In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios. However, existing ICL-based NER methods suffer from three key limitations: (1) reliance on dynamic retrieval of annotated examples, which is problematic when annotated data is scarce; (2) limited generalization to unseen domains due to the LLM's insufficient internal domain knowledge; and (3) failure to incorporate external knowledge or resolve entity ambiguities. To address these challenges, we propose KDR-Agent, a novel multi-agent framework for multi-domain low-resource in-context NER that integrates Knowledge retrieval, Disambiguation, and Reflective analysis. KDR-Agent leverages natural-language type definitions and a static set of entity-level contrastive demonstrations to reduce dependency on large annotated corpora. A central planner coordinates specialized agents to (i) retrieve factual knowledge from Wikipedia for domain-specific mentions, (ii) resolve ambiguous entities via contextualized reasoning, and (iii) reflect on and correct model predictions through structured self-assessment. Experiments across ten datasets from five domains demonstrate that KDR-Agent significantly outperforms existing zero-shot and few-shot ICL baselines across multiple LLM backbones.

Medication recommendation systems have emerged as crucial tools in healthcare, offering personalized and effective drug combinations tailored to individual patient's clinical profiles. However, most existing approaches primarily focus on drug prediction by analyzing patient-drug interactions, often neglecting the intricate correlations between diseases and drugs. To address above limitation, this paper proposes a novel Collaborative Relation augmentation with Hierarchical Prescription inference network (CRHP) for effective medication recommendation. CRHP first constructs multiple covariance knowledge graphs to capture fine-grained interaction relationships between different entities from a global perspective. Based on self-built knowledge graphs, CRHP designs a collaborative relation augmented learning module, which introduces hypergraph convolutional networks to capture high-order association information between different entities. Moreover, CRHP devises a hierarchical prescription inference module that formulates drug prescriptions based on both current and historical patient information. The extensive experiments on two publicly available real-world medical datasets, MIMIC-III and MIMIC-IV, demonstrate the effectiveness of CRHP. The results indicate significant performance improvements over baseline methods, with gains of 2.12 and 1.31 in Jaccard, 1.91 and 1.83 in PRAUC, and 1.79 and 0.98 in F1-score (in percentage points).

Protein complexes play essential roles in cellular functions, and accurate identification of these complexes is critical for understanding biological processes and disease mechanisms. Existing methods frequently compromise the global topology of protein-protein interaction (PPI) networks when incorporating biological resources. Moreover, they fail to adequately address the intrinsic sparsity of PPI data and the widespread occurrence of false positives and false negatives. These approaches also struggle to capture the diverse neighborhood dependencies necessary to represent distinct functional roles of proteins within complexes. To address these limitations, we propose a knowledge-enhanced graph contrastive learning (KEGCL) framework for protein complex identification. KEGCL constructs a knowledge-enhanced PPI network by integrating external biological priors. A perturbation strategy guided by spatiotemporal constraints is then applied to selectively reintroduce functionally relevant interactions, thereby enhancing semantic diversity in the generated graph views. Based on this, graph convolutional encoders with randomized propagation depths are used to capture protein interaction patterns at multiple structural levels, enhancing the model's ability to represent both densely connected cores and loosely associated attachments within protein complexes. Extensive experiments on multiple real-world PPI datasets show that KEGCL achieves competitive performance compared with state-of-the-art methods, and enrichment analyses confirm the biological relevance of the identified complexes.

As an effective and low-risk approach to identify new therapeutic pathways for existing drugs, drug repositioning has been extensively utilized to expedit drug discovery processes. However, current knowledge graph (KG)-based methodologies encounter several hurdles in this context. Firstly, most graph neural network (GNN)-based approaches fail to adequately capture the intricate relationships between drug-drug, drug-disease, or disease-disease. Secondly, the subtle synergistic mechanisms between drugs and diseases remain underexplored. Lastly, the training of knowledge graph embedding (KGE) methods is susceptible to noise, leading to unstable model optimization. To address these challenges, we intruduce KRANE, a knowledge-driven and relation-aware synergistic learning method for drug repositioning. KRANE addresses these issues through three innovative modules. Firstly, we design a relation-aware feature extractor (RAFE), which utilizes the contextual triples attention scores in KG to effectively integrate drug-related knowledge and enhance the representation of complex relational features. Secondly, we adopt a synergistic feature reconstruction module as a decoder to extract synergistic heterogeneous feature interactions between drugs and diseases from entity and relation representations. Finally, we propose a knowledge-regulated loss function to mitigate the impact of noise on model training. Experiments conducted on three publicly available datasets demonstrate that KRANE significantly outperforms existing methods.

Stance detection aims to identify the attitude expressed in text towards a specific target.Recent studies on zero-shot and few-shot stance detection focus primarily on learning generalized representations from explicit targets.However, these methods often neglect implicit yet semantically important targets and fail to adaptively adjust the relative contributions of text and target in light of contextual dependencies.To overcome these limitations, we propose a novel two-stage framework: First, a data augmentation framework named Hierarchical Collaborative Target Augmentation (HCTA) employs Large Language Models (LLMs) to identify and annotate implicit targets via Chain-of-Thought (CoT) prompting and multi-LLM voting, significantly enriching training data with latent semantic relations.Second, we introduce DyMCA, a Dynamic Multi-level Contextaware Attention Network, integrating a joint text-target encoding and a content-aware mechanism to dynamically adjust text-target contributions based on context.Experiments on the benchmark dataset demonstrate that our approach achieves state-of-the-art results, confirming the effectiveness of implicit target augmentation and fine-grained contextual modeling.Our code is publicly available at https: //github.com/EliaukoaYoW/DyMCA.

Recent advancements in radiology report generation have utilized deep neural networks such as CNNs and Transformers, achieving notable improvements in generating accurate and detailed reports. However, their practical adoption is hindered by the challenge of balancing global dependency modeling with computational efficiency. The state space model, particularly its enhanced variant Mamba, offers promising linear-complexity solutions for long-range dependency modeling. Despite its strengths, Mamba’s fixed positional encoding limits its ability to effectively capture complex spatial dependencies. To address this gap, we propose RRG-Mamba, an advanced framework for efficient radiology report generation. Within the RRGMamba, we enhance the vanilla Mamba by integrating rotary position encoding (RoPE), enabling dynamic modeling of relative positional information in visual feature sequences. Furthermore, we design a global dependency learning module to optimize long-range visual feature sequence modeling. Extensive experiments on publicly available datasets, including IU X-Ray and MIMIC-CXR, demonstrate that RRG-Mamba achieves a 3.7% improvement in BLEU-4 score over existing models, along with significant gains in computational and memory efficiency. Our code is available at https://github.com/Eleanorhxd/RRG-Mamba.

Drug repositioning, which involves identifying new therapeutic indications for approved drugs, is pivotal in accelerating drug discovery. Recently, to mitigate the effect of label sparsity on inferring potential drug-disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm to supplement high-quality self-supervised signals through designing auxiliary tasks, then transfer shareable knowledge to main task, i.e. DDA prediction. However, existing approaches still encounter two limitations. The first is how to generate augmented views for fully capturing higher-order interaction semantics. The second is the optimization imbalance issue between auxiliary and main tasks. In this paper, we propose a novel heterogeneous Graph Contrastive learning method with Gradient Balance for DDA prediction, namely GCGB. To handle the first challenge, a fusion view is introduced to integrate both semantic views (drug and disease similarity networks) and interaction view (heterogeneous biomedical network). Next, inter-view contrastive learning auxiliary tasks are designed to contrast the fusion view with semantic and interaction views, respectively. For the second challenge, we adaptively adjust the gradient of GCL auxiliary tasks from the perspective of gradient direction and magnitude for better guiding parameter update toward main task. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness.

Identifying biologically significant protein complexes from protein-protein interaction (PPI) networks and understanding their roles are essential for elucidating protein functions, life processes, and disease mechanisms. Current methods typically rely on static PPI networks and model PPI data as pairwise relationships, which presents several limitations. Firstly, static PPI networks do not adequately represent the scopes and temporal dynamics of protein interactions. Secondly, a large amount of available biological resources have not been fully integrated. Moreover, PPIs in biological systems are not merely one-to-one relationships but involve higher order non-pairwise interactions. To alleviate these issues, we propose HGST, a multi-source biological knowledge-guided hypergraph spatiotemporal subnetwork (subnet) embedding method for identifying biologically significant protein complexes from PPI networks. HGST initially constructs spatiotemporal PPI subnets using the scopes and temporal dynamics of proteins derived from multi-source biological knowledge, treating them as dynamic networks through fine-grained spatiotemporal partitioning. The spatiotemporal subnets are then transformed into hypergraphs, which model higher order non-pairwise relationships via hypergraph embedding. Simultaneously, fine-grained amino acid sequence features and coarse-grained gene ontology attributes are introduced for multi-dimensional feature fusion. Finally, protein complexes are identified from the reweighted subnets based on fused feature representations using the core-attachment strategy. Evaluations on four real PPI datasets demonstrate that HGST achieves competitive performance. Furthermore, a series of biological analyses confirm the high biological significance of the complexes identified by HGST. The source code is available at https://github.com/qifen37/HGST.

With the continuous progress of multimedia and information technology, multimodal sentiment analysis (MSA) has become one of the most advanced and challenging research directions in the field of artificial intelligence . Multimodal data, including text, visual and audio information, provides additional perspectives for sentiment analysis . However, extraneous information in non-verbal modalities affects the accuracy of sentiment analysis, as sentiment-related features are mainly concentrated in changes in mouth movements and pitch changes, which poses a challenge for accurate sentiment analysis. To solve this problem, we propose a manifold knowledge-guided feature fusion network (MKGN). MKGN uses manifold knowledge generated by manifold learning algorithms to guide neural networks to extract effective non-verbal features and establish associations between multiple features while reducing dimensionality. In addition, in order to improve the quality of knowledge, we propose two knowledge enhancement methods: knowledge filter (KF) and knowledge contrastive learning (CL). Among them, KF is used to filter out unreliable knowledge, and CL further strengthens retained knowledge by changing the distance between knowledge. Importantly, the proposed MKGN achieves excellent performance on three datasets compared to state-of-the-art models. On the MOSI dataset, the accuracy is improved by 2% and 1%, respectively. On the MOSEI dataset, the accuracy improved by 3.8% and 1.8%, respectively. On the UR-FUNNY dataset, the accuracy improved by 0.4%.

Medical images are an essential basis for radiologists to write radiology reports and greatly help subsequent clinical treatment. The task of generating automatic radiology reports aims to alleviate the burden of clinical doctors writing reports and has received increasing attention this year, becoming an important research hotspot. However, there are severe issues of visual and textual data bias and long text generation in the medical field. Firstly, Abnormal areas in radiological images only account for a small portion, and most radiological reports only involve descriptions of normal findings. Secondly, there are still significant challenges in generating longer and more accurate descriptive texts for radiology report generation tasks. In this paper, we propose a new Dual Attention and Context Guidance (DACG) model to alleviate visual and textual data bias and promote the generation of long texts. We use a Dual Attention Module, including a Position Attention Block and a Channel Attention Block, to extract finer position and channel features from medical images, enhancing the image feature extraction ability of the encoder. We use the Context Guidance Module to integrate contextual information into the decoder and supervise the generation of long texts. The experimental results show that our proposed model achieves state-of-the-art performance on the most commonly used IU X-ray and MIMIC-CXR datasets. Further analysis also proves that our model can improve reporting through more accurate anomaly detection and more detailed descriptions. The source code is available at https://github.com/LangWY/DACG.

Synthetic lethality (SL) has emerged as a promising strategy in cancer medicine. However, complex biomolecular interactions make wet lab methods time-consuming and expensive. Machine learning methods have gained widespread adoption for SL prediction in recent years. Although these methods have demonstrated particular effectiveness, they suffer from weak interpretability, making it difficult for users to understand the specific reasoning processes of the models. Also, they typically focus on a simple gene pair, thus struggling with more meaningful reasoning tasks involving other medical factors as in real life. To address these gaps, we propose an explainable multi-hop reasoning model EFOL-SL based on first-order logic queries. We first construct query graphs with triplet transformations for different tasks. Node embeddings are then fed into a sparse Transformer encoder and a visualized graph attention decoder to generate comprehensive multi-hop logical reasoning chains. By masking nodes in intermediate reasoning steps, our model can explicitly predict each node, allowing observation of its exact reasoning process. Additionally, we conduct extensive experiments on two widely used benchmarks with complex SL prediction tasks involving diverse medical entities. Evaluations demonstrate superior performance of our model over state-of-the-art methods on various tasks. Notably, EFOL-SL provides specific multi-hop logical reasoning chains behind its predictions, offering meaningful insights into the model's reasoning process.

Drugtarget interaction (DTI) prediction is a pivotal task in the realm of drug discovery. As the volume of biological data has increased rapidly, the integration of multiple data sources to increase prediction accuracy has become increasingly important. However, few methods exploit the heterogeneous information network in the drugtarget network by integrating multisource information to address the task of drugtarget interaction prediction. In this paper, we propose a multitask DTI prediction model, HIN-MTDTI, which is grounded in heterogeneous information networks (HINs). The model employs drugtarget interaction network, drugdrug similarity network and targettarget similarity network as inputs to construct a heterogeneous information network. Moreover, we apply a graph convolutional network (GCN) on the HIN to learn the representations of drugs and targets. To augment the performance further, we integrate a bilinear attention network to capture local drugtarget interaction information fully. The experimental results on several benchmark datasets demonstrate that HIN-MTDTI outperforms state-of-the-art methods for DTI prediction, confirming the effectiveness of our method.

Drug repositioning, which identifies new therapeutic potential of approved drugs, is instrumental in accelerating drug discovery. Recently, to alleviate the effect of data sparsity on predicting possible drug-disease associations (DDAs), graph contrastive learning (GCL) has emerged as a promising paradigm for learning discriminative representations of drugs and diseases through distilling informative self-supervised signals. However, existing GCL-based methods devised for DDA prediction still encounter two limitations. Firstly, the crucial heterogeneous property, which allows for capturing nuanced interaction semantics between biological entities, is overlooked. The second is how to perform contrastive view augmentation without relying on stochastic perturbation. In this study, we propose a novel multi-view contrastive learning approach for DDA prediction, namely MICLE. To handle the first issue, protein-related bipartite graphs are integrated with the original DDA network in advance, thereby composing a heterogeneous biological network (HBN). Besides, heterogeneous graph neural network is applied to mine the rich connectivity patterns implicit in the above HBN. For the second limitation, we design the complementary inter-view and intra-view contrastive learning tasks. Specifically, the former ensures that the mutual information between paired nodes across views is maximized, the latter enhances the agreement between each node and its first-order neighbors on similarity networks. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness.

Drug repositioning, which identifies new therapeutic potential of approved drugs, is pivotal in accelerating drug discovery. Recently, growing efforts are devoted to applying graph neural networks (GNNs) for effectively modeling drug-disease associations (DDAs). However, current GNN-based methods are generally designed for unsigned graphs and fail to gain complementary insights provided by negative links. Despite the proposal of sign-aware GNNs in general fields, there exist two intractable challenges when indiscriminately deploying prior solutions into drug repositioning. (i) How to explicitly connect the nodes within the same set (disease-disease and drug-drug)? (ii) How to design the contrastive learning objective for signed graphs? To this end, we propose a novel sign-aware graph contrastive learning approach, namely SIGDR, which takes both the positive and negative links from signed biological networks into consideration to identify underlying DDAs. To handle the first challenge, we measure the drug and disease similarity and form signed unipartite graphs according to similarity scores. For the second challenge, a signed bipartite graph is then constructed from the annotated DDA dataset. Through dividing above obtained signed graphs into positive and negative subgraphs respectively, we devise the inter-view contrastive learning auxiliary task to enhance the consistency of node representations derived from partitioned subgraphs with the same link type. Extensive experiments conducted on three benchmarks under 10-fold cross-validation demonstrate the model effectiveness.

The traditional drug development process requires a significant investment in workforce and financial resources. Drug repositioning as an efficient alternative has attracted much attention during the last few years. Despite the wide application and success of the method, there are still many shortcomings in the existing model. For example, sparse datasets will seriously affect the existing methods' performance. Additionally, these methods do not pay attention to the noise in datasets. In response to the above defects, we propose a semantic-enriched augmented graph contrastive learning with an adaptive denoising method, called SGCD. This method enhances data from the perspective of the embedding layer, deeply mines potential neighborhood relation-ships in semantic space, and combines similar drugs in the semantic neighborhoods into prototype comparison targets, thus effectively mitigating the impact of data sparsity on the model. Moreover, to enhance the model's robustness to noisy data, we use the adaptive denoising method, which can effectively identify noisy data in the training process. Exhaustive experiments on multiple real datasets show the effectiveness of the proposed model.

The AIDS epidemic has killed 40 million people and caused serious global problems. The identification of new HIV-inhibiting molecules is of great importance for combating the AIDS epidemic. Here, the Classifier Guidance Diffusion model and ligand-based virtual screening strategy are combined to discover potential HIV-inhibiting molecules for the first time. We call it Diff4VS. An extra classifier is trained using the HIV molecule dataset, and the gradient of the classifier is used to guide the Diffusion to generate HIV-inhibiting molecules. Experiments show that Diff4VS can generate more candidate HIV-inhibiting molecules than other methods. Inspired by ligand-based virtual screening, a new metric DrugIndex is proposed. DrugIndex provides a new evaluation method for evolving molecular generative models from a pharmaceutical perspective. Besides, we report a new phenomenon. Compared to real molecules, the generated molecules have a lower proportion that is highly similar to known drug molecules. Based on the data analysis, the Degradation may result from the difficulty of generating molecules with a specific structure. Our research contributes to the applying generative models in drug design from method, metric, and phenomenon analysis.

Document-level biomedical relation extraction (Bio-DocRE) involves automatically identifying relation facts between multiple entity pairs from a document. Logical reasoning has become a recent research focus since many relations of long-distance entity pairs in biomedical documents need to be predicted through reasoning from other existing relations. However, this task faces two crucial challenges: long dependency and evidence selection. Existing graph-based or transformer-based models independently model the internal structure of entities and ignore additional global interactions between relation triples. In addition, evidence graph reasoning plays an important role in boosting the logical reasoning between entities, but it is ignored by these methods. To tackle these issues, we propose a novel Bio-DocRE framework called EGALR based on evidence graph assisted logical reasoning. This allows EGALR to focus on important sentences while predicting implicit relations between entities with relation reasoning. Extensive experiments show that our EGALR model achieves state-of-the-art performance on two widely-used biomedical datasets, CDR and GDA.

Document-level biomedical relation extraction (Bio-DocRE) involves identifying relations between entities distributed across multiple sentences in biomedical literature. Most existing approaches construct a document graph structure to model entity-level relation maps and achieve local implicit reasoning at the entity-pair granularity. However, these methods have two main drawbacks. On the one hand, mention-pair granularity is crucial for modeling entity-level relation map and global reasoning but is often ignored in most approaches. On the other hand, these approaches primarily achieve local reasoning of cross-sentence relation instances with the interaction of sentence or document nodes in the graph. Such an approach has difficulty modeling global reasoning and cannot completely address the sub-optimal performance caused by the long dependency issue. To tackle these issues, we propose a novel framework based on hierarchical multi-granularity learning and reasoning (HMGLR) for Bio-DocRE. Experimental results on two widely used biomedical datasets demonstrate that our model achieves new state-of-the-art performance.

The identification of protein complexes from protein interaction networks is crucial in the understanding of protein function, cellular processes and disease mechanisms. Existing methods commonly rely on the assumption that protein interaction networks are highly reliable, yet in reality, there is considerable noise in the data. In addition, these methods fail to account for the regulatory roles of biomolecules during the formation of protein complexes, which is crucial for understanding the generation of protein interactions. To this end, we propose a SpatioTemporal constrained RNA-protein heterogeneous network for Protein Complex Identification (STRPCI). STRPCI first constructs a multiplex heterogeneous protein information network to capture deep semantic information by extracting spatiotemporal interaction patterns. Then, it utilizes a dual-view aggregator to aggregate heterogeneous neighbor information from different layers. Finally, through contrastive learning, STRPCI collaboratively optimizes the protein embedding representations under different spatiotemporal interaction patterns. Based on the protein embedding similarity, STRPCI reweights the protein interaction network and identifies protein complexes with core-attachment strategy. By considering the spatiotemporal constraints and biomolecular regulatory factors of protein interactions, STRPCI measures the tightness of interactions, thus mitigating the impact of noisy data on complex identification. Evaluation results on four real PPI networks demonstrate the effectiveness and strong biological significance of STRPCI. The source code implementation of STRPCI is available from https://github.com/LI-jasm/STRPCI.

MOTIVATION: Drug recommendation aims to allocate safe and effective drug combinations based on the patient's health status from electronic health records, which is crucial to assist clinical physicians in making decisions. However, the existing drug recommendation works face two key challenges: (i) difficulty in fully representing the patient's health status leads to biased drug representation; (ii) only focusing on diagnostic representations of multiple visits, neglecting the modeling of patient drug history. RESULTS: To address the above limitations, we propose a multi-view gating retrieval network (MGRN) for robust drug recommendation. We design visit-, sequence-, and token-level views to provide different perspectives on the interaction between patients and drugs, obtaining a more comprehensive representation of drugs. Moreover, we develop a gating drug retrieval module to capture critical drug information from multiple visits, which can assist in recommending more reasonable drug combinations for the current visit. When evaluated on publicly real-world MIMIC-III and MIMIC-IV datasets, the proposed MGRN establishes a new benchmark performance, particularly achieving improvements of 1.36%, 1.71%, 1.21% and 2.12%, 2.36%, 1.81% in Jaccard, PRAUC, and F1-score, respectively, compared to state-of-the-art models. AVAILABILITY AND IMPLEMENTATION: The code is available at: https://github.com/kyosen258/MGRN.git.

MOTIVATION: Biomedical relation extraction at the document level (Bio-DocRE) involves extracting relation instances from biomedical texts that span multiple sentences, often containing various entity concepts such as genes, diseases, chemicals, variants, etc. Currently, this task is usually implemented based on graphs or transformers. However, most work directly models entity features to relation prediction, ignoring the effectiveness of entity pair information as an intermediate state for relation prediction. In this article, we decouple this task into a three-stage process to capture sufficient information for improving relation prediction. RESULTS: We propose an innovative framework HTGRS for Bio-DocRE, which constructs a hierarchical tree graph (HTG) to integrate key information sources in the document, achieving relation reasoning based on entity. In addition, inspired by the idea of semantic segmentation, we conceptualize the task as a table-filling problem and develop a relation segmentation (RS) module to enhance relation reasoning based on the entity pair. Extensive experiments on three datasets show that the proposed framework outperforms the state-of-the-art methods and achieves superior performance. AVAILABILITY AND IMPLEMENTATION: Our source code is available at https://github.com/passengeryjy/HTGRS.

Traditional drug development is often high-risk and time-consuming. A promising alternative is to reuse or relocate approved drugs. Recently, some methods based on graph representation learning have started to be used for drug repositioning. These models learn the low dimensional embeddings of drug and disease nodes from the drug-disease interaction network to predict the potential association between drugs and diseases. However, these methods have strict requirements for the dataset, and if the dataset is sparse, the performance of these methods will be severely affected. At the same time, these methods have poor robustness to noise in the dataset. In response to the above challenges, we propose a drug repositioning model based on self-supervised graph learning with adptive denoising, called SADR. SADR uses data augmentation and contrastive learning strategies to learn feature representations of nodes, which can effectively solve the problems caused by sparse datasets. SADR includes an adaptive denoising training (ADT) component that can effectively identify noisy data during the training process and remove the impact of noise on the model. We have conducted comprehensive experiments on three datasets and have achieved better prediction accuracy compared to multiple baseline models. At the same time, we propose the top 10 new predictive approved drugs for treating two diseases. This demonstrates the ability of our model to identify potential drug candidates for disease indications.

Protein complexes, as the fundamental units of cellular function and regulation, play a crucial role in understanding the normal physiological functions of cells. Existing methods for protein complex identification attempt to introduce other biological information on top of the protein-protein interaction (PPI) network to assist in evaluating the degree of association between proteins. However, these methods usually treat protein interaction networks as flat homogeneous static networks. They cannot distinguish the roles and importance of different types of biological information, nor can they reflect the dynamic changes of protein complexes. In recent years, heterogeneous network representation learning has achieved great success in processing complex heterogeneous information and mining deep semantics. We thus propose a temporal protein complex identification method based on Dynamic Heterogeneous Protein information network Representation Learning, DHPRL. DHPRL naturally integrates multiple types of heterogeneous biological information in the cellular temporal dimension. It simultaneously models the temporal dynamic properties of proteins and the heterogeneity of biological information to improve the understanding of protein interactions and the accuracy of complex prediction. Firstly, we construct Dynamic Heterogeneous Protein Information Network (DHPIN) by integrating temporal gene expression information and GO attribute information. Then we design a dual-view collaborative contrast mechanism. Specifically, proposing to learn protein representations from two views of DHPIN (1-hop relation view and meta-path view) to model the consistency and specificity between nearest-neighbour bio information and deeper biological semantics. The dynamic PPI network is thereafter re-weighted based on the learned protein representations. Finally, we perform protein identification on the re-weighted dynamic PPI network. Extensive experimental results demonstrate that DHPRL can effectively model complicated biological information and achieve state-of-the-art performance in most cases.

Predicting drug-drug interaction (DDI) plays a crucial role in drug recommendation and discovery. However, wet lab methods are prohibitively expensive and time-consuming due to drug interactions. In recent years, deep learning methods have gained widespread use in drug reasoning. Although these methods have demonstrated effectiveness, they can only predict the interaction between a drug pair and do not contain any other information. However, DDI is greatly affected by various other biomedical factors (such as the dose of the drug). As a result, it is challenging to apply them to more complex and meaningful reasoning tasks. Therefore, this study regards DDI as a link prediction problem on knowledge graphs and proposes a DDI prediction model based on Cross-Transformer and Graph Convolutional Networks (GCNs) in first-order logical query form, TransFOL. In the model, a biomedical query graph is first built to learn the embedding representation. Subsequently, an enhancement module is designed to aggregate the semantics of entities and relations. Cross-Transformer is used for encoding to obtain semantic information between nodes, and GCN is used to gather neighbour information further and predict inference results. To evaluate the performance of TransFOL on common DDI tasks, we conduct experiments on two benchmark datasets. The experimental results indicate that our model outperforms state-of-the-art methods on traditional DDI tasks. Additionally, we introduce different biomedical information in the other two experiments to make the settings more realistic. Experimental results verify the strong drug reasoning ability and generalization of TransFOL in complex settings.

Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines. Existing studies focus mainly on capturing context- and speaker-sensitive dependencies on the textual modality but ignore the significance of multimodal information. Different from emotion recognition in textual conversations, capturing intra- and inter-modal interactions between utterances, learning weights between different modalities, and enhancing modal representations play important roles in multimodal ERC. In this paper, we propose a transformer-based model with self-distillation (SDT)11The code is available athttps://github.com/butterfliesss/SDT.for the task. The transformer-based model captures intra- and inter-modal interactions by utilizing intra- and inter-modal transformers, and learns weights between modalities dynamically by designing a hierarchical gated fusion strategy. Furthermore, to learn more expressive modal representations, we treat soft labels of the proposed model as extra training supervision. Specifically, we introduce self-distillation to transfer knowledge of hard and soft labels from the proposed model to each modality. Experiments on IEMOCAP and MELD datasets demonstrate that SDT outperforms previous state-of-the-art baselines.

Electronic health records (EHRs) comprehensively describe the health status of many patients during their visits. Combining the records in EHRs with the patient’s current medical treatment status can generate personalized medication combinations. However, the increasing number of drugs poses significant challenges for clinical experts to recommend combination drugs. In recent years, deep learning models have been widely studied and applied in drug recommendation task. Currently, the existing models either lack sufficient mining of patients’ health data or ignore the modelling of patients’ longitudinal medical information. Therefore, we propose a multi-visit interactive recalibration network (MIRNet) for drug recommendation with a triple graph encoder. Specifically, we design a medical recalibration module to capture the feature representations in patient diagnosis and procedure information through cascaded convolutions. To achieve friendly interaction of medical codes between relatively necessary historical visits and the current visit in the drug recommendation process, we propose a multi-visit filter module. Furthermore, we design a triple graph encoder to fuse molecular, EHR, and Drug-Drug Interation (DDI) graphs, which aims to extract implicit drug feature representations from different medical knowledge. We perform experiments on the real-world MIMIC-III dataset, and the experimental results reveal that the model MIRNet outperforms other competitive baselines regarding major indicators.

Automated International Classification of Diseases (ICD) coding tasks are designed to assign diagnosis and procedure codes to patients’ electronic medical records (EMRs). Recent works have applied deep neural network models and related techniques for code assignment to clinical notes. However, most existing methods have overlooked the advantageous complementary information presented in the tabular data from EMRs and the Wikipedia knowledge. Therefore, we propose a Multimodal Knowledge Fusion Network (MKFN) to effectively integrate clinical notes, tabular data, and Wikipedia knowledge, enhancing the model’s predictive capabilities. We incorporate structured tabular data and clinical notes into an initial multimodal representation using label attention and self-attention mechanisms. We propose a knowledge fusion network to leverage tabular data and Wikipedia knowledge for accurate predictions when code descriptions are absent in clinical notes. Experiments on the MIMIC dataset show that our proposed model achieves competitive results among existing ICD coding methods.

Rapid and effective utilization of biomedical literature is paramount to combat diseases like COVID19. Biomedical named entity recognition (BioNER) is a fundamental task in text mining that can help physicians accelerate knowledge discovery to curb the spread of the COVID-19 epidemic. Recent approaches have shown that casting entity extraction as the machine reading comprehension task can significantly improve model performance. However, two major drawbacks impede higher success in identifying entities (1) ignoring the use of domain knowledge to capture the context beyond sentences and (2) lacking the ability to deeper understand the intent of questions. In this paper, to remedy this, we introduce and explore external domain knowledge which cannot be implicitly learned in text sequence. Previous works have focused more on text sequence and explored little of the domain knowledge. To better incorporate domain knowledge, a multi-way matching reader mechanism is devised to model representations of interaction between sequence, question and knowledge retrieved from Unified Medical Language System (UMLS). Benefiting from these, our model can better understand the intent of questions in complex contexts. Experimental results indicate that incorporating domain knowledge can help to obtain competitive results across 10 BioNER datasets, achieving absolute improvement of up to 2.02% in the f1 score.

The automatic extraction of the chemical-disease relation (CDR) from the text becomes critical because it takes a lot of time and effort to extract valuable CDR manually. Studies have shown that prior knowledge from the biomedical knowledge base is important for relation extraction. The method of combining deep learning models with prior knowledge is worthy of our study. In this paper, we propose a new model called Knowledge Guided Attention and Graph Convolutional Networks (KGAGN) for CDR extraction. First, to make full advantage of domain knowledge, we train entity embedding as a feature representation of input sequence, and relation embedding to capture weighted contextual information further through the attention mechanism. Then, to make full advantage of syntactic dependency information in cross-sentence CDR extraction, we construct document-level syntactic dependency graphs and encode them using a graph convolution network (GCN). Finally, the chemical-induced disease (CID) relation is extracted by using weighted context features and long-range dependency features both of which contain additional knowledge information We evaluated our model on the CDR dataset published by the BioCreative-V community and achieves an F1-score of 73.3%, surpassing other state-of-the-art methods. the code implemented by PyTorch 1.7.0 deep learning library can be downloaded from Github: https://github.com/sunyi123/cdr.

Automatic extraction of drug-drug interactions and their adverse effects can promote the research of pharmacovigilance and thus attracts attention from both academia and industry. Recent efforts focus on span-based approaches and show more promising results. However, span-based methods enumerate all possible candidate entity spans while ignoring boundary information of spans. Meanwhile, lacking sufficient interactions in intra-span and inter-span further hinders the performance of the nested entity and overlapping relation extraction. To this end, we propose a syntactic type-aware graph attention network for drug-drug interactions and their adverse effects extraction. Specifically, a boundary heuristic module is designed firstly to generate the boundary of linguistically legitimate entity spans. And then, different from the general syntactic graph (i.e., only considering dependency edges), we construct a syntactic type-aware graph attention network (STG) to capture interactions in intra-span and inter-span by considering syntactic edges and types simultaneously. Results1achieved on two biomedical benchmark datasets, including drug-drug interaction (DDI) and adverse drug effect (ADE), indicate that our model obtains significantly more performance than the state-of-the-art methods, achieving improvements in the relation F1 score of 1.63% on ADE and 2.07% on DDI dataset, respectively.

Medicine recommendation assists physicians in automatically providing medicine combinations, which is critical in health care. Existing efforts focus on making medicine recommendations based on the patient’s electronic health record(EHR). However, they ignore external medicine knowledge and are vulnerable to the missing EHR. In this paper, a knowledge-enhanced dual graph neural network (KDGN) is proposed to recommend medicine sets. KDGN combines diagnosis-level and procedure-level attention mechanisms to encode multiple types of medical codes. In order to mine medicine from medical knowledge, KDGN further designs a dual-graph neural network, which constructs a medicine co-occurrence graph and molecular connection graph, and retrieves potential therapeutic drugs. Furthermore, during the training phase, we introduce the automatic correction loss based on maximum likelihood estimation to mitigate the impact of missing EHR and enhance the robustness of KDGN. We evaluate the proposed model on the public MIMIC-III dataset, and experimental results show that KDGN outperforms the state-of-the-art model in 4 out of 5 evaluation metrics. Our dataset and code are available at: https://github.com/Benjamin-cell/KDGN.

The identification of protein complexes can help understand cellular organization principles and the mechanism of biological evolution. In recent years, researchers have proposed numerous computational methods to identify protein complexes through their interaction networks. Most of these methods identify protein complexes based on the topological structure of the PPI network. However, the topological structure contained in the PPI network is very complicated, and the applicability of advanced representation learning methods has not been researched in depth. This paper proposes a contrastive self-supervised representation learning method to identify protein complexes. Our method uses a mix-hop aggregator based on graph neural network (GNN) to capture high-order interaction in the PPI network and leverage a contrastive self-supervised method to train our model without introducing protein labels. Then, we get the vector representation for each protein and construct a weighted PPI network based on the vector representation similarity. Finally, we apply clustering aggregation to identify protein complexes based on a weighted PPI network. In order to access our method, different PPI networks, DIP, Kroganl4k and Biogrid, are used as datasets. By comparing the competing methods including COACH, CMC, MCODE, ClusterONE, GANE and COAN, experimental results show that our method outperforms classic and state-of-the-art methods.

BACKGROUND: Identifying protein complexes from protein-protein interaction network is one of significant tasks in the postgenome era. Protein complexes, none of which exceeds 10 in size play an irreplaceable role in life activities and are also a hotspot of scientific research, such as PSD-95, CD44, PKM2 and BRD4. And in MIPS, CYC2008, SGD, Aloy and TAP06 datasets, the proportion of small protein complexes is over 75%. But up to now, protein complex identification methods do not perform well in the field of small protein complexes. RESULTS: In this paper, we propose a novel method, called BOPS. It is a three-step procedure. Firstly, it calculates the balanced weights to replace the original weights. Secondly, it divides the graphs larger than MAXP until the original PPIN is divided into small PPINs. Thirdly, it enumerates the connected subset of each small PPINs, identifies potential protein complexes based on cohesion and removes those that are similar. CONCLUSIONS: In four yeast PPINs, experimental results have shown that BOPS has an improvement of about 5% compared with the SOTA model. In addition, we constructed a weighted Homo sapiens PPIN based on STRINGdb and BioGRID, and BOPS gets the best result in it. These results give new insights into the identification of small protein complexes, and the weighted Homo sapiens PPIN provides more data for related research.

BACKGROUND: Protein complexes are essential for biologists to understand cell organization and function effectively. In recent years, predicting complexes from protein-protein interaction (PPI) networks through computational methods is one of the current research hotspots. Many methods for protein complex prediction have been proposed. However, how to use the information of known protein complexes is still a fundamental problem that needs to be solved urgently in predicting protein complexes. RESULTS: To solve these problems, we propose a supervised learning method based on network representation learning and gene ontology knowledge, which can fully use the information of known protein complexes to predict new protein complexes. This method first constructs a weighted PPI network based on gene ontology knowledge and topology information, reducing the network's noise problem. On this basis, the topological information of known protein complexes is extracted as features, and the supervised learning model SVCC is obtained according to the feature training. At the same time, the SVCC model is used to predict candidate protein complexes from the protein interaction network. Then, we use the network representation learning method to obtain the vector representation of the protein complex and train the random forest model. Finally, we use the random forest model to classify the candidate protein complexes to obtain the final predicted protein complexes. We evaluate the performance of the proposed method on two publicly PPI data sets. CONCLUSIONS: Experimental results show that our method can effectively improve the performance of protein complex recognition compared with existing methods. In addition, we also analyze the biological significance of protein complexes predicted by our method and other methods. The results show that the protein complexes predicted by our method have high biological significance.

Biomedical Named Entity Recognition (BioNER) is often modeled as a sequence labeling task, which assigns the predefined label to each token in given input sequence. Although these sequential labeling models achieve significant achievements, they often fail to give precise boundaries of the named entity. In addition, a vast amount of work focuses more on textual sequence representation but ignores label information. To tackle these problems, in this paper, we directly model span-level named entity recognition, specifically, we treat the BioNER as a joint task of boundary detection and span classification under a multitask framework. In order to enhance boundary supervision, we introduce an entity type label as an additional guide and propose a co-attentive interactive mechanism to improve the span representation. Extensive experiments1on four benchmark datasets demonstrate that our proposed method obtains competitive results, achieving 90.26%, 78.04%, 90.21%, and 86.58% on BC5CDR, JNLPBA, NCBI, and BC2GM datasets, respectively, in terms of F1 score.

BACKGROUND: Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale. RESULTS: In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall. CONCLUSIONS: The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.

Extracting protein-protein interaction affected by genetic mutation from biomedical literature automatically is an essential step toward the ultimate goal of precision medicine. However, the existing methods fail to be accurate enough to meet the needs in practice. In this paper, considering the significant progress made by the pre-training model in a wide variety of NLP tasks, we use BioBERT to obtain the representation of the text and adopt a multi-task learning strategy to improve the performance. Evaluated on the BioCreative VI PPIm data set, our proposed model achieves a new state-of-the-art performance that surpassed the previous one by 4.86% in F1-score. The source code is available at https://github.com/dlutwy/ppim.

In this paper, we focus on the Protein-Protein Interaction Article Classification (PPIAC) problem. In order to make better use of domain knowledge, we propose a Hierarchical Knowledge-aware Hybrid Neural Network (HKaHNN) model to classify PPI articles. Inspired by existing work, we introduce two kinds of knowledge embeddings and design a Hierarchical Knowledge-aware Attention (HKaATT) component which implements the interaction between the original token representations and external knowledge from the token-level and sentence-level respectively. In addition, in order to improve the anti-interference ability of the model, we adopt the adversarial training strategy. Our model achieves competitive performance on BioCreative II and BioCreative III corpora, with Fl-scores of 83.67% and 68.86%, respectively.

BACKGROUND: Biomedical document triage is the foundation of biomedical information extraction, which is important to precision medicine. Recently, some neural networks-based methods have been proposed to classify biomedical documents automatically. In the biomedical domain, documents are often very long and often contain very complicated sentences. However, the current methods still find it difficult to capture important features across sentences. RESULTS: In this paper, we propose a hierarchical attention-based capsule model for biomedical document triage. The proposed model effectively employs hierarchical attention mechanism and capsule networks to capture valuable features across sentences and construct a final latent feature representation for a document. We evaluated our model on three public corpora. CONCLUSIONS: Experimental results showed that both hierarchical attention mechanism and capsule networks are helpful in biomedical document triage task. Our method proved itself highly competitive or superior compared with other state-of-the-art methods.

BACKGROUND: Most biomedical information extraction focuses on binary relations within single sentences. However, extracting n-ary relations that span multiple sentences is in huge demand. At present, in the cross-sentence n-ary relation extraction task, the mainstream method not only relies heavily on syntactic parsing but also ignores prior knowledge. RESULTS: In this paper, we propose a novel cross-sentence n-ary relation extraction method that utilizes the multihead attention and knowledge representation that is learned from the knowledge graph. Our model is built on self-attention, which can directly capture the relations between two words regardless of their syntactic relation. In addition, our method makes use of entity and relation information from the knowledge base to impose assistance while predicting the relation. Experiments on n-ary relation extraction show that combining context and knowledge representations can significantly improve the n-ary relation extraction performance. Meanwhile, we achieve comparable results with state-of-the-art methods. CONCLUSIONS: We explored a novel method for cross-sentence n-ary relation extraction. Unlike previous approaches, our methods operate directly on the sequence and learn how to model the internal structures of sentences. In addition, we introduce the knowledge representations learned from the knowledge graph into the cross-sentence n-ary relation extraction. Experiments based on knowledge representation learning show that entities and relations can be extracted in the knowledge graph, and coding this knowledge can provide consistent benefits.

As the biomedical literature increases exponentially, biomedical named entity recognition (BNER) has become an important task in biomedical information extraction. In the previous studies based on deep learning, pretrained word embedding becomes an indispensable part of the neural network models, effectively improving their performance. However, the biomedical literature typically contains numerous polysemous and ambiguous words. Using fixed pretrained word representations is not appropriate. Therefore, this paper adopts the pretrained embeddings from language models (ELMo) to generate dynamic word embeddings according to context. In addition, in order to avoid the problem of insufficient training data in specific fields and introduce richer input representations, we propose a multitask learning multichannel bidirectional gated recurrent unit (BiGRU) model. Multiple feature representations (e.g., word-level, contextualized word-level, character-level) are, respectively, or collectively fed into the different channels. Manual participation and feature engineering can be avoided through automatic capturing features in BiGRU. In merge layer, multiple methods are designed to integrate the outputs of multichannel BiGRU. We combine BiGRU with the conditional random field (CRF) to address labels’ dependence in sequence labeling. Moreover, we introduce the auxiliary corpora with same entity types for the main corpora to be evaluated in multitask learning framework, then train our model on these separate corpora and share parameters with each other. Our model obtains promising results on the JNLPBA and NCBI-disease corpora, with F1-scores of 76.0% and 88.7%, respectively. The latter achieves the best performance among reported existing feature-based models.

BACKGROUND: The number of biomedical research articles have increased exponentially with the advancement of biomedicine in recent years. These articles have thus brought a great difficulty in obtaining the needed information of researchers. Information retrieval technologies seek to tackle the problem. However, information needs cannot be completely satisfied by directly introducing the existing information retrieval techniques. Therefore, biomedical information retrieval not only focuses on the relevance of search results, but also aims to promote the completeness of the results, which is referred as the diversity-oriented retrieval. RESULTS: We address the diversity-oriented biomedical retrieval task using a supervised term ranking model. The model is learned through a supervised query expansion process for term refinement. Based on the model, the most relevant and diversified terms are selected to enrich the original query. The expanded query is then fed into a second retrieval to improve the relevance and diversity of search results. To this end, we propose three diversity-oriented optimization strategies in our model, including the diversified term labeling strategy, the biomedical resource-based term features and a diversity-oriented group sampling learning method. Experimental results on TREC Genomics collections demonstrate the effectiveness of the proposed model in improving the relevance and the diversity of search results. CONCLUSIONS: The proposed three strategies jointly contribute to the improvement of biomedical retrieval performance. Our model yields more relevant and diversified results than the state-of-the-art baseline models. Moreover, our method provides a general framework for improving biomedical retrieval performance, and can be used as the basis for future work.

BACKGROUND: The adverse reactions that are caused by drugs are potentially life-threatening problems. Comprehensive knowledge of adverse drug reactions (ADRs) can reduce their detrimental impacts on patients. Detecting ADRs through clinical trials takes a large number of experiments and a long period of time. With the growing amount of unstructured textual data, such as biomedical literature and electronic records, detecting ADRs in the available unstructured data has important implications for ADR research. Most of the neural network-based methods typically focus on the simple semantic information of sentence sequences; however, the relationship of the two entities depends on more complex semantic information. METHODS: In this paper, we propose multihop self-attention mechanism (MSAM) model that aims to learn the multi-aspect semantic information for the ADR detection task. first, the contextual information of the sentence is captured by using the bidirectional long short-term memory (Bi-LSTM) model. Then, via applying the multiple steps of an attention mechanism, multiple semantic representations of a sentence are generated. Each attention step obtains a different attention distribution focusing on the different segments of the sentence. Meanwhile, our model locates and enhances various keywords from the multiple representations of a sentence. RESULTS: Our model was evaluated by using two ADR corpora. It is shown that the method has a stable generalization ability. Via extensive experiments, our model achieved F-measure of 0.853, 0.799 and 0.851 for ADR detection for TwiMed-PubMed, TwiMed-Twitter, and ADE, respectively. The experimental results showed that our model significantly outperforms other compared models for ADR detection. CONCLUSIONS: In this paper, we propose a modification of multihop self-attention mechanism (MSAM) model for an ADR detection task. The proposed method significantly improved the learning of the complex semantic information of sentences.

The explosive growth of biomedical literature has created a rich source of knowledge, such as that on protein-protein interactions (PPIs) and drug-drug interactions (DDIs), locked in unstructured free text. Biomedical relation classification aims to automatically detect and classify biomedical relations, which has great benefits for various biomedical research and applications. In the past decade, significant progress has been made in biomedical relation classification. With the advance of neural network methodology, neural network-based approaches have been applied in biomedical relation classification and achieved state-of-the-art performance for some public datasets and shared tasks. In this review, we describe the recent advancement of neural network-based approaches for classifying biomedical relations. We summarize the available corpora and introduce evaluation metrics. We present the general framework for neural network-based approaches in biomedical relation extraction and pretrained word embedding resources. We discuss neural network-based approaches, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). We conclude by describing the remaining challenges and outlining future directions.

Motivation: Adverse events resulting from drug-drug interactions (DDI) pose a serious health issue. The ability to automatically extract DDIs described in the biomedical literature could further efforts for ongoing pharmacovigilance. Most of neural networks-based methods typically focus on sentence sequence to identify these DDIs, however the shortest dependency path (SDP) between the two entities contains valuable syntactic and semantic information. Effectively exploiting such information may improve DDI extraction. Results: In this article, we present a hierarchical recurrent neural networks (RNNs)-based method to integrate the SDP and sentence sequence for DDI extraction task. Firstly, the sentence sequence is divided into three subsequences. Then, the bottom RNNs model is employed to learn the feature representation of the subsequences and SDP, and the top RNNs model is employed to learn the feature representation of both sentence sequence and SDP. Furthermore, we introduce the embedding attention mechanism to identify and enhance keywords for the DDI extraction task. We evaluate our approach using the DDI extraction 2013 corpus. Our method is competitive or superior in performance as compared with other state-of-the-art methods. Experimental results show that the sentence sequence and SDP are complementary to each other. Integrating the sentence sequence with SDP can effectively improve the DDI extraction performance. Availability and implementation: The experimental data is available at https://github.com/zhangyijia1979/hierarchical-RNNs-model-for-DDI-extraction. Contact: [email protected] or [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Identifying protein complexes from protein-protein interaction (PPI) network is one of the most important tasks in proteomics. Existing computational methods try to incorporate a variety of biological evidences to enhance the quality of predicted complexes. However, it is still a challenge to integrate different types of biological information into the complexes discovery process under a unified framework. Recently, attributed network embedding methods have be proved to be remarkably effective in generating vector representations for nodes in the network. In the transformed vector space, both the topological proximity and node attributed affinity between different nodes are preserved. Therefore, such attributed network embedding methods provide us a unified framework to integrate various biological evidences into the protein complexes identification process. RESULTS: In this article, we propose a new method called GANE to predict protein complexes based on Gene Ontology (GO) attributed network embedding. Firstly, it learns the vector representation for each protein from a GO attributed PPI network. Based on the pair-wise vector representation similarity, a weighted adjacency matrix is constructed. Secondly, it uses the clique mining method to generate candidate cores. Consequently, seed cores are obtained by ranking candidate cores based on their densities on the weighted adjacency matrix and removing redundant cores. For each seed core, its attachments are the proteins with correlation score that is larger than a given threshold. The combination of a seed core and its attachment proteins is reported as a predicted protein complex by the GANE algorithm. For performance evaluation, we compared GANE with six protein complex identification methods on five yeast PPI networks. Experimental results showes that GANE performs better than the competing algorithms in terms of different evaluation metrics. CONCLUSIONS: GANE provides a framework that integrate many valuable and different biological information into the task of protein complex identification. The protein vector representation learned from our attributed PPI network can also be used in other tasks, such as PPI prediction and disease gene prediction.

Biomedical relation extraction can automatically extract high-quality biomedical relations from biomedical texts, which is a vital step for the mining of biomedical knowledge hidden in the literature. Recurrent neural networks (RNNs) and convolutional neural networks (CNNs) are two major neural network models for biomedical relation extraction. Neural network-based methods for biomedical relation extraction typically focus on the sentence sequence and employ RNNs or CNNs to learn the latent features from sentence sequences separately. However, RNNs and CNNs have their own advantages for biomedical relation extraction. Combining RNNs and CNNs may improve biomedical relation extraction. In this paper, we present a hybrid model for the extraction of biomedical relations that combines RNNs and CNNs. First, the shortest dependency path (SDP) is generated based on the dependency graph of the candidate sentence. To make full use of the SDP, we divide the SDP into a dependency word sequence and a relation sequence. Then, RNNs and CNNs are employed to automatically learn the features from the sentence sequence and the dependency sequences, respectively. Finally, the output features of the RNNs and CNNs are combined to detect and extract biomedical relations. We evaluate our hybrid model using five public (protein-protein interaction) PPI corpora and a (drug-drug interaction) DDI corpus. The experimental results suggest that the advantages of RNNs and CNNs in biomedical relation extraction are complementary. Combining RNNs and CNNs can effectively boost biomedical relation extraction performance.

Genome-wide association study (GWAS), as one primary approach for genetic studies, has been successfully applied to a variety of complex diseases, leading to the discovery of substantial disease-associated loci. These discovered associations provide unprecedented opportunities for deepening our understanding of complex diseases, such as disease-associated risk variants, genes, and pathways. However, it is non-trivial to extract biological knowledge from the GWAS data due to the existence of several non-negligible factors. For example, the majority of associated loci fall into noncoding regions without certain links to any genes, complicating its functional characterization. Network-based GWAS gene prioritization, aiming to integrate gene networks with GWAS data, emerges as one promising direction towards solving these challenges and has attracted much attention recently. However, gene networks are usually sparse and noisy, and existing methods do not explicitly consider these properties, leading to suboptimal performance. In this paper, we proposed a novel method called REGENT for integrating multiple gene networks with GWAS data to prioritize complex disease-associated genes. Specifically, we leveraged the network representation learning, a recently developed technique for analyzing social networks, to learn compact and robust embeddings from multiple gene networks. To integrate these learned embeddings of genes with GWAS data, we developed a hierarchical statistical model and derived an efficient inference algorithm for model estimation and prediction. Applying to GWAS data of six complex diseases, we demonstrated that REGENT outperformed existing methods regarding the identification of known disease-associated genes. Also, pathway analysis showed that REGENT helped discover disease-associated pathways. Therefore, our method is expected to be a useful tool for post-GWAS analysis.

BACKGROUND: Drug-drug interactions (DDIs) often bring unexpected side effects. The clinical recognition of DDIs is a crucial issue for both patient safety and healthcare cost control. However, although text-mining-based systems explore various methods to classify DDIs, the classification performance with regard to DDIs in long and complex sentences is still unsatisfactory. METHODS: In this study, we propose an effective model that classifies DDIs from the literature by combining an attention mechanism and a recurrent neural network with long short-term memory (LSTM) units. In our approach, first, a candidate-drug-oriented input attention acting on word-embedding vectors automatically learns which words are more influential for a given drug pair. Next, the inputs merging the position- and POS-embedding vectors are passed to a bidirectional LSTM layer whose outputs at the last time step represent the high-level semantic information of the whole sentence. Finally, a softmax layer performs DDI classification. RESULTS: Experimental results from the DDIExtraction 2013 corpus show that our system performs the best with respect to detection and classification (84.0% and 77.3%, respectively) compared with other state-of-the-art methods. In particular, for the Medline-2013 dataset with long and complex sentences, our F-score far exceeds those of top-ranking systems by 12.6%. CONCLUSIONS: Our approach effectively improves the performance of DDI classification tasks. Experimental analysis demonstrates that our model performs better with respect to recognizing not only close-range but also long-range patterns among words, especially for long, complex and compound sentences.

BACKGROUND: Recently, high-throughput experimental techniques have generated a large amount of protein-protein interaction (PPI) data which can construct large complex PPI networks for numerous organisms. System biology attempts to understand cellular organization and function by analyzing these PPI networks. However, most studies still focus on static PPI networks which neglect the dynamic information of PPI. RESULTS: The gene expression data under different time points and conditions can reveal the dynamic information of proteins. In this study, we used an active probability-based method to distinguish the active level of proteins at different active time points. We constructed dynamic probabilistic protein networks (DPPN) to integrate dynamic information of protein into static PPI networks. Based on DPPN, we subsequently proposed a novel method to identify protein complexes, which could effectively exploit topological structure as well as dynamic information of DPPN. We used three different yeast PPI datasets and gene expression data to construct three DPPNs. When applied to three DPPNs, many well-characterized protein complexes were accurately identified by this method. CONCLUSION: The shift from static PPI networks to dynamic PPI networks is essential to accurately identify protein complex. This method not only can be applied to identify protein complex, but also establish a framework to integrate dynamic information into static networks for other applications, such as pathway analysis.

BACKGROUND: Accurate determination of protein complexes has become a key task of system biology for revealing cellular organization and function. Up to now, the protein complex prediction methods are mostly focused on static protein protein interaction (PPI) networks. However, cellular systems are highly dynamic and responsive to cues from the environment. The shift from static PPI networks to dynamic PPI networks is essential to accurately predict protein complex. RESULTS: The gene expression data contains crucial dynamic information of proteins and PPIs, along with high-throughput experimental PPI data, are valuable for protein complex prediction. Firstly, we exploit gene expression data to calculate the active time point and the active probability of each protein and PPI. The dynamic active information is integrated into high-throughput PPI data to construct dynamic PPI networks. Secondly, a novel method for predicting protein complexes from the dynamic PPI networks is proposed based on core-attachment structural feature. Our method can effectively exploit not only the dynamic active information but also the topology structure information based on the dynamic PPI networks. CONCLUSIONS: We construct four dynamic PPI networks, and accurately predict many well-characterized protein complexes. The experimental results show that (i) the dynamic active information significantly improves the performance of protein complex prediction; (ii) our method can effectively make good use of both the dynamic active information and the topology structure information of dynamic PPI networks to achieve state-of-the-art protein complex prediction capabilities.

Biomedical events can reveal crucial processes in biomedical research. As an important step in biomedical event extraction, biomedical event trigger detection has become a research hotspot. Traditional machine learning methods, which aim to manually design powerful features fed to the classifiers, greatly depend on the understanding of the specific task. In this paper, we propose an approach to automatically learn good features from raw input without manual intervention. The approach is based on dependency-based word embedding and first learns dependency-based word embedding from all available PubMed abstracts. The word embedding contains rich functional and semantic information. Then neural network architecture is used to learn better feature representation based on raw dependency-based word embedding. Meanwhile, we dynamically adjust the embedding while training for adapting to the trigger classification task. Finally, softmax classifier labels the examples by specific trigger class using the features learned by the model. The experimental results show that our approach achieves a micro F1 score of 78.27% and a macro F1 score of 76.94% in significant trigger classes, and performs better than baseline methods. In addition, we can achieve the semantic distributed representation of every trigger word.

Prediction of protein complexes from protein-protein interaction (PPI) networks is crucial to unraveling the principles of cellular organization. Most existing approaches only exploit high-throughput experimental PPI data to predict protein complexes. In this paper, we integrate the multiple biomedical resources for protein complex prediction by constructing attributed PPI networks, which include high-throughput data, co-expression data, genomic data, text mining data and gene ontology data. Multiple biomedical resources are complementary in attributed PPI networks. We propose a novel approach called IMBP based on attributed PPI networks. IMBP can effectively learn the degree of contributions of different biomedical resource for complex prediction. The experimental results show that IMBP can make good use of multiple biomedical data and achieve state-of-the-art performance.

Protein complexes are important for unraveling the secrets of cellular organization and function. Many computational approaches have been developed to predict protein complexes in protein-protein interaction (PPI) networks. However, most existing approaches focus mainly on the topological structure of PPI networks, and largely ignore the gene ontology (GO) annotation information. In this paper, we constructed ontology attributed PPI networks with PPI data and GO resource. After constructing ontology attributed networks, we proposed a novel approach called CSO (clustering based on network structure and ontology attribute similarity). Structural information and GO attribute information are complementary in ontology attributed networks. CSO can effectively take advantage of the correlation between frequent GO annotation sets and the dense subgraph for protein complex prediction. Our proposed CSO approach was applied to four different yeast PPI data sets and predicted many well-known protein complexes. The experimental results showed that CSO was valuable in predicting protein complexes and achieved state-of-the-art performance.

Extracting protein-protein interaction (PPI) from biomedical literature is an important task in biomedical text mining (BioTM). In this paper, we propose a hash subgraph pairwise (HSP) kernel-based approach for this task. The key to the novel kernel is to use the hierarchical hash labels to express the structural information of subgraphs in a linear time. We apply the graph kernel to compute dependency graphs representing the sentence structure for protein-protein interaction extraction task, which can efficiently make use of full graph structural information, and particularly capture the contiguous topological and label information ignored before. We evaluate the proposed approach on five publicly available PPI corpora. The experimental results show that our approach significantly outperforms all-path kernel approach on all five corpora and achieves state-of-the-art performance.

Protein complexes play a key role in many biological processes. Various computational approaches have been developed to identify complexes from protein-protein interaction (PPI) networks. However, high false-positive rate of PPIs makes the identification challenging. In this paper, we propose a protein semantic similarity measure based on the ontology structure of Gene Ontology (GO) terms and GO annotations to estimate the reliability of interactions in PPI networks. Interaction pairs with low GO semantic similarity are removed from the network as unreliable interactions. Then, a cluster-expanding algorithm is applied to identify complexes with core-attachment structure on the filtered network. We have applied our method on three different yeast PPI networks. The effectiveness of our method is examined on two benchmark complex datasets. Experimental results show that our method outperforms other state-of-the-art approaches in most evaluation metrics. Removing interactions with low similarity significantly improves the performance of complex identification.