Predicting combinations of drugs by exploiting graph embedding of heterogeneous networks

Background Drug combination, offering an insight into the increased therapeutic efficacy and reduced toxicity, plays an essential role in the therapy of many complex diseases. Although significant efforts have been devoted to the identification of drugs, the identification of drug combination is still a challenge. The current algorithms assume that the independence of feature selection and drug prediction procedures, which may result in an undesirable performance. Results To address this issue, we develop a novel Semi-supervised Heterogeneous Network Embedding algorithm (called SeHNE) to predict the combination patterns of drugs by exploiting the graph embedding. Specifically, the ATC similarity of drugs, drug–target, and protein–protein interaction networks are integrated to construct the heterogeneous networks. Then, SeHNE jointly learns drug features by exploiting the topological structure of heterogeneous networks and predicting drug combination. One distinct advantage of SeHNE is that features of drugs are extracted under the guidance of classification, which improves the quality of features, thereby enhancing the performance of prediction of drugs. Experimental results demonstrate that the proposed algorithm is more accurate than state-of-the-art methods on various data, implying that the joint learning is promising for the identification of drug combination. Conclusions The proposed model and algorithm provide an effective strategy for the prediction of combinatorial patterns of drugs, implying that the graph-based drug prediction is promising for the discovery of drugs.

Measuring Patient Similarity on Multiple Diseases by Joint Learning via a Convolutional Neural Network

Patient similarity research is one of the most fundamental tasks in healthcare, helping to make decisions without incurring additional time and costs in clinical practices. Patient similarity can also apply to various medical fields, such as cohort analysis and personalized treatment recommendations. Because of this importance, patient similarity measurement studies are actively being conducted. However, medical data have complex, irregular, and sequential characteristics, making it challenging to measure similarity. Therefore, measuring accurate similarity is a significant problem. Existing similarity measurement studies use supervised learning to calculate the similarity between patients, with similarity measurement studies conducted only on one specific disease. However, it is not realistic to consider only one kind of disease, because other conditions usually accompany it; a study to measure similarity with multiple diseases is needed. This research proposes a convolution neural network-based model that jointly combines feature learning and similarity learning to define similarity in patients with multiple diseases. We used the cohort data from the National Health Insurance Sharing Service of Korea for the experiment. Experimental results verify that the proposed model has outstanding performance when compared to other existing models for measuring multiple-disease patient similarity.

Racial Identity-Aware Facial Expression Recognition Using Deep Convolutional Neural Networks

Multi-culture facial expression recognition remains challenging due to cross cultural variations in facial expressions representation, caused by facial structure variations and culture specific facial characteristics. In this research, a joint deep learning approach called racial identity aware deep convolution neural network is developed to recognize the multicultural facial expressions. In the proposed model, a pre-trained racial identity network learns the racial features. Then, the racial identity aware network and racial identity network jointly learn the racial identity aware facial expressions. By enforcing the marginal independence of facial expression and racial identity, the proposed joint learning approach is expected to be purer for the expression and be robust to facial structure and culture specific facial characteristics variations. For the reliability of the proposed joint learning technique, extensive experiments were performed with racial identity features and without racial identity features. Moreover, culture wise facial expression recognition was performed to analyze the effect of inter-culture variations in facial expression representation. A large scale multi-culture dataset is developed by combining the four facial expression datasets including JAFFE, TFEID, CK+ and RaFD. It contains facial expression images of Japanese, Taiwanese, American, Caucasian and Moroccan cultures. We achieved 96% accuracy with racial identity features and 93% accuracy without racial identity features.

Deep Learning to Ternary Hash Codes by Continuation

Recently, it has been observed that $\{0,\pm1\}$-ternary codes which are simply generated from deep features by hard thresholding, tend to outperform $\{-1, 1\}$-binary codes in image retrieval. To obtain better ternary codes, we for the first time propose to jointly learn the features with the codes by appending a smoothed function to the networks. During training, the function could evolve into a non-smoothed ternary function by a continuation method, and then generate ternary codes. The method circumvents the difficulty of directly training discrete functions and reduces the quantization errors of ternary codes. Experiments show that the proposed joint learning indeed could produce better ternary codes.

Deep Learning to Ternary Hash Codes by Continuation

Recently, it has been observed that $\{0,\pm1\}$-ternary codes which are simply generated from deep features by hard thresholding, tend to outperform $\{-1, 1\}$-binary codes in image retrieval. To obtain better ternary codes, we for the first time propose to jointly learn the features with the codes by appending a smoothed function to the networks. During training, the function could evolve into a non-smoothed ternary function by a continuation method, and then generate ternary codes. The method circumvents the difficulty of directly training discrete functions and reduces the quantization errors of ternary codes. Experiments show that the proposed joint learning indeed could produce better ternary codes.

JLAN: medical code prediction via joint learning attention networks and denoising mechanism

Background Clinical notes are documents that contain detailed information about the health status of patients. Medical codes generally accompany them. However, the manual diagnosis is costly and error-prone. Moreover, large datasets in clinical diagnosis are susceptible to noise labels because of erroneous manual annotation. Therefore, machine learning has been utilized to perform automatic diagnoses. Previous state-of-the-art (SOTA) models used convolutional neural networks to build document representations for predicting medical codes. However, the clinical notes are usually long-tailed. Moreover, most models fail to deal with the noise during code allocation. Therefore, denoising mechanism and long-tailed classification are the keys to automated coding at scale. Results In this paper, a new joint learning model is proposed to extend our attention model for predicting medical codes from clinical notes. On the MIMIC-III-50 dataset, our model outperforms all the baselines and SOTA models in all quantitative metrics. On the MIMIC-III-full dataset, our model outperforms in the macro-F1, micro-F1, macro-AUC, and precision at eight compared to the most advanced models. In addition, after introducing the denoising mechanism, the convergence speed of the model becomes faster, and the loss of the model is reduced overall. Conclusions The innovations of our model are threefold: firstly, the code-specific representation can be identified by adopted the self-attention mechanism and the label attention mechanism. Secondly, the performance of the long-tailed distributions can be boosted by introducing the joint learning mechanism. Thirdly, the denoising mechanism is suitable for reducing the noise effects in medical code prediction. Finally, we evaluate the effectiveness of our model on the widely-used MIMIC-III datasets and achieve new SOTA results.