidirectional encoder representations from transformers (BERT), biomedical-BERT. [ABSTRACT FROM AUTHOR]

Abstract Background Biomedical named entity recognition (BioNER) is a basic and important task for biomedical text mining with the purpose of automatically recognizing and classifying biomedical entities. The performance of BioNER systems directly impacts downstream applications. Recently, deep neural networks, especially pre-trained language models, have made great progress for BioNER. However, because of the lack of high-quality and large-scale annotated data and relevant external knowledge, the capability of the BioNER system remains limited. Results In this paper, we propose a novel fully-shared multi-task learning model based on the pre-trained language model in biomedical domain, namely BioBERT, with a new attention module to integrate the auto-processed syntactic information for the BioNER task. We have conducted numerous experiments on seven benchmark BioNER datasets. The proposed best multi-task model obtains F1 score improvements of 1.03% on BC2GM, 0.91% on NCBI-disease, 0.81% on Linnaeus, 1.26% on JNLPBA, 0.82% on BC5CDR-Chemical, 0.87% on BC5CDR-Disease, and 1.10% on Species-800 compared to the single-task BioBERT model. Conclusion The results demonstrate our model outperforms previous studies on all datasets. Further analysis and case studies are also provided to prove the importance of the proposed attention module and fully-shared multi-task learning method used in our model.

Abstract Background Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format. Results Our novel method identified 0.6 million articles (along with drug and protein information) which are not previously included in public DTI databases. Using 10-fold cross-validation, we obtained ~ 99% accuracy for identifying articles containing quantitative drug-target profiles. The F1 micro for the prediction of assay format is 88%, which leaves room for improvement in future studies. Conclusion The BERT model in this study is robust and the proposed pipeline can be used to identify previously overlooked articles containing quantitative DTIs. Overall, our method provides a significant advancement in machine-assisted DTI extraction and curation. We expect it to be a useful addition to drug mechanism discovery and repurposing.

Abstract Background The abundance of biomedical text data coupled with advances in natural language processing (NLP) is resulting in novel biomedical NLP (BioNLP) applications. These NLP applications, or tasks, are reliant on the availability of domain-specific language models (LMs) that are trained on a massive amount of data. Most of the existing domain-specific LMs adopted bidirectional encoder representations from transformers (BERT) architecture which has limitations, and their generalizability is unproven as there is an absence of baseline results among common BioNLP tasks. Results We present 8 variants of BioALBERT, a domain-specific adaptation of a lite bidirectional encoder representations from transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine-tuned for 6 different tasks across 20 benchmark datasets. Experiments show that a large variant of BioALBERT trained on PubMed outperforms the state-of-the-art on named-entity recognition (+ 11.09% BLURB score improvement), relation extraction (+ 0.80% BLURB score), sentence similarity (+ 1.05% BLURB score), document classification (+ 0.62% F1-score), and question answering (+ 2.83% BLURB score). It represents a new state-of-the-art in 5 out of 6 benchmark BioNLP tasks. Conclusions The large variant of BioALBERT trained on PubMed achieved a higher BLURB score than previous state-of-the-art models on 5 of the 6 benchmark BioNLP tasks. Depending on the task, 5 different variants of BioALBERT outperformed previous state-of-the-art models on 17 of the 20 benchmark datasets, showing that our model is robust and generalizable in the common BioNLP tasks. We have made BioALBERT freely available which will help the BioNLP community avoid computational cost of training and establish a new set of baselines for future efforts across a broad range of BioNLP tasks.

Document-level relation triplet extraction is crucial in biomedical text mining, aiding in drug discovery and the construction of biomedical knowledge graphs. Current language models face challenges in generalizing to unseen datasets and relation types in biomedical relation triplet extraction, which limits their effectiveness in these crucial tasks. To address this challenge, our study optimizes models from two critical dimensions: data-task relevance and granularity of relations, aiming to enhance their generalization capabilities significantly. We introduce a novel progressive learning strategy to obtain the PLRTE model. This strategy not only enhances the model's capability to comprehend diverse relation types in the biomedical domain but also implements a structured four-level progressive learning process through semantic relation augmentation, compositional instruction, and dual-axis level learning. Our experiments on the DDI and BC5CDR document-level biomedical relation triplet datasets demonstrate a significant performance improvement of 5% to 20% over the current state-of-the-art baselines. Furthermore, our model exhibits exceptional generalization capabilities on the unseen Chemprot and GDA datasets, further validating the effectiveness of optimizing data-task association and relation granularity for enhancing model generalizability. [Display omitted] [ABSTRACT FROM AUTHOR]

[Display omitted] This study aims to review the recent advances in community challenges for biomedical text mining in China. We collected information of evaluation tasks released in community challenges of biomedical text mining, including task description, dataset description, data source, task type and related links. A systematic summary and comparative analysis were conducted on various biomedical natural language processing tasks, such as named entity recognition, entity normalization, attribute extraction, relation extraction, event extraction, text classification, text similarity, knowledge graph construction, question answering, text generation, and large language model evaluation. We identified 39 evaluation tasks from 6 community challenges that spanned from 2017 to 2023. Our analysis revealed the diverse range of evaluation task types and data sources in biomedical text mining. We explored the potential clinical applications of these community challenge tasks from a translational biomedical informatics perspective. We compared with their English counterparts, and discussed the contributions, limitations, lessons and guidelines of these community challenges, while highlighting future directions in the era of large language models. Community challenge evaluation competitions have played a crucial role in promoting technology innovation and fostering interdisciplinary collaboration in the field of biomedical text mining. These challenges provide valuable platforms for researchers to develop state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

Background: Biomedical named entity recognition (BioNER) is a basic and important task for biomedical text mining with the purpose of automatically recognizing and classifying biomedical entities. The performance of BioNER systems directly impacts downstream applications. Recently, deep neural networks, especially pre-trained language models, have made great progress for BioNER. However, because of the lack of high-quality and large-scale annotated data and relevant external knowledge, the capability of the BioNER system remains limited. Results: In this paper, we propose a novel fully-shared multi-task learning model based on the pre-trained language model in biomedical domain, namely BioBERT, with a new attention module to integrate the auto-processed syntactic information for the BioNER task. We have conducted numerous experiments on seven benchmark BioNER datasets. The proposed best multi-task model obtains F1 score improvements of 1.03% on BC2GM, 0.91% on NCBI-disease, 0.81% on Linnaeus, 1.26% on JNLPBA, 0.82% on BC5CDR-Chemical, 0.87% on BC5CDR-Disease, and 1.10% on Species-800 compared to the single-task BioBERT model. Conclusion: The results demonstrate our model outperforms previous studies on all datasets. Further analysis and case studies are also provided to prove the importance of the proposed attention module and fully-shared multi-task learning method used in our model. [ABSTRACT FROM AUTHOR]

The rapid growth of biomedical literature poses a significant challenge for curation and interpretation. This has become more evident during the COVID-19 pandemic. LitCovid, a literature database of COVID-19 related papers in PubMed, has accumulated over 200,000 articles with millions of accesses. Approximately 10,000 new articles are added to LitCovid every month. A main curation task in LitCovid is topic annotation where an article is assigned with up to eight topics, e.g., Treatment and Diagnosis. The annotated topics have been widely used both in LitCovid (e.g., accounting for ∼18% of total uses) and downstream studies such as network generation. However, it has been a primary curation bottleneck due to the nature of the task and the rapid literature growth. This study proposes LITMC-BERT, a transformer-based multi-label classification method in biomedical literature. It uses a shared transformer backbone for all the labels while also captures label-specific features and the correlations between label pairs. We compare LITMC-BERT with three baseline models on two datasets. Its micro-F1 and instance-based F1 are 5% and 4% higher than the current best results, respectively, and only requires ∼18% of the inference time than the Binary BERT baseline. The related datasets and models are available via https://github.com/ncbi/ml-transformer. [ABSTRACT FROM AUTHOR]

Background: Drug-target interactions (DTIs) are critical for drug repurposing and elucidation of drug mechanisms, and are manually curated by large databases, such as ChEMBL, BindingDB, DrugBank and DrugTargetCommons. However, the number of curated articles likely constitutes only a fraction of all the articles that contain experimentally determined DTIs. Finding such articles and extracting the experimental information is a challenging task, and there is a pressing need for systematic approaches to assist the curation of DTIs. To this end, we applied Bidirectional Encoder Representations from Transformers (BERT) to identify such articles. Because DTI data intimately depends on the type of assays used to generate it, we also aimed to incorporate functions to predict the assay format. Results: Our novel method identified 0.6 million articles (along with drug and protein information) which are not previously included in public DTI databases. Using 10-fold cross-validation, we obtained ~ 99% accuracy for identifying articles containing quantitative drug-target profiles. The F1 micro for the prediction of assay format is 88%, which leaves room for improvement in future studies. Conclusion: The BERT model in this study is robust and the proposed pipeline can be used to identify previously overlooked articles containing quantitative DTIs. Overall, our method provides a significant advancement in machine-assisted DTI extraction and curation. We expect it to be a useful addition to drug mechanism discovery and repurposing. [ABSTRACT FROM AUTHOR]

Abstract Background Stroke has an acute onset and a high mortality rate, making it one of the most fatal diseases worldwide. Its underlying biology and treatments have been widely studied both in the “Western” biomedicine and the Traditional Chinese Medicine (TCM). However, these two approaches are often studied and reported in insolation, both in the literature and associated databases. Results To aid research in finding effective prevention methods and treatments, we integrated knowledge from the literature and a number of databases (e.g. CID, TCMID, ETCM). We employed a suite of biomedical text mining (i.e. named-entity) approaches to identify mentions of genes, diseases, drugs, chemicals, symptoms, Chinese herbs and patent medicines, etc. in a large set of stroke papers from both biomedical and TCM domains. Then, using a combination of a rule-based approach with a pre-trained BioBERT model, we extracted and classified links and relationships among stroke-related entities as expressed in the literature. We construct StrokeKG, a knowledge graph includes almost 46 k nodes of nine types, and 157 k links of 30 types, connecting diseases, genes, symptoms, drugs, pathways, herbs, chemical, ingredients and patent medicine. Conclusions Our Stroke-KG can provide practical and reliable stroke-related knowledge to help with stroke-related research like exploring new directions for stroke research and ideas for drug repurposing and discovery. We make StrokeKG freely available at http://114.115.208.144:7474/browser/ (Please click "Connect" directly) and the source structured data for stroke at https://github.com/yangxi1016/Stroke

BackgroundNumerous publicly available biomedical databases derive data by curating from literatures. The curated data can be useful as training examples for information extraction, but curated data usually lack the exact mentions and their locations in the text required for supervised machine learning. This paper describes a general approach to information extraction using curated data as training examples. The idea is to formulate the problem as cost-sensitive learning from noisy labels, where the cost is estimated by a committee of weak classifiers that consider both curated data and the text.ResultsWe test the idea on two information extraction tasks of Genome-Wide Association Studies (GWAS). The first task is to extract target phenotypes (diseases or traits) of a study and the second is to extract ethnicity backgrounds of study subjects for different stages (initial or replication). Experimental results show that our approach can achieve 87% of Precision-at-2 (P@2) for disease/trait extraction, and 0.83 of F1-Score for stage-ethnicity extraction, both outperforming their cost-insensitive baseline counterparts.ConclusionsThe results show that curated biomedical databases can potentially be reused as training examples to train information extractors without expert annotation or refinement, opening an unprecedented opportunity of using "big data" in biomedical text mining.

Background: The abundance of biomedical text data coupled with advances in natural language processing (NLP) is resulting in novel biomedical NLP (BioNLP) applications. These NLP applications, or tasks, are reliant on the availability of domain-specific language models (LMs) that are trained on a massive amount of data. Most of the existing domain-specific LMs adopted bidirectional encoder representations from transformers (BERT) architecture which has limitations, and their generalizability is unproven as there is an absence of baseline results among common BioNLP tasks. Results: We present 8 variants of BioALBERT, a domain-specific adaptation of a lite bidirectional encoder representations from transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine-tuned for 6 different tasks across 20 benchmark datasets. Experiments show that a large variant of BioALBERT trained on PubMed outperforms the state-of-the-art on named-entity recognition (+ 11.09% BLURB score improvement), relation extraction (+ 0.80% BLURB score), sentence similarity (+ 1.05% BLURB score), document classification (+ 0.62% F1-score), and question answering (+ 2.83% BLURB score). It represents a new state-of-the-art in 5 out of 6 benchmark BioNLP tasks. Conclusions: The large variant of BioALBERT trained on PubMed achieved a higher BLURB score than previous state-of-the-art models on 5 of the 6 benchmark BioNLP tasks. Depending on the task, 5 different variants of BioALBERT outperformed previous state-of-the-art models on 17 of the 20 benchmark datasets, showing that our model is robust and generalizable in the common BioNLP tasks. We have made BioALBERT freely available which will help the BioNLP community avoid computational cost of training and establish a new set of baselines for future efforts across a broad range of BioNLP tasks. [ABSTRACT FROM AUTHOR]

Motivation: The scientific literature embeds an enormous amount of relational knowledge, encompassing interactions between biomedical entities, like proteins, drugs, and symptoms. To cope with the ever-increasing number of publications, researchers are experiencing a surge of interest in extracting valuable, structured, concise, and unambiguous information from plain texts. With the development of deep learning, the granularity of information extraction is evolving from entities and pairwise relations to events. Events can model complex interactions involving multiple participants having a specific semantic role, also handling nested and overlapping definitions. After being studied for years, automatic event extraction is on the road to significantly impact biology in a wide range of applications, from knowledge base enrichment to the formulation of new research hypotheses. Results: This paper provides a comprehensive and up-to-date survey on the link between event extraction and natural language understanding, focusing on the biomedical domain. First, we establish a flexible event definition, summarizing the terminological efforts conducted in various areas. Second, we present the event extraction task, the related challenges, and the available annotated corpora. Third, we deeply explore the most representative methods and present an analysis of the current state-of-the-art, accompanied by performance discussion. To help researchers navigate the avalanche of event extraction works, we provide a detailed taxonomy for classifying the contributions proposed by the community. Fourth, we compare solutions applied in biomedicine with those evaluated in other domains, identifying research opportunities and providing insights for strategies not yet explored. Finally, we discuss applications and our envisions about future perspectives, moving the needle on explainability and knowledge injection.

The body of biomedical literature is growing at an unprecedented rate, exceeding the ability of researchers to make effective use of this knowledge-rich amount of information. This growth has created interest in biomedical relation extraction approaches to extract domain-specific knowledge for diverse applications. Despite the great progress in the techniques, the retrieved evidence still needs to undergo a time-consuming manual curation process to be truly useful. Most relation extraction systems have been conceived in the context of Shared Tasks, with the goal of maximizing the F1 score on restricted, domain-specific test sets. However, in industrial applications relations typically serve as input to a pipeline of biologically driven analyses; as a result, highly precise extractions are central for cutting down the manual curation effort, thus to translate the research evidence into practice smoothly and reliably. In this paper, we present a highly precise relation extraction system designed to reduce human curation efforts. The engine is made up of sophisticated rules that leverage linguistic aspects of the texts rather than sticking on application-specific training data. As a result, the system could be applied to diverse needs. Experiments on gold-standard corpora show that the system achieves the highest precision compared with previous rule-based, kernel-based, and neural approaches, while maintaining a F1 score comparable or superior to other methods. To show the usefulness of our approach in industrial scenarios, we finally present a case study on the mTOR pathway, showing how it could be applied on a large-scale.

Abstract Background Microbes have been shown to play a crucial role in various ecosystems. Many human diseases have been proved to be associated with bacteria, so it is essential to extract the interaction between bacteria for medical research and application. At the same time, many bacterial interactions with certain experimental evidences have been reported in biomedical literature. Integrating this knowledge into a database or knowledge graph could accelerate the progress of biomedical research. A crucial and necessary step in interaction extraction (IE) is named entity recognition (NER). However, due to the specificity of bacterial naming, there are still challenges in bacterial named entity recognition. Results In this paper, we propose a novel method for bacterial named entity recognition, which integrates domain features into a deep learning framework combining bidirectional long short-term memory network and convolutional neural network. When domain features are not added, F1-measure of the model achieves 89.14%. After part-of-speech (POS) features and dictionary features are added, F1-measure of the model achieves 89.7%. Hence, our model achieves an advanced performance in bacterial NER with the domain features. Conclusions We propose an efficient method for bacterial named entity recognition which combines domain features and deep learning models. Compared with the previous methods, the effect of our model has been improved. At the same time, the process of complex manual extraction and feature design are significantly reduced.

Abstract Background The Bacteria Biotope (BB) task is a biomedical relation extraction (RE) that aims to study the interaction between bacteria and their locations. This task is considered to pertain to fundamental knowledge in applied microbiology. Some previous investigations conducted the study by applying feature-based models; others have presented deep-learning-based models such as convolutional and recurrent neural networks used with the shortest dependency paths (SDPs). Although SDPs contain valuable and concise information, some parts of crucial information that is required to define bacterial location relationships are often neglected. Moreover, the traditional word-embedding used in previous studies may suffer from word ambiguation across linguistic contexts. Results Here, we present a deep learning model for biomedical RE. The model incorporates feature combinations of SDPs and full sentences with various attention mechanisms. We also used pre-trained contextual representations based on domain-specific vocabularies. To assess the model’s robustness, we introduced a mean F1 score on many models using different random seeds. The experiments were conducted on the standard BB corpus in BioNLP-ST’16. Our experimental results revealed that the model performed better (in terms of both maximum and average F1 scores; 60.77% and 57.63%, respectively) compared with other existing models. Conclusions We demonstrated that our proposed contributions to this task can be used to extract rich lexical, syntactic, and semantic features that effectively boost the model’s performance. Moreover, we analyzed the trade-off between precision and recall to choose the proper cut-off to use in real-world applications.

Background: Medical image analysis, particularly in the context of visual question answering (VQA) and image captioning, is crucial for accurate diagnosis and educational purposes., Objective: Our study aims to introduce BioMedBLIP models, fine-tuned for VQA tasks using specialized medical data sets such as Radiology Objects in Context and Medical Information Mart for Intensive Care-Chest X-ray, and evaluate their performance in comparison to the state of the art (SOTA) original Bootstrapping Language-Image Pretraining (BLIP) model., Methods: We present 9 versions of BioMedBLIP across 3 downstream tasks in various data sets. The models are trained on a varying number of epochs. The findings indicate the strong overall performance of our models. We proposed BioMedBLIP for the VQA generation model, VQA classification model, and BioMedBLIP image caption model. We conducted pretraining in BLIP using medical data sets, producing an adapted BLIP model tailored for medical applications., Results: In VQA generation tasks, BioMedBLIP models outperformed the SOTA on the Semantically-Labeled Knowledge-Enhanced (SLAKE) data set, VQA in Radiology (VQA-RAD), and Image Cross-Language Evaluation Forum data sets. In VQA classification, our models consistently surpassed the SOTA on the SLAKE data set. Our models also showed competitive performance on the VQA-RAD and PathVQA data sets. Similarly, in image captioning tasks, our model beat the SOTA, suggesting the importance of pretraining with medical data sets. Overall, in 20 different data sets and task combinations, our BioMedBLIP excelled in 15 (75%) out of 20 tasks. BioMedBLIP represents a new SOTA in 15 (75%) out of 20 tasks, and our responses were rated higher in all 20 tasks (P<.005) in comparison to SOTA models., Conclusions: Our BioMedBLIP models show promising performance and suggest that incorporating medical knowledge through pretraining with domain-specific medical data sets helps models achieve higher performance. Our models thus demonstrate their potential to advance medical image analysis, impacting diagnosis, medical education, and research. However, data quality, task-specific variability, computational resources, and ethical considerations should be carefully addressed. In conclusion, our models represent a contribution toward the synergy of artificial intelligence and medicine. We have made BioMedBLIP freely available, which will help in further advancing research in multimodal medical tasks., (©Usman Naseem, Surendrabikram Thapa, Anum Masood. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 05.08.2024.)

Aims: To explore the pathogenic mechanisms of Candida albicans ( C. albicans ), focusing on its impact on human health, particularly through invasive infections in the gastrointestinal and respiratory tracts., Methods: In this study, we evaluated the demographic and clinical profiles of 7 pneumonia patients. Meanwhile, we used Gene Set Enrichment Analysis (GSEA) and Evolutionary Dynamics method to analyze the role of candidalysin in C. albicans pathogenicity., Results: By analyzing genomic data and conducting biomedical text mining, we identified novel mutation sites in the candidalysin coding gene ECE1-III , shedding light into the genetic diversity within C. albicans strains and their potential implications for antifungal resistance. Our results revealed significant associations between C. albicans and respiratory as well as gastrointestinal diseases, emphasizing the fungus's role in the pathogenesis of these diseases. Additionally, we identified a new mutation site in the C. albicans strain YF2-5, isolated from patients with pneumonia. This mutation may be associated with its heightened pathogenicity., Conclusion: Our research advances the understanding of C. albicans pathogenicity and opens new avenues for developing targeted antifungal therapies. By focusing on the molecular basis of fungal virulence, we aim to contribute to the development of more effective treatment strategies, addressing the challenge of multidrug resistance in invasive fungal infections., Competing Interests: None., (AJTR Copyright © 2024.)

Background: Stroke has an acute onset and a high mortality rate, making it one of the most fatal diseases worldwide. Its underlying biology and treatments have been widely studied both in the "Western" biomedicine and the Traditional Chinese Medicine (TCM). However, these two approaches are often studied and reported in insolation, both in the literature and associated databases. Results: To aid research in finding effective prevention methods and treatments, we integrated knowledge from the literature and a number of databases (e.g. CID, TCMID, ETCM). We employed a suite of biomedical text mining (i.e. named-entity) approaches to identify mentions of genes, diseases, drugs, chemicals, symptoms, Chinese herbs and patent medicines, etc. in a large set of stroke papers from both biomedical and TCM domains. Then, using a combination of a rule-based approach with a pre-trained BioBERT model, we extracted and classified links and relationships among stroke-related entities as expressed in the literature. We construct StrokeKG, a knowledge graph includes almost 46 k nodes of nine types, and 157 k links of 30 types, connecting diseases, genes, symptoms, drugs, pathways, herbs, chemical, ingredients and patent medicine. Conclusions: Our Stroke-KG can provide practical and reliable stroke-related knowledge to help with stroke-related research like exploring new directions for stroke research and ideas for drug repurposing and discovery. We make StrokeKG freely available at http://114.115.208.144:7474/browser/ (Please click "Connect" directly) and the source structured data for stroke at https://github.com/yangxi1016/Stroke [ABSTRACT FROM AUTHOR]