BACKGROUND: Drug combination therapy often outperforms monotherapy in cancer treatment, but the vast number of available drugs makes manual screening for synergistic combinations costly. Computational methods, especially deep learning, can reduce the search space by predicting likely synergistic drug combinations. Recent studies have improved drug synergy prediction by modeling associations among different biological entities, but drug-drug interactions have not been fully leveraged in this scenario, which motivated the work presented in this paper. METHODS: This paper proposes a deep learning method named HGTSynergy to predict synergistic drug combinations, which employs a heterogeneous graph attention network and a tailored task to capture complex latent patterns in the drug network as prior knowledge. The learned knowledge is then transferred through a transfer learning framework to the downstream task of predicting drug synergy scores, effectively enhancing predictive performance. RESULTS: A five-fold nested cross-validation is employed to train HGTSynergy. In the synergy regression task, HGTSynergy outperforms seven deep learning methods, achieving a mean squared error of 222.83, root mean squared error of 14.91, and Pearson correlation coefficient of 0.75. For the synergy classification task, it also surpasses other methods with an area under the receiver operating characteristic curve of 0.90, area under the precision-recall curve of 0.63, accuracy of 0.94, precision of 0.72, and Cohen's Kappa of 0.52. The ablation study verifies that the heterogeneous graph attention network and the transfer learning framework both have a positive effect on prediction performance. Moreover, a series of analyses demonstrates that the proposed method exhibits strong generalization performance and interpretability. The case study further validates its consistency with prior research. CONCLUSIONS: This study suggests that drug synergy prediction can be improved by comprehensively modeling diverse drug-drug interaction types and leveraging transfer learning to extract prior knowledge from them. The ability of HGTSynergy to discover new anticancer synergistic drug combinations outperforms other state-of-the-art methods. HGTSynergy promises to be a powerful tool to pre-screen anticancer synergistic drug combinations.

Identifying synergistic anticancer drug combinations is a key challenge due to the vast number of potential drug pairs and the high cost of experimental screening. Recent advances leverage deep learning and graph neural networks (GNNs) to learn molecular representations directly from drug structures, but the limited number of unique drugs in available datasets restricts the effectiveness of such models. In this paper, we propose a framework that addresses this issue through a DDI-enhanced Deep Graph InfoMax pretraining strategy. Our approach captures structural and relational drug features by jointly maximizing local–global mutual information and incorporating drug–drug interaction prediction. A multi-level interaction model with semantic attention further enhances feature fusion, leading to improved synergy prediction performance. We compared our method with five advanced methods on two public datasets. The results demonstrate that the proposed method exhibits superior generalization ability.

Drug combination therapy is highly regarded in cancer treatment. Computational methods offer a time- and cost-effective opportunity to explore the vast combination space. Although deep learning-based prediction methods lead the field, their generalization ability remains unsatisfactory. Few previous studies have the ability to finely characterize drugs and cell lines at both the micro-scale and macro-scale. Furthermore, the interaction of cross-scale information is often overlooked. These two points limit models' ability of predicting the synergism of drug combinations in cell lines. To address the issues, we propose a novel anticancer synergistic drug combination prediction method termed MMFSynergy in this article. The construction of MMFSynergy involves three phases. First, MMFSynergy pretrains two micro encoders and a macro graph encoder, which can capture micro- or macro-scale information from large volumes of unlabeled data and generate generic features for drugs and proteins. Second, it represents drugs and proteins by fusing cross-scale information through a self-supervised task. Finally, it employs a Transformer Encoder-based model to predict synergy scores, taking representations of drugs in the combinations and the associated proteins of cell lines as input. We compared our method with eight advanced methods across three typical scenarios based on two public datasets. The results consistently demonstrated that the proposed method's generalization ability outperforms six advanced methods'. We also conducted experiments including but not limited to ablation study and case study to further exhibit the effectiveness of MMFSynergy.

Nowadays, many knowledge graph completion models are proposed to assist the automatic construction of large knowledge graphs. While knowledge graph embedding models and textual information enhanced models are two tendencies in this area, they both suffer from some shortcomings, for example, relying too much on one single modal information may cause the limitation of performance. However, only a few works attempt to integrate multiple modalities. Besides, we found that the semantic similarity between head and tail entities correlates to the enhancing effect of textual information, and the semantic similarity is also related to relation types. We call this phenomenon relational sensitivity. To address these issues, we propose a relation sensitive textual information enhanced knowledge graph completion model (RSTIE-KGC). In our work, by integrating pre-trained language models (PLM) with knowledge graph embedding models, we fuse structural information and textual information, taking advantage of both topological and semantic features. Instead of finetuning the whole PLMs as existing models do, we choose a more efficient way, using frozen PLMs followed by an adapter to fit the text embeddings to our tasks, so that we can reduce training costs and enlarge the scale of negative samples, which maintains accuracy and effectiveness of our model. Based on the relational sensitivity, we propose our RelRank block, which selectively enhances textual information by calculating and filtering mean rank proportion (MRP) score for each relation type, thereby making better use of beneficial semantic information and reducing the noise and redundancy caused by textual information. The prediction process makes more refined use of textual information, as a result improving the accuracy of the model in the link prediction task. We conducted link prediction experiments on two real-world datasets. On FB15k-237, our model outperformed the current state-of-art textual information enhanced models in both MRR and Hit@k metrics. On WN18RR, our model also showed a stable prediction performance, and the results of both MRR and Hits@1 metrics were better than the most textual information enhanced models.

Advancements in satellite remote sensing have enhanced Earth observation, enabling the acquisition of images crucial for various remote sensing applications.However, cloud cover degrades image quality and obstructs surface information.Traditional cloud removal techniques struggle to restore both low-level and high-level features, especially under complex conditions.To address these challenges, we propose STGAN-CR, a novel framework integrating Swin Transformer with Generative Adversarial Networks (GANs) to optimize image detail recovery.Leveraging the Swin Transformer's global modeling capabilities, our method enhances feature extraction and restoration, overcoming limitations of conventional models.We introduce a new evaluation metric focused on scene classification accuracy postde-clouding to better assess practical utility.Extensive experiments and ablation studies show that STGAN-CR outperforms existing models in visual quality and classification performance.These advancements offer an effective solution for enhancing the quality and utility of remote sensing images, balancing the restoration of both low-level and high-level features, and providing more meaningful de-clouded images for downstream applications.

Synthetic lethality (SL) refers to the phenomenon that simultaneous mutation of two genes is lethal to cells, while mutation of either gene alone is not lethal. Exploiting this genetic interaction holds immense clinical potential for selectively killing cancer cells without harming normal cells. Given the vast genomic combinatorial space, relying solely on wet lab experiments for screening synthetic lethal gene pairs is impractical, leading to the emergence of various computational methods. Existing computational methods often rely on single-feature extraction methods or single data sources for prediction, resulting in poor predictive accuracy when faced with unseen genes. In this work, we propose a novel deep ensemble model for synthetic lethality prediction based on a stacking strategy (DSESL). Firstly, leveraging the publicly available SynLethKG knowledge graph, we learn gene embed dings at three different focus-levels: single-entity single-relation, single-entity multi-relation, and multi-entity multi-relation, constructing three sub-models for prediction from the knowledge graph. Additionally, we incorporate signaling pathway data and utilize graph neural network-based methods to construct a pathway sub-model. Finally, we adopt a stacking strategy-based ensemble approach to effectively integrate the prediction results from different sub-models. Based experimental results, our proposed DSESL model outperforms existing state-of-the-art SL prediction methods in all three prediction scenarios. The source code of DSESL is available at https://github.com/TOJSSE-iData/DSESL/.

In the field of change detection, detecting changes in images with different resolutions is crucial for both long-term interval scenes and scenarios that require rapid detection. However, existing methods face two main issues. Firstly, they require more stringent prior knowledge. The SPM-based methods require pixel-level class labeling of high-resolution(HR) images, while the approaches based on image super-resolution require HR images corresponding to low-resolutionr(LR) images. Such prior knowledge is either costly for labeling or difficult to meet in realistic scenarios. The second is that redundant error accumulation affects detection accuracy. Whether in traditional sub-pixel mapping(SPM) methods or deep learning methods based on image super-resolution, the final detection results are obtained after generating HR images from LR images. The redundant error produced in this step will be accumulated and affect the final detection results. Although the unsupervised methods do not have this problem, the detection accuracy is not as good as that of the supervised. To address these issues, we propose a multi-scale Transformer network(MTN). This model first uses a multi-scale feature extractor(MFE) to extract multi-scale features and perform scale matching at the feature level. Then, the Transformer is used to extract long-range relationships of ground objects on the multi-scale features to enhance the features. Finally, the multi-scale features are fused, and a classifier composed of a convolutional network is used to obtain binary change detection results. In addition, we consider that the edges of objects may be affected during the scale matching process, and introduce a CEBoundary Loss to better detect object edges. The results on the LEVIR and Google datasets demonstrate the effectiveness of our proposed method. The source code of MTN is available at https://github.com/Gavin-debug/MultiResolutionCD.

BACKGROUND: The discovery of anticancer drug combinations is a crucial work of anticancer treatment. In recent years, pre-screening drug combinations with synergistic effects in a large-scale search space adopting computational methods, especially deep learning methods, is increasingly popular with researchers. Although achievements have been made to predict anticancer synergistic drug combinations based on deep learning, the application of multi-task learning in this field is relatively rare. The successful practice of multi-task learning in various fields shows that it can effectively learn multiple tasks jointly and improve the performance of all the tasks. METHODS: In this paper, we propose MTLSynergy which is based on multi-task learning and deep neural networks to predict synergistic anticancer drug combinations. It simultaneously learns two crucial prediction tasks in anticancer treatment, which are synergy prediction of drug combinations and sensitivity prediction of monotherapy. And MTLSynergy integrates the classification and regression of prediction tasks into the same model. Moreover, autoencoders are employed to reduce the dimensions of input features. RESULTS: Compared with the previous methods listed in this paper, MTLSynergy achieves the lowest mean square error of 216.47 and the highest Pearson correlation coefficient of 0.76 on the drug synergy prediction task. On the corresponding classification task, the area under the receiver operator characteristics curve and the area under the precision-recall curve are 0.90 and 0.62, respectively, which are equivalent to the comparison methods. Through the ablation study, we verify that multi-task learning and autoencoder both have a positive effect on prediction performance. In addition, the prediction results of MTLSynergy in many cases are also consistent with previous studies. CONCLUSION: Our study suggests that multi-task learning is significantly beneficial for both drug synergy prediction and monotherapy sensitivity prediction when combining these two tasks into one model. The ability of MTLSynergy to discover new anticancer synergistic drug combinations noteworthily outperforms other state-of-the-art methods. MTLSynergy promises to be a powerful tool to pre-screen anticancer synergistic drug combinations.

Although drug combinations in cancer treatment appear to be a promising therapeutic strategy with respect to monotherapy, it is arduous to discover new synergistic drug combinations due to the combinatorial explosion. Deep learning technology holds immense promise for better prediction of in vitro synergistic drug combinations for certain cell lines. In methods applying such technology, omics data are widely adopted to construct cell line features. However, biological network data are rarely considered yet, which is worthy of in-depth study. In this study, we propose a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations. By leveraging the Graph Convolutional Network, PRODeepSyn integrates the protein-protein interaction (PPI) network with omics data to construct low-dimensional dense embeddings for cell lines. PRODeepSyn then builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features. PRODeepSyn achieves the lowest root mean square error of 15.08 and the highest Pearson correlation coefficient of 0.75, outperforming two deep learning methods and four machine learning methods. On the classification task, PRODeepSyn achieves an area under the receiver operator characteristics curve of 0.90, an area under the precision-recall curve of 0.63 and a Cohen's Kappa of 0.53. In the ablation study, we find that using the multi-omics data and the integrated PPI network's information both can improve the prediction results. Additionally, the case study demonstrates the consistency between PRODeepSyn and previous studies.

With the rapid growth of multimodal data in social medias and the huge requirement of short but abundant information. Multimodal summarization has drawn much attention in both industry and academia. It usually obtains textual summary from multiple sources by computer vision or nature language processing technologies. However, there are also two challenges in modeling such task: 1) The feature representation is limited by the non-alignment among multimodal data; 2) Massive parallel data is required during training, which is time-consuming and laborious. In this paper, we introduce an unsupervised architecture (Compress-then-Reconstruct, CtnR) to generate the summary in an end-to-end manner and a Cross-Modal Transformer module (CMTrans) to fuse the multimodal non-alignment information. Comprehensive experiments show that the proposed CtnR framework with CMTrans outperforms mainstream unsupervised approaches in terms of BLEU, ROUGE and relevance scores on MSMO and Youtube News dataset, which increase 8.82% and 11.01% on average respectively.

The commit messages in source code repositories are valuable but not easy to be generated manually in time for tracking issues, reporting bugs, and understanding codes. Recently published works indicated that the deep neural machine translation approaches have drawn considerable attentions on automatic generation of commit messages. However, they could not deal with out-of-vocabulary (OOV) words, which are essential context-specific identifiers such as class names and method names in code diffs. In this paper, we propose PtrGNCMsg, a novel approach which is based on an improved sequence-to-sequence model with the pointer-generator network to translate code diffs into commit messages. By searching the smallest identifier set with the highest probability, PtrGNCMsg outperforms recent approaches based on neural machine translation, and first enables the prediction of OOV words. The experimental results based on the corpus of diffs and manual commit messages from the top 2,000 Java projects in GitHub show that PtrGNCMsg outperforms the state-of-the-art approach with improved BLEU by 1.02, ROUGE-1 by 4.00 and ROUGE-L by 3.78, respectively.

Multistep flow prediction is an essential task for the car-sharing systems.An accurate flow prediction model can help system operators to pre-allocate the cars to meet the demand of users.However, this task is challenging due to the complex spatial and temporal relations among stations.Existing works only considered temporal relations (e.g., using LSTM) or spatial relations (e.g., using CNN) independently.In this paper, we propose an attention multi-graph convolutional sequenceto-sequence model (AMGC-Seq2Seq), which is a novel deep learning model for multistep flow prediction.The proposed model uses the encoder-decoder architecture, wherein the encoder part, spatial and temporal relations are encoded simultaneously.Then the encoded information is passed to the decoder to generate multistep outputs.In this work, specific multiple graphs are constructed to reflect spatial relations from different aspects, and we model them by using the proposed multi-graph convolution.Attention mechanism is also used to capture the important relations from previous information.Experiments on a large-scale real-world car-sharing dataset demonstrate the effectiveness of our approach over state-of-the-art methods.

Multistep flow prediction is an essential task for the car-sharing systems. An accurate flow prediction model can help system operators to pre-allocate the cars to meet the demand of users. However, this task is challenging due to the complex spatial and temporal relations among stations. Existing works only considered temporal relations (e.g. using LSTM) or spatial relations (e.g. using CNN) independently. In this paper, we propose an attention to multi-graph convolutional sequence-to-sequence model (AMGC-Seq2Seq), which is a novel deep learning model for multistep flow prediction. The proposed model uses the encoder–decoder architecture, wherein the encoder part, spatial and temporal relations are encoded simultaneously. Then the encoded information is passed to the decoder to generate multistep outputs. In this work, specific multiple graphs are constructed to reflect spatial relations from different aspects, and we model them by using the proposed multi-graph convolution. Attention mechanism is also used to capture the important relations from previous information. Experiments on a large-scale real-world car-sharing dataset demonstrate the effectiveness of our approach over state-of-the-art methods.

Real-time collaborative programming allows programmers to concurrently edit shared source code over communication networks. To support semantic conflict prevention, prior work has proposed a bask dependency-based automatic locking (DAL) approach to automatically grant locks on source code regions with dependency relationships, under the assumptions that there exists no locking-scope overlapping among concurrent editing operations, and the source code structure remains static during the collaboration process. To address major restrictions of the basic DAL scheme, this paper presents a shard-locking approach and techniques to fully support unconstrained real-time collaborative programming with semantic conflict prevention. The approach allows multiple programmers to concurrently edit source code regions with overlapping locking scopes in the presence of concurrent editing operations and dynamic source code structures. The techniques and solutions have been implemented in a research prototype for evaluations.

Recent years witnessed popular use of various mobile devices, e.g., smart phones, vehicle networks and wearable watches. Such mobile devices generate massive trajectory data, and literature have proposed various algorithms to leverage the trajectory data for map inference. Unfortunately, such algorithms are hard to achieve both high map quality and computation efficiency. In this paper, we propose a solution framework to infer road network maps with high quality and efficiency. The key of our map inference is to divide map extent into smaller cells and maintain a binary cell-trajectory matrix. The binary matrix determines whether or not a trajectory passes a cell. We infer the importance of each cell from the matrix using a popular topic model (e.g., LDA [13] and pLSA [8]). Based on such computed importance, we next infer representative points and road segments to derive a road network map. Our extensive experiments on real data sets verify that the proposed inference algorithm can achieve higher map quality and meanwhile 1.5 ×, 6.8 × and 280 × shorter running time, when compared with three state of the arts including three representative work [4], [7], [14].

Feature selection methods are designed to obtain the optimal feature subset from the original features to give the most accurate prediction. So far, supervised and unsupervised feature selection methods have been discussed and developed separately. However, these two methods can be combined together as a hybrid feature selection method for some data sets. In this paper, we propose a mutual information-based (MI-based) hybrid feature selection method using feature clustering. In the unsupervised learning stage, the original features are grouped into several clusters based on the feature similarity to each other with agglomerative hierarchical clustering. Then in the supervised learning stage, the feature in each cluster that can maximize the feature similarity with the response feature which represents the class label is selected as the representative feature. These representative features compose the feature subset. Our contribution includes 1)the newly proposed feature selection method and 2)the application of feature clustering for software cost estimation. The proposed method employs wrapper approaches, so it can evaluate the prediction performance of each feature subset to determine the optimal one. The experimental results in software cost estimation demonstrate that the proposed method can outperform at least 11.5% and 14.8% than the supervised feature selection method INMIFS and mRMRFS in ISBSG R8 and Desharnais data set in terms of PRED (0.25) value.