Anália Lourenço

Text mining for the biocuration workflow

Molecular biology has become heavily dependent on biological knowledge encoded in expert curated biological databases. As the volume of biological literature increases, biocurators need help in keeping up with the literature; (semi-) automated aids for biocuration would seem to be an ideal application for natural language processing and text mining. However, to date, there have been few documented successes for improving biocuration throughput using text mining. Our initial investigations took place for the workshop on ‘Text Mining for the BioCuration Workflow’ at the third International Biocuration Conference (Berlin, 2009). We interviewed biocurators to obtain workflows from eight biological databases. This initial study revealed high-level commonalities, including (i) selection of documents for curation; (ii) indexing of documents with biologically relevant entities (e.g. genes); and (iii) detailed curation of specific relations (e.g. interactions); however, the detailed workflows also showed many variabilities. Following the workshop, we conducted a survey of biocurators. The survey identified biocurator priorities, including the handling of full text indexed with biological entities and support for the identification and prioritization of documents for curation. It also indicated that two-thirds of the biocuration teams had experimented with text mining and almost half were using text mining at that time. Analysis of our interviews and survey provide a set of requirements for the integration of text mining into the biocuration workflow. These can guide the identification of common needs across curated databases and encourage joint experimentation involving biocurators, text mining developers and the larger biomedical research community.

Extraction of pharmacokinetic evidence of drug-drug interactions from the literature.

Drug-drug interaction (DDI) is a major cause of morbidity and mortality and a subject of intense scientific interest. Biomedical literature mining can aid DDI research by extracting evidence for large numbers of potential interactions from published literature and clinical databases. Though DDI is investigated in domains ranging in scale from intracellular biochemistry to human populations, literature mining has not been used to extract specific types of experimental evidence, which are reported differently for distinct experimental goals. We focus on pharmacokinetic evidence for DDI, essential for identifying causal mechanisms of putative interactions and as input for further pharmacological and pharmacoepidemiology investigations. We used manually curated corpora of PubMed abstracts and annotated sentences to evaluate the efficacy of literature mining on two tasks: first, identifying PubMed abstracts containing pharmacokinetic evidence of DDIs; second, extracting sentences containing such evidence from abstracts. We implemented a text mining pipeline and evaluated it using several linear classifiers and a variety of feature transforms. The most important textual features in the abstract and sentence classification tasks were analyzed. We also investigated the performance benefits of using features derived from PubMed metadata fields, various publicly available named entity recognizers, and pharmacokinetic dictionaries. Several classifiers performed very well in distinguishing relevant and irrelevant abstracts (reaching F1≈0.93, MCC≈0.74, iAUC≈0.99) and sentences (F1≈0.76, MCC≈0.65, iAUC≈0.83). We found that word bigram features were important for achieving optimal classifier performance and that features derived from Medical Subject Headings (MeSH) terms significantly improved abstract classification. We also found that some drug-related named entity recognition tools and dictionaries led to slight but significant improvements, especially in classification of evidence sentences. Based on our thorough analysis of classifiers and feature transforms and the high classification performance achieved, we demonstrate that literature mining can aid DDI discovery by supporting automatic extraction of specific types of experimental evidence.

Critical review on biofilm methods

Abstract Biofilms are widespread in nature and constitute an important strategy implemented by microorganisms to survive in sometimes harsh environmental conditions. They can be beneficial or have a negative impact particularly when formed in industrial settings or on medical devices. As such, research into the formation and elimination of biofilms is important for many disciplines. Several new methodologies have been recently developed for, or adapted to, biofilm studies that have contributed to deeper knowledge on biofilm physiology, structure and composition. In this review, traditional and cutting-edge methods to study biofilm biomass, viability, structure, composition and physiology are addressed. Moreover, as there is a lack of consensus among the diversity of techniques used to grow and study biofilms. This review intends to remedy this, by giving a critical perspective, highlighting the advantages and limitations of several methods. Accordingly, this review aims at helping scientists in finding the most appropriate and up-to-date methods to study their biofilms.

New trends in peptide-based anti-biofilm strategies: a review of recent achievements and bioinformatic approaches

Antimicrobial peptides (AMPs) have a broad spectrum of activity and unspecific mechanisms of action. Therefore, they are seen as valid alternatives to overcome clinically relevant biofilms and reduce the chance of acquired resistance. This paper reviews AMPs and anti-biofilm AMP-based strategies and discusses ongoing and future work. Recent studies report successful AMP-based prophylactic and therapeutic strategies, several databases catalogue AMP information and analysis tools, and novel bioinformatics tools are supporting AMP discovery and design. However, most AMP studies are performed with planktonic cultures, and most studies on sessile cells test AMPs on growing rather than mature biofilms. Promising preliminary synergistic studies have to be consubstantiated and the study of functionalized coatings with AMPs must be further explored. Standardized operating protocols, to enforce the repeatability and reproducibility of AMP anti-biofilm tests, and automated means of screening and processing the ever-expanding literature are still missing.

Catching web crawlers in the act

This paper recommends a new approach to the detection and containment of Web crawler traverses based on clickstream data mining. Timely detection prevents crawler abusive consumption of Web server resources and eventual site contents privacy or copyrights violation. Clickstream data differentiation ensures focused usage analysis, valuable both for regular users and crawler profiling. Our platform, named ClickTips, sustains a site-specific, updatable detection model that tags Web crawler traverses based on incremental Web session inspection and a decision model that assesses eventual containment. The goal is to deliver a model flexible enough to keep up with crawling continuous evolving and that is capable of detecting crawler presence as soon as possible. We use a real-world Web site case study as a support for process description, as well as, to evaluate the accuracy of the obtained classification models and their ability for discovering previously unknown Web crawlers.

BioDR: Semantic indexing networks for biomedical document retrieval

In Biomedical research, retrieving documents that match an interesting query is a task performed quite frequently. Typically, the set of obtained results is extensive containing many non-interesting documents and consists in a flat list, i.e., not organized or indexed in any way. This work proposes BioDR, a novel approach that allows the semantic indexing of the results of a query, by identifying relevant terms in the documents. These terms emerge from a process of Named Entity Recognition that annotates occurrences of biological terms (e.g. genes or proteins) in abstracts or full-texts. The system is based on a learning process that builds an Enhanced Instance Retrieval Network (EIRN) from a set of manually classified documents, regarding their relevance to a given problem. The resulting EIRN implements the semantic indexing of documents and terms, allowing for enhanced navigation and visualization tools, as well as the assessment of relevance for new documents.

Minimum information about a biofilm experiment ( MIABiE): standards for reporting experiments and data on sessile microbial communities living at interfaces

The minimum information about a biofilm experiment (MIABiE) initiative has arisen from the need to find an adequate and scientifically sound way to control the quality of the documentation accompanying the public deposition of biofilm-related data, particularly those obtained using high-throughput devices and techniques. Thereby, the MIABiE consortium has initiated the identification and organization of a set of modules containing the minimum information that needs to be reported to guarantee the interpretability and independent verification of experimental results and their integration with knowledge coming from other fields. MIABiE does not intend to propose specific standards on how biofilms experiments should be performed, because it is acknowledged that specific research questions require specific conditions which may deviate from any standardization. Instead, MIABiE presents guidelines about the data to be recorded and published in order for the procedure and results to be easily and unequivocally interpreted and reproduced. Overall, MIABiE opens up the discussion about a number of particular areas of interest and attempts to achieve a broad consensus about which biofilm data and metadata should be reported in scientific journals in a systematic, rigorous and understandable manner.

BiofOmics: a Web platform for the systematic and standardized collection of high-throughput biofilm data.

Background Consortia of microorganisms, commonly known as biofilms, are attracting much attention from the scientific community due to their impact in human activity. As biofilm research grows to be a data-intensive discipline, the need for suitable bioinformatics approaches becomes compelling to manage and validate individual experiments, and also execute inter-laboratory large-scale comparisons. However, biofilm data is widespread across ad hoc, non-standardized individual files and, thus, data interchange among researchers, or any attempt of cross-laboratory experimentation or analysis, is hardly possible or even attempted. Methodology/Principal Findings This paper presents BiofOmics, the first publicly accessible Web platform specialized in the management and analysis of data derived from biofilm high-throughput studies. The aim is to promote data interchange across laboratories, implementing collaborative experiments, and enable the development of bioinformatics tools in support of the processing and analysis of the increasing volumes of experimental biofilm data that are being generated. BiofOmics’ data deposition facility enforces data structuring and standardization, supported by controlled vocabulary. Researchers are responsible for the description of the experiments, their results and conclusions. BiofOmics’ curators interact with submitters only to enforce data structuring and the use of controlled vocabulary. Then, BiofOmics’ search facility makes publicly available the profile and data associated with a submitted study so that any researcher can profit from these standardization efforts to compare similar studies, generate new hypotheses to be tested or even extend the conditions experimented in the study. Significance BiofOmics’ novelty lies in its support to standardized data deposition, the availability of computerizable data files and the free-of-charge dissemination of biofilm studies across the community. Hopefully, this will open promising research possibilities, namely the comparison of results between different laboratories, the reproducibility of methods within and between laboratories, and the development of guidelines and standardized protocols for biofilm formation operating procedures and analytical methods.

Web scraping technologies in an API world

Web services are the de facto standard in biomedical data integration. However, there are data integration scenarios that cannot be fully covered by Web services. A number of Web databases and tools do not support Web services, and existing Web services do not cover for all possible user data demands. As a consequence, Web data scraping, one of the oldest techniques for extracting Web contents, is still in position to offer a valid and valuable service to a wide range of bioinformatics applications, ranging from simple extraction robots to online meta-servers. This article reviews existing scraping frameworks and tools, identifying their strengths and limitations in terms of extraction capabilities. The main focus is set on showing how straightforward it is today to set up a data scraping pipeline, with minimal programming effort, and answer a number of practical needs. For exemplification purposes, we introduce a biomedical data extraction scenario where the desired data sources, well-known in clinical microbiology and similar domains, do not offer programmatic interfaces yet. Moreover, we describe the operation of WhichGenes and PathJam, two bioinformatics meta-servers that use scraping as means to cope with gene set enrichment analysis.

From amino acid sequence to bioactivity: the biomedical potential of antitumor peptides

Chemoprevention is the use of natural and/or synthetic substances to block, reverse, or retard the process of carcinogenesis. In this field, the use of antitumor peptides is of interest as, (i) these molecules are small in size, (ii) they show good cell diffusion and permeability, (iii) they affect one or more specific molecular pathways involved in carcinogenesis, and (iv) they are not usually genotoxic. We have checked the Web of Science Database (23/11/2015) in order to collect papers reporting on bioactive peptide (1691 registers), which was further filtered searching terms such as “antiproliferative,” “antitumoral,” or “apoptosis” among others. Works reporting the amino acid sequence of an antiproliferative peptide were kept (60 registers), and this was complemented with the peptides included in CancerPPD, an extensive resource for antiproliferative peptides and proteins. Peptides were grouped according to one of the following mechanism of action: inhibition of cell migration, inhibition of tumor angiogenesis, antioxidative mechanisms, inhibition of gene transcription/cell proliferation, induction of apoptosis, disorganization of tubulin structure, cytotoxicity, or unknown mechanisms. The main mechanisms of action of those antiproliferative peptides with known amino acid sequences are presented and finally, their potential clinical usefulness and future challenges on their application is discussed.