PCorral--interactive mining of protein interactions from MEDLINE

Text mining for identification of biological entities related to antibiotic resistant organisms

Antimicrobial resistance is a significant public health problem worldwide. In recent years, the scientific community has been intensifying efforts to combat this problem; many experiments have been developed, and many articles are published in this area. However, the growing volume of biological literature increases the difficulty of the biocuration process due to the cost and time required. Modern text mining tools with the adoption of artificial intelligence technology are helpful to assist in the evolution of research. In this article, we propose a text mining model capable of identifying and ranking prioritizing scientific articles in the context of antimicrobial resistance. We retrieved scientific articles from the PubMed database, adopted machine learning techniques to generate the vector representation of the retrieved scientific articles, and identified their similarity with the context. As a result of this process, we obtained a dataset labeled "Relevant" and "Irrelevant" and used this dataset to implement one supervised learning algorithm to classify new records. The model's overall performance reached 90% accuracy and the f-measure (harmonic mean between the metrics) reached 82% accuracy for positive class and 93% for negative class, showing quality in the identification of scientific articles relevant to the context. The dataset, scripts and models are available at https://github.com/engbiopct/TextMiningAMR.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

Information Retrieval and Text Mining Technologies for Chemistry

Efficient access to chemical information contained in scientific literature, patents, technical reports, or the web is a pressing need shared by researchers and patent attorneys from different chemical disciplines. Retrieval of important chemical information in most cases starts with finding relevant documents for a particular chemical compound or family. Targeted retrieval of chemical documents is closely connected to the automatic recognition of chemical entities in the text, which commonly involves the extraction of the entire list of chemicals mentioned in a document, including any associated information. In this Review, we provide a comprehensive and in-depth description of fundamental concepts, technical implementations, and current technologies for meeting these information demands. A strong focus is placed on community challenges addressing systems performance, more particularly CHEMDNER and CHEMDNER patents tasks of BioCreative IV and V, respectively. Considering the growing interest in the construction of automatically annotated chemical knowledge bases that integrate chemical information and biological data, cheminformatics approaches for mapping the extracted chemical names into chemical structures and their subsequent annotation together with text mining applications for linking chemistry with biological information are also presented. Finally, future trends and current challenges are highlighted as a roadmap proposal for research in this emerging field.

Networks of neuroinjury semantic predications to identify biomarkers for mild traumatic brain injury

Objective

Mild traumatic brain injury (mTBI) has high prevalence in the military, among athletes, and in the general population worldwide (largely due to falls). Consequences can include a range of neuropsychological disorders. Unfortunately, such neural injury often goes undiagnosed due to the difficulty in identifying symptoms, so the discovery of an effective biomarker would greatly assist diagnosis; however, no single biomarker has been identified. We identify several body substances as potential components of a panel of biomarkers to support the diagnosis of mild traumatic brain injury.

Methods

Our approach to diagnostic biomarker discovery combines ideas and techniques from systems medicine, natural language processing, and graph theory. We create a molecular interaction network that represents neural injury and is composed of relationships automatically extracted from the literature. We retrieve citations related to neurological injury and extract relationships (semantic predications) that contain potential biomarkers. After linking all relationships together to create a network representing neural injury, we filter the network by relationship frequency and concept connectivity to reduce the set to a manageable size of higher interest substances.

Results

99,437 relevant citations yielded 26,441 unique relations. 18,085 of these contained a potential biomarker as subject or object with a total of 6246 unique concepts. After filtering by graph metrics, the set was reduced to 1021 relationships with 49 unique concepts, including 17 potential biomarkers.

Conclusion

We created a network of relationships containing substances derived from 99,437 citations and filtered using graph metrics to provide a set of 17 potential biomarkers. We discuss the interaction of several of these (glutamate, glucose, and lactate) as the basis for more effective diagnosis than is currently possible. This method provides an opportunity to focus the effort of wet bench research on those substances with the highest potential as biomarkers for mTBI.

Generation of silver standard concept annotations from biomedical texts with special relevance to phenotypes

Electronic health records and scientific articles possess differing linguistic characteristics that may impact the performance of natural language processing tools developed for one or the other. In this paper, we investigate the performance of four extant concept recognition tools: the clinical Text Analysis and Knowledge Extraction System (cTAKES), the National Center for Biomedical Ontology (NCBO) Annotator, the Biomedical Concept Annotation System (BeCAS) and MetaMap. Each of the four concept recognition systems is applied to four different corpora: the i2b2 corpus of clinical documents, a PubMed corpus of Medline abstracts, a clinical trails corpus and the ShARe/CLEF corpus. In addition, we assess the individual system performances with respect to one gold standard annotation set, available for the ShARe/CLEF corpus. Furthermore, we built a silver standard annotation set from the individual systems’ output and assess the quality as well as the contribution of individual systems to the quality of the silver standard. Our results demonstrate that mainly the NCBO annotator and cTAKES contribute to the silver standard corpora (F1-measures in the range of 21% to 74%) and their quality (best F1-measure of 33%), independent from the type of text investigated. While BeCAS and MetaMap can contribute to the precision of silver standard annotations (precision of up to 42%), the F1-measure drops when combined with NCBO Annotator and cTAKES due to a low recall. In conclusion, the performances of individual systems need to be improved independently from the text types, and the leveraging strategies to best take advantage of individual systems’ annotations need to be revised. The textual content of the PubMed corpus, accession numbers for the clinical trials corpus, and assigned annotations of the four concept recognition systems as well as the generated silver standard annotation sets are available from http://purl.org/phenotype/resources. The textual content of the ShARe/CLEF (https://sites.google.com/site/shareclefehealth/data) and i2b2 (https://i2b2.org/NLP/DataSets/) corpora needs to be requested with the individual corpus providers.

Evaluating gold standard corpora against gene/protein tagging solutions and lexical resources

Motivation

The identification of protein and gene names (PGNs) from the scientific literature requires semantic resources: Terminological and lexical resources deliver the term candidates into PGN tagging solutions and the gold standard corpora (GSC) train them to identify term parameters and contextual features. Ideally all three resources, i.e. corpora, lexica and taggers, cover the same domain knowledge, and thus support identification of the same types of PGNs and cover all of them. Unfortunately, none of the three serves as a predominant standard and for this reason it is worth exploring, how these three resources comply with each other. We systematically compare different PGN taggers against publicly available corpora and analyze the impact of the included lexical resource in their performance. In particular, we determine the performance gains through false positive filtering, which contributes to the disambiguation of identified PGNs.

Results

In general, machine learning approaches (ML-Tag) for PGN tagging show higher F1-measure performance against the BioCreative-II and Jnlpba GSCs (exact matching), whereas the lexicon based approaches (LexTag) in combination with disambiguation methods show better results on FsuPrge and PennBio. The ML-Tag solutions balance precision and recall, whereas the LexTag solutions have different precision and recall profiles at the same F1-measure across all corpora. Higher recall is achieved with larger lexical resources, which also introduce more noise (false positive results). The ML-Tag solutions certainly perform best, if the test corpus is from the same GSC as the training corpus. As expected, the false negative errors characterize the test corpora and – on the other hand – the profiles of the false positive mistakes characterize the tagging solutions. Lex-Tag solutions that are based on a large terminological resource in combination with false positive filtering produce better results, which, in addition, provide concept identifiers from a knowledge source in contrast to ML-Tag solutions.

Conclusion

The standard ML-Tag solutions achieve high performance, but not across all corpora, and thus should be trained using several different corpora to reduce possible biases. The LexTag solutions have different profiles for their precision and recall performance, but with similar F1-measure. This result is surprising and suggests that they cover a portion of the most common naming standards, but cope differently with the term variability across the corpora. The false positive filtering applied to LexTag solutions does improve the results by increasing their precision without compromising significantly their recall. The harmonisation of the annotation schemes in combination with standardized lexical resources in the tagging solutions will enable their comparability and will pave the way for a shared standard.

GeneRIF indexing: sentence selection based on machine learning

BACKGROUND

A Gene Reference Into Function (GeneRIF) describes novel functionality of genes. GeneRIFs are available from the National Center for Biotechnology Information (NCBI) Gene database. GeneRIF indexing is performed manually, and the intention of our work is to provide methods to support creating the GeneRIF entries. The creation of GeneRIF entries involves the identification of the genes mentioned in MEDLINE®; citations and the sentences describing a novel function.

RESULTS

We have compared several learning algorithms and several features extracted or derived from MEDLINE sentences to determine if a sentence should be selected for GeneRIF indexing. Features are derived from the sentences or using mechanisms to augment the information provided by them: assigning a discourse label using a previously trained model, for example. We show that machine learning approaches with specific feature combinations achieve results close to one of the annotators. We have evaluated different feature sets and learning algorithms. In particular, Naïve Bayes achieves better performance with a selection of features similar to one used in related work, which considers the location of the sentence, the discourse of the sentence and the functional terminology in it.

CONCLUSIONS

The current performance is at a level similar to human annotation and it shows that machine learning can be used to automate the task of sentence selection for GeneRIF annotation. The current experiments are limited to the human species. We would like to see how the methodology can be extended to other species, specifically the normalization of gene mentions in other species.