DAVIS Dataset Research Articles

EnNet: Enhanced Interactive Information Network with Zero-Order Optimization.

Interactive image segmentation extremely accelerates the generation of high-quality annotation image datasets, which are the pillars of the applications of deep learning. However, these methods suffer from the insignificance of interaction information and excessively high optimization costs, resulting in unexpected segmentation outcomes and increased computational burden. To address these issues, this paper focuses on interactive information mining from the network architecture and optimization procedure. In terms of network architecture, the issue mentioned above arises from two perspectives: the less representative feature of interactive regions in each layer and the interactive information weakened by the network hierarchy structure. Therefore, the paper proposes a network called EnNet. The network addresses the two aforementioned issues by employing attention mechanisms to integrate user interaction information across the entire image and incorporating interaction information twice in a design that progresses from coarse to fine. In terms of optimization, this paper proposes a method of using zero-order optimization during the first four iterations of training. This approach can reduce computational overhead with only a minimal reduction in accuracy. The experimental results on GrabCut, Berkeley, DAVIS, and SBD datasets validate the effectiveness of the proposed method, with our approach achieving an average NOC@90 that surpasses RITM by 0.35.

SSR-DTA: Substructure-aware multi-layer graph neural networks for drug–target binding affinity prediction

Accurate prediction of drug–target binding affinity (DTA) is essential in the field of drug discovery. Recently, scientists have been attempting to utilize artificial intelligence prediction to screen out a significant number of ineffective compounds, thereby mitigating labor and financial losses. While graph neural networks (GNNs) have been applied to DTA, existing GNNs have limitations in effectively extracting substructural features across various sizes. Functional groups play a crucial role in modulating molecular properties, but existing GNNs struggle with feature extraction from certain motifs due to scale mismatches. Additionally, sequence-based models for target proteins lack the integration of structural information. To address these limitations, we present SSR-DTA, a multi-layer graph network capable of adapting to diverse structural sizes, which can extract richer biological features, thereby improving the robustness and accuracy of predictions. Multi-layer GNNs enable the capture of molecular motifs across different scales, ranging from atomic to macrocyclic motifs. Furthermore, we introduce BiGNN to simultaneously learn sequence and structural information. Sequence information corresponds to the primary structure of proteins, while graph information represents the tertiary structure. BiGNN assimilates richer information compared to sequence-based methods while mitigating the impact of errors from predicted structures, resulting in more accurate predictions. Through rigorous experimental evaluations conducted on four benchmark datasets, we demonstrate the superiority of SSR-DTA over state-of-the-art models. Particularly, in comparison to state-of-the-art models, SSR-DTA demonstrates an impressive 20% reduction in mean squared error on the Davis dataset and a 5% reduction on the KIBA dataset, underscoring its potential as a valuable tool for advancing DTA prediction.

Optimized differential evolution and hybrid deep learning for superior drug-target binding affinity prediction

Investigating Drug-Target Interactions (DTI) is crucial for drug repositioning and discovery tasks. However, discovering DTIs through experimental approaches is time-consuming and requires substantial financial resources. To address these challenges, machine learning-based methodologies have been adopted to reduce costs and save time. Unfortunately, the effectiveness of these methods has been limited due to the binary classification approach and the lack of empirically validated negative samples. The availability of abundant DTI datasets and protein structure data has enabled the development of new approaches, such as redefining the DTI problem as a regression task. Given this context, we propose an innovative deep-learning approach to predict binding affinities between drugs and targets. Our model, named the Convolution Self-Attention Network with Attention-based Bidirectional Long Short-Term Memory Network (CSAN-BiLSTM-Att), integrates convolutional neural network (CNN) blocks with self-attention mechanisms to create an attention-based bidirectional long short-term memory (BiLSTM) model, followed by fully connected layers. Due to the model's complexity, proper hyperparameter tuning is essential. To optimize this, we employ the Differential Evolution (DE) technique to select the most suitable hyperparameters. Experimental results demonstrate that the DE-based CSAN-BiLSTM-Att model outperforms previous approaches. Specifically, the model achieved a concordance index of 0.898 and a mean square error of 0.228 on the DAVIS dataset, and a concordance value of 0.971 with a mean square error of 0.014 on the KIBA dataset.

DFDTA-MultiAtt: Multi-attention based deep learning ensemble fusion network for drug target affinity prediction

<p>An essential step in the drug development process is the accurate detection of drug-target interactions (DTI). The importance of binding affinity values in understanding protein-ligand interactions was previously disregarded, and DTI prediction was only seen as a binary classification problem. In this regard, we introduced the DFDTA-MultiAtt model for predicting the drug target binding affinity in two stages using the structural and sequential information. The first step of the first stage involves retrieving features from sequence data using a bi-directional long short term memory (Bi-LSTM) architecture together with a multi-attention module and dilated convolutional neural network (dilated-CNN) architecture, and the second step features are learnt from structure representation once again using a dilated-CNN. To predict the binding affinity, the second stage uses an ensemble learning model. The proposed model also produces findings with a greater overall accuracy when compared to contemporary state-of-the-art methods. The model generates an enormous +0.006 concordance index (CI) score on the Davis dataset and reduces the mean square error (MSE) by 0.174 on the KIBA dataset.</p>

Graph Convolutional Capsule Regression (GCCR): A Model for Accelerated Filtering of Novel Potential Candidates for SARS-CoV-2 Based on Binding Affinity.

There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation. In this work, 'Graph Convolutional Capsule Regression' (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model's predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations. The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5%. The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, SimBoost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT).

Bio-inspired algorithm-based hyperparameter tuning for drug-target binding affinity prediction in healthcare

The greatest challenge for healthcare in drug repositioning and discovery is identifying interactions between known drugs and targets. Experimental methods can reveal some drug-target interactions (DTI) but identifying all of them is an expensive and time-consuming endeavor. Machine learning-based algorithms currently cover the DTI prediction problem as a binary classification problem. However, the performance of the DTI prediction is negatively impacted by the lack of experimentally validated negative samples due to an imbalanced class distribution. Hence recasting the DTI prediction task as a regression problem may be one way to solve this problem. This paper proposes a novel convolutional neural network with an attention-based bidirectional long short-term memory (CNN-AttBiLSTM), a new deep-learning hybrid model for predicting drug-target binding affinities. Secondly, it can be arduous and time-intensive to tune the hyperparameters of a CNN-AttBiLSTM hybrid model to augment its performance. To tackle this issue, we suggested a Memetic Particle Swarm Optimization (MPSOA) algorithm, for ascertaining the best settings for the proposed model. According to experimental results, the suggested MPSOA-based CNN- Att-BiLSTM model outperforms baseline techniques with a 0.90 concordance index and 0.228 mean square error in DAVIS dataset, and 0.97 concordance index and 0.010 mean square error in the KIBA dataset.

TeM-DTBA: time-efficient drug target binding affinity prediction using multiple modalities with Lasso feature selection.

Drug discovery, especially virtual screening and drug repositioning, can be accelerated through deeper understanding and prediction of Drug Target Interactions (DTIs). The advancement of deep learning as well as the time and financial costs associated with conventional wet-lab experiments have made computational methods for DTI prediction more popular. However, the majority of these computational methods handle the DTI problem as a binary classification task, ignoring the quantitative binding affinity that determines the drug efficacy to their target proteins. Moreover, computational space as well as execution time of the model is often ignored over accuracy. To address these challenges, we introduce a novel method, called Time-efficient Multimodal Drug Target Binding Affinity (TeM-DTBA), which predicts the binding affinity between drugs and targets by fusing different modalities based on compound structures and target sequences. We employ the Lasso feature selection method, which lowers the dimensionality of feature vectors and speeds up the proposed model training time by more than 50%. The results from two benchmark datasets demonstrate that our method outperforms state-of-the-art methods in terms of performance. The mean squared errors of 18.8% and 23.19%, achieved on the KIBA and Davis datasets, respectively, suggest that our method is more accurate in predicting drug-target binding affinity.

CPNet: Continuity Preservation Network for infrared video colorization

Infrared video colorization can significantly improve perceptual quality by predicting reasonable colors and restoring vivid details, especially in harsh environments. However, as an inconspicuous computer vision task, there is no specialized method. Besides, directly applying current grayscale colorization methods may generate structurally obscure and temporally inconsistent frames. In this paper, we design an infrared video colorization network CPNet aims to generate visually plausible and spatial–temporal consistent colorized videos. To achieve this, a feature fusion module and a hierarchical colorizer are designed to learn the importance of each consecutive frame and the local and global correlation of the integrated features, respectively. In addition, to consolidate the temporal consistency at a fine-grained level, we further introduce a composite loss function to narrow the distance between high-level feature representations while retaining pixel-wise correspondence. Moreover, a new metric named Mean Temporal Variation Similarity (MTVS) is proposed for effectively evaluating the degree of video continuity. Comprehensive experiments conducted on the KAIST dataset demonstrate the superiority of CPNet to produce more authentic colorized videos than state-of-the-art colorization methods. In terms of quantitative comparison, CPNet achieves improvements of at least 0.89 dB on PSNR, 0.016 on SSIM, and a significant promotion on MTVS. In addition, experiments conducted on the DAVIS dataset also prove the applicability of CPNet for grayscale video colorization task.

NHGNN-DTA: a node-adaptive hybrid graph neural network for interpretable drug-target binding affinity prediction.

Large-scale prediction of drug-target affinity (DTA) plays an important role in drug discovery. In recent years, machine learning algorithms have made great progress in DTA prediction by utilizing sequence or structural information of both drugs and proteins. However, sequence-based algorithms ignore the structural information of molecules and proteins, while graph-based algorithms are insufficient in feature extraction and information interaction. In this article, we propose NHGNN-DTA, a node-adaptive hybrid neural network for interpretable DTA prediction. It can adaptively acquire feature representations of drugs and proteins and allow information to interact at the graph level, effectively combining the advantages of both sequence-based and graph-based approaches. Experimental results have shown that NHGNN-DTA achieved new state-of-the-art performance. It achieved the mean squared error (MSE) of 0.196 on the Davis dataset (below 0.2 for the first time) and 0.124 on the KIBA dataset (3% improvement). Meanwhile, in the case of cold start scenario, NHGNN-DTA proved to be more robust and more effective with unseen inputs than baseline methods. Furthermore, the multi-head self-attention mechanism endows the model with interpretability, providing new exploratory insights for drug discovery. The case study on Omicron variants of SARS-CoV-2 illustrates the efficient utilization of drug repurposing in COVID-19. The source code and data are available at https://github.com/hehh77/NHGNN-DTA.

Deep interactive image segmentation based on region and Boundary-click guidance

In interactive image segmentation, the target object of interest can be extracted based on the guidance of user interactions. One of the main goals in this task is to reduce the user interaction burden and ensure satisfactory segmentation with as few interactions as possible. Thanks to the development of deep learning technology, neural network-based interactive approaches have significantly improved the segmentation performance through powerful feature representation. Only limited point (click) interaction is required for the user to complete the segmentation. This paper mainly follows the deep learning-based interactive segmentation methods and explores more efficient interaction strategies and effective segmentation models. We further simplify user interaction to two clicks, where the first click is utilized to select the target region and the other aims to determine the target boundary. Based on the region and boundary clicks, an interactive two-stream network structure is naturally derived to learn the region and boundary features of interest. Furthermore, we also construct an information diffusion module to better propagate the region and boundary-click labels, which helps to enhance the similarity within the region and the discrimination between boundaries. Vast experiments on the popular GrabCut, Berkeley, DAVIS, MS COCO and SBD datasets verified the effectiveness of the proposed method.

Modality-DTA: Multimodality Fusion Strategy for Drug-Target Affinity Prediction.

Prediction of the drug-target affinity (DTA) plays an important role in drug discovery. Existing deep learning methods for DTA prediction typically leverage a single modality, namely simplified molecular input line entry specification (SMILES) or amino acid sequence to learn representations. SMILES or amino acid sequences can be encoded into different modalities. Multimodality data provide different kinds of information, with complementary roles for DTA prediction. We propose Modality-DTA, a novel deep learning method for DTA prediction that leverages the multimodality of drugs and targets. A group of backward propagation neural networks is applied to ensure the completeness of the reconstruction process from the latent feature representation to original multimodality data. The tag between the drug and target is used to reduce the noise information in the latent representation from multimodality data. Experiments on three benchmark datasets show that our Modality-DTA outperforms existing methods in all metrics. Modality-DTA reduces the mean square error by 15.7% and improves the area under the precisionrecall curve by 12.74% in the Davis dataset. We further find that the drug modality Morgan fingerprint and the target modality generated by one-hot-encoding play the most significant roles. To the best of our knowledge, Modality-DTA is the first method to explore multimodality for DTA prediction.

Optical flow correction network for repairing video

Some areas in the video may be defective due to storage medium damage or data transmission loss. The defective area can be repaired utilizing the optical flow since the optical flow represents the motion information of the pixel and contains the information redundancy properties of the video. However, it is a challenge for current algorithms to directly calculate the correct optical flow in the defective area. Therefore, an optical flow correction network (OFC-Net) is proposed to solve this problem. Firstly, as the basic framework, OFC-Net employs a lightweight U-shaped structure to gradually “repair” the broken optical flow map based on the known information in the defective neighborhood. And then, the activation function that conforms to the property of optical flow is used to accelerate the model’s convergence during training, while the simplified loss function is adopted to evaluate the similarity of the optical flow map from a global perspective to improve the prediction accuracy. As a result, the corrected optical flow output at the masked position can be obtained. Secondly, the optical flow corrected by OFC-Net can guide locating the pixels in nearby frames to repair the defective region. Optical flow correction and video repair experiments were conducted on MPI Sintel, DAVIS datasets, and real movie clips. The experimental results show that the corrected optical flow map is accurate without bringing artifacts under a wide range of scenarios and the arbitrary irregular mask shapes, which demonstrate the network’s strong generalization capabilities. The average PSNR and SSIM of repaired video frames are greater than 33.67 and 0.986, respectively, outperforming the results from the traditional method PatchMatch and deep learning-based synthetic pixel methods.

GraphATT-DTA: Attention-Based Novel Representation of Interaction to Predict Drug-Target Binding Affinity.

Drug-target binding affinity (DTA) prediction is an essential step in drug discovery. Drug-target protein binding occurs at specific regions between the protein and drug, rather than the entire protein and drug. However, existing deep-learning DTA prediction methods do not consider the interactions between drug substructures and protein sub-sequences. This work proposes GraphATT-DTA, a DTA prediction model that constructs the essential regions for determining interaction affinity between compounds and proteins, modeled with an attention mechanism for interpretability. We make the model consider the local-to-global interactions with the attention mechanism between compound and protein. As a result, GraphATT-DTA shows an improved prediction of DTA performance and interpretability compared with state-of-the-art models. The model is trained and evaluated with the Davis dataset, the human kinase dataset; an external evaluation is achieved with the independently proposed human kinase dataset from the BindingDB dataset.

ICAN: Interpretable cross-attention network for identifying drug and target protein interactions.

Drug–target protein interaction (DTI) identification is fundamental for drug discovery and drug repositioning, because therapeutic drugs act on disease-causing proteins. However, the DTI identification process often requires expensive and time-consuming tasks, including biological experiments involving large numbers of candidate compounds. Thus, a variety of computation approaches have been developed. Of the many approaches available, chemo-genomics feature-based methods have attracted considerable attention. These methods compute the feature descriptors of drugs and proteins as the input data to train machine and deep learning models to enable accurate prediction of unknown DTIs. In addition, attention-based learning methods have been proposed to identify and interpret DTI mechanisms. However, improvements are needed for enhancing prediction performance and DTI mechanism elucidation. To address these problems, we developed an attention-based method designated the interpretable cross-attention network (ICAN), which predicts DTIs using the Simplified Molecular Input Line Entry System of drugs and amino acid sequences of target proteins. We optimized the attention mechanism architecture by exploring the cross-attention or self-attention, attention layer depth, and selection of the context matrixes from the attention mechanism. We found that a plain attention mechanism that decodes drug-related protein context features without any protein-related drug context features effectively achieved high performance. The ICAN outperformed state-of-the-art methods in several metrics on the DAVIS dataset and first revealed with statistical significance that some weighted sites in the cross-attention weight matrix represent experimental binding sites, thus demonstrating the high interpretability of the results. The program is freely available at https://github.com/kuratahiroyuki/ICAN.

DeepFusionDTA: Drug-Target Binding Affinity Prediction With Information Fusion and Hybrid Deep-Learning Ensemble Model

Identification of drug-target interaction (DTI) is the most important issue in the broad field of drug discovery. Using purely biological experiments to verify drug-target binding profiles takes lots of time and effort, so computational technologies for this task obviously have great benefits in reducing the drug search space. Most of computational methods to predict DTI are proposed to solve a binary classification problem, which ignore the influence of binding strength. Therefore, drug-target binding affinity prediction is still a challenging issue. Currently, lots of studies only extract sequence information that lacks feature-rich representation, but we consider more spatial features in order to merge various data in drug and target spaces. In this study, we propose a two-stage deep neural network ensemble model for detecting drug-target binding affinity, called DeepFusionDTA, via various information analysis modules. First stage is to utilize sequence and structure information to generate fusion feature map of candidate protein and drug pair through various analysis modules based deep learning. Second stage is to apply bagging-based ensemble learning strategy for regression prediction, and we obtain outstanding results by combining the advantages of various algorithms in efficient feature abstraction and regression calculation. Importantly, we evaluate our novel method, DeepFusionDTA, which delivers 1.5 percent CI increase on KIBA dataset and 1.0 percent increase on Davis dataset, by comparing with existing prediction tools, DeepDTA. Furthermore, the ideas we have offered can be applied to in-silico screening of the interaction space, to provide novel DTIs which can be experimentally pursued. The codes and data are available from https://github.com/guofei-tju/DeepFusionDTA.

A Novel Deep Neural Network Technique for Drug-Target Interaction.

Drug discovery (DD) is a time-consuming and expensive process. Thus, the industry employs strategies such as drug repositioning and drug repurposing, which allows the application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pandemic. The prediction of drug–target interactions is an essential part of the DD process because it can accelerate it and reduce the required costs. DTI prediction performed in silico have used approaches based on molecular docking simulations, including similarity-based and network- and graph-based ones. This paper presents MPS2IT-DTI, a DTI prediction model obtained from research conducted in the following steps: the definition of a new method for encoding molecule and protein sequences onto images; the definition of a deep-learning approach based on a convolutional neural network in order to create a new method for DTI prediction. Training results conducted with the Davis and KIBA datasets show that MPS2IT-DTI is viable compared to other state-of-the-art (SOTA) approaches in terms of performance and complexity of the neural network model. With the Davis dataset, we obtained 0.876 for the concordance index and 0.276 for the MSE; with the KIBA dataset, we obtained 0.836 and 0.226 for the concordance index and the MSE, respectively. Moreover, the MPS2IT-DTI model represents molecule and protein sequences as images, instead of treating them as an NLP task, and as such, does not employ an embedding layer, which is present in other models.

Structure-Aware Multimodal Deep Learning for Drug–Protein Interaction Prediction

Identifying drug-protein interactions (DPIs) is crucial in drug discovery, and a number of machine learning methods have been developed to predict DPIs. Existing methods usually use unrealistic data sets with hidden bias, which will limit the accuracy of virtual screening methods. Meanwhile, most DPI prediction methods pay more attention to molecular representation but lack effective research on protein representation and high-level associations between different instances. To this end, we present the novel structure-aware multimodal deep DPI prediction model, STAMP-DPI, which was trained on a curated industry-scale benchmark data set. We built a high-quality benchmark data set named GalaxyDB for DPI prediction. This industry-scale data set along with an unbiased training procedure resulted in a more robust benchmark study. For informative protein representation, we constructed a structure-aware graph neural network method from the protein sequence by combining predicted contact maps and graph neural networks. Through further integration of structure-based representation and high-level pretrained embeddings for molecules and proteins, our model effectively captures the feature representation of the interactions between them. As a result, STAMP-DPI outperformed state-of-the-art DPI prediction methods by decreasing 7.00% mean square error (MSE) in the Davis data set and improving 8.89% area under the curve (AUC) in the GalaxyDB data set. Moreover, our model is an interpretable model with the transformer-based interaction mechanism, which can accurately reveal the binding sites between molecules and proteins.

Automatic Video Segmentation Based on Information Centroid and Optimized SaliencyCut

We propose an automatic video segmentation method based on an optimized SaliencyCut equipped with information centroid (IC) detection according to level balance principle in physical theory. Unlike the existing methods, the image information of another dimension is provided by the IC to enhance the video segmentation accuracy. Specifically, our IC is implemented based on the information-level balance principle in the image, and denoted as the information pivot by aggregating all the image information to a point. To effectively enhance the saliency value of the target object and suppress the background area, we also combine the color and the coordinate information of the image in calculating the local IC and the global IC in the image. Then saliency maps for all frames in the video are calculated based on the detected IC. By applying IC smoothing to enhance the optimized saliency detection, we can further correct the unsatisfied saliency maps, where sharp variations of colors or motions may exist in complex videos. Finally, we obtain the segmentation results based on IC-based saliency maps and optimized SaliencyCut. Our method is evaluated on the DAVIS dataset, consisting of different kinds of challenging videos. Comparisons with the state-of-the-art methods are also conducted to evaluate our method. Convincing visual results and statistical comparisons demonstrate its advantages and robustness for automatic video segmentation.

Self-propagating video segmentation using patch matching and enhanced Onecut

In this paper, a self-propagating video segmentation approach based on patch matching and enhanced Onecut is proposed, which takes full advantage of the target’s color feature, shape feature, and motion information. Firstly, an interactive key frame segmentation is performed to obtain the accurate initial contour of target. Secondly, some sampling patches are uniformly selected along the target contour of previous frame to initialize the localized classifiers. Afterwards, the patch matching is used to pass this contour to the current frame. Simultaneously, the localized classifiers are moved to current frame similarly, and their corresponding positions and parameters are also updated. Eventually, the foreground and background probability maps of current frame are calculated through the localized classifiers as well as global probability models, and then the enhanced Onecut model is constructed to obtain its segmentation result. Compared with the state-of-the-art video segmentation methods, our proposed approach performs outstandingly on the DAVIS dataset.

Strong target constrained video saliency detection

Aiming at the problem of video saliency detection, a strong target constrained video saliency detection method is proposed in this paper. In order to detect the salient region fast and effectively, strong target constraints forcing by the location, scale and color model are introduced into the video saliency detection. First, a target locating strategy for obtaining the location and scale information is proposed by correcting the result of video tracking with the optical flow result and the segmentation result of the last frame. Second, the estimated color model of the target is also calculated by the obtained segmentation results. Finally, the strong target constraints are integrated into the saliency model in the way of extending the significance hypothesis, and a high quality saliency map is obtained, where segmentation is employed for constrained parameters updating. In details, Densecut is initialized by the obtained saliency map to calculate the segmentation result of the last frame. Compared with some state-of-art saliency detection methods, our proposed method performs outstandingly, and the results on DAVIS dataset are significantly improved in terms of accuracy and robustness.