Multichannel Convolutional Neural Network for Biological Relation Extraction

Quan, Chanqin; Hua, Lei; Sun, Xiao; Bai, Wenjun

doi:10.1155/2016/1850404

Cited by 120 publications

(96 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also show the performance of the existing models with negative instance filtering for reference. In the comparison without negative instance filtering, our model outperformed the existing CNN models Quan et al, 2016;Zhao et al, 2016). The model was competitive with Joint AB-LSTM model (Sahu and Anand, 2017) that was composed of multiple RNN models.…”

Section: Comparison With Existing Modelsmentioning

confidence: 84%

“…We mainly compare Methods P (%) R (%) F (%) No negative instance filtering CNN 75.29 60.37 67.01 MCCNN (Quan et al, 2016) --67.80 SCNN (Zhao et al, 2016) 68 (2015) --67.0 CNN 75.72 64.66 69.75 MCCNN (Quan et al, 2016) 75.99 65.25 70.21 SCNN (Zhao et al, 2016) 72.5 65.1 68.6 Joint AB-LSTM (Sahu and Anand, 2017) 73.41 69.66 71.48 Table 6: Comparison with existing models Comparison of attention mechanisms on CNN models with ranking objective function the performance without negative instance filtering, which omits some apparent negative instance pairs with rules (Chowdhury and Lavelli, 2013), since we did not incorporate it. We also show the performance of the existing models with negative instance filtering for reference.…”

Section: Comparison With Existing Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Extracting Drug-Drug Interactions with Attention CNNs

Asada¹,

Misawa²,

Sasaki³

2017

BioNLP 2017

View full text Add to dashboard Cite

We propose a novel attention mechanism for a Convolutional Neural Network (CNN)-based Drug-Drug Interaction (DDI) extraction model. CNNs have been shown to have a great potential on DDI extraction tasks; however, attention mechanisms, which emphasize important words in the sentence of a target-entity pair, have not been investigated with the CNNs despite the fact that attention mechanisms are shown to be effective for a general domain relation classification task. We evaluated our model on the Task 9.2 of the DDIExtraction-2013 shared task. As a result, our attention mechanism improved the performance of our base CNN-based DDI model, and the model achieved an F-score of 69.12%, which is competitive with the state-of-the-art models.

show abstract

Section: Comparison With Existing Modelsmentioning

confidence: 84%

Section: Comparison With Existing Modelsmentioning

confidence: 99%

Extracting Drug-Drug Interactions with Attention CNNs

Asada¹,

Misawa²,

Sasaki³

2017

BioNLP 2017

View full text Add to dashboard Cite

show abstract

“…In Figure 1, f irst − layer entities would be carbamazepine and HLA − B, and second − layer entities are carbamazepine hypersensitivity and HLA-B*1502. Finally, we trained a model similar to the one described in [48] to extract relationships between identified entities. Reasonable meta-parameters were selected according to previous experiments.…”

Section: With the Biomedical Literaturementioning

confidence: 99%

PGxO and PGxLOD: a reconciliation of pharmacogenomic knowledge of various provenances, enabling further comparison

Monnin

Legrand

Husson

et al. 2018

Preprint

View full text Add to dashboard Cite

Background Pharmacogenomics (PGx) studies how genomic variations impact variations in drug response phenotypes. Knowledge in pharmacogenomics is typically composed of units that have the form of ternary relationships gene variant -drug -adverse event. Such a relationship states that an adverse event may occur for patients having the specified gene variant and being exposed to the specified drug. State-of-the-art knowledge in PGx is mainly available in reference databases such as PharmGKB and reported in scientific biomedical literature. But, PGx knowledge can also be discovered from clinical data, such as Electronic Health Records (EHRs), and in this case, may either correspond to new knowledge or confirm state-of-the-art knowledge that lacks "clinical counterpart" or validation. For this reason, there is a need for automatic comparison of knowledge units from distinct sources. Results In this article, we propose an approach, based on Semantic Web technologies, to represent and compare PGx knowledge units. To this end, we developed PGxO, a simple ontology that represents PGx knowledge units and their components. Combined with PROV-O, an ontology developed by the W3C to represent provenance information, PGxO enables encoding and associating provenance information to PGx relationships. Additionally, we introduce a set of rules to reconcile PGx knowledge, i.e. to identify when two relationships, potentially expressed using different vocabularies and levels of granularity, refer to the same, or to different knowledge units. We evaluated our ontology and rules by populating PGxO with knowledge units extracted from PharmGKB (2,701), the literature (65,720) and from discoveries reported in EHR analysis studies (only 10, manually extracted); and by testing their similarity. We called PGxLOD (PGx Linked Open Data) the resulting knowledge base that represents and reconciles knowledge units of those various origins. Conclusions The proposed ontology and reconciliation rules constitute a first step toward a more complete framework for knowledge comparison in PGx. In this direction, the experimental instantiation of PGxO, named PGxLOD, illustrates the ability and difficulties of reconciling various existing knowledge sources. BackgroundIn this article, we present a simple ontology named PGxO, developed to reconcile and trace knowledge in pharmacogenomics (PGx). We instantiated this ontology with knowledge of various origins to both 1/23 illustrate the relevance of the ontology and constitute a Linked Open Data (LOD) data set for PGx [5].PGx itself studies how genomics impact individual variations in drug response phenotypes [63]. Knowledge in pharmacogenomics is of particular interest for the implementation of personalized medicine, i.e. a medicine tailoring treatments (chosen drugs and dosages) to every patient, in order to reduce the risk of adverse events. Indeed, best known examples of PGx knowledge already led to the development of clinical guidelines and practices [9] that recommend considering individual genotype when ...

show abstract

“…Quan et al used a multichannel CNN model with five types of word embedding to extract DDIs from unstructured biomedical literature [22]. Asada et al encoded textual drug pairs with CNNs and encoded their molecular pairs with graph convolutional networks (GCNs) to predict DDIs [23], and obtained the best result so far for CNN-based DDI extraction methods.…”

Section: Introductionmentioning

confidence: 99%

Drug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Loss

Sun

Dong

et al. 2019

Entropy

View full text Add to dashboard Cite

Drug-drug interactions (DDIs) may bring huge health risks and dangerous effects to a patient’s body when taking two or more drugs at the same time or within a certain period of time. Therefore, the automatic extraction of unknown DDIs has great potential for the development of pharmaceutical agents and the safety of drug use. In this article, we propose a novel recurrent hybrid convolutional neural network (RHCNN) for DDI extraction from biomedical literature. In the embedding layer, the texts mentioning two entities are represented as a sequence of semantic embeddings and position embeddings. In particular, the complete semantic embedding is obtained by the information fusion between a word embedding and its contextual information which is learnt by recurrent structure. After that, the hybrid convolutional neural network is employed to learn the sentence-level features which consist of the local context features from consecutive words and the dependency features between separated words for DDI extraction. Lastly but most significantly, in order to make up for the defects of the traditional cross-entropy loss function when dealing with class imbalanced data, we apply an improved focal loss function to mitigate against this problem when using the DDIExtraction 2013 dataset. In our experiments, we achieve DDI automatic extraction with a micro F-score of 75.48% on the DDIExtraction 2013 dataset, outperforming the state-of-the-art approach by 2.49%.

show abstract

Multichannel Convolutional Neural Network for Biological Relation Extraction

Cited by 120 publications

References 24 publications

Extracting Drug-Drug Interactions with Attention CNNs

Extracting Drug-Drug Interactions with Attention CNNs

PGxO and PGxLOD: a reconciliation of pharmacogenomic knowledge of various provenances, enabling further comparison

Drug-Drug Interaction Extraction via Recurrent Hybrid Convolutional Neural Networks with an Improved Focal Loss

Contact Info

Product

Resources

About