Graph Neural Networks (GNNs) are becoming increasingly popular in graph data processing due to their excellent performance in feature extraction on graph datasets. Compared to GPUs, CPUs are more widely accessible and serve as a practical platform for GNN inference. However, achieving efficient GNN execution on CPUs remains a challenge. We first comprehensively evaluate and quantitatively analyze the performance of GNN inference on multi-core CPUs using the state-of-the-art frameworks, identifying four key performance bottlenecks: inefficient sparse computation, poor data locality, workload imbalance, and inefficient General Matrix Multiplication (GEMM). To tackle these issues, we introduce a set of joint optimizations. Specifically, for the aggregation phase, we propose three optimizations: a register padding and tiling Graph Sparse-dense Matrix Multiplication (GSpMM) algorithm that leverages the computation capability of long vector processing units on modern multi-core CPUs, a destination node-oriented indexes reorganization to enhance data locality, and a boundary buffer-based method to balance the workloads. Additionally, for the update phase, we develop an efficient bias fusion GEMM algorithm, tailored for the irregular matrices. We evaluate the proposed optimizations extensively with three popular GNN models on three typical multi-core CPU platforms. Experimental results on Intel, AMD, and ARM platforms show that our optimizations outperform the state-of-the-art GNN framework DGL by an average factor of 2.41×, 1.58×, and 2.04× (up to 4.75×, 2.70×, and 3.55×), respectively. Compared to PyG, our implementations achieve an average speedup of 1.70×, 1.86×, and 2.44×, respectively.

The overset grid method is widely employed to solve moving boundary problems in numerical simulations. However, the heavy and inevitable communication resulting from boundary movements severely impedes the improvement of parallel efficiency. This paper proposes a Motion Trace Decomposition (MTD) method to alleviate this issue. The MTD method minimizes communication overhead between processors by decomposing sub-grids and distributing them according to the object motion trajectory, negating the need to reproduce communication areas when boundaries move. Various tests were conducted to evaluate the MTD method, incorporating diverse motion types, such as displacement and rotation. Results from experimental simulations with 1.9 × 106 grid cells indicate that the proposed method enhances the parallel efficiency of the assembly process by up to 20.35% using 72 processors. These findings showcase the significant potential of the MTD method in alleviating communication challenges associated with simulating moving boundary problems using overset grids.

With the exponential growth of biomedical knowledge in unstructured text repositories such as PubMed, it is imminent to establish a knowledge graph-style, efficient searchable and targeted database that can support the need of information retrieval from researchers and clinicians. To mine knowledge from graph databases, most previous methods view a triple in a graph (see Fig. 1) as the basic processing unit and embed the triplet element (i.e. drugs/chemicals, proteins/genes and their interaction) as separated embedding matrices, which cannot capture the semantic correlation among triple elements. To remedy the loss of semantic correlation caused by disjoint embeddings, we propose a novel approach to learn triple embeddings by combining entities and interactions into a unified representation. Furthermore, traditional methods usually learn triple embeddings from scratch, which cannot take advantage of the rich domain knowledge embedded in pre-trained models, and is also another significant reason for the fact that they cannot distinguish the differences implied by the same entity in the multi-interaction triples. In this paper, we propose a novel fine-tuning based approach to learn better triple embeddings by creating weakly supervised signals from pre-trained knowledge graph embeddings. The method automatically samples triples from knowledge graphs and estimates their pairwise similarity from pre-trained embedding models. The triples are then fed pairwise into a Siamese-like neural architecture, where the triple representation is fine-tuned in the manner bootstrapped by triple similarity scores. Finally, we demonstrate that triple embeddings learned with our method can be readily applied to several downstream applications (e.g. triple classification and triple clustering). We evaluated the proposed method on two open-source drug-protein knowledge graphs constructed from PubMed abstracts, as provided by BioCreative. Our method achieves consistent improvement in both triple classification and triple clustering tasks when compared to other state-of-the-art triple embedding methods, with an average 35% improvement of F1 score for the multi-interaction triples.

The scale of model parameters and the amount of training data is exponentially increasing. It requires more GPU memory with the exponential increasement of model parameters. Recomputation and swapping are two main memory optimization methods that have been extensively studied, and there are also optimization strategies that combine the two methods. However, most of them are based on heuristic search strategies, which do not explore the complete solution space and can’t guarantee the optimality of the solution results. An optimal search strategy with tensor-level recomputation and swapping is expected in large-scale model training. In this paper, we propose an optimal strategy searching algorithm combining tensor-based recomputation and swapping. Specifically, the memory swapping strategy is reformulated as an optimization problem, which converts the memory constraints into mixed integer programming, to find the optimal memory optimization strategy. By leveraging the advantages of both recomputation and swapping, this approach minimizes computation consumption without exceeding the available memory limitation. Experimental results show that our method exhibits about 60% reduction in memory requirements during the training process. Furthermore, our method can reduce the overall training time beyond the existing algorithms. Compared to Checkmate, our approach achieves about 0.3–0.9% reduction in computation cost per iteration.

MOTIVATION: Understanding chemical-gene interactions (CGIs) is crucial for screening drugs. Wet experiments are usually costly and laborious, which limits relevant studies to a small scale. On the contrary, computational studies enable efficient in-silico exploration. For the CGI prediction problem, a common method is to perform systematic analyses on a heterogeneous network involving various biomedical entities. Recently, graph neural networks become popular in the field of relation prediction. However, the inherent heterogeneous complexity of biological interaction networks and the massive amount of data pose enormous challenges. This paper aims to develop a data-driven model that is capable of learning latent information from the interaction network and making correct predictions. RESULTS: We developed BioNet, a deep biological networkmodel with a graph encoder-decoder architecture. The graph encoder utilizes graph convolution to learn latent information embedded in complex interactions among chemicals, genes, diseases and biological pathways. The learning process is featured by two consecutive steps. Then, embedded information learnt by the encoder is then employed to make multi-type interaction predictions between chemicals and genes with a tensor decomposition decoder based on the RESCAL algorithm. BioNet includes 79 325 entities as nodes, and 34 005 501 relations as edges. To train such a massive deep graph model, BioNet introduces a parallel training algorithm utilizing multiple Graphics Processing Unit (GPUs). The evaluation experiments indicated that BioNet exhibits outstanding prediction performance with a best area under Receiver Operating Characteristic (ROC) curve of 0.952, which significantly surpasses state-of-theart methods. For further validation, top predicted CGIs of cancer and COVID-19 by BioNet were verified by external curated data and published literature.

BACKGROUND: Stroke has an acute onset and a high mortality rate, making it one of the most fatal diseases worldwide. Its underlying biology and treatments have been widely studied both in the "Western" biomedicine and the Traditional Chinese Medicine (TCM). However, these two approaches are often studied and reported in insolation, both in the literature and associated databases. RESULTS: To aid research in finding effective prevention methods and treatments, we integrated knowledge from the literature and a number of databases (e.g. CID, TCMID, ETCM). We employed a suite of biomedical text mining (i.e. named-entity) approaches to identify mentions of genes, diseases, drugs, chemicals, symptoms, Chinese herbs and patent medicines, etc. in a large set of stroke papers from both biomedical and TCM domains. Then, using a combination of a rule-based approach with a pre-trained BioBERT model, we extracted and classified links and relationships among stroke-related entities as expressed in the literature. We construct StrokeKG, a knowledge graph includes almost 46 k nodes of nine types, and 157 k links of 30 types, connecting diseases, genes, symptoms, drugs, pathways, herbs, chemical, ingredients and patent medicine. CONCLUSIONS: Our Stroke-KG can provide practical and reliable stroke-related knowledge to help with stroke-related research like exploring new directions for stroke research and ideas for drug repurposing and discovery. We make StrokeKG freely available at http://114.115.208.144:7474/browser/ (Please click "Connect" directly) and the source structured data for stroke at https://github.com/yangxi1016/Stroke.

BACKGROUND: Elucidation of interactive relation between chemicals and genes is of key relevance not only for discovering new drug leads in drug development but also for repositioning existing drugs to novel therapeutic targets. Recently, biological network-based approaches have been proven to be effective in predicting chemical-gene interactions. RESULTS: We present CGINet, a graph convolutional network-based method for identifying chemical-gene interactions in an integrated multi-relational graph containing three types of nodes: chemicals, genes, and pathways. We investigate two different perspectives on learning node embeddings. One is to view the graph as a whole, and the other is to adopt a subgraph view that initial node embeddings are learned from the binary association subgraphs and then transferred to the multi-interaction subgraph for more focused learning of higher-level target node representations. Besides, we reconstruct the topological structures of target nodes with the latent links captured by the designed substructures. CGINet adopts an end-to-end way that the encoder and the decoder are trained jointly with known chemical-gene interactions. We aim to predict unknown but potential associations between chemicals and genes as well as their interaction types. CONCLUSIONS: We study three model implementations CGINet-1/2/3 with various components and compare them with baseline approaches. As the experimental results suggest, our models exhibit competitive performances on identifying chemical-gene interactions. Besides, the subgraph perspective and the latent link both play positive roles in learning much more informative node embeddings and can lead to improved prediction.

BACKGROUND: The detection and interpretation of CNVs are of clinical importance in genetic testing. Several databases and web services are already being used by clinical geneticists to interpret the medical relevance of identified CNVs in patients. However, geneticists or physicians would like to obtain the original literature context for more detailed information, especially for rare CNVs that were not included in databases. RESULTS: The resulting CNVdigest database includes 440,485 sentences for CNV-disease relationship. A total number of 1582 CNVs and 2425 diseases are involved. Sentences describing CNV-disease correlations are indexed in CNVdigest, with CNV mentions and disease mentions annotated. CONCLUSIONS: In this paper, we use a systematic text mining method to construct a database for the relationship between CNVs and diseases. Based on that, we also developed a concise front-end to facilitate the analysis of CNV/disease association, providing a user-friendly web interface for convenient queries. The resulting system is publically available at http://cnv.gtxlab.com /.

BACKGROUND: Drug-drug interaction extraction (DDI) needs assistance from automated methods to address the explosively increasing biomedical texts. In recent years, deep neural network based models have been developed to address such needs and they have made significant progress in relation identification. METHODS: We propose a dependency-based deep neural network model for DDI extraction. By introducing the dependency-based technique to a bi-directional long short term memory network (Bi-LSTM), we build three channels, namely, Linear channel, DFS channel and BFS channel. All of these channels are constructed with three network layers, including embedding layer, LSTM layer and max pooling layer from bottom up. In the embedding layer, we extract two types of features, one is distance-based feature and another is dependency-based feature. In the LSTM layer, a Bi-LSTM is instituted in each channel to better capture relation information. Then max pooling is used to get optimal features from the entire encoding sequential data. At last, we concatenate the outputs of all channels and then link it to the softmax layer for relation identification. RESULTS: To the best of our knowledge, our model achieves new state-of-the-art performance with the F-score of 72.0% on the DDIExtraction 2013 corpus. Moreover, our approach obtains much higher Recall value compared to the existing methods. CONCLUSIONS: The dependency-based Bi-LSTM model can learn effective relation information with less feature engineering in the task of DDI extraction. Besides, the experimental results show that our model excels at balancing the Precision and Recall values.