multi-type neighbors enhanced global topology and pairwise attribute learning for drug-protein interaction prediction

MOTIVATION

Accurate identification of proteins interacted with drugs helps reduce the time and cost of drug development. Most of previous methods focused on integrating multisource data about drugs and proteins for predicting drug-target interactions (DTIs). There are both similarity connection and interaction connection between two drugs, and these connections reflect their relationships from different perspectives. Similarly, two proteins have various connections from multiple perspectives. However, most of previous methods failed to deeply integrate these connections. In addition, multiple drug-protein heterogeneous networks can be constructed based on multiple kinds of connections. The diverse topological structures of these networks are still not exploited completely.

RESULTS

We propose a novel model to extract and integrate multi-type neighbor topology information, diverse similarities and interactions related to drugs and proteins. Firstly, multiple drug-protein heterogeneous networks are constructed according to multiple kinds of connections among drugs and those among proteins. The multi-type neighbor node sequences of a drug node (or a protein node) are formed by random walks on each network and they reflect the hidden neighbor topological structure of the node. Secondly, a module based on graph neural network (GNN) is proposed to learn the multi-type neighbor topologies of each node. We propose attention mechanisms at neighbor node level and at neighbor type level to learn more informative neighbor nodes and neighbor types. A network-level attention is also designed to enhance the context dependency among multiple neighbor topologies of a pair of drug and protein nodes. Finally, the attribute embedding of the drug-protein pair is formulated by a proposed embedding strategy, and the embedding covers the similarities and interactions about the pair. A module based on three-dimensional convolutional neural networks (CNN) is constructed to deeply integrate pairwise attributes. Extensive experiments have been performed and the results indicate GCDTI outperforms several state-of-the-art prediction methods. The recall rate estimation over the top-ranked candidates and case studies on 5 drugs further demonstrate GCDTI's ability in discovering potential drug-protein interactions.

Polar Vortex Multi-Day Intensity Prediction Relying on New Deep Learning Model: A Combined Convolution Neural Network with Long Short-Term Memory Based on Gaussian Smoothing Method

The variation of polar vortex intensity is a significant factor affecting the atmospheric conditions and weather in the Northern Hemisphere (NH) and even the world. However, previous studies on the prediction of polar vortex intensity are insufficient. This paper establishes a deep learning (DL) model for multi-day and long-time intensity prediction of the polar vortex. Focusing on the winter period with the strongest polar vortex intensity, geopotential height (GPH) data of NCEP from 1948 to 2020 at 50 hPa are used to construct the dataset of polar vortex anomaly distribution images and polar vortex intensity time series. Then, we propose a new convolution neural network with long short-term memory based on Gaussian smoothing (GSCNN-LSTM) model which can not only accurately predict the variation characteristics of polar vortex intensity from day to day, but also can produce a skillful forecast for lead times of up to 20 days. Moreover, the innovative GSCNN-LSTM model has better stability and skillful correlation prediction than the traditional and some advanced spatiotemporal sequence prediction models. The accuracy of the model suggests important implications that DL methods have good applicability in forecasting the nonlinear system and vortex spatial-temporal characteristics variation in the atmosphere.

Deep Learning With 3D Convolutional Neural Network for Noninvasive Prediction of Microvascular Invasion in Hepatocellular Carcinoma

BACKGROUND

Microvascular invasion (MVI) is a critical prognostic factor of hepatocellular carcinoma (HCC). However, it could only be obtained by postoperative histological examination.

PURPOSE

To develop an end-to-end deep-learning models based on MRI images for preoperative prediction of MVI in HCC patients who underwent surgical resection.

STUDY TYPE

Retrospective.

POPULATION

Two hundred and thirty-seven patients with histologically confirmed HCC.

FIELD STRENGTH

1.5 T and 3.0 T.

SEQUENCE

Axial T₂ -weighted (T₂ -w) with turbo spin echo sequence, T₂ -Spectral Presaturation with Inversion Recovery (T₂ -SPIR), and dynamic contrast-enhanced (DCE) imaging with fat suppressed enhanced T₁ high-resolution isotropic volume examination.

ASSESSMENT

The patients were randomly divided into training (N = 158) and validation (N = 79) sets. Data augmentation by random rotation was performed on the training set and the sample size increased to 1940 for each MR sequence. A three-dimensional convolutional neural network (3D CNN) was used to develop four deep-learning models, including three single-layer models based on single-sequence, and fusion model combining three sequences. MVI status was obtained from the postoperative pathology reports.

STATISTICAL TESTS

The dice similarity coefficient (DSC) and Hausdorff distance (HD) were applied to assess the similarity and reproducibility between the manual segmentations of tumor from two radiologists. Receiver operating characteristic curve analysis was used to evaluate model performance. MVI was identified in 92 (38.8%) patients. Good reproducibility with interobserver DSCs of 0.90, 0.89, and 0.89 and HDs of 4.09, 3.67, and 3.60 was observed for PVP, T₂ WI, and T₂ -SPIR, respectively. The fusion model achieved an area under the curve (AUC) of 0.81, sensitivity of 69%, and specificity of 79% in the training set and 0.72, sensitivity of 55%, and specificity of 81% in the validation set.

DATA CONCLUSION

3D CNN model may serve as a noninvasive tool to predict MVI in HCC, whereas its accuracy needs to be enhanced with larger cohort.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Privacy-Preserved Fall Detection Method with Three-Dimensional Convolutional Neural Network Using Low-Resolution Infrared Array Sensor

Due to the rapid aging of the population in recent years, the number of elderly people in hospitals and nursing homes is increasing, which results in a shortage of staff. Therefore, the situation of elderly citizens requires real-time attention, especially when dangerous situations such as falls occur. If staff cannot find and deal with them promptly, it might become a serious problem. For such a situation, many kinds of human motion detection systems have been in development, many of which are based on portable devices attached to a user’s body or external sensing devices such as cameras. However, portable devices can be inconvenient for users, while optical cameras are affected by lighting conditions and face privacy issues. In this study, a human motion detection system using a low-resolution infrared array sensor was developed to protect the safety and privacy of people who need to be cared for in hospitals and nursing homes. The proposed system can overcome the above limitations and have a wide range of application. The system can detect eight kinds of motions, of which falling is the most dangerous, by using a three-dimensional convolutional neural network. As a result of experiments of 16 participants and cross-validations of fall detection, the proposed method could achieve 98.8% and 94.9% of accuracy and F1-measure, respectively. They were 1% and 3.6% higher than those of a long short-term memory network, and show feasibility of real-time practical application.

Stable polyp-scene classification via subsampling and residual learning from an imbalanced large dataset

This Letter presents a stable polyp-scene classification method with low false positive (FP) detection. Precise automated polyp detection during colonoscopies is essential for preventing colon-cancer deaths. There is, therefore, a demand for a computer-assisted diagnosis (CAD) system for colonoscopies to assist colonoscopists. A high-performance CAD system with spatiotemporal feature extraction via a three-dimensional convolutional neural network (3D CNN) with a limited dataset achieved about 80% detection accuracy in actual colonoscopic videos. Consequently, further improvement of a 3D CNN with larger training data is feasible. However, the ratio between polyp and non-polyp scenes is quite imbalanced in a large colonoscopic video dataset. This imbalance leads to unstable polyp detection. To circumvent this, the authors propose an efficient and balanced learning technique for deep residual learning. The authors’ method randomly selects a subset of non-polyp scenes whose number is the same number of still images of polyp scenes at the beginning of each epoch of learning. Furthermore, they introduce post-processing for stable polyp-scene classification. This post-processing reduces the FPs that occur in the practical application of polyp-scene classification. They evaluate several residual networks with a large polyp-detection dataset consisting of 1027 colonoscopic videos. In the scene-level evaluation, their proposed method achieves stable polyp-scene classification with 0.86 sensitivity and 0.97 specificity.

[Research on glioma magnetic resonance imaging segmentation based on dual-channel three-dimensional densely connected network]

Focus on the inconsistency of the shape, location and size of brain glioma, a dual-channel 3-dimensional (3D) densely connected network is proposed to automatically segment brain glioma tumor on magnetic resonance images. Our method is based on a 3D convolutional neural network frame, and two convolution kernel sizes are adopted in each channel to extract multi-scale features in different scales of receptive fields. Then we construct two densely connected blocks in each pathway for feature learning and transmission. Finally, the concatenation of two pathway features was sent to classification layer to classify central region voxels to segment brain tumor automatically. We train and test our model on open brain tumor segmentation challenge dataset, and we also compared our results with other models. Experimental results show that our algorithm can segment different tumor lesions more accurately. It has important application value in the clinical diagnosis and treatment of brain tumor diseases.

Pulmonary nodule classification in lung cancer screening with three-dimensional convolutional neural networks

A three-dimensional (3-D) convolutional neural network (CNN) trained from scratch is presented for the classification of pulmonary nodule malignancy from low-dose chest CT scans. Recent approval of lung cancer screening in the United States provides motivation for determining the likelihood of malignancy of pulmonary nodules from the initial CT scan finding to minimize the number of follow-up actions. Classifier ensembles of different combinations of the 3-D CNN and traditional machine learning models based on handcrafted 3-D image features are also explored. The dataset consisting of 326 nodules is constructed with balanced size and class distribution with the malignancy status pathologically confirmed. The results show that both the 3-D CNN single model and the ensemble models with 3-D CNN outperform the respective counterparts constructed using only traditional models. Moreover, complementary information can be learned by the 3-D CNN and the conventional models, which together are combined to construct an ensemble model with statistically superior performance compared with the single traditional model. The performance of the 3-D CNN model demonstrates the potential for improving the lung cancer screening follow-up protocol, which currently mainly depends on the nodule size.