Graph Convolutional Networks (GCNs) have demonstrated significant efficacy in graph representation learning. Existing approaches often rely on stacking multiple GCN layers to incorporate high-order neighborhood information. How-ever, deeper GCN architectures tend to learn similar node representations by more focusing on the global topology of the graph, thereby diminishing the influence of local structures and leading to over-smoothing. To address this, we propose a Localized Differential Attention Graph Convolutional Network (LDA -GCN), designed to enhance the preservation of local structural information. LDA-GCN introduces a localized differential attention mechanism that diversifies node representations and includes a drop aggregation module to strengthen the robustness of this differential attention. Extensive experiments conducted on several benchmark datasets confirm that LDA-GCN achieves superior performance compared to state-of-the-art methods.

Accurate diagnosis of malignant lung nodules in Computed Tomography (CT) images is crucial for reducing patient mortality. However, deep learning-based approaches for lung nodule diagnosis often struggle to achieve high accuracy due to the interference of redundant noise from tissue slices and insufficient exploration of the interactions between cross-modal attribute data, such as spiculation, lobulation, and calcification. To overcome these obstacles, we propose a novel Multi-perspective Information Enhancement Graph Attention Network (MIE-GAT) for automated lung nodule diagnosis. Unlike existing methods, our approach integrates slice-based image retrieval with cross-modal attribute interaction knowledge to effectively reduce redundant noise from tissue slices and capture the intricate relationships between various nodule attributes, significantly improving diagnostic accuracy. MIE-GAT consists of two subgraphs: a slice subgraph for spatial relationships within CT slices, and an attribute subgraph for nodule attribute interactions. The model introduces multiple central nodes, each focusing on different perspectives of the 3D CT scan. By facilitating directed information propagation between central nodes, MIE-GAT enhances feature representations across multiple scales, progressively improving its ability to distinguish subtle features of the nodule. Ultimately, this multi-perspective information enhancement mechanism enables the model to align attribute-based interaction knowledge and perform effective slice-based retrieval, focusing on the most relevant slices while reducing the interference of redundant noise. Extensive experiments on the LIDC-IDRI and LIDP datasets demonstrate that MIE-GAT outperforms state-of-the-art methods, confirming its effectiveness in improving the accuracy of automated lung nodule diagnosis. The source code for MIE-GAT is available in the anonymous repository at https://github.com/MindExpanse/NoduleClassification.

Inductive relation reasoning in knowledge graphs aims at predicting missing triplets involving unseen entities and/or unseen relations. While subgraph-based methods that reason about the local structure surrounding a candidate triplet have shown promise, they often fall short in accurately modeling the causal dependence between a triplet's subgraph and its ground-truth label. This limitation typically results in a susceptibility to spurious correlations caused by confounders, adversely affecting generalization capabilities. Herein, we introduce a novel front-door adjustment-based approach designed to learn the causal relationship between subgraphs and their ground-truth labels, specifically for inductive relation prediction. We conceptualize the semantic information of subgraphs as a mediator and employ a graph data augmentation mechanism to create augmented subgraphs. Furthermore, we integrate a fusion module and a decoder within the front-door adjustment framework, enabling the estimation of the mediator's combination with augmented subgraphs. We also introduce the reparameterization trick in the fusion model to enhance model robustness. Extensive experiments on widely recognized benchmark datasets demonstrate the proposed method's superiority in inductive relation prediction, particularly for tasks involving unseen entities and unseen relations. Additionally, the subgraphs reconstructed by our decoder offer valuable insights into the model's decision-making process, enhancing transparency and interpretability.

Accurate prediction of protein-ligand binding affinities can significantly advance the development of drug discovery. Several graph neural network (GNN)-based methods learn representations of protein-ligand complexes via modeling intermolecule interactions and spatial structures (e.g., distances and angles) of complexes. However, these methods fail to emphasize the importance of bonds and learn hierarchical structures of complexes, which are significant for binding affinity prediction. In this article, we propose the structure-aware graph attention diffusion network (SGADN) to incorporate both distance and angle information for efficient spatial structure learning. We model complexes as line graphs with distance and angle information, focusing on bonds as nodes. Then we perform line graph attention diffusion layers (LGADLs) on line graphs to explore long-range bond node interactions and enhance spatial structure learning. Furthermore, we propose an attentive pooling layer (APL) to refine the hierarchical structures in complexes. Extensive experimental studies on two benchmarks demonstrate the superiority of SGADN for binding affinity prediction.

Drug-target interaction (DTI) prediction is an essential step in drug repositioning. A few graph neural network (GNN)-based methods have been proposed for DTI prediction using heterogeneous biological data. However, existing GNN-based methods only aggregate information from directly connected nodes restricted in a drug-related or a target-related network and are incapable of capturing high-order dependencies in the biological heterogeneous graph. In this paper, we propose a metapath-aggregated heterogeneous graph neural network (MHGNN) to capture complex structures and rich semantics in the biological heterogeneous graph for DTI prediction. Specifically, MHGNN enhances heterogeneous graph structure learning and high-order semantics learning by modeling high-order relations via metapaths. Additionally, MHGNN enriches high-order correlations between drug-target pairs (DTPs) by constructing a DTP correlation graph with DTPs as nodes. We conduct extensive experiments on three biological heterogeneous datasets. MHGNN favorably surpasses 17 state-of-the-art methods over 6 evaluation metrics, which verifies its efficacy for DTI prediction. The code is available at https://github.com/Zora-LM/MHGNN-DTI.

Open-source software (OSS) licenses dictate the conditions, which should be followed to reuse, distribute, and modify software. Apart from widely-used licenses such as the MIT License, developers are also allowed to customize their own licenses (called custom license), whose descriptions are more flexible. The presence of such various licenses imposes challenges to understand licenses and their compatibility. To avoid financial and legal risks, it is essential to ensure license compatibility when integrating third-party packages or reusing code accompanied with licenses. In this work, we propose LiDetector , an effective tool that extracts and interprets OSS licenses (including both official licenses and custom licenses), and detects license incompatibility among these licenses. Specifically, LiDetector introduces a learning-based method to automatically identify meaningful license terms from an arbitrary license, and employs Probabilistic Context-Free Grammar (PCFG) to infer rights and obligations for incompatibility detection. Experiments demonstrate that LiDetector outperforms existing methods with 93.28% precision for term identification, and 91.09% accuracy for right and obligation inference, and can effectively detect incompatibility with 10.06% FP rate and 2.56% FN rate. Furthermore, with LiDetector , our large-scale empirical study on 1,846 projects reveals that 72.91% of the projects are suffering from license incompatibility, including popular ones such as the MIT License and the Apache License. We highlighted lessons learned from perspectives of different stakeholders and made all related data and the replication package publicly available to facilitate follow-up research.

Early detection of lung cancer is crucial for five-year survival of patients. Compared with the pathological analysis and CT scans, the circulating tumor DNA (ctDNA) methylation based approach is noninvasive and cost-effective, and thus is one of the most promising methods for early detection of lung cancer. Existing studies on ctDNA methylation data measure the methylation level of each region with a predefined metric, ignoring the positions of methylated CpG sites and methylation patterns, thus are not able to capture the early cancer signals. In this paper, we propose a blood-based lung cancer detection method, and present the first ever study to represent methylation regions by continuous vectors. Specifically, we propose DeepMeth to regard each region as a one-channel image and develop an auto-encoder model to learn its representation. For each ctDNA methylation sample, DeepMeth achieves its representation via concatenating the region vectors. We evaluate DeepMeth on a multicenter clinical dataset collected from 14 hospitals. The experiments show that DeepMeth achieves about 5%-8% improvements compared with the baselines in terms of Area Under the Curve (AUC). Moreover, the experiments also demonstrate that DeepMeth can be combined with traditional scalar metrics to enhance the diagnostic power of ctDNA methylation classifiers. DeepMeth has been clinically deployed and applied to 450 patients from 94 hospitals nationally since April 2020.

Effective drug-target binding affinity (DTA) prediction is essential for drug discovery and development. The development of machine learning techniques considerably advances it. However, the cold-start problems in DTA prediction are still under-explored, which significantly degrades prediction performances on novel drugs and novel targets. In this paper, we propose a contrastive meta-learning (CML) framework to address these issues. We define drug-anchored tasks and target-anchored tasks, which enables the employment of meta-learning to accumulate common knowledge from various tasks so as to adapt to new tasks faster and better. Besides, we utilize a task inequality loss to measure task disparities and enhance model sensitivities to new tasks. We also propose a contrastive learning block (CLB) to explore correlations among drug-target pairs across tasks, which facilitates DTA prediction performance improvements. We compare CML with various baselines on two benchmarks and comparison results show that CML outperforms or achieves competitive results to its competitors.

Mortality from lung cancer has ranked high among cancers for many years. Early detection of lung cancer is critical for disease prevention, cure, and mortality rate reduction. Many existing detection methods on lung nodules can achieve high sensitivity but meanwhile introduce an excessive number of false-positive proposals, which is clinically unpractical. In this paper, we propose the multi-head detection and spatial attention network, shortly MHSnet, to address this crucial false-positive issue. Specifically, we first introduce multi-head detectors and skip connections to capture multi-scale features so as to customize for the variety of nodules in sizes, shapes, and types. Then, inspired by how experienced clinicians screen CT images, we implemented a spatial attention module to enable the network to focus on different regions, which can successfully distinguish nodules from noisy tissues. Finally, we designed a lightweight but effective false-positive reduction module to cut down the number of false-positive proposals, without any constraints on the front network. Compared with the state-of-the-art models, our extensive experimental results show the superiority of this MHSnet not only in the average FROC but also in the false discovery rate (2.64% improvement for the average FROC, 6.39% decrease for the false discovery rate). The false-positive reduction module takes a further step to decrease the false discovery rate by 14.29%, indicating its very promising utility of reducing distracted proposals for the downstream tasks relied on detection results.

Identification of drug-target interactions (DTIs) is crucial for drug discovery and drug repositioning. Existing graph neural network (GNN) based methods only aggregate information from directly connected nodes restricted in a drug-related or a target-related network, and are incapable of capturing long-range dependencies in the biological heterogeneous graph. In this paper, we propose the heterogeneous graph attention network (HGAN) to capture the complex structures and rich semantics in the biological heterogeneous graph for DTI prediction. HGAN enhances heterogeneous graph structure learning from both the intra-layer perspective and the inter-layer perspective. Concretely, we develop an enhanced graph attention diffusion layer (EGADL), which efficiently builds connections between node pairs that may not be directly connected, enabling information passing from important nodes multiple hops away. By stacking multiple EGADLs, we further enlarge the receptive field from the inter-layer perspective. HGAN advances 15 state-of-the-art methods on two heterogeneous biological datasets, achieving the results near to 1 in terms of AUC and AUPR. We also find that enlarging receptive fields from the inter-layer perspective (stacking layers) is more effective than that from the intra-layer perspective (attention diffusion) for HGAN to achieve promising DTI prediction performances. The code is available at https://github.com/Zora-LM/HGAN-DTI.

The segmentation module which precisely outlines the nodules is a crucial step in a computer-aided diagnosis(CAD) system. The most challenging part of such a module is how to achieve high accuracy of the segmentation, especially for the juxtapleural, non-solid and small nodules. In this research, we present a coarse-to-fine methodology that greatly improves the thresholding method performance with a novel self-adapting correction algorithm and effectively removes noisy pixels with well-defined knowledge-based principles. Compared with recent strong morphological baselines, our algorithm, by combining dataset features, achieves state-of-the-art performance on both the public LIDC-IDRI dataset (DSC 0.699) and our private LC015 dataset (DSC 0.760) which closely approaches the SOTA deep learning-based models’ performances. Furthermore, unlike most available morphological methods that can only segment the isolated and well-circumscribed nodules accurately, the precision of our method is less affected by the nodule type or diameter, proving its applicability and generality.

Deep learning (DL) brings autonomous vehicles (AVs) close to reality. However, the witness of many safety issues has raised a big concern about the reliability of AVs. To solve this problem, much research has been done to test deep learning-driven AVs. Generally, once a test input is produced, a developer needs to manually check its expected output. However, there often exists massive unlabeled test data (e.g., raw context traces in the real world). It is impractical to manually label all test inputs. Despite some works on automatic generation of test oracles, they are either task-specific or constrained to synthetic inputs. In this paper, we present a general and extensible framework,DeepSuite, to mitigate the manual effort of generating test oracles. The intuition behind is that not all test inputs are equally worth labelling. With limited testing budget, it is desirable to label a test suite with high diversity and a reasonable size. Due to the large search space, to optimize such test suites is of great challenge. To address it,DeepSuiteemploys a three-phase optimization method (i.e., selection, crossover, and mutation) to iteratively select representative but non-redundant test suites. Such conflicting profit/cost objectives are attained through a genetic algorithm with a well-defined multi-objective fitness function. In the experiments, we first show that the diversity of tests can be revealed by test criteria. Then, experiments on three widely-used datasets demonstrated the effectiveness ofDeepSuitein generating test suites with competitive testing coverage and 68.42% smaller size, which greatly improves the data collection efficiency of testing DL-driven autonomous vehicles.

Fault localization can facilitate software debugging and thus is a key technology in software maintenance. Spectrum-based fault localization (SBFL) has been known as an effective and lightweight approach. Nevertheless, the existence of multiple faults within the same system is still the bottleneck of SBFL. Inspired by feature selection in data mining, this paper improves the Relief algorithm and proposes fault-relevant statistics (FRS) to calculate the suspiciousness of program elements. Specifically, it takes test cases as samples, execution results as labels, and spectrum information as features, so that the problem of multi-fault localization can be viewed as a feature selection problem. Unlike the clustering method, this paper only takes into account the closest failing and successful case for each sampled test case when computing FRS. Experiments on open source software systems show that FRS improves the efficiency of fault localization with low computational cost.