RESUMO
BACKGROUND: Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects. CLINICALTRIALS: gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance. RESULTS: In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, the Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy. CONCLUSION: This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.
Assuntos
Ontologias Biológicas , Ensaios Clínicos como Assunto , Vacinas , Vacinas/imunologia , Humanos , Processamento de Linguagem Natural , Unified Medical Language SystemRESUMO
BACKGROUND: The exploration of cancer vaccines has yielded a multitude of studies, resulting in a diverse collection of information. The heterogeneity of cancer vaccine data significantly impedes effective integration and analysis. While CanVaxKB serves as a pioneering database for over 670 manually annotated cancer vaccines, it is important to distinguish that a database, on its own, does not offer the structured relationships and standardized definitions found in an ontology. Recognizing this, we expanded the Vaccine Ontology (VO) to include those cancer vaccines present in CanVaxKB that were not initially covered, enhancing VO's capacity to systematically define and interrelate cancer vaccines. RESULTS: An ontology design pattern (ODP) was first developed and applied to semantically represent various cancer vaccines, capturing their associated entities and relations. By applying the ODP, we generated a cancer vaccine template in a tabular format and converted it into the RDF/OWL format for generation of cancer vaccine terms in the VO. '12MP vaccine' was used as an example of cancer vaccines to demonstrate the application of the ODP. VO also reuses reference ontology terms to represent entities such as cancer diseases and vaccine hosts. Description Logic (DL) and SPARQL query scripts were developed and used to query for cancer vaccines based on different vaccine's features and to demonstrate the versatility of the VO representation. Additionally, ontological modeling was applied to illustrate cancer vaccine related concepts and studies for in-depth cancer vaccine analysis. A cancer vaccine-specific VO view, referred to as "CVO," was generated, and it contains 928 classes including 704 cancer vaccines. The CVO OWL file is publicly available on: http://purl.obolibrary.org/obo/vo/cvo.owl , for sharing and applications. CONCLUSION: To facilitate the standardization, integration, and analysis of cancer vaccine data, we expanded the Vaccine Ontology (VO) to systematically model and represent cancer vaccines. We also developed a pipeline to automate the inclusion of cancer vaccines and associated terms in the VO. This not only enriches the data's standardization and integration, but also leverages ontological modeling to deepen the analysis of cancer vaccine information, maximizing benefits for researchers and clinicians. AVAILABILITY: The VO-cancer GitHub website is: https://github.com/vaccineontology/VO/tree/master/CVO .
Assuntos
Ontologias Biológicas , Vacinas Anticâncer , Humanos , Análise de Dados , Padrões de ReferênciaRESUMO
Many data resources generate, process, store, or provide kidney related molecular, pathological, and clinical data. Reference ontologies offer an opportunity to support knowledge and data integration. The Kidney Precision Medicine Project (KPMP) team contributed to the representation and addition of 329 kidney phenotype terms to the Human Phenotype Ontology (HPO), and identified many subcategories of acute kidney injury (AKI) or chronic kidney disease (CKD). The Kidney Tissue Atlas Ontology (KTAO) imports and integrates kidney-related terms from existing ontologies (e.g., HPO, CL, and Uberon) and represents 259 kidney-related biomarkers. We also developed a precision medicine metadata ontology (PMMO) to integrate 50 variables from KPMP and CZ CellxGene data resources and applied PMMO for integrative kidney data analysis. The gene expression profiles of kidney gene biomarkers were specifically analyzed under healthy control or AKI/CKD disease statuses. This work demonstrates how ontology-based approaches support multi-domain data and knowledge integration in precision medicine.
RESUMO
BACKGROUND: Pathogenic parasites are responsible for multiple diseases, such as malaria and Chagas disease, in humans and livestock. Traditionally, pathogenic parasites have been largely an evasive topic for vaccine design, with most successful vaccines only emerging recently. To aid vaccine design, the VIOLIN vaccine knowledgebase has collected vaccines from all sources to serve as a comprehensive vaccine knowledgebase. VIOLIN utilizes the Vaccine Ontology (VO) to standardize the modeling of vaccine data. VO did not model complex life cycles as seen in parasites. With the inclusion of successful parasite vaccines, an update in parasite vaccine modeling was needed. RESULTS: VIOLIN was expanded to include 258 parasite vaccines against 23 protozoan species, and 607 new parasite vaccine-related terms were added to VO since 2022. The updated VO design for parasite vaccines accounts for parasite life stages and for transmission-blocking vaccines. A total of 356 terms from the Ontology of Parasite Lifecycle (OPL) were imported to VO to help represent the effect of different parasite life stages. A new VO class term, 'transmission-blocking vaccine,' was added to represent vaccines able to block infectious transmission, and one new VO object property, 'blocks transmission of pathogen via vaccine,' was added to link vaccine and pathogen in which the vaccine blocks the transmission of the pathogen. Additionally, our Gene Set Enrichment Analysis (GSEA) of 140 parasite antigens used in the parasitic vaccines identified enriched features. For example, significant patterns, such as signal, plasma membrane, and entry into host, were found in the antigens of the vaccines against two parasite species: Plasmodium falciparum and Toxoplasma gondii. The analysis found 18 out of the 140 parasite antigens involved with the malaria disease process. Moreover, a majority (15 out of 54) of P. falciparum parasite antigens are localized in the cell membrane. T. gondii antigens, in contrast, have a majority (19/24) of their proteins related to signaling pathways. The antigen-enriched patterns align with the life cycle stage patterns identified in our ontological parasite vaccine modeling. CONCLUSIONS: The updated VO modeling and GSEA analysis capture the influence of the complex parasite life cycles and their associated antigens on vaccine development.
Assuntos
Ontologias Biológicas , Animais , Parasitos/imunologia , Vacinas Protozoárias/imunologia , Humanos , Vacinas/imunologia , Modelos BiológicosRESUMO
Cancer vaccines have been increasingly studied and developed to prevent or treat various types of cancers. To systematically survey and analyze different reported cancer vaccines, we developed CanVaxKB (https://violinet.org/canvaxkb), the first web-based cancer vaccine knowledgebase that compiles over 670 therapeutic or preventive cancer vaccines that have been experimentally verified to be effective at various stages. Vaccine construction and host response data are also included. These cancer vaccines are developed against various cancer types such as melanoma, hematological cancer, and prostate cancer. CanVaxKB has stored 263 genes or proteins that serve as cancer vaccine antigen genes, which we have collectively termed 'canvaxgens'. Top three mostly used canvaxgens are PMEL, MLANA and CTAG1B, often targeting multiple cancer types. A total of 193 canvaxgens are also reported in cancer-related ONGene, Network of Cancer Genes and/or Sanger Cancer Gene Consensus databases. Enriched functional annotations and clusters of canvaxgens were identified and analyzed. User-friendly web interfaces are searchable for querying and comparing cancer vaccines. CanVaxKB cancer vaccines are also semantically represented by the community-based Vaccine Ontology to support data exchange. Overall, CanVaxKB is a timely and vital cancer vaccine source that facilitates efficient collection and analysis, further helping researchers and physicians to better understand cancer mechanisms.
RESUMO
The COVID-19 pandemic prompted immense work on the investigation of the SARS-CoV-2 virus. Rapid, accurate, and consistent interpretation of generated data is thereby of fundamental concern. Ontologies-structured, controlled, vocabularies-are designed to support consistency of interpretation, and thereby to prevent the development of data silos. This paper describes how ontologies are serving this purpose in the COVID-19 research domain, by following principles of the Open Biological and Biomedical Ontology (OBO) Foundry and by reusing existing ontologies such as the Infectious Disease Ontology (IDO) Core, which provides terminological content common to investigations of all infectious diseases. We report here on the development of an IDO extension, the Virus Infectious Disease Ontology (VIDO), a reference ontology covering viral infectious diseases. We motivate term and definition choices, showcase reuse of terms from existing OBO ontologies, illustrate how ontological decisions were motivated by relevant life science research, and connect VIDO to the Coronavirus Infectious Disease Ontology (CIDO). We next use terms from these ontologies to annotate selections from life science research on SARS-CoV-2, highlighting how ontologies employing a common upper-level vocabulary may be seamlessly interwoven. Finally, we outline future work, including bacteria and fungus infectious disease reference ontologies currently under development, then cite uses of VIDO and CIDO in host-pathogen data analytics, electronic health record annotation, and ontology conflict-resolution projects.
Assuntos
Ontologias Biológicas , COVID-19 , Doenças Transmissíveis , Viroses , Humanos , Pandemias , Vocabulário Controlado , COVID-19/epidemiologiaRESUMO
To fully understand COVID-19, it is critical to study all possible hosts of SARS-CoV-2 (the pathogen of COVID-19). In this work, we collected, annotated, and performed ontology-based taxonomical analysis of all the reported and verified hosts for all human coronaviruses including SARS-CoV, MERS-CoV, SARS-CoV-2, HCoV-229E, HCoV-NL63, HCoV-OC43, and HCoV-HKU1. A total of 37 natural hosts and 19 laboratory animal hosts of human coronaviruses were identified based on experimental evidence. Our analysis found that all the verified susceptible natural and laboratory animals belong to therian mammals. Specifically, these 37 natural therian hosts include one wildlife marsupial mammal (i.e., Virginia opossum) and 36 Eutheria mammals (a.k.a. placental mammals). The 19 laboratory animal hosts are also classified as therian mammals. The mouse models with genetically modified human ACE2 or DPP4 were more susceptible to virulent human coronaviruses with clear symptoms, suggesting the critical role of ACE2 and DPP4 to coronavirus virulence. Coronaviruses became more virulent and adaptive in the mouse hosts after a series of viral passages in the mice, providing clue to the possible coronavirus origination. The Huanan Seafood Wholesale Market animals identified early in the COVID-19 outbreak were also systematically analyzed as possible COVID-19 hosts. To support knowledge standardization and query, the annotated host knowledge was modeled and represented in the Coronavirus Infectious Disease Ontology (CIDO). Based on our and others' findings, we further propose a MOVIE model (i.e., Multiple-Organism viral Variations and Immune Evasion) to address how viral variations in therian animal hosts and the host immune evasion might have led to dynamic COVID-19 pandemic outcomes.
Assuntos
COVID-19 , Marsupiais , Feminino , Gravidez , Humanos , Animais , Camundongos , SARS-CoV-2 , Enzima de Conversão de Angiotensina 2 , Dipeptidil Peptidase 4 , Pandemias , Placenta , EutériosRESUMO
BACKGROUND AND OBJECTIVE: While impact of heat exposure on human health is well-documented, limited research exists on its effect on kidney disease hospital admissions especially in Texas, a state with diverse demographics and a high heat-related death rate. We aimed to explore the link between high temperatures and emergency kidney disease hospital admissions across 12 Texas Metropolitan Statistical Areas (MSAs) from 2004 to 2013, considering causes, age groups, and ethnic populations. METHODS: To investigate the correlation between high temperatures and emergency hospital admissions, we utilized MSA-level hospital admission and weather data. We employed a Generalized Additive Model to calculate the association specific to each MSA, and then performed a random effects meta-analysis to estimate the overall correlation. Analyses were stratified by age groups, admission causes, and racial/ethnic disparities. Sensitivity analysis involved lag modifications and ozone inclusion in the model. RESULTS: Our analysis found that each 1 °C increase in temperature was associated with a 1.73 % (95 % CI [1.43, 2.03]) increase in hospital admissions related to all types of kidney diseases. Besides, the effect estimates varied across different age groups and specific types of kidney diseases. We observed statistically significant associations between high temperatures and emergency hospital admissions for Acute Kidney Injury (AKI) (3.34 % (95 % CI [2.86, 3.82])), Kidney Stone (1.76 % (95 % CI [0.94, 2.60])), and Urinary Tract Infections (UTI) (1.06 % (95 % CI [0.61, 1.51])). Our research findings indicate disparities in certain Metropolitan Statistical Areas (MSAs). In Austin, Houston, San Antonio, and Dallas metropolitan areas, the estimated effects are more pronounced for African Americans when compared to the White population. Additionally, in Dallas, Houston, El Paso, and San Antonio, the estimated effects are greater for the Hispanic group compared to the Non-Hispanic group. CONCLUSIONS: This study finds a strong link between higher temperatures and kidney disease-related hospital admissions in Texas, especially for AKI. Public health actions are necessary to address these temperature-related health risks, including targeted kidney health initiatives. More research is needed to understand the mechanisms and address health disparities among racial/ethnic groups.
Assuntos
Injúria Renal Aguda , Temperatura Alta , Humanos , Texas/epidemiologia , Hospitalização , Hospitais , Injúria Renal Aguda/epidemiologiaRESUMO
Reverse vaccinology (RV) provides a systematic approach to identifying potential vaccine candidates based on protein sequences. The integration of machine learning (ML) into this process has greatly enhanced our ability to predict viable vaccine candidates from these sequences. We have previously developed a Vaxign-ML program based on the eXtreme Gradient Boosting (XGBoost). In this study, we further extend our work to develop a Vaxign-DL program based on deep learning techniques. Deep neural networks assemble non-linear models and learn multilevel abstraction of data using hierarchically structured layers, offering a data-driven approach in computational design models. Vaxign-DL uses a three-layer fully connected neural network model. Using the same bacterial vaccine candidate training data as used in Vaxign-ML development, Vaxign-DL was able to achieve an Area Under the Receiver Operating Characteristic of 0.94, specificity of 0.99, sensitivity of 0.74, and accuracy of 0.96. Using the Leave-One-Pathogen-Out Validation (LOPOV) method, Vaxign-DL was able to predict vaccine candidates for 10 pathogens. Our benchmark study shows that Vaxign-DL achieved comparable results with Vaxign-ML in most cases, and our method outperforms Vaxi-DL in the accurate prediction of bacterial protective antigens.
RESUMO
Background: Vaccines have revolutionized public health by providing protection against infectious diseases. They stimulate the immune system and generate memory cells to defend against targeted diseases. Clinical trials evaluate vaccine performance, including dosage, administration routes, and potential side effects. ClinicalTrials.gov is a valuable repository of clinical trial information, but the vaccine data in them lacks standardization, leading to challenges in automatic concept mapping, vaccine-related knowledge development, evidence-based decision-making, and vaccine surveillance. Results: In this study, we developed a cascaded framework that capitalized on multiple domain knowledge sources, including clinical trials, Unified Medical Language System (UMLS), and the Vaccine Ontology (VO), to enhance the performance of domain-specific language models for automated mapping of VO from clinical trials. The Vaccine Ontology (VO) is a community-based ontology that was developed to promote vaccine data standardization, integration, and computer-assisted reasoning. Our methodology involved extracting and annotating data from various sources. We then performed pre-training on the PubMedBERT model, leading to the development of CTPubMedBERT. Subsequently, we enhanced CTPubMedBERT by incorporating SAPBERT, which was pretrained using the UMLS, resulting in CTPubMedBERT + SAPBERT. Further refinement was accomplished through fine-tuning using the Vaccine Ontology corpus and vaccine data from clinical trials, yielding the CTPubMedBERT + SAPBERT + VO model. Finally, we utilized a collection of pre-trained models, along with the weighted rule-based ensemble approach, to normalize the vaccine corpus and improve the accuracy of the process. The ranking process in concept normalization involves prioritizing and ordering potential concepts to identify the most suitable match for a given context. We conducted a ranking of the Top 10 concepts, and our experimental results demonstrate that our proposed cascaded framework consistently outperformed existing effective baselines on vaccine mapping, achieving 71.8% on top 1 candidate's accuracy and 90.0% on top 10 candidate's accuracy. Conclusion: This study provides a detailed insight into a cascaded framework of fine-tuned domain-specific language models improving mapping of VO from clinical trials. By effectively leveraging domain-specific information and applying weighted rule-based ensembles of different pre-trained BERT models, our framework can significantly enhance the mapping of VO from clinical trials.
RESUMO
Increasing evidence implicates the tumor microbiota as a factor that can influence cancer progression. In patients with colorectal cancer (CRC), we found that pre-resection antibiotics targeting anaerobic bacteria substantially improved disease-free survival by 25.5%. For mouse studies, we designed an antibiotic silver-tinidazole complex encapsulated in liposomes (LipoAgTNZ) to eliminate tumor-associated bacteria in the primary tumor and liver metastases without causing gut microbiome dysbiosis. Mouse CRC models colonized by tumor-promoting bacteria (Fusobacterium nucleatum spp.) or probiotics (Escherichia coli Nissle spp.) responded to LipoAgTNZ therapy, which enabled more than 70% long-term survival in two F. nucleatum-infected CRC models. The antibiotic treatment generated microbial neoantigens that elicited anti-tumor CD8+ T cells. Heterologous and homologous bacterial epitopes contributed to the immunogenicity, priming T cells to recognize both infected and uninfected tumors. Our strategy targets tumor-associated bacteria to elicit anti-tumoral immunity, paving the way for microbiome-immunotherapy interventions.
RESUMO
Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federated annotation and evaluation to resolve several pitfalls encountered in the course of these efforts.
Assuntos
COVID-19 , Processamento de Linguagem Natural , Humanos , Registros Eletrônicos de Saúde , AlgoritmosRESUMO
Host responses to vaccines are complex but important to investigate. To facilitate the study, we have developed a tool called Vaccine Induced Gene Expression Analysis Tool (VIGET), with the aim to provide an interactive online tool for users to efficiently and robustly analyze the host immune response gene expression data collected in the ImmPort/GEO databases. VIGET allows users to select vaccines, choose ImmPort studies, set up analysis models by choosing confounding variables and two groups of samples having different vaccination times, and then perform differential expression analysis to select genes for pathway enrichment analysis and functional interaction network construction using the Reactome's web services. VIGET provides features for users to compare results from two analyses, facilitating comparative response analysis across different demographic groups. VIGET uses the Vaccine Ontology (VO) to classify various types of vaccines such as live or inactivated flu vaccines, yellow fever vaccines, etc. To showcase the utilities of VIGET, we conducted a longitudinal analysis of immune responses to yellow fever vaccines and found an intriguing complex activity response pattern of pathways in the immune system annotated in Reactome, demonstrating that VIGET is a valuable web portal that supports effective vaccine response studies using Reactome pathways and ImmPort data.
Assuntos
Vacina contra Febre Amarela , Febre Amarela , Humanos , Febre Amarela/prevenção & controle , Vacinação , Vacinas de Produtos Inativados , Perfilação da Expressão GênicaRESUMO
BACKGROUND: The extensive international research for medications and vaccines for the devastating COVID-19 pandemic requires a standard reference ontology. Among the current COVID-19 ontologies, the Coronavirus Infectious Disease Ontology (CIDO) is the largest one. Furthermore, it keeps growing very frequently. Researchers using CIDO as a reference ontology, need a quick update about the content added in a recent release to know how relevant the new concepts are to their research needs. Although CIDO is only a medium size ontology, it is still a large knowledge base posing a challenge for a user interested in obtaining the "big picture" of content changes between releases. Both a theoretical framework and a proper visualization are required to provide such a "big picture". METHODS: The child-of-based layout of the weighted aggregate partial-area taxonomy summarization network (WAT) provides a "big picture" convenient visualization of the content of an ontology. In this paper we address the "big picture" of content changes between two releases of an ontology. We introduce a new DIFF framework named Diff Weighted Aggregate Taxonomy (DWAT) to display the differences between the WATs of two releases of an ontology. We use a layered approach which consists first of a DWAT of major subjects in CIDO, and then drill down a major subject of interest in the top-level DWAT to obtain a DWAT of secondary subjects and even further refined layers. RESULTS: A visualization of the Diff Weighted Aggregate Taxonomy is demonstrated on the CIDO ontology. The evolution of CIDO between 2020 and 2022 is demonstrated in two perspectives. Drilling down for a DWAT of secondary subject networks is also demonstrated. We illustrate how the DWAT of CIDO provides insight into its evolution. CONCLUSIONS: The new Diff Weighted Aggregate Taxonomy enables a layered approach to view the "big picture" of the changes in the content between two releases of an ontology.
Assuntos
COVID-19 , Humanos , Pandemias , Conhecimento , Bases de ConhecimentoRESUMO
BACKGROUND: AKI is associated with mortality in patients hospitalized with coronavirus disease 2019 (COVID-19); however, its incidence, geographic distribution, and temporal trends since the start of the pandemic are understudied. METHODS: Electronic health record data were obtained from 53 health systems in the United States in the National COVID Cohort Collaborative. We selected hospitalized adults diagnosed with COVID-19 between March 6, 2020, and January 6, 2022. AKI was determined with serum creatinine and diagnosis codes. Time was divided into 16-week periods (P1-6) and geographical regions into Northeast, Midwest, South, and West. Multivariable models were used to analyze the risk factors for AKI or mortality. RESULTS: Of a total cohort of 336,473, 129,176 (38%) patients had AKI. Fifty-six thousand three hundred and twenty-two (17%) lacked a diagnosis code but had AKI based on the change in serum creatinine. Similar to patients coded for AKI, these patients had higher mortality compared with those without AKI. The incidence of AKI was highest in P1 (47%; 23,097/48,947), lower in P2 (37%; 12,102/32,513), and relatively stable thereafter. Compared with the Midwest, the Northeast, South, and West had higher adjusted odds of AKI in P1. Subsequently, the South and West regions continued to have the highest relative AKI odds. In multivariable models, AKI defined by either serum creatinine or diagnostic code and the severity of AKI was associated with mortality. CONCLUSIONS: The incidence and distribution of COVID-19-associated AKI changed since the first wave of the pandemic in the United States. PODCAST: This article contains a podcast at https://dts.podtrac.com/redirect.mp3/www.asn-online.org/media/podcast/CJASN/2023_08_08_CJN0000000000000192.mp3.
Assuntos
Injúria Renal Aguda , COVID-19 , Adulto , Humanos , COVID-19/complicações , COVID-19/epidemiologia , Estudos Retrospectivos , Creatinina , Fatores de Risco , Injúria Renal Aguda/diagnóstico , Mortalidade HospitalarRESUMO
Detecting protein-protein interactions (PPIs) is crucial for understanding genetic mechanisms, disease pathogenesis, and drug design. However, with the fast-paced growth of biomedical literature, there is a growing need for automated and accurate extraction of PPIs to facilitate scientific knowledge discovery. Pre-trained language models, such as generative pre-trained transformers (GPT) and bidirectional encoder representations from transformers (BERT), have shown promising results in natural language processing (NLP) tasks. We evaluated the performance of PPI identification of multiple GPT and BERT models using three manually curated gold-standard corpora: Learning Language in Logic (LLL) with 164 PPIs in 77 sentences, Human Protein Reference Database with 163 PPIs in 145 sentences, and Interaction Extraction Performance Assessment with 335 PPIs in 486 sentences. BERT-based models achieved the best overall performance, with BioBERT achieving the highest recall (91.95%) and F1-score (86.84%) and PubMedBERT achieving the highest precision (85.25%). Interestingly, despite not being explicitly trained for biomedical texts, GPT-4 achieved commendable performance, comparable to the top-performing BERT models. It achieved a precision of 88.37%, a recall of 85.14%, and an F1-score of 86.49% on the LLL dataset. These results suggest that GPT models can effectively detect PPIs from text data, offering promising avenues for application in biomedical literature mining. Further research could explore how these models might be fine-tuned for even more specialized tasks within the biomedical domain.
RESUMO
Purpose: Three licensed human papillomavirus (HPV) vaccines (Cervarix, Gardasil, and Gardasil 9) have been effectively used to prevent infection with oncogenic HPV types; however, many adverse events (AEs) have also been reported following their vaccinations. We assessed AE profiles after receiving the HPV vaccines based on the reported data from Vaccine Adverse Event Reporting System (VAERS). Methods: The AE data associated with Cervarix, Gardasil, and Gardasil 9 were retrieved from VAERS database respectively. The combinatorial biomedical statistical methods were used to identify the statistically significant AEs. The Gamma-Poisson Shrinker (GPS) model with gender/age stratification was applied to ascertain the serious adverse events (SAEs) related to the three licensed HPV vaccines. The AE profiles were classified and represented by the Ontology of Adverse Events (OAE) for further analysis. Results: As of July 31, 2020, VAERS recorded 3,112, 31,606, and 6,872 AE case reports for Cervarix, Gardasil, and Gardasil 9, respectively. Our Frequentist statistical methods identified 135 Cervarix-enriched AEs, 55 Gardasil-enriched AEs, and 17 Gardasil 9-enriched AEs. Based on the OAE hierarchical classification, these AEs were clustered in the AEs related to behavioral and neurological conditions, immune system, nervous system, and reproductive system. Combined with GPS modeling, 46 unique statistically significant SAEs were founded to be associated with at least one of the three vaccines. Conclusions: Our study led to the better understanding of the AEs associated with the licensed HPV vaccines. The hypotheses on the cause and effect relationships between the HPV vaccination and specific AEs deserve further epidemiological investigations as well as clinical trial studies.
RESUMO
BACKGROUND: The current COVID-19 pandemic and the previous SARS/MERS outbreaks of 2003 and 2012 have resulted in a series of major global public health crises. We argue that in the interest of developing effective and safe vaccines and drugs and to better understand coronaviruses and associated disease mechenisms it is necessary to integrate the large and exponentially growing body of heterogeneous coronavirus data. Ontologies play an important role in standard-based knowledge and data representation, integration, sharing, and analysis. Accordingly, we initiated the development of the community-based Coronavirus Infectious Disease Ontology (CIDO) in early 2020. RESULTS: As an Open Biomedical Ontology (OBO) library ontology, CIDO is open source and interoperable with other existing OBO ontologies. CIDO is aligned with the Basic Formal Ontology and Viral Infectious Disease Ontology. CIDO has imported terms from over 30 OBO ontologies. For example, CIDO imports all SARS-CoV-2 protein terms from the Protein Ontology, COVID-19-related phenotype terms from the Human Phenotype Ontology, and over 100 COVID-19 terms for vaccines (both authorized and in clinical trial) from the Vaccine Ontology. CIDO systematically represents variants of SARS-CoV-2 viruses and over 300 amino acid substitutions therein, along with over 300 diagnostic kits and methods. CIDO also describes hundreds of host-coronavirus protein-protein interactions (PPIs) and the drugs that target proteins in these PPIs. CIDO has been used to model COVID-19 related phenomena in areas such as epidemiology. The scope of CIDO was evaluated by visual analysis supported by a summarization network method. CIDO has been used in various applications such as term standardization, inference, natural language processing (NLP) and clinical data integration. We have applied the amino acid variant knowledge present in CIDO to analyze differences between SARS-CoV-2 Delta and Omicron variants. CIDO's integrative host-coronavirus PPIs and drug-target knowledge has also been used to support drug repurposing for COVID-19 treatment. CONCLUSION: CIDO represents entities and relations in the domain of coronavirus diseases with a special focus on COVID-19. It supports shared knowledge representation, data and metadata standardization and integration, and has been used in a range of applications.
Assuntos
COVID-19 , Doenças Transmissíveis , Coronavirus , Vacinas , Humanos , SARS-CoV-2 , Pandemias , Aminoácidos , Tratamento Farmacológico da COVID-19RESUMO
Background: Acute kidney injury (AKI) is associated with mortality in patients hospitalized with COVID-19, however, its incidence, geographic distribution, and temporal trends since the start of the pandemic are understudied. Methods: Electronic health record data were obtained from 53 health systems in the United States (US) in the National COVID Cohort Collaborative (N3C). We selected hospitalized adults diagnosed with COVID-19 between March 6th, 2020, and January 6th, 2022. AKI was determined with serum creatinine (SCr) and diagnosis codes. Time were divided into 16-weeks (P1-6) periods and geographical regions into Northeast, Midwest, South, and West. Multivariable models were used to analyze the risk factors for AKI or mortality. Results: Out of a total cohort of 306,061, 126,478 (41.0 %) patients had AKI. Among these, 17.9% lacked a diagnosis code but had AKI based on the change in SCr. Similar to patients coded for AKI, these patients had higher mortality compared to those without AKI. The incidence of AKI was highest in P1 (49.3%), reduced in P2 (40.6%), and relatively stable thereafter. Compared to the Midwest, the Northeast, South, and West had higher adjusted AKI incidence in P1, subsequently, the South and West regions continued to have the highest relative incidence. In multivariable models, AKI defined by either SCr or diagnostic code, and the severity of AKI was associated with mortality. Conclusions: Uncoded cases of COVID-19-associated AKI are common and associated with mortality. The incidence and distribution of COVID-19-associated AKI have changed since the first wave of the pandemic in the US.