Heterogeneous graph inference with range constrainted L2,1-collaborative matrix factorization for small molecule-miRNA association prediction.

MicroRNAs (miRNAs) play a vital role in regulating gene expression and various biological processes. As a result, they have been identified as effective targets for small molecule (SM) drugs in disease treatment. Heterogeneous graph inference stands as a classical approach for predicting SM-miRNA associations, showcasing commendable convergence accuracy and speed. However, most existing methods do not adequately address the inherent sparsity in SM-miRNA association networks, and imprecise SM/miRNA similarity metrics reduce the accuracy of predicting SM-miRNA associations. In this research, we proposed a heterogeneous graph inference with range constrained L2,1-collaborative matrix factorization (HGIRCLMF) method to predict potential SM-miRNA associations. First, we computed the multi-source similarities of SM/miRNA and integrated these similarity information into a comprehensive SM/miRNA similarity. This step improved the accuracy of SM and miRNA similarity, ensuring reliability for the subsequent inference of the heterogeneity map. Second, we used a range constrained L2,1-collaborative matrix factorization (RCLMF) model to pre-populate the SM-miRNA association matrix with missing values. In this step, we developed a novel matrix decomposition method that enhances the robustness and formative nature of SM-miRNA edges between SM networks and miRNA networks. Next, we built a well-established SM-miRNA heterogeneous network utilizing the processed biological information. Finally, HGIRCLMF used this network data to infer unknown association pair scores. We implemented four cross-validation experiments on two distinct datasets, and HGIRCLMF acquired the highest areas under the curve, surpassing six state-of-the-art computational approaches. Furthermore, we performed three case studies to validate the predictive power of our method in practical application.

CHL-DTI: A Novel High-Low Order Information Convergence Framework for Effective Drug-Target Interaction Prediction.

Recognizing drug-target interactions (DTI) stands as a pivotal element in the expansive field of drug discovery. Traditional biological wet experiments, although valuable, are time-consuming and costly as methods. Recently, computational methods grounded in network learning have demonstrated great advantages by effective topological feature extraction and attracted extensive research attention. However, most existing network-based learning methods only consider the low-order binary correlation between individual drug and target, neglecting the potential higher-order correlation information derived from multiple drugs and targets. High-order information, as an essential component, exhibits complementarity with low-order information. Hence, the incorporation of higher-order associations between drugs and targets, while adequately integrating them with the existing lower-order information, could potentially yield substantial breakthroughs in predicting drug-target interactions. We propose a novel dual channels network-based learning model CHL-DTI that converges high-order information from hypergraphs and low-order information from ordinary graph for drug-target interaction prediction. The convergence of high-low order information in CHL-DTI is manifested in two key aspects. First, during the feature extraction stage, the model integrates both high-level semantic information and low-level topological information by combining hypergraphs and ordinary graph. Second, CHL-DTI fully fuse the innovative introduced drug-protein pairs (DPP) hypergraph network structure with ordinary topological network structure information. Extensive experimentation conducted on three public datasets showcases the superior performance of CHL-DTI in DTI prediction tasks when compared to SOTA methods. The source code of CHL-DTI is available at https://github.com/UPCLyy/CHL-DTI .

scSID: A lightweight algorithm for identifying rare cell types by capturing differential expression from single-cell sequencing data.

Single-cell RNA sequencing (scRNA-seq) is currently an important technology for identifying cell types and studying diseases at the genetic level. Identifying rare cell types is biologically important as one of the downstream data analyses of single-cell RNA sequencing. Although rare cell identification methods have been developed, most of these suffer from insufficient mining of intercellular similarities, low scalability, and being time-consuming. In this paper, we propose a single-cell similarity division algorithm (scSID) for identifying rare cells. It takes cell-to-cell similarity into consideration by analyzing both inter-cluster and intra-cluster similarities, and discovers rare cell types based on the similarity differences. We show that scSID outperforms other existing methods by benchmarking it on different experimental datasets. Application of scSID to multiple datasets, including 68K PBMC and intestine, highlights its exceptional scalability and remarkable ability to identify rare cell populations.

Identifying potential small molecule-miRNA associations via Robust PCA based on γ-norm regularization.

Dysregulation of microRNAs (miRNAs) is closely associated with refractory human diseases, and the identification of potential associations between small molecule (SM) drugs and miRNAs can provide valuable insights for clinical treatment. Existing computational techniques for inferring potential associations suffer from limitations in terms of accuracy and efficiency. To address these challenges, we devise a novel predictive model called RPCA$\Gamma $NR, in which we propose a new Robust principal component analysis (PCA) framework based on $\gamma $-norm and $l_{2,1}$-norm regularization and design an Augmented Lagrange Multiplier method to optimize it, thereby deriving the association scores. The Gaussian Interaction Profile Kernel Similarity is calculated to capture the similarity information of SMs and miRNAs in known associations. Through extensive evaluation, including Cross Validation Experiments, Independent Validation Experiment, Efficiency Analysis, Ablation Experiment, Matrix Sparsity Analysis, and Case Studies, RPCA$\Gamma $NR outperforms state-of-the-art models concerning accuracy, efficiency and robustness. In conclusion, RPCA$\Gamma $NR can significantly streamline the process of determining SM-miRNA associations, thus contributing to advancements in drug development and disease treatment.

Cross-domain policy adaptation with dynamics alignment.

The implementation of robotic reinforcement learning is hampered by problems such as an unspecified reward function and high training costs. Many previous works have used cross-domain policy transfer to obtain the policy of the problem domain. However, these researches require paired and aligned dynamics trajectories or other interactions with the environment. We propose a cross-domain dynamics alignment framework for the problem domain policy acquisition that can transfer the policy trained in the source domain to the problem domain. Our framework aims to learn dynamics alignment across two domains that differ in agents' physical parameters (armature, rotation range, or torso mass) or agents' morphologies (limbs). Most importantly, we learn dynamics alignment between two domains using unpaired and unaligned dynamics trajectories. For these two scenarios, we propose a cross-physics-domain policy adaptation algorithm (CPD) and a cross-morphology-domain policy adaptation algorithm (CMD) based on our cross-domain dynamics alignment framework. In order to improve the performance of policy in the source domain so that a better policy can be transferred to the problem domain, we propose the Boltzmann TD3 (BTD3) algorithm. We conduct diverse experiments on agent continuous control domains to demonstrate the performance of our approaches. Experimental results show that our approaches can obtain better policies and higher rewards for the agents in the problem domains even when the dataset of the problem domain is small.

Generative Adversarial Matrix Completion Network based on Multi-Source Data Fusion for miRNA-Disease Associations Prediction.

Numerous biological studies have shown that considering disease-associated micro RNAs (miRNAs) as potential biomarkers or therapeutic targets offers new avenues for the diagnosis of complex diseases. Computational methods have gradually been introduced to reveal disease-related miRNAs. Considering that previous models have not fused sufficiently diverse similarities, that their inappropriate fusion methods may lead to poor quality of the comprehensive similarity network and that their results are often limited by insufficiently known associations, we propose a computational model called Generative Adversarial Matrix Completion Network based on Multi-source Data Fusion (GAMCNMDF) for miRNA-disease association prediction. We create a diverse network connecting miRNAs and diseases, which is then represented using a matrix. The main task of GAMCNMDF is to complete the matrix and obtain the predicted results. The main innovations of GAMCNMDF are reflected in two aspects: GAMCNMDF integrates diverse data sources and employs a nonlinear fusion approach to update the similarity networks of miRNAs and diseases. Also, some additional information is provided to GAMCNMDF in the form of a 'hint' so that GAMCNMDF can work successfully even when complete data are not available. Compared with other methods, the outcomes of 10-fold cross-validation on two distinct databases validate the superior performance of GAMCNMDF with statistically significant results. It is worth mentioning that we apply GAMCNMDF in the identification of underlying small molecule-related miRNAs, yielding outstanding performance results in this specific domain. In addition, two case studies about two important neoplasms show that GAMCNMDF is a promising prediction method.

DETHACDA: A Dual-view Edge and Topology Hybrid Attention Model for CircRNA-Disease Associations Prediction.

There exists growing evidence that circRNAs are concerned with many complex diseases physiological processes and pathogenesis and may serve as critical therapeutic targets. Identifying disease-associated circRNAs through biological experiments is time-consuming, and designing an intelligent, precise calculation model is essential. Recently, many models based on graph technology have been proposed to predict circRNA-disease association. However, most existing methods only capture the neighborhood topology of the association network and ignore the complex semantic information. Therefore, we propose a Dual-view Edge and Topology Hybrid Attention model for predicting CircRNA-Disease Associations (DETHACDA), effectively capturing the neighborhood topology and various semantics of circRNA and disease nodes in a heterogeneous network. The 5-fold cross-validation experiments on circRNADisease indicate that the proposed DETHACDA achieves the area under receiver operating characteristic curve of 0.9882, better than four state-of-the-art calculation methods.

scASGC: An adaptive simplified graph convolution model for clustering single-cell RNA-seq data.

Single-cell RNA sequencing (scRNA-seq) is now a successful technique for identifying cellular heterogeneity, revealing novel cell subpopulations, and forecasting developmental trajectories. A crucial component of the processing of scRNA-seq data is the precise identification of cell subpopulations. Although many unsupervised clustering methods have been developed to cluster cell subpopulations, the performance of these methods is vulnerable to dropouts and high dimensionality. In addition, most existing methods are time-consuming and fail to adequately account for potential associations between cells. In the manuscript, we present an unsupervised clustering method based on an adaptive simplified graph convolution model called scASGC. The proposed method builds plausible cell graphs, aggregates neighbor information using a simplified graph convolution model, and adaptively determines the most optimal number of convolution layers for various graphs. Experiments on 12 public datasets show that scASGC outperforms both classical and state-of-the-art clustering methods. In addition, in a study of mouse intestinal muscle containing 15,983 cells, we identified distinct marker genes based on the clustering results of scASGC. The source code of scASGC is available at https://github.com/ZzzOctopus/scASGC.

Predicting potential small molecule-miRNA associations utilizing truncated schatten p-norm.

MicroRNAs (miRNAs) have significant implications in diverse human diseases and have proven to be effectively targeted by small molecules (SMs) for therapeutic interventions. However, current SM-miRNA association prediction models do not adequately capture SM/miRNA similarity. Matrix completion is an effective method for association prediction, but existing models use nuclear norm instead of rank function, which has some drawbacks. Therefore, we proposed a new approach for predicting SM-miRNA associations by utilizing the truncated schatten p-norm (TSPN). First, the SM/miRNA similarity was preprocessed by incorporating the Gaussian interaction profile kernel similarity method. This identified more SM/miRNA similarities and significantly improved the SM-miRNA prediction accuracy. Next, we constructed a heterogeneous SM-miRNA network by combining biological information from three matrices and represented the network with its adjacency matrix. Finally, we constructed the prediction model by minimizing the truncated schatten p-norm of this adjacency matrix and we developed an efficient iterative algorithmic framework to solve the model. In this framework, we also used a weighted singular value shrinkage algorithm to avoid the problem of excessive singular value shrinkage. The truncated schatten p-norm approximates the rank function more closely than the nuclear norm, so the predictions are more accurate. We performed four different cross-validation experiments on two separate datasets, and TSPN outperformed various most advanced methods. In addition, public literature confirms a large number of predictive associations of TSPN in four case studies. Therefore, TSPN is a reliable model for SM-miRNA association prediction.

AMCSMMA: Predicting Small Molecule-miRNA Potential Associations Based on Accurate Matrix Completion.

Exploring potential associations between small molecule drugs (SMs) and microRNAs (miRNAs) is significant for drug development and disease treatment. Since biological experiments are expensive and time-consuming, we propose a computational model based on accurate matrix completion for predicting potential SM-miRNA associations (AMCSMMA). Initially, a heterogeneous SM-miRNA network is constructed, and its adjacency matrix is taken as the target matrix. An optimization framework is then proposed to recover the target matrix with the missing values by minimizing its truncated nuclear norm, an accurate, robust, and efficient approximation to the rank function. Finally, we design an effective two-step iterative algorithm to solve the optimization problem and obtain the prediction scores. After determining the optimal parameters, we conduct four kinds of cross-validation experiments based on two datasets, and the results demonstrate that AMCSMMA is superior to the state-of-the-art methods. In addition, we implement another validation experiment, in which more evaluation metrics in addition to the AUC are introduced and finally achieve great results. In two types of case studies, a large number of SM-miRNA pairs with high predictive scores are confirmed by the published experimental literature. In summary, AMCSMMA has superior performance in predicting potential SM-miRNA associations, which can provide guidance for biological experiments and accelerate the discovery of new SM-miRNA associations.

MSGNN-DTA: Multi-Scale Topological Feature Fusion Based on Graph Neural Networks for Drug-Target Binding Affinity Prediction.

The accurate prediction of drug-target binding affinity (DTA) is an essential step in drug discovery and drug repositioning. Although deep learning methods have been widely adopted for DTA prediction, the complexity of extracting drug and target protein features hampers the accuracy of these predictions. In this study, we propose a novel model for DTA prediction named MSGNN-DTA, which leverages a fused multi-scale topological feature approach based on graph neural networks (GNNs). To address the challenge of accurately extracting drug and target protein features, we introduce a gated skip-connection mechanism during the feature learning process to fuse multi-scale topological features, resulting in information-rich representations of drugs and proteins. Our approach constructs drug atom graphs, motif graphs, and weighted protein graphs to fully extract topological information and provide a comprehensive understanding of underlying molecular interactions from multiple perspectives. Experimental results on two benchmark datasets demonstrate that MSGNN-DTA outperforms the state-of-the-art models in all evaluation metrics, showcasing the effectiveness of the proposed approach. Moreover, the study conducts a case study based on already FDA-approved drugs in the DrugBank dataset to highlight the potential of the MSGNN-DTA framework in identifying drug candidates for specific targets, which could accelerate the process of virtual screening and drug repositioning.

MSHGANMDA: Meta-Subgraphs Heterogeneous Graph Attention Network for miRNA-Disease Association Prediction.

MicroRNAs (miRNAs) influence several biological processes involved in human disease. Biological experiments for verifying the association between miRNA and disease are always costly in terms of both money and time. Although numerous biological experiments have identified multi-types of associations between miRNAs and diseases, existing computational methods are unable to sufficiently mine the knowledge in these associations to predict unknown associations. In this study, we innovatively propose a heterogeneous graph attention network model based on meta-subgraphs (MSHGANMDA) to predict the potential miRNA-disease associations. Firstly, we define five types of meta-subgraph from the known miRNA-disease associations. Then, we use meta-subgraph attention and meta-subgraph semantic attention to extract features of miRNA-disease pairs within and between these five meta-subgraphs, respectively. Finally, we apply a fully-connected layer (FCL) to predict the scores of unknown miRNA-disease associations and cross-entropy loss to train our model end-to-end. To evaluate the effectiveness of MSHGANMDA, we apply five-fold cross-validation to calculate the mean values of evaluation metrics Accuracy, Precision, Recall, and F1-score as 0.8595, 0.8601, 0.8596, and 0.8595, respectively. Experiments show that our model, which primarily utilizes multi-types of miRNA-disease association data, gets the greatest ROC-AUC value of 0.934 when compared to other state-of-the-art approaches. Furthermore, through case studies, we further confirm the effectiveness of MSHGANMDA in predicting unknown diseases.

A Pseudo-Siamese Feature Fusion Generative Adversarial Network for Synthesizing High-Quality Fetal Four-Chamber Views.

Four-chamber (FC) views are the primary ultrasound(US) images that cardiologists diagnose whether the fetus has congenital heart disease (CHD) in prenatal diagnosis and screening. FC views intuitively depict the developmental morphology of the fetal heart. Early diagnosis of fetal CHD has always been the focus and difficulty of prenatal screening. Furthermore, deep learning technology has achieved great success in medical image analysis. Hence, applying deep learning technology in the early screening of fetal CHD helps improve diagnostic accuracy. However, the lack of large-scale and high-quality fetal FC views brings incredible difficulties to deep learning models or cardiologists. Hence, we propose a Pseudo-Siamese Feature Fusion Generative Adversarial Network (PSFFGAN), synthesizing high-quality fetal FC views using FC sketch images. In addition, we propose a novel Triplet Generative Adversarial Loss Function (TGALF), which optimizes PSFFGAN to fully extract the cardiac anatomical structure information provided by FC sketch images to synthesize the corresponding fetal FC views with speckle noises, artifacts, and other ultrasonic characteristics. The experimental results show that the fetal FC views synthesized by our proposed PSFFGAN have the best objective evaluation values: SSIM of 0.4627, MS-SSIM of 0.6224, and FID of 83.92, respectively. More importantly, two professional cardiologists evaluate healthy FC views and CHD FC views synthesized by our PSFFGAN, giving a subjective score that the average qualified rate is 82% and 79%, respectively, which further proves the effectiveness of the PSFFGAN.

SPReCHD: Four-Chamber Semantic Parsing Network for Recognizing Fetal Congenital Heart Disease in Medical Metaverse.

Echocardiography is essential for evaluating cardiac anatomy and function during early recognition and screening for congenital heart disease (CHD), a widespread and complex congenital malformation. However, fetal CHD recognition still faces many difficulties due to instinctive fetal movements, artifacts in ultrasound images, and distinctive fetal cardiac structures. These factors hinder capturing robust and discriminative representations from ultrasound images, resulting in CHD's low prenatal detection rate. Hence, we propose a multi-scale gated axial-transformer network (MSGATNet) to capture fetal four-chamber semantic information. Then, we propose a SPReCHD: four-chamber semantic parsing network for recognizing fetal CHD in the clinical treatment of the medical metaverse, integrating MSGATNet to segment and locate four-chamber arbitrary contours, further capturing distinguished representations for the fetal heart. Comprehensive experiments indicate that our SPReCHD is sufficient in recognizing fetal CHD, achieving a precision of 95.92%, a recall of 94%, an accuracy of 95%, and a F1 score of 94.95% on the test set, dramatically improving the fetal CHD's prenatal detection rate.

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene.

Cancer is a highly heterogeneous disease, which leads to the fact that even the same cancer can be further classified into different subtypes according to its pathology. With the multi-omics data widely used in cancer subtypes identification, effective feature selection is essential for accurately identifying cancer subtypes. However, the feature selection in the existing cancer subtypes identification methods has the problem that the most helpful features cannot be selected from a biomolecular perspective, and the relationship between the selected features cannot be reflected. To solve this problem, we propose a method for feature selection to identify cancer subtypes based on the heterogeneity score of a single gene: HSSG. In the proposed method, the sample-similarity network of a single gene is constructed, and pseudo-F statistics calculates the heterogeneity score for cancer subtypes identification of each gene. Finally, we construct gene-gene networks using genes with higher heterogeneity scores and mine essential genes from the networks. From the seven TCGA data sets for three experiments, including cancer subtypes identification in single-omics data, the performance in feature selection of multi-omics data, and the effectiveness and stability of the selected features, HSSG achieves good performance in all. This indicates that HSSG can effectively select features for subtypes identification.

FLDS: An Intelligent Feature Learning Detection System for Visualizing Medical Images Supporting Fetal Four-Chamber Views.

Fetal congenital heart disease (CHD) is the most common type of fatal congenital malformation. Fetal four-chamber (FC) view is a significant and easily accessible ultrasound (US) image among fetal echocardiography images. Automatic detection of four fetal heart chambers considerably contributes to the early diagnosis of fetal CHD. Furthermore, robust and discriminative features are essential for detecting crucial visualizing medical images, especially fetal FC views. However, it is an incredibly challenging task due to several key factors, such as numerous speckles in US images, the fetal four chambers with small size and unfixed positions, and category confusion caused by the similarity of cardiac chambers. These factors hinder the process of capturing robust and discriminative features, hence destroying the fetal four chambers' precise detection. Therefore, we propose an intelligent feature learning detection system (FLDS) for FC views to detect the four chambers. A multistage residual hybrid attention module (MRHAM) presented in this paper is incorporated in the FLDS for learning powerful and robust features, helping FLDS accurately locate the four chambers in the fetal FC views. Extensive experiments demonstrate that our proposed FLDS outperforms the current state-of-the-art, including the precision of 0.919, the recall of 0.971, the F1 score of 0.944, the mAP of 0.953, and the frames per second (FPS) of 43. In addition, our proposed FLDS is also validated on other visualizing nature images such as the PASCAL VOC dataset, achieving a higher mAP of 0.878 while input size is 608 × 608.

AMDE: a novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction.

The properties of the drug may be altered by the combination, which may cause unexpected drug-drug interactions (DDIs). Prediction of DDIs provides combination strategies of drugs for systematic and effective treatment. In most of deep learning-based methods for predicting DDI, encoded information about the drugs is insufficient in some extent, which limits the performances of DDIs prediction. In this work, we propose a novel attention-mechanism-based multidimensional feature encoder for DDIs prediction, namely attention-based multidimensional feature encoder (AMDE). Specifically, in AMDE, we encode drug features from multiple dimensions, including information from both Simplified Molecular-Input Line-Entry System sequence and atomic graph of the drug. Data experiments are conducted on DDI data set selected from Drugbank, involving a total of 34 282 DDI relationships with 17 141 positive DDI samples and 17 141 negative samples. Experimental results show that our AMDE performs better than some state-of-the-art baseline methods, including Random Forest, One-Dimension Convolutional Neural Networks, DeepDrug, Long Short-Term Memory, Seq2seq, Deepconv, DeepDDI, Graph Attention Networks and Knowledge Graph Neural Networks. In practice, we select a set of 150 drugs with 3723 DDIs, which are never appeared in training, validation and test sets. AMDE performs well in DDIs prediction task, with AUROC and AUPRC 0.981 and 0.975. As well, we use Torasemide (DB00214) as an example and predict the most likely drug to interact with it. The top 15 scores all have been reported with clear interactions in literatures.

EOESGC: predicting miRNA-disease associations based on embedding of embedding and simplified graph convolutional network.

BACKGROUND: A large number of biological studies have shown that miRNAs are inextricably linked to many complex diseases. Studying the miRNA-disease associations could provide us a root cause understanding of the underlying pathogenesis in which promotes the progress of drug development. However, traditional biological experiments are very time-consuming and costly. Therefore, we come up with an efficient models to solve this challenge. RESULTS: In this work, we propose a deep learning model called EOESGC to predict potential miRNA-disease associations based on embedding of embedding and simplified convolutional network. Firstly, integrated disease similarity, integrated miRNA similarity, and miRNA-disease association network are used to construct a coupled heterogeneous graph, and the edges with low similarity are removed to simplify the graph structure and ensure the effectiveness of edges. Secondly, the Embedding of embedding model (EOE) is used to learn edge information in the coupled heterogeneous graph. The training rule of the model is that the associated nodes are close to each other and the unassociated nodes are far away from each other. Based on this rule, edge information learned is added into node embedding as supplementary information to enrich node information. Then, node embedding of EOE model training as a new feature of miRNA and disease, and information aggregation is performed by simplified graph convolution model, in which each level of convolution can aggregate multi-hop neighbor information. In this step, we only use the miRNA-disease association network to further simplify the graph structure, thus reducing the computational complexity. Finally, feature embeddings of both miRNA and disease are spliced into the MLP for prediction. On the EOESGC evaluation part, the AUC, AUPR, and F1-score of our model are 0.9658, 0.8543 and 0.8644 by 5-fold cross-validation respectively. Compared with the latest published models, our model shows better results. In addition, we predict the top 20 potential miRNAs for breast cancer and lung cancer, most of which are validated in the dbDEMC and HMDD3.2 databases. CONCLUSION: The comprehensive experimental results show that EOESGC can effectively identify the potential miRNA-disease associations.

PESM: A novel approach of tumor purity estimation based on sample specific methylation sites.

Background: Tumor purity is of great significance for the study of tumor genotyping and the prediction of recurrence, which is significantly affected by tumor heterogeneity. Tumor heterogeneity is the basis of drug resistance in various cancer treatments, and DNA methylation plays a core role in the generation of tumor heterogeneity. Almost all types of cancer cells are associated with abnormal DNA methylation in certain regions of the genome. The selection of tumor-related differential methylation sites, which can be used as an indicator of tumor purity, has important implications for purity assessment. At present, the selection of information sites mostly focuses on inter-tumor heterogeneity and ignores the heterogeneity of tumor growth space that is sample specificity. Results: Considering the specificity of tumor samples and the information gain of individual tumor sample relative to the normal samples, we present an approach, PESM, to evaluate the tumor purity through the specificity difference methylation sites of tumor samples. Applied to more than 200 tumor samples of Prostate adenocarcinoma (PRAD) and Kidney renal clear cell carcinoma (KIRC), it shows that the tumor purity estimated by PESM is highly consistent with other existing methods. In addition, PESM performs better than the method that uses the integrated signal of methylation sites to estimate purity. Therefore, different information sites selection methods have an important impact on the estimation of tumor purity, and the selection of sample specific information sites has a certain significance for accurate identification of tumor purity of samples.

An artificial intelligent diagnostic system on mobile Android terminals for cholelithiasis by lightweight convolutional neural network.

Artificial intelligence (AI) tools have been applied to diagnose or predict disease risk from medical images with recent data disclosure actions, but few of them are designed for mobile terminals due to the limited computational power and storage capacity of mobile devices. In this work, a novel AI diagnostic system is proposed for cholelithiasis recognition on mobile devices with Android platform. To this aim, a data set of CT images of cholelithiasis is firstly collected from The Third Hospital of Shandong Province, China, and then we technically use histogram equalization to preprocess these CT images. As results, a lightweight convolutional neural network is obtained in a constructive way to extract cholelith features and recognize gallstones. In terms of implementation, we compile Java and C++ to adapt to the application of deep learning algorithm on mobile devices with Android platform. Noted that, the training task is completed offline on PC, but cholelithiasis recognition tasks are performed on mobile terminals. We evaluate and compare the performance of our MobileNetV2 with MobileNetV1, Single Shot Detector (SSD), YOLOv2 and original SSD (with VGG-16) as feature extractors for object detection. It is achieved that our MobileNetV2 achieve similar accuracy rate, about 91% with the other four methods, but the number of parameters used is reduced from 36.1M (SSD 300, SSD512), 50.7M (Yolov2) and 5.1M (MobileNetV1) to 4.3M (MobileNetV2). The complete process on testing mobile devices, including Virtual machine, Xiaomi 7 and Htc One M8 can be controlled within 4 seconds in recognizing cholelithiasis as well as the degree of the disease.