RESUMEN
Predicting biomolecular interactions is significant for understanding biological systems. Most existing methods for link prediction are based on graph convolution. Although graph convolution methods are advantageous in extracting structure information of biomolecular interactions, two key challenges still remain. One is how to consider both the immediate and highorder neighbors. Another is how to reduce noise when aggregating high-order neighbors. To address these challenges, we propose a novel method, called mixed high-order graph convolution with filter network via LSTM and channel attention (HGLA), to predict biomolecular interactions. Firstly, the basic and high-order features are extracted respectively through the traditional graph convolutional network (GCN) and the two-layer Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing (MixHop). Secondly, these features are mixed and input into the filter network composed of LayerNorm, SENet and LSTM to generate filtered features, which are concatenated and used for link prediction. The advantages of HGLA are: 1) HGLA processes high-order features separately, rather than simply concatenating them; 2) HGLA better balances the basic features and high-order features; 3) HGLA effectively filters the noise from high-order neighbors. It outperforms state-ofthe-art networks on four benchmark datasets. The codes are available at https://github.com/zznb123/HGLA.
RESUMEN
MOTIVATION: Drug-target interaction (DTI) prediction refers to the prediction of whether a given drug molecule will bind to a specific target and thus exert a targeted therapeutic effect. Although intelligent computational approaches for drug target prediction have received much attention and made many advances, they are still a challenging task that requires further research. The main challenges are manifested as follows: (i) most graph neural network-based methods only consider the information of the first-order neighboring nodes (drug and target) in the graph, without learning deeper and richer structural features from the higher-order neighboring nodes. (ii) Existing methods do not consider both the sequence and structural features of drugs and targets, and each method is independent of each other, and cannot combine the advantages of sequence and structural features to improve the interactive learning effect. RESULTS: To address the above challenges, a Multi-view Integrated learning Network that integrates Deep learning and Graph Learning (MINDG) is proposed in this study, which consists of the following parts: (i) a mixed deep network is used to extract sequence features of drugs and targets, (ii) a higher-order graph attention convolutional network is proposed to better extract and capture structural features, and (iii) a multi-view adaptive integrated decision module is used to improve and complement the initial prediction results of the above two networks to enhance the prediction performance. We evaluate MINDG on two dataset and show it improved DTI prediction performance compared to state-of-the-art baselines. AVAILABILITY AND IMPLEMENTATION: https://github.com/jnuaipr/MINDG.
Asunto(s)
Algoritmos , Redes Neurales de la ComputaciónRESUMEN
As a class of extremely significant of biocatalysts, enzymes play an important role in the process of biological reproduction and metabolism. Therefore, the prediction of enzyme function is of great significance in biomedicine fields. Recently, computational methods for predicting enzyme function have been proposed, and they effectively reduce the cost of enzyme function prediction. However, there are still deficiencies for effectively mining the discriminant information for enzyme function recognition in existing methods. In this study, we present MVDINET, a novel method for multi-level enzyme function prediction. First, the initial multi-view feature data is extracted by the enzyme sequence. Then, the above initial views are fed into various deep specific network modules to learn the depth-specificity information. Further, a deep view interaction network is designed to extract the interaction information. Finally, the specificity information and interaction information are fed into a multi-view adaptively weighted classification. We compressively evaluate MVDINET on benchmark datasets and demonstrate that MVDINET is superior to existing methods.
Asunto(s)
Benchmarking , Entrenamiento Simulado , ReproducciónRESUMEN
Cell classification underpins intelligent cervical cancer screening, a cytology examination that effectively decreases both the morbidity and mortality of cervical cancer. This task, however, is rather challenging, mainly due to the difficulty of collecting a training dataset representative sufficiently of the unseen test data, as there are wide variations of cells' appearance and shape at different cancerous statuses. This difficulty makes the classifier, though trained properly, often classify wrongly for cells that are underrepresented by the training dataset, eventually leading to a wrong screening result. To address it, we propose a new learning algorithm, called worse-case boosting, for classifiers effectively learning from under-representative datasets in cervical cell classification. The key idea is to learn more from worse-case data for which the classifier has a larger gradient norm compared to other training data, so these data are more likely to correspond to underrepresented data, by dynamically assigning them more training iterations and larger loss weights for boosting the generalizability of the classifier on underrepresented data. We achieve this idea by sampling worse-case data per the gradient norm information and then enhancing their loss values to update the classifier. We demonstrate the effectiveness of this new learning algorithm on two publicly available cervical cell classification datasets (the two largest ones to the best of our knowledge), and positive results (4% accuracy improvement) yield in the extensive experiments. The source codes are available at: https://github.com/YouyiSong/Worse-Case-Boosting.
Asunto(s)
Neoplasias del Cuello Uterino , Femenino , Humanos , Detección Precoz del Cáncer , Algoritmos , Programas InformáticosRESUMEN
OBJECTIVE: Convolutional neural network (CNN), a classical structure in deep learning, has been commonly deployed in the motor imagery brain-computer interface (MIBCI). Many methods have been proposed to evaluate the vulnerability of such CNN models, primarily by attacking them using direct temporal perturbations. In this work, we propose a novel attacking approach based on perturbations in the frequency domain instead. METHODS: For a given natural MI trial in the frequency domain, the proposed approach, called frequency domain channel-wise attack (FDCA), generates perturbations at each channel one after another to fool the CNN classifiers. The advances of this strategy are two-fold. First, instead of focusing on the temporal domain, perturbations are generated in the frequency domain where discriminative patterns can be extracted for motor imagery (MI) classification tasks. Second, the perturbing optimization is performed based on differential evolution algorithm in a black-box scenario where detailed model knowledge is not required. RESULTS: Experimental results demonstrate the effectiveness of the proposed FDCA which achieves a significantly higher success rate than the baselines and existing methods in attacking three major CNN classifiers on four public MI benchmarks. CONCLUSION: Perturbations generated in the frequency domain yield highly competitive results in attacking MIBCI deployed by CNN models even in a black-box setting, where the model information is well-protected. SIGNIFICANCE: To our best knowledge, existing MIBCI attack approaches are all gradient-based methods and require details about the victim model, e.g., the parameters and objective function. We provide a more flexible strategy that does not require model details but still produces an effective attack outcome.
Asunto(s)
Algoritmos , Interfaces Cerebro-Computador , Imaginación , Redes Neurales de la Computación , Humanos , Imaginación/fisiología , Seguridad Computacional , Procesamiento de Señales Asistido por ComputadorRESUMEN
Early detection of individuals with a high risk of dementia is crucial for prompt intervention and clinical care. This study aims to identify high-risk groups for developing dementia by predicting the outcome of the Mini-Mental State Examination (MMSE), using historical data collected from community-based primary care services. To mitigate the effect of inter-individual variability and enhance the accuracy of the prediction, we implemented a multi-stage method powered by supervised and unsupervised machine learning methods. Firstly, we preprocessed the original data by imputing missing values and using a wrapper-based feature selection algorithm to pick significant features, resulting in ten variables out of 567 being selected for further modeling. Secondly, we optimized hierarchical clustering to partition the unlabeled data into groups by their similarities, and then applied supervised machine learning models to build subgroup-specific prediction models for the identified groups. The results demonstrate that the proposed subgroup-specific prediction models generated from the multi-stage method achieved satisfactory performance in predicting the outcome classes of dementia risk. This study highlights the potential of incorporating unsupervised and supervised learning models to predict high-risk cases of dementia early and facilitate better clinical decision-making.
Asunto(s)
Demencia , Aprendizaje Automático Supervisado , Humanos , Anciano , Algoritmos , Demencia/diagnóstico , Atención Primaria de SaludRESUMEN
MOTIVATION: CircRNAs play a critical regulatory role in physiological processes, and the abnormal expression of circRNAs can mediate the processes of diseases. Therefore, exploring circRNAs-disease associations is gradually becoming an important area of research. Due to the high cost of validating circRNA-disease associations using traditional wet-lab experiments, novel computational methods based on machine learning are gaining more and more attention in this field. However, current computational methods suffer to insufficient consideration of latent features in circRNA-disease interactions. RESULTS: In this study, a multilayer attention neural graph-based collaborative filtering (MLNGCF) is proposed. MLNGCF first enhances multiple biological information with autoencoder as the initial features of circRNAs and diseases. Then, by constructing a central network of different diseases and circRNAs, a multilayer cooperative attention-based message propagation is performed on the central network to obtain the high-order features of circRNAs and diseases. A neural network-based collaborative filtering is constructed to predict the unknown circRNA-disease associations and update the model parameters. Experiments on the benchmark datasets demonstrate that MLNGCF outperforms state-of-the-art methods, and the prediction results are supported by the literature in the case studies. AVAILABILITY AND IMPLEMENTATION: The source codes and benchmark datasets of MLNGCF are available at https://github.com/ABard0/MLNGCF.
Asunto(s)
Redes Neurales de la Computación , ARN Circular , Aprendizaje Automático , Programas Informáticos , Biología Computacional/métodosRESUMEN
Generalizing the electroencephalogram (EEG) decoding methods to unseen subjects is an important research direction for realizing practical application of brain-computer interfaces (BCIs). Since distribution shifts across subjects, the performance of most current deep neural networks for decoding EEG signals degrades when dealing with unseen subjects. Domain generalization (DG) aims to tackle this issue by learning invariant representations across subjects. To this end, we propose a novel domain-generalized EEG classification framework, named FDCL, to generalize EEG decoding through category-relevant and -irrelevant Feature Decorrelation and Cross-view invariant feature Learning. Specifically, we first devise data augmented regularization through mixing the segments of same-category features from multiple subjects, which increases the diversity of EEG data by spanning the space of subjects. Furthermore, we introduce feature decorrelation regularization to learn the weights of the augmented EEG trials to remove the dependencies between their features, so that the true mapping relationship between relevant features and corresponding labels can be better established. To further distill subject-invariant EEG feature representations, cross-view consistency learning regularization is introduced to encourage consistent predictions of category-relevant features induced from different augmented EEG views. We seamlessly integrate three complementary regularizations into a unified DG framework to jointly improve the generalizability and robustness of the model on unseen subjects. Experimental results on motor imagery (MI) based EEG datasets validate that the proposed FDCL outperforms the available state-of-the-art methods.
Asunto(s)
Algoritmos , Interfaces Cerebro-Computador , Humanos , Redes Neurales de la Computación , Aprendizaje , Electroencefalografía/métodos , ImaginaciónRESUMEN
Cross-network node classification (CNNC), which aims to classify nodes in a label-deficient target network by transferring the knowledge from a source network with abundant labels, draws increasing attention recently. To address CNNC, we propose a domain-adaptive message passing graph neural network (DM-GNN), which integrates graph neural network (GNN) with conditional adversarial domain adaptation. DM-GNN is capable of learning informative representations for node classification that are also transferrable across networks. Firstly, a GNN encoder is constructed by dual feature extractors to separate ego-embedding learning from neighbor-embedding learning so as to jointly capture commonality and discrimination between connected nodes. Secondly, a label propagation node classifier is proposed to refine each node's label prediction by combining its own prediction and its neighbors' prediction. In addition, a label-aware propagation scheme is devised for the labeled source network to promote intra-class propagation while avoiding inter-class propagation, thus yielding label-discriminative source embeddings. Thirdly, conditional adversarial domain adaptation is performed to take the neighborhood-refined class-label information into account during adversarial domain adaptation, so that the class-conditional distributions across networks can be better matched. Comparisons with eleven state-of-the-art methods demonstrate the effectiveness of the proposed DM-GNN.
Asunto(s)
Conocimiento , Redes Neurales de la ComputaciónRESUMEN
Multiview data are widespread in real-world applications, and multiview clustering is a commonly used technique to effectively mine the data. Most of the existing algorithms perform multiview clustering by mining the commonly hidden space between views. Although this strategy is effective, there are two challenges that still need to be addressed to further improve the performance. First, how to design an efficient hidden space learning method so that the learned hidden spaces contain both shared and specific information of multiview data. Second, how to design an efficient mechanism to make the learned hidden space more suitable for the clustering task. In this study, a novel one-step multiview fuzzy clustering (OMFC-CS) method is proposed to address the two challenges by collaborative learning between the common and specific space information. To tackle the first challenge, we propose a mechanism to extract the common and specific information simultaneously based on matrix factorization. For the second challenge, we design a one-step learning framework to integrate the learning of common and specific spaces and the learning of fuzzy partitions. The integration is achieved in the framework by performing the two learning processes alternately and thereby yielding mutual benefit. Furthermore, the Shannon entropy strategy is introduced to obtain the optimal views weight assignment during clustering. The experimental results based on benchmark multiview datasets demonstrate that the proposed OMFC-CS outperforms many existing methods.
RESUMEN
Deformable lung CT image registration is an essential task for computer-assisted interventions and other clinical applications, especially when organ motion is involved. While deep-learning-based image registration methods have recently achieved promising results by inferring deformation fields in an end-to-end manner, large and irregular deformations caused by organ motion still pose a significant challenge. In this paper, we present a method for registering lung CT images that is tailored to the specific patient being imaged. To address the challenge of large deformations between the source and target images, we break the deformation down into multiple continuous intermediate fields. These fields are then combined to create a spatio-temporal motion field. We further refine this field using a self-attention layer that aggregates information along motion trajectories. By leveraging temporal information from a respiratory cycle, our proposed methods can generate intermediate images that facilitate image-guided tumor tracking. We evaluated our approach extensively on a public dataset, and our numerical and visual results demonstrate the effectiveness of the proposed method.
RESUMEN
Protein is the most important component in organisms and plays an indispensable role in life activities. In recent years, a large number of intelligent methods have been proposed to predict protein function. These methods obtain different types of protein information, including sequence, structure and interaction network. Among them, protein sequences have gained significant attention where methods are investigated to extract the information from different views of features. However, how to fully exploit the views for effective protein sequence analysis remains a challenge. In this regard, we propose a multi-view, multi-scale and multi-attention deep neural model (MMSMA) for protein function prediction. First, MMSMA extracts multi-view features from protein sequences, including one-hot encoding features, evolutionary information features, deep semantic features and overlapping property features based on physiochemistry. Second, a specific multi-scale multi-attention deep network model (MSMA) is built for each view to realize the deep feature learning and preliminary classification. In MSMA, both multi-scale local patterns and long-range dependence from protein sequences can be captured. Third, a multi-view adaptive decision mechanism is developed to make a comprehensive decision based on the classification results of all the views. To further improve the prediction performance, an extended version of MMSMA, MMSMAPlus, is proposed to integrate homology-based protein prediction under the framework of multi-view deep neural model. Experimental results show that the MMSMAPlus has promising performance and is significantly superior to the state-of-the-art methods. The source code can be found at https://github.com/wzy-2020/MMSMAPlus.
Asunto(s)
Redes Neurales de la Computación , Proteínas , Secuencia de Aminoácidos , Programas Informáticos , Análisis de Secuencia de ProteínaRESUMEN
Deep neural networks often suffer from performance inconsistency for multiorgan segmentation in medical images; some organs are segmented far worse than others. The main reason might be organs with different levels of learning difficulty for segmentation mapping, due to variations such as size, texture complexity, shape irregularity, and imaging quality. In this article, we propose a principled class-reweighting algorithm, termed dynamic loss weighting, which dynamically assigns a larger loss weight to organs if they are discriminated as more difficult to learn according to the data and network's status, for forcing the network to learn from them more to maximally promote the performance consistency. This new algorithm uses an extra autoencoder to measure the discrepancy between the segmentation network's output and the ground truth and dynamically estimates the loss weight of organs per the contribution of the organ to the new updated discrepancy. It can capture the variation in organs' learning difficult during training, and it is neither sensitive to data's property nor dependent on human priors. We evaluate this algorithm in two multiorgan segmentation tasks: abdominal organs and head-neck structures, on publicly available datasets, with positive results obtained from extensive experiments which confirm the validity and effectiveness. Source codes are available at: https://github.com/YouyiSong/Dynamic-Loss-Weighting.
RESUMEN
Collecting sufficient high-quality training data for deep neural networks is often expensive or even unaffordable in medical image segmentation tasks. We thus propose to train the network by using external data that can be collected in a cheaper way, e.g., crowd-sourcing. We show that by data discernment, the network is able to mine valuable knowledge from external data, even though the data distribution is very different from that of the original (internal) data. We discern the external data by learning an importance weight for each of them, with the goal to enhance the contribution of informative external data to network updating, while suppressing the data that are 'useless' or even 'harmful'. An iterative algorithm that alternatively estimates the importance weight and updates the network is developed by formulating the data discernment as a constrained nonlinear programming problem. It estimates the importance weight according to the distribution discrepancy between the external data and the internal dataset, and imposes a constraint to drive the network to learn more effectively, compared with the network without using the external data. We evaluate the proposed algorithm on two tasks: abdominal CT image and cervical smear image segmentation, using totally 6 publicly available datasets. The effectiveness of the algorithm is demonstrated by extensive experiments. Source codes are available at: https://github.com/YouyiSong/Data-Discernment.
Asunto(s)
Algoritmos , Colaboración de las Masas , Redes Neurales de la Computación , Programas Informáticos , Procesamiento de Imagen Asistido por ComputadorRESUMEN
Domain adaptation (DA) is a popular strategy for pattern recognition and classification tasks. It leverages a large amount of data from the source domain to help train the model applied in the target domain. Supervised domain adaptation (SDA) approaches are desirable when only few labeled samples from the target domain are available. They can be easily adopted in many real-world applications where data collection is expensive. In this study, we propose a new supervision signal, namely center transfer loss (CTL), to efficiently align features under the SDA setting in the deep learning (DL) field. Unlike most previous SDA methods that rely on pairing up training samples, the proposed loss is trainable only using one-stream input based on the mini-batch strategy. The CTL exhibits two main functionalities in training to increase the performance of DL models, i.e., domain alignment and increasing the feature's discriminative power. The hyper-parameter to balance these two functionalities is waived in CTL, which is the second improvement from the previous approaches. Extensive experiments completed on well-known public datasets show that the proposed method performs better than recent state-of-the-art approaches.
RESUMEN
This article proposes a novel low-rank matrix factorization model for semisupervised image clustering. In order to alleviate the negative effect of outliers, the maximum correntropy criterion (MCC) is incorporated as a metric to build the model. To utilize the label information to improve the clustering results, a constraint graph learning framework is proposed to adaptively learn the local structure of the data by considering the label information. Furthermore, an iterative algorithm based on Fenchel conjugate (FC) and block coordinate update (BCU) is proposed to solve the model. The convergence properties of the proposed algorithm are analyzed, which shows that the algorithm exhibits both objective sequential convergence and iterate sequential convergence. Experiments are conducted on six real-world image datasets, and the proposed algorithm is compared with eight state-of-the-art methods. The results show that the proposed method can achieve better performance in most situations in terms of clustering accuracy and mutual information.
RESUMEN
Realistic modelling of human soft tissue is very important in medical applications. This paper proposes a novel method by dynamically incorporating soft tissue characterisation in the process of soft tissue modelling to increase the modelling fidelity. This method defines nonlinear tissue deformation with unknown mechanical properties as a problem of nonlinear filtering identification to dynamically identify mechanical properties and further estimate nonlinear deformation behaviour of soft tissue. It combines maximum likelihood theory, nonlinear filtering and nonlinear finite element method (NFEM) for modelling of nonlinear tissue deformation behaviour based on dynamic identification of homogeneous tissue properties. On the basis of hyperelasticity, a nonlinear state-space equation is established by discretizing tissue deformation through NFEM for dynamic filtering. A maximum likelihood algorithm is also established to dynamically identify tissue mechanical properties during the deformation process. Upon above, a maximum likelihood-based extended Kalman filter is further developed for dynamically estimating tissue nonlinear deformation based on dynamic identification of tissue mechanical properties. Simulation and experimental analyses reveal that the proposed method not only overcomes the NFEM limitation of expensive computations, but also absorbs the NFEM merit of high accuracy for modelling of homogeneous tissue deformation. Further, the proposed method also effectively identifies tissue mechanical properties during the deformation modelling process.
Asunto(s)
Algoritmos , Humanos , Funciones de Verosimilitud , Simulación por ComputadorRESUMEN
The emerging matrix learning methods have achieved promising performances in electroencephalogram (EEG) classification by exploiting the structural information between the columns or rows of feature matrices. Due to the intersubject variability of EEG data, these methods generally need to collect a large amount of labeled individual EEG data, which would cause fatigue and inconvenience to the subjects. Insufficient subject-specific EEG data will weaken the generalization capability of the matrix learning methods in neural pattern decoding. To overcome this dilemma, we propose an adaptive multimodel knowledge transfer matrix machine (AMK-TMM), which can selectively leverage model knowledge from multiple source subjects and capture the structural information of the corresponding EEG feature matrices. Specifically, by incorporating least-squares (LS) loss with spectral elastic net regularization, we first present an LS support matrix machine (LS-SMM) to model the EEG feature matrices. To boost the generalization capability of LS-SMM in scenarios with limited EEG data, we then propose a multimodel adaption method, which can adaptively choose multiple correlated source model knowledge with a leave-one-out cross-validation strategy on the available target training data. We extensively evaluate our method on three independent EEG datasets. Experimental results demonstrate that our method achieves promising performances on EEG classification.
RESUMEN
Circular RNA (circRNA) is closely involved in physiological and pathological processes of many diseases. Discovering the associations between circRNAs and diseases is of great significance. Due to the high-cost to verify the circRNA-disease associations by wet-lab experiments, computational approaches for predicting the associations become a promising research direction. In this paper, we propose a method, MDGF-MCEC, based on multi-view dual attention graph convolution network (GCN) with cooperative ensemble learning to predict circRNA-disease associations. First, MDGF-MCEC constructs two disease relation graphs and two circRNA relation graphs based on different similarities. Then, the relation graphs are fed into a multi-view GCN for representation learning. In order to learn high discriminative features, a dual-attention mechanism is introduced to adjust the contribution weights, at both channel level and spatial level, of different features. Based on the learned embedding features of diseases and circRNAs, nine different feature combinations between diseases and circRNAs are treated as new multi-view data. Finally, we construct a multi-view cooperative ensemble classifier to predict the associations between circRNAs and diseases. Experiments conducted on the CircR2Disease database demonstrate that the proposed MDGF-MCEC model achieves a high area under curve of 0.9744 and outperforms the state-of-the-art methods. Promising results are also obtained from experiments on the circ2Disease and circRNADisease databases. Furthermore, the predicted associated circRNAs for hepatocellular carcinoma and gastric cancer are supported by the literature. The code and dataset of this study are available at https://github.com/ABard0/MDGF-MCEC.