Biological events such as gene expression, regulation, phosphorylation, localization and protein catabolism play important roles in the development of diseases. Understanding the association between diseases and genes can be enhanced with the identification of involved biological events in this association. Although biological knowledge has been accumulated in several databases and can be accessed through the Web, there is no specialized Web tool yet allowing for a query into the relationship among diseases, genes and biological events. For this task, we developed DigSee to search MEDLINE abstracts for evidence sentences describing that ‘genes’ are involved in the development of ‘cancer’ through ‘biological events’. DigSee is available through http://gcancer.org/digsee.

Identification of AD (Alzheimer’s disease)-related genes obtained from blood samples is crucial for early AD diagnosis. We used three public datasets, ADNI, AddNeuroMed1 (ANM1), and ANM2, for this study. Five feature selection methods and five classifiers were used to curate AD-related genes and discriminate AD patients, respectively. In the internal validation (five-fold cross-validation within each dataset), the best average values of the area under the curve (AUC) were 0.657, 0.874, and 0.804 for ADNI, ANMI, and ANM2, respectively. In the external validation (training and test sets from different datasets), the best AUCs were 0.697 (training: ADNI to testing: ANM1), 0.764 (ADNI to ANM2), 0.619 (ANM1 to ADNI), 0.79 (ANM1 to ANM2), 0.655 (ANM2 to ADNI), and 0.859 (ANM2 to ANM1), respectively. These results suggest that although the classification performance of ADNI is relatively lower than that of ANM1 and ANM2, classifiers trained using blood gene expression can be used to classify AD for other data sets. In addition, pathway analysis showed that AD-related genes were enriched with inflammation, mitochondria, and Wnt signaling pathways. Our study suggests that blood gene expression data are useful in predicting the AD classification.

Background: In biomedical text mining, named entity recognition (NER) is an important task used to extract information from biomedical articles. Previously proposed methods for NER are dictionary- or rule-based methods and machine learning approaches. However, these traditional approaches are heavily reliant on large-scale dictionaries, target-specific rules, or well-constructed corpora. These methods to NER have been superseded by the deep learning-based approach that is independent of hand-crafted features. However, although such methods of NER employ additional conditional random fields (CRF) to capture important correlations between neighboring labels, they often do not incorporate all the contextual information from text into the deep learning layers. Results: We propose herein an NER system for biomedical entities by incorporating n-grams with bi-directional long short-term memory (BiLSTM) and CRF; this system is referred to as a contextual long short-term memory networks with CRF (CLSTM). We assess the CLSTM model on three corpora: the disease corpus of the National Center for Biotechnology Information (NCBI), the BioCreative II Gene Mention corpus (GM), and the BioCreative V Chemical Disease Relation corpus (CDR). Our framework was compared with several deep learning approaches, such as BiLSTM, BiLSTM with CRF, GRAM-CNN, and BERT. On the NCBI corpus, our model recorded an F-score of 85.68% for the NER of diseases, showing an improvement of 1.50% over previous methods. Moreover, although BERT used transfer learning by incorporating more than 2.5 billion words, our system showed similar performance with BERT with an F-scores of 81.44% for gene NER on the GM corpus and a outperformed F-score of 86.44% for the NER of chemicals and diseases on the CDR corpus. We conclude that our method significantly improves performance on biomedical NER tasks. Conclusion: The proposed approach is robust in recognizing biological entities in text.

Accurate diagnostic classification and biological interpretation are important in biology and medicine, which are data-rich sciences. Thus, integration of different data types is necessary for the high predictive accuracy of clinical phenotypes, and more comprehensive analyses for predicting the prognosis of complex diseases are required. Here, we propose a novel multi-task attention learning algorithm for multi-omics data, termed MOMA, which captures important biological processes for high diagnostic performance and interpretability. MOMA vectorizes features and modules using a geometric approach and focuses on important modules in multi-omics data via an attention mechanism. Experiments using public data on Alzheimer’s disease and cancer with various classification tasks demonstrated the superior performance of this approach. The utility of MOMA was also verified using a comparison experiment with an attention mechanism that was turned on or off and biological analysis. The source codes are available at https://github.com/dmcb-gist/MOMA. Supplementary materials are available at Bioinformatics online.

Background: Laser therapy has been proposed as a physical therapy for musculoskeletal disorders and has attained popularity because no side effects have been reported after treatment. However, its true effectiveness is still controversial because several clinical trials have reported the ineffectiveness of lasers in treating pain. Methods: In this systematic review, we investigate the clinical effectiveness of low-level laser therapy (LLLT) on joint pain. Clinical trials on joint pain satisfying the following conditions are included: the laser is irradiated on the joint area, the PEDro scale score is at least 5, and the effectiveness of the trial is measured using a visual analogue scale (VAS). To estimate the overall effectiveness of all included clinical trials, a mean weighted difference in change of pain on VAS was used. Results: MEDLINE is the main source of the literature search. After the literature search, 22 trials related to joint pain were selected. The average methodological quality score of the 22 trials consisting of 1014 patients was 7.96 on the PEDro scale; 11 trials reported positive effects and 11 trials reported negative effects. The mean weighted difference in change of pain on VAS was 13.96 mm (95% CI, 7.24–20.69) in favor of the active LLLT groups. When we only considered the clinical trials in which the energy dose was within the dose range suggested in the review by Bjordal et al. in 2003 and in World Association for Laser Therapy (WALT) dose recommendation, the mean effect sizes were 19.88 and 21.05 mm in favor of the true LLLT groups, respectively. Conclusions: The review shows that laser therapy on the joint reduces pain in patients. Moreover, when we restrict the energy doses of the laser therapy into the dose window suggested in the previous study, we can expect more reliable pain relief treatments.

In biomedical articles, a named entity recognition (NER) technique that identifies entity names from texts is an important element for extracting biological knowledge from articles. After NER is applied to articles, the next step is to normalize the identified names into standard concepts (i.e., disease names are mapped to the National Library of Medicine’s Medical Subject Headings disease terms). In biomedical articles, many entity normalization methods rely on domain-specific dictionaries for resolving synonyms and abbreviations. However, the dictionaries are not comprehensive except for some entities such as genes. In recent years, biomedical articles have accumulated rapidly, and neural network-based algorithms that incorporate a large amount of unlabeled data have shown considerable success in several natural language processing problems. In this study, we propose an approach for normalizing biological entities, such as disease names and plant names, by using word embeddings to represent semantic spaces. For diseases, training data from the National Center for Biotechnology Information (NCBI) disease corpus and unlabeled data from PubMed abstracts were used to construct word representations. For plants, a training corpus that we manually constructed and unlabeled PubMed abstracts were used to represent word vectors. We showed that the proposed approach performed better than the use of only the training corpus or only the unlabeled data and showed that the normalization accuracy was improved by using our model even when the dictionaries were not comprehensive. We obtained F-scores of 0.808 and 0.690 for normalizing the NCBI disease corpus and manually constructed plant corpus, respectively. We further evaluated our approach using a data set in the disease normalization task of the BioCreative V challenge. When only the disease corpus was used as a dictionary, our approach significantly outperformed the best system of the task. The proposed approach shows robust performance for normalizing biological entities. The manually constructed plant corpus and the proposed model are available at http://gcancer.org/plant and http://gcancer.org/normalization , respectively.