PubTator central: automated concept annotation for biomedical full text articles

RegEl corpus: identifying DNA regulatory elements in the scientific literature

High-throughput technologies led to the generation of a wealth of data on regulatory DNA elements in the human genome. However, results from disease-driven studies are primarily shared in textual form as scientific articles. Information extraction (IE) algorithms allow this information to be (semi-)automatically accessed. Their development, however, is dependent on the availability of annotated corpora. Therefore, we introduce RegEl (Regulatory Elements), the first freely available corpus annotated with regulatory DNA elements comprising 305 PubMed abstracts for a total of 2690 sentences. We focus on enhancers, promoters and transcription factor binding sites. Three annotators worked in two stages, achieving an overall 0.73 F1 inter-annotator agreement and 0.46 for regulatory elements. Depending on the entity type, IE baselines reach F1-scores of 0.48–0.91 for entity detection and 0.71–0.88 for entity normalization. Next, we apply our entity detection models to the entire PubMed collection and extract co-occurrences of genes or diseases with regulatory elements. This generates large collections of regulatory elements associated with 137 870 unique genes and 7420 diseases, which we make openly available.

Database URL: https://zenodo.org/record/6418451#.YqcLHvexVqg

Genetic pain loss disorders

Genetic pain loss includes congenital insensitivity to pain (CIP), hereditary sensory neuropathies and, if autonomic nerves are involved, hereditary sensory and autonomic neuropathy (HSAN). This heterogeneous group of disorders highlights the essential role of nociception in protecting against tissue damage. Patients with genetic pain loss have recurrent injuries, burns and poorly healing wounds as disease hallmarks. CIP and HSAN are caused by pathogenic genetic variants in >20 genes that lead to developmental defects, neurodegeneration or altered neuronal excitability of peripheral damage-sensing neurons. These genetic variants lead to hyperactivity of sodium channels, disturbed haem metabolism, altered clathrin-mediated transport and impaired gene regulatory mechanisms affecting epigenetic marks, long non-coding RNAs and repetitive elements. Therapies for pain loss disorders are mainly symptomatic but the first targeted therapies are being tested. Conversely, chronic pain remains one of the greatest unresolved medical challenges, and the genes and mechanisms associated with pain loss offer new targets for analgesics. Given the progress that has been made, the coming years are promising both in terms of targeted treatments for pain loss disorders and the development of innovative pain medicines based on knowledge of these genetic diseases.

Creation and evaluation of full-text literature-derived, feature-weighted disease models of genetically determined developmental disorders

There are >2500 different genetically determined developmental disorders (DD), which, as a group, show very high levels of both locus and allelic heterogeneity. This has led to the wide-spread use of evidence-based filtering of genome-wide sequence data as a diagnostic tool in DD. Determining whether the association of a filtered variant at a specific locus is a plausible explanation of the phenotype in the proband is crucial and commonly requires extensive manual literature review by both clinical scientists and clinicians. Access to a database of weighted clinical features extracted from rigorously curated literature would increase the efficiency of this process and facilitate the development of robust phenotypic similarity metrics. However, given the large and rapidly increasing volume of published information, conventional biocuration approaches are becoming impractical. Here, we present a scalable, automated method for the extraction of categorical phenotypic descriptors from the full-text literature. Papers identified through literature review were downloaded and parsed using the Cadmus custom retrieval package. Human Phenotype Ontology terms were extracted using MetaMap, with 76-84% precision and 65-73% recall. Mean terms per paper increased from 9 in title + abstract, to 68 using full text. We demonstrate that these literature-derived disease models plausibly reflect true disease expressivity more accurately than widely used manually curated models, through comparison with prospectively gathered data from the Deciphering Developmental Disorders study. The area under the curve for receiver operating characteristic (ROC) curves increased by 5-10% through the use of literature-derived models. This work shows that scalable automated literature curation increases performance and adds weight to the need for this strategy to be integrated into informatic variant analysis pipelines. Database URL: https://doi.org/10.1093/database/baac038.

AnthraxKP: a knowledge graph-based, Anthrax Knowledge Portal mined from biomedical literature

Anthrax is a zoonotic infectious disease caused by Bacillus anthracis (anthrax bacterium) that affects not only domestic and wild animals worldwide but also human health. As the study develops in-depth, a large quantity of related biomedical publications emerge. Acquiring knowledge from the literature is essential for gaining insight into anthrax etiology, diagnosis, treatment and research. In this study, we used a set of text mining tools to identify nearly 14 000 entities of 29 categories, such as genes, diseases, chemicals, species, vaccines and proteins, from nearly 8000 anthrax biomedical literature and extracted 281 categories of association relationships among the entities. We curated Anthrax-related Entities Dictionary and Anthrax Ontology. We formed Anthrax Knowledge Graph (AnthraxKG) containing more than 6000 nodes, 6000 edges and 32 000 properties. An interactive visualized Anthrax Knowledge Portal(AnthraxKP) was also developed based on AnthraxKG by using Web technology. AnthraxKP in this study provides rich and authentic relevant knowledge in many forms, which can help researchers carry out research more efficiently.

Database URL: AnthraxKP is permitted users to query and download data at http://139.224.212.120:18095/.

Hierarchical network analysis of co-occurring bioentities in literature

Biomedical databases grow by more than a thousand new publications every day. The large volume of biomedical literature that is being published at an unprecedented rate hinders the discovery of relevant knowledge from keywords of interest to gather new insights and form hypotheses. A text-mining tool, PubTator, helps to automatically annotate bioentities, such as species, chemicals, genes, and diseases, from PubMed abstracts and full-text articles. However, the manual re-organization and analysis of bioentities is a non-trivial and highly time-consuming task. ChexMix was designed to extract the unique identifiers of bioentities from query results. Herein, ChexMix was used to construct a taxonomic tree with allied species among Korean native plants and to extract the medical subject headings unique identifier of the bioentities, which co-occurred with the keywords in the same literature. ChexMix discovered the allied species related to a keyword of interest and experimentally proved its usefulness for multi-species analysis.

Gilda: biomedical entity text normalization with machine-learned disambiguation as a service

Summary

Gilda is a software tool and web service that implements a scored string matching algorithm for names and synonyms across entries in biomedical ontologies covering genes, proteins (and their families and complexes), small molecules, biological processes and diseases. Gilda integrates machine-learned disambiguation models to choose between ambiguous strings given relevant surrounding text as context, and supports species-prioritization in case of ambiguity.

Availability and implementation

The Gilda web service is available at http://grounding.indra.bio with source code, documentation and tutorials available via https://github.com/indralab/gilda.

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

SARS-CoV-2 and Prevotella spp.: friend or foe? A systematic literature review

During this global pandemic of the COVID-19 disease, a lot of information has arisen in the media and online without scientific validation, and among these is the possibility that this disease could be aggravated by a secondary bacterial infection such as Prevotella, as well as the interest or not in using azithromycin, a potentially active antimicrobial agent. The aim of this study was to carry out a systematic literature review, to prove or disprove these allegations by scientific arguments. The search included Medline, PubMed, and Pubtator Central databases for English-language articles published 1999-2021. After removing duplicates, a total of final eligible studies (n=149) were selected. There were more articles showing an increase of Prevotella abundance in the presence of viral infection like that related to Human Immunodeficiency Virus (HIV), Papillomavirus (HPV), Herpesviridae and respiratory virus, highlighting differences according to methodologies and patient groups. The arguments for or against the use of azithromycin are stated in light of the results of the literature, showing the role of intercurrent factors, such as age, drug consumption, the presence of cancer or periodontal diseases. However, clinical trials are lacking to prove the direct link between the presence of Prevotella spp. and a worsening of COVID-19, mainly those using azithromycin alone in this indication.

GeneCup: mining PubMed and GWAS catalog for gene-keyword relationships

Interpreting and integrating results from omics studies typically requires a comprehensive and time consuming survey of extant literature. GeneCup is a literature mining web service that retrieves sentences containing user-provided gene symbols and keywords from PubMed abstracts. The keywords are organized into an ontology and can be extended to include results from human genome-wide association studies. We provide a drug addiction keyword ontology that contains over 300 keywords as an example. The literature search is conducted by querying the PubMed server using a programming interface, which is followed by retrieving abstracts from a local copy of the PubMed archive. The main results presented to the user are sentences where gene symbol and keywords co-occur. These sentences are presented through an interactive graphical interface or as tables. All results are linked to the original abstract in PubMed. In addition, a convolutional neural network is employed to distinguish sentences describing systemic stress from those describing cellular stress. The automated and comprehensive search strategy provided by GeneCup facilitates the integration of new discoveries from omic studies with existing literature. GeneCup is free and open source software. The source code of GeneCup and the link to a running instance is available at https://github.com/hakangunturkun/GeneCup.

BioTAGME: A Comprehensive Platform for Biological Knowledge Network Analysis

The inference of novel knowledge and new hypotheses from the current literature analysis is crucial in making new scientific discoveries. In bio-medicine, given the enormous amount of literature and knowledge bases available, the automatic gain of knowledge concerning relationships among biological elements, in the form of semantically related terms (or entities), is rising novel research challenges and corresponding applications. In this regard, we propose BioTAGME, a system that combines an entity-annotation framework based on Wikipedia corpus (i.e., TAGME tool) with a network-based inference methodology (i.e., DT-Hybrid). This integration aims to create an extensive Knowledge Graph modeling relations among biological terms and phrases extracted from titles and abstracts of papers available in PubMed. The framework consists of a back-end and a front-end. The back-end is entirely implemented in Scala and runs on top of a Spark cluster that distributes the computing effort among several machines. The front-end is released through the Laravel framework, connected with the Neo4j graph database to store the knowledge graph.

HerbKG: Constructing a Herbal-Molecular Medicine Knowledge Graph Using a Two-Stage Framework Based on Deep Transfer Learning

Recent advances have witnessed a growth of herbalism studies adopting a modern scientific approach in molecular medicine, offering valuable domain knowledge that can potentially boost the development of herbalism with evidence-supported efficacy and safety. However, these domain-specific scientific findings have not been systematically organized, affecting the efficiency of knowledge discovery and usage. Existing knowledge graphs in herbalism mainly focus on diagnosis and treatment with an absence of knowledge connection with molecular medicine. To fill this gap, we present HerbKG, a knowledge graph that bridges herbal and molecular medicine. The core bio-entities of HerbKG include herbs, chemicals extracted from the herbs, genes that are affected by the chemicals, and diseases treated by herbs due to the functions of genes. We have developed a learning framework to automate the process of HerbKG construction. The resulting HerbKG, after analyzing over 500K PubMed abstracts, is populated with 53K relations, providing extensive herbal-molecular domain knowledge in support of downstream applications. The code and an interactive tool are available at https://github.com/FeiYee/HerbKG.

PAGER Web APP: An Interactive, Online Gene Set and Network Interpretation Tool for Functional Genomics

Functional genomics studies have helped researchers annotate differentially expressed gene lists, extract gene expression signatures, and identify biological pathways from omics profiling experiments conducted on biological samples. The current geneset, network, and pathway analysis (GNPA) web servers, e.g., DAVID, EnrichR, WebGestaltR, or PAGER, do not allow automated integrative functional genomic downstream analysis. In this study, we developed a new web-based interactive application, “PAGER Web APP”, which supports online R scripting of integrative GNPA. In a case study of melanoma drug resistance, we showed that the new PAGER Web APP enabled us to discover highly relevant pathways and network modules, leading to novel biological insights. We also compared PAGER Web APP’s pathway analysis results retrieved among PAGER, EnrichR, and WebGestaltR to show its advantages in integrative GNPA. The interactive online web APP is publicly accessible from the link, https://aimed-lab.shinyapps.io/PAGERwebapp/.

Causative Variants for Inherited Cardiac Conditions in a Southeast Asian Population Cohort

Background:

Variable penetrance and late-onset phenotypes are key challenges for classifying causal as well as incidental findings in inherited cardiac conditions. Allele frequencies of variants in ancestry-specific populations, along with clinical variant analysis and interpretation, are critical to determine their true significance.

Methods:

Here, we carefully reviewed and classified variants in genes associated with inherited cardiac conditions based on a population whole-genome sequencing cohort of 4810 Singaporeans representing Southeast Asian ancestries.

Results:

Eighty-nine (1.85%) individuals carried either pathogenic or likely pathogenic variants across 25 genes. Forty-six (51.7%) had variants in causal genes for familial hyperlipidemia, but there were also recurrent variants in SCN5A and MYBPC3 , causal genes for inherited arrhythmia and cardiomyopathy, which, despite previous reports, we determined to lack criteria for pathogenicity.

Conclusions:

Our findings highlight the incidence of disease-related variants in inherited cardiac conditions and emphasize the value of large-scale sequencing in specific ancestries. Follow-up detailed phenotyping and analysis of pedigrees are crucial because assigning pathogenicity will significantly affect clinical management for individuals and their family members.

MedTator: a serverless annotation tool for corpus development

SUMMARY

Building a high-quality annotation corpus requires expenditure of considerable time and expertise, particularly for biomedical and clinical research applications. Most existing annotation tools provide many advanced features to cover a variety of needs where the installation, integration and difficulty of use present a significant burden for actual annotation tasks. Here, we present MedTator, a serverless annotation tool, aiming to provide an intuitive and interactive user interface that focuses on the core steps related to corpus annotation, such as document annotation, corpus summarization, annotation export and annotation adjudication.

AVAILABILITY AND IMPLEMENTATION

MedTator and its tutorial are freely available from https://ohnlp.github.io/MedTator. MedTator source code is available under the Apache 2.0 license: https://github.com/OHNLP/MedTator.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

The implication of holocytochrome c synthase mutation in Korean familial hypoplastic amelogenesis imperfecta

Objectives

This study aimed to comprehensively characterise genetic variants of amelogenesis imperfecta in a single Korean family through whole-exome sequencing and bioinformatics analysis.

Material and methods

Thirty-one individuals of a Korean family, 9 of whom were affected and 22 unaffected by amelogenesis imperfecta, were enrolled. Whole-exome sequencing was performed on 12 saliva samples, including samples from 8 affected and 4 unaffected individuals. The possible candidate genes associated with the disease were screened by segregation analysis and variant filtering. In silico mutation impact analysis was then performed on the filtered variants based on sequence conservation and protein structure.

Results

Whole-exome sequencing data revealed an X-linked dominant, heterozygous genomic missense mutation in the mitochondrial gene holocytochrome c synthase (HCCS). We also found that HCCS is potentially related to the role of mitochondria in amelogenesis. The HCCS variant was expected to be deleterious in both evolution-based and large population-based analyses. Further, the variant was predicted to have a negative effect on catalytic function of HCCS by in silico analysis of protein structure. In addition, HCCS had significant association with amelogenesis in literature mining analysis.

Conclusions

These findings suggest new evidence for the relationship between amelogenesis and mitochondria function, which could be implicated in the pathogenesis of amelogenesis imperfecta.

Clinical relevance

The discovery of HCCS mutations and a deeper understanding of the pathogenesis of amelogenesis imperfecta could lead to finding solutions for the fundamental treatment of this disease. Furthermore, it enables dental practitioners to establish predictable prosthetic treatment plans at an early stage by early detection of amelogenesis imperfecta through personalised medicine.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00784-022-04413-0.

Systematic illumination of druggable genes in cancer genomes

By combining 6 druggable genome resources, we identify 6,083 genes as potential druggable genes (PDGs). We characterize their expression, recurrent genomic alterations, cancer dependencies, and therapeutic potentials by integrating genome, functionome, and druggome profiles across cancers. 81.5% of PDGs are reliably expressed in major adult cancers, 46.9% show selective expression patterns, and 39.1% exhibit at least one recurrent genomic alteration. We annotate a total of 784 PDGs as dependent genes for cancer cell growth. We further quantify 16 cancer-related features and estimate a PDG cancer drug target score (PCDT score). PDGs with higher PCDT scores are significantly enriched for genes encoding kinases and histone modification enzymes. Importantly, we find that a considerable portion of high PCDT score PDGs are understudied genes, providing unexplored opportunities for drug development in oncology. By integrating the druggable genome and the cancer genome, our study thus generates a comprehensive blueprint of potential druggable genes across cancers.

Jiang et al. generate a comprehensive blueprint of potential druggable genes (PDGs) across cancers by a systematic integration of the druggable genome and the cancer genome. This resource is publicly available to the cancer research community in The Cancer Druggable Gene Atlas (TCDA) through the Functional Cancer Genome data portal.

Parsing Immune Correlates of Protection Against SARS-CoV-2 from Biomedical Literature

After the emergence of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) in 2019, identification of immune correlates of protection (CoPs) have become increasingly important to understand the immune response to SARS-CoV-2. The vast amount of preprint and published literature related to COVID-19 makes it challenging for researchers to stay up to date on research results regarding CoPs against SARS-CoV-2. To address this problem, we developed a machine learning classifier to identify papers relevant to CoPs and a customized named entity recognition (NER) model to extract terms of interest, including CoPs, vaccines, assays, and animal models. A user-friendly visualization tool was populated with the extracted and normalized NER results and associated publication information including links to full-text articles and clinical trial information where available. The goal of this pilot project is to provide a basis for developing real-time informatics platforms that can inform researchers with scientific insights from emerging research.

Examining linguistic shifts between preprints and publications

Preprints allow researchers to make their findings available to the scientific community before they have undergone peer review. Studies on preprints within bioRxiv have been largely focused on article metadata and how often these preprints are downloaded, cited, published, and discussed online. A missing element that has yet to be examined is the language contained within the bioRxiv preprint repository. We sought to compare and contrast linguistic features within bioRxiv preprints to published biomedical text as a whole as this is an excellent opportunity to examine how peer review changes these documents. The most prevalent features that changed appear to be associated with typesetting and mentions of supporting information sections or additional files. In addition to text comparison, we created document embeddings derived from a preprint-trained word2vec model. We found that these embeddings are able to parse out different scientific approaches and concepts, link unannotated preprint-peer-reviewed article pairs, and identify journals that publish linguistically similar papers to a given preprint. We also used these embeddings to examine factors associated with the time elapsed between the posting of a first preprint and the appearance of a peer-reviewed publication. We found that preprints with more versions posted and more textual changes took longer to publish. Lastly, we constructed a web application (https://greenelab.github.io/preprint-similarity-search/) that allows users to identify which journals and articles that are most linguistically similar to a bioRxiv or medRxiv preprint as well as observe where the preprint would be positioned within a published article landscape.

Thrombocytopenia in COVID‑19 and vaccine‑induced thrombotic thrombocytopenia

The highly heterogeneous symptomatology and unpredictable progress of COVID-19 triggered unprecedented intensive biomedical research and a number of clinical research projects. Although the pathophysiology of the disease is being progressively clarified, its complexity remains vast. Moreover, some extremely infrequent cases of thrombotic thrombocytopenia following vaccination against SARS-CoV-2 infection have been observed. The present study aimed to map the signaling pathways of thrombocytopenia implicated in COVID-19, as well as in vaccine-induced thrombotic thrombocytopenia (VITT). The biomedical literature database, MEDLINE/PubMed, was thoroughly searched using artificial intelligence techniques for the semantic relations among the top 50 similar words (>0.9) implicated in COVID-19-mediated human infection or VITT. Additionally, STRING, a database of primary and predicted associations among genes and proteins (collected from diverse resources, such as documented pathway knowledge, high-throughput experimental studies, cross-species extrapolated information, automated text mining results, computationally predicted interactions, etc.), was employed, with the confidence threshold set at 0.7. In addition, two interactomes were constructed: i) A network including 119 and 56 nodes relevant to COVID-19 and thrombocytopenia, respectively; and ii) a second network containing 60 nodes relevant to VITT. Although thrombocytopenia is a dominant morbidity in both entities, three nodes were observed that corresponded to genes (AURKA, CD46 and CD19) expressed only in VITT, whilst ADAM10, CDC20, SHC1 and STXBP2 are silenced in VITT, but are commonly expressed in both COVID-19 and thrombocytopenia. The calculated average node degree was immense (11.9 in COVID-19 and 6.43 in VITT), illustrating the complexity of COVID-19 and VITT pathologies and confirming the importance of cytokines, as well as of pathways activated following hypoxic events. In addition, PYCARD, NLP3 and P2RX7 are key potential therapeutic targets for all three morbid entities, meriting further research. This interactome was based on wild-type genes, revealing the predisposition of the body to hypoxia-induced thrombosis, leading to the acute COVID-19 phenotype, the 'long-COVID syndrome', and/or VITT. Thus, common nodes appear to be key players in illness prevention, progression and treatment.

HLA-SPREAD: a natural language processing based resource for curating HLA association from PubMed abstracts

Extreme complexity in the Human Leukocyte Antigens (HLA) system and its nomenclature makes it difficult to interpret and integrate relevant information for HLA associations with diseases, Adverse Drug Reactions (ADR) and Transplantation. PubMed search displays ~ 146,000 studies on HLA reported from diverse locations. Currently, IPD-IMGT/HLA (Robinson et al., Nucleic Acids Research 48:D948-D955, 2019) database houses data on 28,320 HLA alleles. We developed an automated pipeline with a unified graphical user interface HLA-SPREAD that provides a structured information on SNPs, Populations, REsources, ADRs and Diseases information. Information on HLA was extracted from ~ 28 million PubMed abstracts extracted using Natural Language Processing (NLP). Python scripts were used to mine and curate information on diseases, filter false positives and categorize to 24 tree hierarchical groups and named Entity Recognition (NER) algorithms followed by semantic analysis to infer HLA association(s). This resource from 109 countries and 40 ethnic groups provides interesting insights on: markers associated with allelic/haplotypic association in autoimmune, cancer, viral and skin diseases, transplantation outcome and ADRs for hypersensitivity. Summary information on clinically relevant biomarkers related to HLA disease associations with mapped susceptible/risk alleles are readily retrievable from HLASPREAD. The resource is available at URL http://hla-spread.igib.res.in/ . This resource is first of its kind that can help uncover novel patterns in HLA gene-disease associations.

Acronyms and Opportunities for Improving Deep Nets

Recently, several studies have reported promising results with BERT-like methods on acronym tasks. In this study, we find an older rule-based program, Ab3P, not only performs better, but error analysis suggests why. There is a well-known spelling convention in acronyms where each letter in the short form (SF) refers to “salient” letters in the long form (LF). The error analysis uses decision trees and logistic regression to show that there is an opportunity for many pre-trained models (BERT, T5, BioBert, BART, ERNIE) to take advantage of this spelling convention.

HIT 2.0: an enhanced platform for Herbal Ingredients' Targets

Literature-described targets of herbal ingredients have been explored to facilitate the mechanistic study of herbs, as well as the new drug discovery. Though several databases provided similar information, the majority of them are limited to literatures before 2010 and need to be updated urgently. HIT 2.0 was here constructed as the latest curated dataset focusing on Herbal Ingredients’ Targets covering PubMed literatures 2000–2020. Currently, HIT 2.0 hosts 10 031 compound-target activity pairs with quality indicators between 2208 targets and 1237 ingredients from more than 1250 reputable herbs. The molecular targets cover those genes/proteins being directly/indirectly activated/inhibited, protein binders, and enzymes substrates or products. Also included are those genes regulated under the treatment of individual ingredient. Crosslinks were made to databases of TTD, DrugBank, KEGG, PDB, UniProt, Pfam, NCBI, TCM-ID and others. More importantly, HIT enables automatic Target-mining and My-target curation from daily released PubMed literatures. Thus, users can retrieve and download the latest abstracts containing potential targets for interested compounds, even for those not yet covered in HIT. Further, users can log into ‘My-target’ system, to curate personal target-profiling on line based on retrieved abstracts. HIT can be accessible at http://hit2.badd-cao.net.

ViMIC: a database of human disease-related virus mutations, integration sites and cis-effects

Molecular mechanisms of virus-related diseases involve multiple factors, including viral mutation accumulation and integration of a viral genome into the host DNA. With increasing attention being paid to virus-mediated pathogenesis and the development of many useful technologies to identify virus mutations (VMs) and viral integration sites (VISs), much research on these topics is available in PubMed. However, knowledge of VMs and VISs is widely scattered in numerous published papers which lack standardization, integration and curation. To address these challenges, we built a pilot database of human disease-related Virus Mutations, Integration sites and Cis-effects (ViMIC), which specializes in three features: virus mutation sites, viral integration sites and target genes. In total, the ViMIC provides information on 31 712 VMs entries, 105 624 VISs, 16 310 viral target genes and 1 110 015 virus sequences of eight viruses in 77 human diseases obtained from the public domain. Furthermore, in ViMIC users are allowed to explore the cis-effects of virus-host interactions by surveying 78 histone modifications, binding of 1358 transcription regulators and chromatin accessibility on these VISs. We believe ViMIC will become a valuable resource for the virus research community. The database is available at http://bmtongji.cn/ViMIC/index.php.

NETME: on-the-fly knowledge network construction from biomedical literature

BACKGROUND

The rapidly increasing biological literature is a key resource to automatically extract and gain knowledge concerning biological elements and their relations. Knowledge Networks are helpful tools in the context of biological knowledge discovery and modeling.

RESULTS

We introduce a novel system called NETME, which, starting from a set of full-texts obtained from PubMed, through an easy-to-use web interface, interactively extracts biological elements from ontological databases and then synthesizes a network inferring relations among such elements. The results clearly show that our tool is capable of inferring comprehensive and reliable biological networks.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s41109-021-00435-x.

Exploration of the core protein network under endometriosis symptomatology using a computational approach

BACKGROUND

Endometriosis is defined by implantation and invasive growth of endometrial tissue in extra-uterine locations causing heterogeneous symptoms, and a unique clinical picture for each patient. Understanding the complex biological mechanisms underlying these symptoms and the protein networks involved may be useful for early diagnosis and identification of pharmacological targets.

METHODS

In the present study, we combined three approaches (i) a text-mining analysis to perform a systematic search of proteins over existing literature, (ii) a functional enrichment analysis to identify the biological pathways in which proteins are most involved, and (iii) a protein-protein interaction (PPI) network to identify which proteins modulate the most strongly the symptomatology of endometriosis.

RESULTS

Two hundred seventy-eight proteins associated with endometriosis symptomatology in the scientific literature were extracted. Thirty-five proteins were selected according to degree and betweenness scores criteria. The most enriched biological pathways associated with these symptoms were (i) Interleukin-4 and Interleukin-13 signaling (p = 1.11 x 10^-16), (ii) Signaling by Interleukins (p = 1.11 x 10^-16), (iii) Cytokine signaling in Immune system (p = 1.11 x 10^-16), and (iv) Interleukin-10 signaling (p = 5.66 x 10^-15).

CONCLUSION

Our study identified some key proteins with the ability to modulate endometriosis symptomatology. Our findings indicate that both pro- and anti-inflammatory biological pathways may play important roles in the symptomatology of endometriosis. This approach represents a genuine systemic method that may complement traditional experimental studies. The current data can be used to identify promising biomarkers for early diagnosis and potential therapeutic targets.

The characteristics of early-stage research into human genes are substantially different from subsequent research

Throughout the last 2 decades, several scholars observed that present day research into human genes rarely turns toward genes that had not already been extensively investigated in the past. Guided by hypotheses derived from studies of science and innovation, we present here a literature-wide data-driven meta-analysis to identify the specific scientific and organizational contexts that coincided with early-stage research into human genes throughout the past half century. We demonstrate that early-stage research into human genes differs in team size, citation impact, funding mechanisms, and publication outlet, but that generalized insights derived from studies of science and innovation only partially apply to early-stage research into human genes. Further, we demonstrate that, presently, genome biology accounts for most of the initial early-stage research, while subsequent early-stage research can engage other life sciences fields. We therefore anticipate that the specificity of our findings will enable scientists and policymakers to better promote early-stage research into human genes and increase overall innovation within the life sciences.

MedTAG: a portable and customizable annotation tool for biomedical documents

BACKGROUND

Semantic annotators and Natural Language Processing (NLP) methods for Named Entity Recognition and Linking (NER+L) require plenty of training and test data, especially in the biomedical domain. Despite the abundance of unstructured biomedical data, the lack of richly annotated biomedical datasets poses hindrances to the further development of NER+L algorithms for any effective secondary use. In addition, manual annotation of biomedical documents performed by physicians and experts is a costly and time-consuming task. To support, organize and speed up the annotation process, we introduce MedTAG, a collaborative biomedical annotation tool that is open-source, platform-independent, and free to use/distribute.

RESULTS

We present the main features of MedTAG and how it has been employed in the histopathology domain by physicians and experts to annotate more than seven thousand clinical reports manually. We compare MedTAG with a set of well-established biomedical annotation tools, including BioQRator, ezTag, MyMiner, and tagtog, comparing their pros and cons with those of MedTag. We highlight that MedTAG is one of the very few open-source tools provided with an open license and a straightforward installation procedure supporting cross-platform use.

CONCLUSIONS

MedTAG has been designed according to five requirements (i.e. available, distributable, installable, workable and schematic) defined in a recent extensive review of manual annotation tools. Moreover, MedTAG satisfies 20 over 22 criteria specified in the same study.

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

Knowledge bases and software support for variant interpretation in precision oncology

Precision oncology is a rapidly evolving interdisciplinary medical specialty. Comprehensive cancer panels are becoming increasingly available at pathology departments worldwide, creating the urgent need for scalable cancer variant annotation and molecularly informed treatment recommendations. A wealth of mainly academia-driven knowledge bases calls for software tools supporting the multi-step diagnostic process. We derive a comprehensive list of knowledge bases relevant for variant interpretation by a review of existing literature followed by a survey among medical experts from university hospitals in Germany. In addition, we review cancer variant interpretation tools, which integrate multiple knowledge bases. We categorize the knowledge bases along the diagnostic process in precision oncology and analyze programmatic access options as well as the integration of knowledge bases into software tools. The most commonly used knowledge bases provide good programmatic access options and have been integrated into a range of software tools. For the wider set of knowledge bases, access options vary across different parts of the diagnostic process. Programmatic access is limited for information regarding clinical classifications of variants and for therapy recommendations. The main issue for databases used for biological classification of pathogenic variants and pathway context information is the lack of standardized interfaces. There is no single cancer variant interpretation tool that integrates all identified knowledge bases. Specialized tools are available and need to be further developed for different steps in the diagnostic process.

The Gene Regulation Knowledge Commons: The action area of GREEKC

The COST Action Gene Regulation Ensemble Effort for the Knowledge Commons (GREEKC, CA15205, www.greekc.org) organized nine workshops in a four-year period, starting September 2016. The workshops brought together a wide range of experts from all over the world working on various parts of the knowledge cycle that is central to understanding gene regulatory mechanisms. The discussions between ontologists, curators, text miners, biologists, bioinformaticians, philosophers and computational scientists spawned a host of activities aimed to update and standardise existing knowledge management workflows, encourage new experimental approaches and thoroughly involve end-users in the process to design the Gene Regulation Knowledge Commons (GRKC). The GREEKC consortium describes its main achievements, contextualised in a state-of-the-art of current tools and resources that today represent the GRKC.

COVID-19 knowledge graph from semantic integration of biomedical literature and databases

SUMMARY

The global response to the COVID-19 pandemic has led to a rapid increase of scientific literature on this deadly disease. Extracting knowledge from biomedical literature and integrating it with relevant information from curated biological databases is essential to gain insight into COVID-19 etiology, diagnosis, and treatment. We used Semantic Web technology RDF to integrate COVID-19 knowledge mined from literature by iTextMine, PubTator, and SemRep with relevant biological databases and formalized the knowledge in a standardized and computable COVID-19 Knowledge Graph (KG). We published the COVID-19 KG via a SPARQL endpoint to support federated queries on the Semantic Web and developed a knowledge portal with browsing and searching interfaces. We also developed a RESTful API to support programmatic access and provided RDF dumps for download.

AVAILABILITY AND IMPLEMENTATION

The COVID-19 Knowledge Graph is publicly available under CC-BY 4.0 license at https://research.bioinformatics.udel.edu/covid19kg/.

LitCovid-AGAC: cellular and molecular level annotation data set based on COVID-19

Currently, coronavirus disease 2019 (COVID-19) literature has been increasing dramatically, and the increased text amount make it possible to perform large scale text mining and knowledge discovery. Therefore, curation of these texts becomes a crucial issue for Bio-medical Natural Language Processing (BioNLP) community, so as to retrieve the important information about the mechanism of COVID-19. PubAnnotation is an aligned annotation system which provides an efficient platform for biological curators to upload their annotations or merge other external annotations. Inspired by the integration among multiple useful COVID-19 annotations, we merged three annotations resources to LitCovid data set, and constructed a cross-annotated corpus, LitCovid-AGAC. This corpus consists of 12 labels including Mutation, Species, Gene, Disease from PubTator, GO, CHEBI from OGER, Var, MPA, CPA, NegReg, PosReg, Reg from AGAC, upon 50,018 COVID-19 abstracts in LitCovid. Contain sufficient abundant information being possible to unveil the hidden knowledge in the pathological mechanism of COVID-19.

Cell2Chem: mining explored and unexplored biosynthetic chemical spaces

SUMMARY

Living cell strains have important applications in synthesizing their native compounds and potential for use in studies exploring the universal chemical space. Here, we present a web server named as Cell2Chem which accelerates the search for explored compounds in organisms, facilitating investigations of biosynthesis in unexplored chemical spaces. Cell2Chem uses co-occurrence networks and natural language processing to provide a systematic method for linking living organisms to biosynthesized compounds and the processes that produce these compounds. The Cell2Chem platform comprises 40 370 species and 125 212 compounds. Using reaction pathway and enzyme function in silico prediction methods, Cell2Chem reveals possible biosynthetic pathways of compounds and catalytic functions of proteins to expand unexplored biosynthetic chemical spaces. Cell2Chem can help improve biosynthesis research and enhance the efficiency of synthetic biology.

AVAILABILITY AND IMPLEMENTATION

Cell2Chem is available at: http://www.rxnfinder.org/cell2chem/.

CovidExpress: an interactive portal for intuitive investigation on SARS-CoV-2 related transcriptomes

Infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in humans could cause coronavirus disease 2019 (COVID-19). Since its first discovery in Dec 2019, SARS-CoV-2 has become a global pandemic and caused 3.3 million direct/indirect deaths (2021 May). Amongst the scientific community's response to COVID-19, data sharing has emerged as an essential aspect of the combat against SARS-CoV-2. Despite the ever-growing studies about SARS-CoV-2 and COVID-19, to date, only a few databases were curated to enable access to gene expression data. Furthermore, these databases curated only a small set of data and do not provide easy access for investigators without computational skills to perform analyses. To fill this gap and advance open-access to the growing gene expression data on this deadly virus, we collected about 1,500 human bulk RNA-seq datasets from publicly available resources, developed a database and visualization tool, named CovidExpress (https://stjudecab.github.io/covidexpress). This open access database will allow research investigators to examine the gene expression in various tissues, cell lines, and their response to SARS-CoV-2 under different experimental conditions, accelerating the understanding of the etiology of this disease to inform the drug and vaccine development. Our integrative analysis of this big dataset highlights a set of commonly regulated genes in SARS-CoV-2 infected lung and Rhinovirus infected nasal tissues, including OASL that were under-studied in COVID-19 related reports. Our results also suggested a potential FURIN positive feedback loop that might explain the evolutional advantage of SARS-CoV-2.

Improved biomedical word embeddings in the transformer era

BACKGROUND

Recent natural language processing (NLP) research is dominated by neural network methods that employ word embeddings as basic building blocks. Pre-training with neural methods that capture local and global distributional properties (e.g., skip-gram, GLoVE) using free text corpora is often used to embed both words and concepts. Pre-trained embeddings are typically leveraged in downstream tasks using various neural architectures that are designed to optimize task-specific objectives that might further tune such embeddings.

OBJECTIVE

Despite advances in contextualized language model based embeddings, static word embeddings still form an essential starting point in BioNLP research and applications. They are useful in low resource settings and in lexical semantics studies. Our main goal is to build improved biomedical word embeddings and make them publicly available for downstream applications.

METHODS

We jointly learn word and concept embeddings by first using the skip-gram method and further fine-tuning them with correlational information manifesting in co-occurring Medical Subject Heading (MeSH) concepts in biomedical citations. This fine-tuning is accomplished with the transformer-based BERT architecture in the two-sentence input mode with a classification objective that captures MeSH pair co-occurrence. We conduct evaluations of these tuned static embeddings using multiple datasets for word relatedness developed by previous efforts.

RESULTS

Both in qualitative and quantitative evaluations we demonstrate that our methods produce improved biomedical embeddings in comparison with other static embedding efforts. Without selectively culling concepts and terms (as was pursued by previous efforts), we believe we offer the most exhaustive evaluation of biomedical embeddings to date with clear performance improvements across the board.

CONCLUSION

We repurposed a transformer architecture (typically used to generate dynamic embeddings) to improve static biomedical word embeddings using concept correlations. We provide our code and embeddings for public use for downstream applications and research endeavors: https://github.com/bionlproc/BERT-CRel-Embeddings.

LitSuggest: a web-based system for literature recommendation and curation using machine learning

Searching and reading relevant literature is a routine practice in biomedical research. However, it is challenging for a user to design optimal search queries using all the keywords related to a given topic. As such, existing search systems such as PubMed often return suboptimal results. Several computational methods have been proposed as an effective alternative to keyword-based query methods for literature recommendation. However, those methods require specialized knowledge in machine learning and natural language processing, which can make them difficult for biologists to utilize. In this paper, we propose LitSuggest, a web server that provides an all-in-one literature recommendation and curation service to help biomedical researchers stay up to date with scientific literature. LitSuggest combines advanced machine learning techniques for suggesting relevant PubMed articles with high accuracy. In addition to innovative text-processing methods, LitSuggest offers multiple advantages over existing tools. First, LitSuggest allows users to curate, organize, and download classification results in a single interface. Second, users can easily fine-tune LitSuggest results by updating the training corpus. Third, results can be readily shared, enabling collaborative analysis and curation of scientific literature. Finally, LitSuggest provides an automated personalized weekly digest of newly published articles for each user's project. LitSuggest is publicly available at https://www.ncbi.nlm.nih.gov/research/litsuggest.

Artificial Intelligence in Action: Addressing the COVID-19 Pandemic with Natural Language Processing

The COVID-19 (coronavirus disease 2019) pandemic has had a significant impact on society, both because of the serious health effects of COVID-19 and because of public health measures implemented to slow its spread. Many of these difficulties are fundamentally information needs; attempts to address these needs have caused an information overload for both researchers and the public. Natural language processing (NLP)-the branch of artificial intelligence that interprets human language-can be applied to address many of the information needs made urgent by the COVID-19 pandemic. This review surveys approximately 150 NLP studies and more than 50 systems and datasets addressing the COVID-19 pandemic. We detail work on four core NLP tasks: information retrieval, named entity recognition, literature-based discovery, and question answering. We also describe work that directly addresses aspects of the pandemic through four additional tasks: topic modeling, sentiment and emotion analysis, caseload forecasting, and misinformation detection. We conclude by discussing observable trends and remaining challenges.

Polymorphisms at site 469 of B-RAF protein associated with skin melanoma may be correlated with dabrafenib resistance: An in silico study

Melanoma is a type of skin cancer. Numerous genes and their proteins are strongly associated with melanoma susceptibility. This study aims to use an in silico method to identify genetic variants in the melanoma susceptibility gene. The COSMIC database was queried for genes and cross-referenced with three environment-gene interaction databases (EGP, SeattleSNPs and CTD) to identify shared genes. The majority of approved skin melanoma drugs were found to act on the protein serine/threonine-protein kinase (B-RAF) encoded by the BRAF gene, which was also present in all three referenced databases. Comprehensive computational analysis was performed to predict deleterious genetic variants associated with skin melanoma, and the nsSNPs G469V and G469E were prioritized based on their predicted deleterious effects. Molecular dynamic simulation analysis of the B-RAF protein mutants G469V and G469E reveals that variations in the amino acid conformation at the drug binding site result in inconsistency in drug interaction. Additionally, this analysis showed that the G469V and G469E mutants have lower binding energy for dabrafenib than the wild type. The population with the highest frequency of each deleterious and pathogenic variant has been determined. The study's findings would support the development of more effective treatment strategies for skin melanoma. Communicated by Ramaswamy H. Sarma.

Utilizing image and caption information for biomedical document classification

Motivation

Biomedical research findings are typically disseminated through publications. To simplify access to domain-specific knowledge while supporting the research community, several biomedical databases devote significant effort to manual curation of the literature—a labor intensive process. The first step toward biocuration requires identifying articles relevant to the specific area on which the database focuses. Thus, automatically identifying publications relevant to a specific topic within a large volume of publications is an important task toward expediting the biocuration process and, in turn, biomedical research. Current methods focus on textual contents, typically extracted from the title-and-abstract. Notably, images and captions are often used in publications to convey pivotal evidence about processes, experiments and results.

Results

We present a new document classification scheme, using both image and caption information, in addition to titles-and-abstracts. To use the image information, we introduce a new image representation, namely Figure-word, based on class labels of subfigures. We use word embeddings for representing captions and titles-and-abstracts. To utilize all three types of information, we introduce two information integration methods. The first combines Figure-words and textual features obtained from captions and titles-and-abstracts into a single larger vector for document representation; the second employs a meta-classification scheme. Our experiments and results demonstrate the usefulness of the newly proposed Figure-words for representing images. Moreover, the results showcase the value of Figure-words, captions and titles-and-abstracts in providing complementary information for document classification; these three sources of information when combined, lead to an overall improved classification performance.

Availability and implementation

Source code and the list of PMIDs of the publications in our datasets are available upon request.

RENET2: high-performance full-text gene-disease relation extraction with iterative training data expansion

Relation extraction (RE) is a fundamental task for extracting gene–disease associations from biomedical text. Many state-of-the-art tools have limited capacity, as they can extract gene–disease associations only from single sentences or abstract texts. A few studies have explored extracting gene–disease associations from full-text articles, but there exists a large room for improvements. In this work, we propose RENET2, a deep learning-based RE method, which implements Section Filtering and ambiguous relations modeling to extract gene–disease associations from full-text articles. We designed a novel iterative training data expansion strategy to build an annotated full-text dataset to resolve the scarcity of labels on full-text articles. In our experiments, RENET2 achieved an F1-score of 72.13% for extracting gene–disease associations from an annotated full-text dataset, which was 27.22, 30.30, 29.24 and 23.87% higher than BeFree, DTMiner, BioBERT and RENET, respectively. We applied RENET2 to (i) ∼1.89M full-text articles from PubMed Central and found ∼3.72M gene–disease associations; and (ii) the LitCovid articles and ranked the top 15 proteins associated with COVID-19, supported by recent articles. RENET2 is an efficient and accurate method for full-text gene–disease association extraction. The source-code, manually curated abstract/full-text training data, and results of RENET2 are available at GitHub.

Untangling the genetic link between type 1 and type 2 diabetes using functional genomics

There is evidence pointing towards shared etiological features between type 1 diabetes (T1D) and type 2 diabetes (T2D) despite both phenotypes being considered genetically distinct. However, the existence of shared genetic features for T1D and T2D remains complex and poorly defined. To better understand the link between T1D and T2D, we employed an integrated functional genomics approach involving extensive chromatin interaction data (Hi-C) and expression quantitative trait loci (eQTL) data to characterize the tissue-specific impacts of single nucleotide polymorphisms associated with T1D and T2D. We identified 195 pleiotropic genes that are modulated by tissue-specific spatial eQTLs associated with both T1D and T2D. The pleiotropic genes are enriched in inflammatory and metabolic pathways that include mitogen-activated protein kinase activity, pertussis toxin signaling, and the Parkinson's disease pathway. We identified 8 regulatory elements within the TCF7L2 locus that modulate transcript levels of genes involved in immune regulation as well as genes important in the etiology of T2D. Despite the observed gene and pathway overlaps, there was no significant genetic correlation between variant effects on T1D and T2D risk using European ancestral summary data. Collectively, our findings support the hypothesis that T1D and T2D specific genetic variants act through genetic regulatory mechanisms to alter the regulation of common genes, and genes that co-locate in biological pathways, to mediate pleiotropic effects on disease development. Crucially, a high risk genetic profile for T1D alters biological pathways that increase the risk of developing both T1D and T2D. The same is not true for genetic profiles that increase the risk of developing T2D. The conversion of information on genetic susceptibility to the protein pathways that are altered provides an important resource for repurposing or designing novel therapies for the management of diabetes.

HLA-dependent heterogeneity and macrophage immunoproteasome activation during lung COVID-19 disease

BACKGROUND

The worldwide pandemic caused by the SARS-CoV-2 virus is characterized by significant and unpredictable heterogeneity in symptoms that remains poorly understood.

METHODS

Transcriptome and single cell transcriptome of COVID19 lung were integrated with deeplearning analysis of MHC class I immunopeptidome against SARS-COV2 proteome.

RESULTS

An analysis of the transcriptomes of lung samples from COVID-19 patients revealed that activation of MHC class I antigen presentation in these tissues was correlated with the amount of SARS-CoV-2 RNA present. Similarly, a positive relationship was detected in these samples between the level of SARS-CoV-2 and the expression of a genomic cluster located in the 6p21.32 region (40 kb long, inside the MHC-II cluster) that encodes constituents of the immunoproteasome. An analysis of single-cell transcriptomes of bronchoalveolar cells highlighted the activation of the immunoproteasome in CD68 + M1 macrophages of COVID-19 patients in addition to a PSMB8-based trajectory in these cells that featured an activation of defense response during mild cases of the disease, and an impairment of alveolar clearance mechanisms during severe COVID-19. By examining the binding affinity of the SARS-CoV-2 immunopeptidome with the most common HLA-A, -B, and -C alleles worldwide, we found higher numbers of stronger presenters in type A alleles and in Asian populations, which could shed light on why this disease is now less widespread in this part of the world.

CONCLUSIONS

HLA-dependent heterogeneity in macrophage immunoproteasome activation during lung COVID-19 disease could have implications for efforts to predict the response to HLA-dependent SARS-CoV-2 vaccines in the global population.

Mining Proteome Research Reports: A Bird's Eye View

The complexity of data has burgeoned to such an extent that scientists of every realm are encountering the incessant challenge of data management. Modern-day analytical approaches with the help of free source tools and programming languages have facilitated access to the context of the various domains as well as specific works reported. Here, with this article, an attempt has been made to provide a systematic analysis of all the available reports at PubMed on Proteome using text mining. The work is comprised of scientometrics as well as information extraction to provide the publication trends as well as frequent keywords, bioconcepts and most importantly gene–gene co-occurrence network. Out of 33,028 PMIDs collected initially, the segregation of 24,350 articles under 28 Medical Subject Headings (MeSH) was analyzed and plotted. Keyword link network and density visualizations were provided for the top 1000 frequent Mesh keywords. PubTator was used, and 322,026 bioconcepts were able to extracted under 10 classes (such as Gene, Disease, CellLine, etc.). Co-occurrence networks were constructed for PMID-bioconcept as well as bioconcept–bioconcept associations. Further, for creation of subnetwork with respect to gene–gene co-occurrence, a total of 11,100 unique genes participated with mTOR and AKT showing the highest (64) number of connections. The gene p53 was the most popular one in the network in accordance with both the degree and weighted degree centrality, which were 425 and 1414, respectively. The present piece of study is an amalgam of bibliometrics and scientific data mining methods looking deeper into the whole scale analysis of available literature on proteome.

Public data sources for regulatory genomic features

High-throughput technologies have led to a continuously growing amount of information about regulatory features in the genome. A wealth of data generated by large international research consortia is available from online databases. Disease-driven studies provide details on specific DNA elements or epigenetic modifications regulating gene expression in specific cellular and developmental contexts, but these results are usually only published in scientific articles. All this information can be helpful in interpreting variants in the regulatory genome. This review describes a selection of high-profile data sources providing information on the non-coding genome, as well as pitfalls and techniques to search and capture information from the literature.

NLM-Gene, a richly annotated gold standard dataset for gene entities that addresses ambiguity and multi-species gene recognition

The automatic recognition of gene names and their corresponding database identifiers in biomedical text is an important first step for many downstream text-mining applications. While current methods for tagging gene entities have been developed for biomedical literature, their performance on species other than human is substantially lower due to the lack of annotation data. We therefore present the NLM-Gene corpus, a high-quality manually annotated corpus for genes developed at the US National Library of Medicine (NLM), covering ambiguous gene names, with an average of 29 gene mentions (10 unique identifiers) per document, and a broader representation of different species (including Homo sapiens, Mus musculus, Rattus norvegicus, Drosophila melanogaster, Arabidopsis thaliana, Danio rerio, etc.) when compared to previous gene annotation corpora. NLM-Gene consists of 550 PubMed abstracts from 156 biomedical journals, doubly annotated by six experienced NLM indexers, randomly paired for each document to control for bias. The annotators worked in three annotation rounds until they reached complete agreement. This gold-standard corpus can serve as a benchmark to develop & test new gene text mining algorithms. Using this new resource, we have developed a new gene finding algorithm based on deep learning which improved both on precision and recall from existing tools. The NLM-Gene annotated corpus is freely available at ftp://ftp.ncbi.nlm.nih.gov/pub/lu/NLMGene. We have also applied this tool to the entire PubMed/PMC with their results freely accessible through our web-based tool PubTator (www.ncbi.nlm.nih.gov/research/pubtator).

Analyzing the vast coronavirus literature with CoronaCentral

The SARS-CoV-2 pandemic has caused a surge in research exploring all aspects of the virus and its effects on human health. The overwhelming publication rate means that researchers are unable to keep abreast of the literature. To ameliorate this, we present the CoronaCentral resource that uses machine learning to process the research literature on SARS-CoV-2 together with SARS-CoV and MERS-CoV. We categorize the literature into useful topics and article types and enable analysis of the contents, pace, and emphasis of research during the crisis with integration of Altmetric data. These topics include therapeutics, disease forecasting, as well as growing areas such as “long COVID” and studies of inequality. This resource, available at https://coronacentral.ai, is updated daily.

SimText: A text mining framework for interactive analysis and visualization of similarities among biomedical entities

Summary

Literature exploration in PubMed on a large number of biomedical entities (e.g. genes, diseases or experiments) can be time-consuming and challenging, especially when assessing associations between entities. Here, we describe SimText, a user-friendly toolset that provides customizable and systematic workflows for the analysis of similarities among a set of entities based on text. SimText can be used for (i) text collection from PubMed and extraction of words with different text mining approaches, and (ii) interactive analysis and visualization of data using unsupervised learning techniques in an interactive app.

Availability and implementation

We developed SimText as an open-source R software and integrated it into Galaxy (https://usegalaxy.eu), an online data analysis platform with supporting self-learning training material available at https://training.galaxyproject.org. A command-line version of the toolset is available for download from GitHub (https://github.com/dlal-group/simtext) or as Docker image (https://hub.docker.com/r/dlalgroup/simtext/tags.).

Supplementary information

Supplementary data are available at Bioinformatics online.

Profiling COVID-19 Genetic Research: A Data-Driven Study Utilizing Intelligent Bibliometrics

The COVID-19 pandemic constitutes an ongoing worldwide threat to human society and has caused massive impacts on global public health, the economy and the political landscape. The key to gaining control of the disease lies in understanding the genetics of SARS-CoV-2 and the disease spectrum that follows infection. This study leverages traditional and intelligent bibliometric methods to conduct a multi-dimensional analysis on 5,632 COVID-19 genetic research papers, revealing that 1) the key players include research institutions from the United States, China, Britain and Canada; 2) research topics predominantly focus on virus infection mechanisms, virus testing, gene expression related to the immune reactions and patient clinical manifestation; 3) studies originated from the comparison of SARS-CoV-2 to previous human coronaviruses, following which research directions diverge into the analysis of virus molecular structure and genetics, the human immune response, vaccine development and gene expression related to immune responses; and 4) genes that are frequently highlighted include ACE2, IL6, TMPRSS2, and TNF. Emerging genes to the COVID-19 consist of FURIN, CXCL10, OAS1, OAS2, OAS3, and ISG15. This study demonstrates that our suite of novel bibliometric tools could help biomedical researchers follow this rapidly growing field and provide substantial evidence for policymakers’ decision-making on science policy and public health administration.

LabelRS: An Automated Toolbox to Make Deep Learning Samples from Remote Sensing Images

Deep learning technology has achieved great success in the field of remote sensing processing. However, the lack of tools for making deep learning samples with remote sensing images is a problem, so researchers have to rely on a small amount of existing public data sets that may influence the learning effect. Therefore, we developed an add-in (LabelRS) based on ArcGIS to help researchers make their own deep learning samples in a simple way. In this work, we proposed a feature merging strategy that enables LabelRS to automatically adapt to both sparsely distributed and densely distributed scenarios. LabelRS solves the problem of size diversity of the targets in remote sensing images through sliding windows. We have designed and built in multiple band stretching, image resampling, and gray level transformation algorithms for LabelRS to deal with the high spectral remote sensing images. In addition, the attached geographic information helps to achieve seamless conversion between natural samples, and geographic samples. To evaluate the reliability of LabelRS, we used its three sub-tools to make semantic segmentation, object detection and image classification samples, respectively. The experimental results show that LabelRS can produce deep learning samples with remote sensing images automatically and efficiently.

Recent advances of automated methods for searching and extracting genomic variant information from biomedical literature

MOTIVATION

To obtain key information for personalized medicine and cancer research, clinicians and researchers in the biomedical field are in great need of searching genomic variant information from the biomedical literature now than ever before. Due to the various written forms of genomic variants, however, it is difficult to locate the right information from the literature when using a general literature search system. To address the difficulty of locating genomic variant information from the literature, researchers have suggested various solutions based on automated literature-mining techniques. There is, however, no study for summarizing and comparing existing tools for genomic variant literature mining in terms of how to search easily for information in the literature on genomic variants.

RESULTS

In this article, we systematically compared currently available genomic variant recognition and normalization tools as well as the literature search engines that adopted these literature-mining techniques. First, we explain the problems that are caused by the use of non-standard formats of genomic variants in the PubMed literature by considering examples from the literature and show the prevalence of the problem. Second, we review literature-mining tools that address the problem by recognizing and normalizing the various forms of genomic variants in the literature and systematically compare them. Third, we present and compare existing literature search engines that are designed for a genomic variant search by using the literature-mining techniques. We expect this work to be helpful for researchers who seek information about genomic variants from the literature, developers who integrate genomic variant information from the literature and beyond.

The multilayer community structure of medulloblastoma

Multilayer networks allow interpreting the molecular basis of diseases, which is particularly challenging in rare diseases where the number of cases is small compared with the size of the associated multi-omics datasets. In this work, we develop a dimensionality reduction methodology to identify the minimal set of genes that characterize disease subgroups based on their persistent association in multilayer network communities. We use this approach to the study of medulloblastoma, a childhood brain tumor, using proteogenomic data. Our approach is able to recapitulate known medulloblastoma subgroups (accuracy >94%) and provide a clear characterization of gene associations, with the downstream implications for diagnosis and therapeutic interventions. We verified the general applicability of our method on an independent medulloblastoma dataset (accuracy >98%). This approach opens the door to a new generation of multilayer network-based methods able to overcome the specific dimensionality limitations of rare disease datasets.

•

The molecular interpretation of rare diseases is a challenging task

•

Multilayer networks allow patient stratification and explainability

•

We identify subgroup-specific genes and multilayer associations in medulloblastoma

•

Multilayer community analysis enables the molecular interpretation of rare diseases