Effects of the low-speed continuous infusion catheter technique on double-lumen central venous catheters: A randomized controlled trial.

BACKGROUND: Central venous catheters are widely used in clinical practice, and the incidence of central venous catheter occlusion is between 25 % and 38 %. The turbulence caused by the pulsatile flushing technique is harmful to the vascular endothelium and may lead to phlebitis. The low-speed continuous infusion catheter technique is a new type of continuous infusion that ensures that the catheter is always in a keep-vein-open state by continuous low-speed flushing; hence, avoiding the problem of catheter occlusion. OBJECTIVE: To investigate the effectiveness of the low-speed continuous infusion catheter technique and the routine care of double-lumen central venous catheters. DESIGN: This was a prospective, randomized, controlled, open-label trial. SETTING: Patients were recruited from 14 medical institutions in China between February and June 2023. PARTICIPANTS: In total, 251 patients were recruited, with 125 in the intervention group and 126 in the control group. METHODS: Patients who used double-lumen central venous catheters for infusion treatment were selected, and those who met the sampling criteria were randomly divided into intervention and control groups using the random envelope method. The intervention group used the low-speed continuous infusion catheter technique to maintain catheter patency, whereas the control group used routine care with a trial period of 7 days. The primary outcome was the occlusion rate. The secondary outcomes included nursing satisfaction and complication rates of the two groups. RESULTS: After 7 days, the rate of catheter occlusion was 28.0 % (35/125, 95 % confidence interval (CI):0.203, 0.367) in the intervention group and 53.97 % (68/126, 95 % CI: 0.449-0.629) in the control group, with a statistically significant difference (χ2 = 17.488, p < 0.001); at 3 days of intervention, the rate of catheter blockage was 8.0 % (10/125, 95 % CI: 0.039-0.142) in the intervention group and 23.8 % (30/126, 0.167-0.322) in the control group, with a statistically significant difference (χ2 = 11.707, p < 0.001). Nurse satisfaction was significantly higher in the intervention group (115/125, 92.0 %, 95 % CI: 0.858-0.961) than in the control group (104/126, 82.54 %, 95 % CI: 0.748-0.887) (χ2 = 5.049, p = 0.025). There were no statistically significant complication rates in either group (p = 0.622). CONCLUSION: The low-speed continuous infusion catheter technique helps maintain catheter patency, improves nurse satisfaction, and provides a high level of safety. REGISTRATION: Chinese Clinical Trial Registry (ChiCTR2200064007, www.chictr.org.cn). The first recruitment was conducted in February. https://www.chictr.org.cn/showproj.html?proj=177311.

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation.

Radiology report generation (RRG) has gained increasing research attention because of its huge potential to mitigate medical resource shortages and aid the process of disease decision making by radiologists. Recent advancements in Radiology Report Generation (RRG) are largely driven by improving a model's capabilities in encoding single-modal feature representations, while few studies explicitly explore the cross-modal alignment between image regions and words. Radiologists typically focus first on abnormal image regions before composing the corresponding text descriptions, thus cross-modal alignment is of great importance to learn a RRG model which is aware of abnormalities in the image. Motivated by this, we propose a Class Activation Map guided Attention Network (CAMANet) which explicitly promotes cross-modal alignment by employing aggregated class activation maps to supervise cross-modal attention learning, and simultaneously enrich the discriminative information. Experimental results demonstrate that CAMANet outperforms previous SOTA methods on two commonly used RRG benchmarks.

Non-adherent culture method affects the proliferation and apoptosis of mesenchymal stem cells through inhibiting LINC00707 to promote RNF6-mediated QKI ubiquitination.

Exploration of the molecular mechanisms of mesenchymal stem cell (MSC) growth has significant clinical benefits. Long non-coding RNAs (lncRNAs) have been reported to play vital roles in the regulation of the osteogenic differentiation of MSCs. However, the mechanism by which lncRNA affects the proliferation and apoptosis of MSCs is unclear. In this study, sequencing analysis revealed that LINC00707 was significantly decreased in non-adherent human MSCs (non-AC-hMSCs) compared to adherent human MSCs. Moreover, LINC00707 overexpression promoted non-AChMSC proliferation, cell cycle progression from the G0/G1 phase to the S phase and inhibited apoptosis, whereas LINC00707 silencing had the opposite effect. Furthermore, LINC00707 interacted directly with the quaking (QKI) protein and enhanced the E3 ubiquitin-protein ligase ring finger protein 6 (RNF6)-mediated ubiquitination of the QKI protein. Additionally, the overexpression of QKI rescued the promotive effects on proliferation and inhibitory effects on apoptosis in non-AC-hMSCs induced by the ectopic expression of LINC00707. Thus, LINC00707 contributes to the proliferation and apoptosis in non-AChMSCs by regulating the ubiquitination and degradation of the QKI protein.

Genome-wide SNPs reveal novel patterns of spatial genetic structure in Aedes albopictus (Diptera Culicidae) population in China.

Introduction: Since the second half of the 20th century, Aedes albopictus, a vector for more than 20 arboviruses, has spread worldwide. Aedes albopictus is the main vector of infectious diseases transmitted by Aedes mosquitoes in China, and it has caused concerns regarding public health. A comprehensive understanding of the spatial genetic structure of this vector species at a genomic level is essential for effective vector control and the prevention of vector-borne diseases. Methods: During 2016-2018, adult female Ae. albopictus mosquitoes were collected from eight different geographical locations across China. Restriction site-associated DNA sequencing (RAD-seq) was used for high-throughput identification of single nucleotide polymorphisms (SNPs) and genotyping of the Ae. albopictus population. The spatial genetic structure was analyzed and compared to those exhibited by mitochondrial cytochrome c oxidase subunit 1 (cox1) and microsatellites in the Ae. albopictus population. Results: A total of 9,103 genome-wide SNP loci in 101 specimens and 32 haplotypes of cox1 in 231 specimens were identified in the samples from eight locations in China. Principal component analysis revealed that samples from Lingshui and Zhanjiang were more genetically different than those from the other locations. The SNPs provided a better resolution and stronger signals for novel spatial population genetic structures than those from the cox1 data and a set of previously genotyped microsatellites. The fixation indexes from the SNP dataset showed shallow but significant genetic differentiation in the population. The Mantel test indicated a positive correlation between genetic distance and geographical distance. However, the asymmetric gene flow was detected among the populations, and it was higher from south to north and west to east than in the opposite directions. Conclusions: The genome-wide SNPs revealed seven gene pools and fine spatial genetic structure of the Ae. albopictus population in China. The RAD-seq approach has great potential to increase our understanding of the spatial dynamics of population spread and establishment, which will help us to design new strategies for controlling vectors and mosquito-borne diseases.

Effects of Guangzhou seasonal climate change on the development of Aedes albopictus and its susceptibility to DENV-2.

The susceptibility of Asian tiger mosquitoes to DENV-2 in different seasons was observed in simulated field environments as a reference to design dengue fever control strategies in Guangzhou. The life table experiments of mosquitoes in four seasons were carried out in the field. The susceptibility of Ae. albopictus to dengue virus was observed in both environments in Guangzhou in summer and winter. Ae. albopictus was infected with dengue virus by oral feeding. On day 7 and 14 after infection, the viral load in the head, ovary, and midgut of the mosquito was detected using real-time fluorescent quantitative PCR. Immune-associated gene expression in infected mosquitoes was performed using quantitative real-time reverse transcriptase PCR. The hatching rate and pupation rate of Ae. albopictus larvae in different seasons differed significantly. The winter hatching rate of larvae was lower than that in summer, and the incubation time was longer than in summer. In the winter field environment, Ae. albopictus still underwent basic growth and development processes. Mosquitoes in the simulated field environment were more susceptible to DENV-2 than those in the simulated laboratory environment. In the midgut, viral RNA levels on day 7 in summer were higher than those on day 7 in winter (F = 14.459, P = 0.01); ovarian viral RNA levels on day 7 in summer were higher than those on day 7 in winter (F = 8.656, P < 0.001), but there was no significant difference in the viral load at other time points (P > 0.05). Dicer-2 mRNA expression on day 7 in winter was 4.071 times than that on day 7 in summer: the viral load and Dicer-2 expression correlated moderately. Ae. albopictus could still develop and transmit dengue virus in winter in Guangzhou. Mosquitoes under simulated field conditions were more susceptible to DENV-2 than those under simulated laboratory conditions.

Understanding patient reviews with minimum supervision.

Understanding patient opinions expressed towards healthcare services in online platforms could allow healthcare professionals to respond to address patients' concerns in a timely manner. Extracting patient opinion towards various aspects of health services is closely related to aspect-based sentiment analysis (ABSA) in which we need to identify both opinion targets and target-specific opinion expressions. The lack of aspect-level annotations however makes it difficult to build such an ABSA system. This paper proposes a joint learning framework for simultaneous unsupervised aspect extraction at the sentence level and supervised sentiment classification at the document level. It achieves 98.2% sentiment classification accuracy when tested on the reviews about healthcare services collected from Yelp, outperforming several strong baselines. Moreover, our model can extract coherent aspects and can automatically infer the distribution of aspects under different polarities without requiring aspect-level annotations for model learning.

Semi-field life-table studies of Aedes albopictus (Diptera: Culicidae) in Guangzhou, China.

BACKGROUND: Aedes albopictus is a major vector for several tropical infectious diseases. Characterization of Ae. albopictus development under natural conditions is crucial for monitoring vector population expansion, dengue virus transmission, and disease outbreak preparedness. METHODS: This study employed mosquito traits as a proxy to understanding life-table traits in mosquitoes using a semi-field study. Ae. albopictus larval and adult life-table experiments were conducted using microcosms under semi-field conditions in Guangzhou. Stage-specific development times and survivorship rates were determined and compared under semi-field conditions in different seasons from early summer (June) to winter (January), to determine the lower temperature limit for larval development and adult survivorship and reproductivity. RESULTS: The average egg- hatching rate was 60.1%, with the highest recorded in October (77.1%; mid-autumn). The larval development time was on average 13.2 days (range, 8.5-24.1 days), with the shortest time observed in September(8.7 days; early autumn) and longest in November (22.8 days). The pupation rates of Ae. albopictus larvae were on average 88.9% (range, 81.6-93.4%); they were stable from June to September but decreased from October to November. The adult emergence rates were on average 82.5% (range, 76.8-87.9%) and decreased from July to November. The median survival time of Ae. albopictus adults was on average 7.4 (range, 4.5-9.8), with the shortest time recorded in September. The average lifetime egg mass under semi-field conditions was 37.84 eggs/female. The larvae could develop into adults at temperatures as low as 12.3°C, and the adults could survive for 30.0 days at 16.3°C and still produce eggs. Overall, correlation analysis found that mean temperature and relative humidity were variables significantly affecting larval development and adult survivorship. CONCLUSION: Ae. albopictus larvae could develop and emerge and the adults could survive and produce eggs in early winter in Guangzhou. The major impact of changes in ambient temperature, relative humidity, and light intensity was on the egg hatching rates, adult survival time, and egg mass production, rather than on pupation or adult emergence rates.

Research progress in RNA interference against the infection of mosquito-borne viruses.

Mosquito-borne diseases have become an important public health issue of global concern because of their high incidence and transmission rate. As a vector for mosquito-borne diseases, studying the interaction mechanism between mosquitoes and mosquito-borne viruses will help control mosquito-borne diseases. The impaired innate immunity and immune barriers evasion caused by mosquito-borne viruses in mosquitoes pose a potential risk for the persistent infection of the virus in mosquitoes and the outbreak of mosquito-borne diseases. The RNA interference (RNAi) pathway, as a powerful antiviral defense barrier in mosquitoes, can inhibit viral replication and transmission by producing a variety of small RNAs to degrade viral RNA. In this review, we summarize the related studies on the innate immune mechanism against mosquito- borne virus infection in mosquitoes about small interfering RNA (siRNA), microRNA (miRNA), and Piwi-interacting RNA (piRNA), aiming to provide a theoretical reference for the prevention and control of mosquito-borne diseases.

Seasonality modeling of the distribution of Aedes albopictus in China based on climatic and environmental suitability.

BACKGROUND: Aedes albopictus is a highly invasive mosquito species and a major vector of numerous viral pathogens. Many recent dengue fever outbreaks in China have been caused solely by the vector. Mapping of the potential distribution ranges of Ae. albopictus is crucial for epidemic preparedness and the monitoring of vector populations for disease control. Climate is a key factor influencing the distribution of the species. Despite field studies indicating seasonal population variations, very little modeling work has been done to analyze how environmental conditions influence the seasonality of Ae. albopictus. The aim of the present study was to develop a model based on available observations, climatic and environmental data, and machine learning methods for the prediction of the potential seasonal ranges of Ae. albopictus in China. METHODS: We collected comprehensive up-to-date surveillance data in China, particularly records from the northern distribution margin of Ae. albopictus. All records were assigned long-term (1970-2000) climatic data averages based on the WorldClim 2.0 data set. Machine learning regression tree models were developed using a 10-fold cross-validation method to predict the potential seasonal (or monthly) distribution ranges of Ae. albopictus in China at high resolution based on environmental conditions. The models were assessed based on sensitivity, specificity, and accuracy, using area under curve (AUC). WorldClim 2.0 and climatic and environmental data were used to produce environmental conduciveness (probability) prediction surfaces. Predicted probabilities were generated based on the averages of the 10 models. RESULTS: During 1998-2017, Ae. albopictus was observed at 200 out of the 242 localities surveyed. In addition, at least 15 new Ae. albopictus occurrence sites lay outside the potential ranges that have been predicted using models previously. The average accuracy was 98.4% (97.1-99.5%), and the average AUC was 99.1% (95.6-99.9%). The predicted Ae. albopictus distribution in winter (December-February) was limited to a small subtropical-tropical area of China, and Ae. albopictus was predicted to occur in northern China only during the short summer season (usually June-September). The predicted distribution areas in summer could reach northeastern China bordering Russia and the eastern part of the Qinghai-Tibet Plateau in southwestern China. Ae. albopictus could remain active in expansive areas from central to southern China in October and November. CONCLUSIONS: Climate and environmental conditions are key factors influencing the seasonal distribution of Ae. albopictus in China. The areas predicted to potentially host Ae. albopictus seasonally in the present study could reach northeastern China and the eastern slope of the Qinghai-Tibet Plateau. Our results present new evidence and suggest the expansion of systematic vector population monitoring activities and regular re-assessment of epidemic risk potential.

Patterns of spatial genetic structures in Aedes albopictus (Diptera: Culicidae) populations in China.

BACKGROUND: The Asian tiger mosquito, Aedes albopictus, is one of the 100 worst invasive species in the world and the vector for several arboviruses including dengue, Zika and chikungunya viruses. Understanding the population spatial genetic structure, migration, and gene flow of vector species is critical to effectively preventing and controlling vector-borne diseases. Little is known about the population structure and genetic differentiation of native Ae. albopictus in China. The aim of this study was to examine the patterns of the spatial genetic structures of native Ae. albopictus populations, and their relationship to dengue incidence, on a large geographical scale. METHODS: During 2016-2018, adult female Ae. albopictus mosquitoes were collected by human landing catch (HLC) or human-bait sweep-net collections in 34 localities across China. Thirteen microsatellite markers were used to examine the patterns of genetic diversity, population structure, and gene flow among native Ae. albopictus populations. The correlation between population genetic indices and dengue incidence was also examined. RESULTS: A total of 153 distinct alleles were identified at the 13 microsatellite loci in the tested populations. All loci were polymorphic, with the number of distinct alleles ranging from eight to sixteen. Genetic parameters such as PIC, heterozygosity, allelic richness and fixation index (FST) revealed highly polymorphic markers, high genetic diversity, and low population genetic differentiation. In addition, Bayesian analysis of population structure showed two distinct genetic groups in southern-western and eastern-central-northern China. The Mantel test indicated a positive correlation between genetic distance and geographical distance (R2 = 0.245, P = 0.01). STRUCTURE analysis, PCoA and GLS interpolation analysis indicated that Ae. albopictus populations in China were regionally clustered. Gene flow and relatedness estimates were generally high between populations. We observed no correlation between population genetic indices of microsatellite loci in Ae. albopictus populations and dengue incidence. CONCLUSION: Strong gene flow probably assisted by human activities inhibited population differentiation and promoted genetic diversity among populations of Ae. albopictus. This may represent a potential risk of rapid spread of mosquito-borne diseases. The spatial genetic structure, coupled with the association between genetic indices and dengue incidence, may have important implications for understanding the epidemiology, prevention, and control of vector-borne diseases.

Position-aware deep multi-task learning for drug-drug interaction extraction.

OBJECTIVE: A drug-drug interaction (DDI) is a situation in which a drug affects the activity of another drug synergistically or antagonistically when being administered together. The information of DDIs is crucial for healthcare professionals to prevent adverse drug events. Although some known DDIs can be found in purposely-built databases such as DrugBank, most information is still buried in scientific publications. Therefore, automatically extracting DDIs from biomedical texts is sorely needed. METHODS AND MATERIAL: In this paper, we propose a novel position-aware deep multi-task learning approach for extracting DDIs from biomedical texts. In particular, sentences are represented as a sequence of word embeddings and position embeddings. An attention-based bidirectional long short-term memory (BiLSTM) network is used to encode each sentence. The relative position information of words with the target drugs in text is combined with the hidden states of BiLSTM to generate the position-aware attention weights. Moreover, the tasks of predicting whether or not two drugs interact with each other and further distinguishing the types of interactions are learned jointly in multi-task learning framework. RESULTS: The proposed approach has been evaluated on the DDIExtraction challenge 2013 corpus and the results show that with the position-aware attention only, our proposed approach outperforms the state-of-the-art method by 0.99% for binary DDI classification, and with both position-aware attention and multi-task learning, our approach achieves a micro F-score of 72.99% on interaction type identification, outperforming the state-of-the-art approach by 1.51%, which demonstrates the effectiveness of the proposed approach.

EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation.

BACKGROUND: Prediction of DNA-binding residue is important for understanding the protein-DNA recognition mechanism. Many computational methods have been proposed for the prediction, but most of them do not consider the relationships of evolutionary information between residues. RESULTS: In this paper, we first propose a novel residue encoding method, referred to as the Position Specific Score Matrix (PSSM) Relation Transformation (PSSM-RT), to encode residues by utilizing the relationships of evolutionary information between residues. PDNA-62 and PDNA-224 are used to evaluate PSSM-RT and two existing PSSM encoding methods by five-fold cross-validation. Performance evaluations indicate that PSSM-RT is more effective than previous methods. This validates the point that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction. An ensemble learning classifier (EL_PSSM-RT) is also proposed by combining ensemble learning model and PSSM-RT to better handle the imbalance between binding and non-binding residues in datasets. EL_PSSM-RT is evaluated by five-fold cross-validation using PDNA-62 and PDNA-224 as well as two independent datasets TS-72 and TS-61. Performance comparisons with existing predictors on the four datasets demonstrate that EL_PSSM-RT is the best-performing method among all the predicting methods with improvement between 0.02-0.07 for MCC, 4.18-21.47% for ST and 0.013-0.131 for AUC. Furthermore, we analyze the importance of the pair-relationships extracted by PSSM-RT and the results validates the usefulness of PSSM-RT for encoding DNA-binding residues. CONCLUSIONS: We propose a novel prediction method for the prediction of DNA-binding residue with the inclusion of relationship of evolutionary information and ensemble learning. Performance evaluation shows that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction and ensemble learning can be used to address the data imbalance issue between binding and non-binding residues. A web service of EL_PSSM-RT ( http://hlt.hitsz.edu.cn:8080/PSSM-RT_SVM/ ) is provided for free access to the biological research community.

Disease named entity recognition by combining conditional random fields and bidirectional recurrent neural networks.

The recognition of disease and chemical named entities in scientific articles is a very important subtask in information extraction in the biomedical domain. Due to the diversity and complexity of disease names, the recognition of named entities of diseases is rather tougher than those of chemical names. Although there are some remarkable chemical named entity recognition systems available online such as ChemSpot and tmChem, the publicly available recognition systems of disease named entities are rare. This article presents a system for disease named entity recognition (DNER) and normalization. First, two separate DNER models are developed. One is based on conditional random fields model with a rule-based post-processing module. The other one is based on the bidirectional recurrent neural networks. Then the named entities recognized by each of the DNER model are fed into a support vector machine classifier for combining results. Finally, each recognized disease named entity is normalized to a medical subject heading disease name by using a vector space model based method. Experimental results show that using 1000 PubMed abstracts for training, our proposed system achieves an F1-measure of 0.8428 at the mention level and 0.7804 at the concept level, respectively, on the testing data of the chemical-disease relation task in BioCreative V.Database URL: http://219.223.252.210:8080/SS/cdr.html.

PDNAsite: Identification of DNA-binding Site from Protein Sequence by Incorporating Spatial and Sequence Context.

Protein-DNA interactions are involved in many fundamental biological processes essential for cellular function. Most of the existing computational approaches employed only the sequence context of the target residue for its prediction. In the present study, for each target residue, we applied both the spatial context and the sequence context to construct the feature space. Subsequently, Latent Semantic Analysis (LSA) was applied to remove the redundancies in the feature space. Finally, a predictor (PDNAsite) was developed through the integration of the support vector machines (SVM) classifier and ensemble learning. Results on the PDNA-62 and the PDNA-224 datasets demonstrate that features extracted from spatial context provide more information than those from sequence context and the combination of them gives more performance gain. An analysis of the number of binding sites in the spatial context of the target site indicates that the interactions between binding sites next to each other are important for protein-DNA recognition and their binding ability. The comparison between our proposed PDNAsite method and the existing methods indicate that PDNAsite outperforms most of the existing methods and is a useful tool for DNA-binding site identification. A web-server of our predictor (http://hlt.hitsz.edu.cn:8080/PDNAsite/) is made available for free public accessible to the biological research community.

Identifying DNA-binding proteins by combining support vector machine and PSSM distance transformation.

BACKGROUND: DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. Identification of DNA-binding proteins is one of the major challenges in the field of genome annotation. There have been several computational methods proposed in the literature to deal with the DNA-binding protein identification. However, most of them can't provide an invaluable knowledge base for our understanding of DNA-protein interactions. RESULTS: We firstly presented a new protein sequence encoding method called PSSM Distance Transformation, and then constructed a DNA-binding protein identification method (SVM-PSSM-DT) by combining PSSM Distance Transformation with support vector machine (SVM). First, the PSSM profiles are generated by using the PSI-BLAST program to search the non-redundant (NR) database. Next, the PSSM profiles are transformed into uniform numeric representations appropriately by distance transformation scheme. Lastly, the resulting uniform numeric representations are inputted into a SVM classifier for prediction. Thus whether a sequence can bind to DNA or not can be determined. In benchmark test on 525 DNA-binding and 550 non DNA-binding proteins using jackknife validation, the present model achieved an ACC of 79.96%, MCC of 0.622 and AUC of 86.50%. This performance is considerably better than most of the existing state-of-the-art predictive methods. When tested on a recently constructed independent dataset PDB186, SVM-PSSM-DT also achieved the best performance with ACC of 80.00%, MCC of 0.647 and AUC of 87.40%, and outperformed some existing state-of-the-art methods. CONCLUSIONS: The experiment results demonstrate that PSSM Distance Transformation is an available protein sequence encoding method and SVM-PSSM-DT is a useful tool for identifying the DNA-binding proteins. A user-friendly web-server of SVM-PSSM-DT was constructed, which is freely accessible to the public at the web-site on http://bioinformatics.hitsz.edu.cn/PSSM-DT/.

Identification of DNA-binding proteins by incorporating evolutionary information into pseudo amino acid composition via the top-n-gram approach.

DNA-binding proteins are crucial for various cellular processes and hence have become an important target for both basic research and drug development. With the avalanche of protein sequences generated in the postgenomic age, it is highly desired to establish an automated method for rapidly and accurately identifying DNA-binding proteins based on their sequence information alone. Owing to the fact that all biological species have developed beginning from a very limited number of ancestral species, it is important to take into account the evolutionary information in developing such a high-throughput tool. In view of this, a new predictor was proposed by incorporating the evolutionary information into the general form of pseudo amino acid composition via the top-n-gram approach. It was observed by comparing the new predictor with the existing methods via both jackknife test and independent data-set test that the new predictor outperformed its counterparts. It is anticipated that the new predictor may become a useful vehicle for identifying DNA-binding proteins. It has not escaped our notice that the novel approach to extract evolutionary information into the formulation of statistical samples can be used to identify many other protein attributes as well.

Biomedical relation extraction: from binary to complex.

Biomedical relation extraction aims to uncover high-quality relations from life science literature with high accuracy and efficiency. Early biomedical relation extraction tasks focused on capturing binary relations, such as protein-protein interactions, which are crucial for virtually every process in a living cell. Information about these interactions provides the foundations for new therapeutic approaches. In recent years, more interests have been shifted to the extraction of complex relations such as biomolecular events. While complex relations go beyond binary relations and involve more than two arguments, they might also take another relation as an argument. In the paper, we conduct a thorough survey on the research in biomedical relation extraction. We first present a general framework for biomedical relation extraction and then discuss the approaches proposed for binary and complex relation extraction with focus on the latter since it is a much more difficult task compared to binary relation extraction. Finally, we discuss challenges that we are facing with complex relation extraction and outline possible solutions and future directions.

Semi-supervised learning of statistical models for natural language understanding.

Natural language understanding is to specify a computational model that maps sentences to their semantic mean representation. In this paper, we propose a novel framework to train the statistical models without using expensive fully annotated data. In particular, the input of our framework is a set of sentences labeled with abstract semantic annotations. These annotations encode the underlying embedded semantic structural relations without explicit word/semantic tag alignment. The proposed framework can automatically induce derivation rules that map sentences to their semantic meaning representations. The learning framework is applied on two statistical models, the conditional random fields (CRFs) and the hidden Markov support vector machines (HM-SVMs). Our experimental results on the DARPA communicator data show that both CRFs and HM-SVMs outperform the baseline approach, previously proposed hidden vector state (HVS) model which is also trained on abstract semantic annotations. In addition, the proposed framework shows superior performance than two other baseline approaches, a hybrid framework combining HVS and HM-SVMs and discriminative training of HVS, with a relative error reduction rate of about 25% and 15% being achieved in F-measure.

enDNA-Prot: identification of DNA-binding proteins by applying ensemble learning.

DNA-binding proteins are crucial for various cellular processes, such as recognition of specific nucleotide, regulation of transcription, and regulation of gene expression. Developing an effective model for identifying DNA-binding proteins is an urgent research problem. Up to now, many methods have been proposed, but most of them focus on only one classifier and cannot make full use of the large number of negative samples to improve predicting performance. This study proposed a predictor called enDNA-Prot for DNA-binding protein identification by employing the ensemble learning technique. Experiential results showed that enDNA-Prot was comparable with DNA-Prot and outperformed DNAbinder and iDNA-Prot with performance improvement in the range of 3.97-9.52% in ACC and 0.08-0.19 in MCC. Furthermore, when the benchmark dataset was expanded with negative samples, the performance of enDNA-Prot outperformed the three existing methods by 2.83-16.63% in terms of ACC and 0.02-0.16 in terms of MCC. It indicated that enDNA-Prot is an effective method for DNA-binding protein identification and expanding training dataset with negative samples can improve its performance. For the convenience of the vast majority of experimental scientists, we developed a user-friendly web-server for enDNA-Prot which is freely accessible to the public.

Event trigger identification for biomedical events extraction using domain knowledge.

MOTIVATION: In molecular biology, molecular events describe observable alterations of biomolecules, such as binding of proteins or RNA production. These events might be responsible for drug reactions or development of certain diseases. As such, biomedical event extraction, the process of automatically detecting description of molecular interactions in research articles, attracted substantial research interest recently. Event trigger identification, detecting the words describing the event types, is a crucial and prerequisite step in the pipeline process of biomedical event extraction. Taking the event types as classes, event trigger identification can be viewed as a classification task. For each word in a sentence, a trained classifier predicts whether the word corresponds to an event type and which event type based on the context features. Therefore, a well-designed feature set with a good level of discrimination and generalization is crucial for the performance of event trigger identification. RESULTS: In this article, we propose a novel framework for event trigger identification. In particular, we learn biomedical domain knowledge from a large text corpus built from Medline and embed it into word features using neural language modeling. The embedded features are then combined with the syntactic and semantic context features using the multiple kernel learning method. The combined feature set is used for training the event trigger classifier. Experimental results on the golden standard corpus show that >2.5% improvement on F-score is achieved by the proposed framework when compared with the state-of-the-art approach, demonstrating the effectiveness of the proposed framework.