Classifying breast cancer using multi-view graph neural network based on multi-omics data.

Introduction: As the evaluation indices, cancer grading and subtyping have diverse clinical, pathological, and molecular characteristics with prognostic and therapeutic implications. Although researchers have begun to study cancer differentiation and subtype prediction, most of relevant methods are based on traditional machine learning and rely on single omics data. It is necessary to explore a deep learning algorithm that integrates multi-omics data to achieve classification prediction of cancer differentiation and subtypes. Methods: This paper proposes a multi-omics data fusion algorithm based on a multi-view graph neural network (MVGNN) for predicting cancer differentiation and subtype classification. The model framework consists of a graph convolutional network (GCN) module for learning features from different omics data and an attention module for integrating multi-omics data. Three different types of omics data are used. For each type of omics data, feature selection is performed using methods such as the chi-square test and minimum redundancy maximum relevance (mRMR). Weighted patient similarity networks are constructed based on the selected omics features, and GCN is trained using omics features and corresponding similarity networks. Finally, an attention module integrates different types of omics features and performs the final cancer classification prediction. Results: To validate the cancer classification predictive performance of the MVGNN model, we conducted experimental comparisons with traditional machine learning models and currently popular methods based on integrating multi-omics data using 5-fold cross-validation. Additionally, we performed comparative experiments on cancer differentiation and its subtypes based on single omics data, two omics data, and three omics data. Discussion: This paper proposed the MVGNN model and it performed well in cancer classification prediction based on multiple omics data.

AcneTyper: An automatic diagnosis method of dermoscopic acne image via self-ensemble and stacking.

BACKGROUND: Acne is a skin lesion type widely existing in adolescents, and poses computational challenges for automatic diagnosis. Computer vision algorithms are utilized to detect and determine different subtypes of acne. Most of the existing acne detection algorithms are based on the facial natural images, which carry noisy factors like illuminations. OBJECTIVE: In order to tackle this issue, this study collected a dataset ACNEDer of dermoscopic acne images with annotations. Deep learning methods have demonstrated powerful capabilities in automatic acne diagnosis, and they usually release the training epoch with the best performance as the delivered model. METHODS: This study proposes a novel self-ensemble and stacking-based framework AcneTyper for diagnosing the acne subtypes. Instead of delivering the best epoch, AcneTyper consolidates the prediction results of all training epochs as the latent features and stacks the best subset of these latent features for distinguishing different acne subtypes. RESULTS: The proposed AcneTyper framework achieves a promising detection performance of acne subtypes and even outperforms a clinical dermatologist with two-year experiences by 6.8% in accuracy. CONCLUSION: The method we proposed is used to determine different subtypes of acne and outperforms inexperienced dermatologists and contributes to reducing the probability of misdiagnosis.

[Effect of polydatin on the proliferation and apoptosis of THP-1 cells and the mechanism]. / 虎杖苷对THP-1ç»†èƒžå¢žæ®–åŠå‡‹äº¡çš„å½±å“åŠå ¶ä½œç”¨æœºåˆ¶ç ”ç©¶.

OBJECTIVES: To explore the effect of polydatin on the proliferation and apoptosis of acute monocytic leukemia cell line THP-1 and the possible mechanism. METHODS: After THP-1 cells were treated with polydatin at gradient concentrations for 24 hours and 48 hours, their proliferation was determined by CCK-8 assay, and half maximal inhibitory concentration (IC50) was calculated. Logarithmically growing THP-1 cells were divided into two groups, a polydatin treatment group (treated with IC50 of polydatin) and a blank control group (treated without polydatin solution), and incubated for 48 hours. Cell apoptosis and cell cycle were measured by flow cytometry. The expression levels of PI3K, AKT, p-AKT, mTOR, p-mTOR, p70 S6K, and p-p70 S6K proteins were measured by Western blotting. RESULTS: After treatment with polydatin, the proliferation of THP-1 cells was strongly inhibited, and the IC50 at 48 hours was 1 800 µmol/L. After treatment with 1 800 µmol/L polydatin solution for 48 hours, the apoptosis rate of THP-1 cells increased significantly compared with the blank control group (P<0.05). The cell cycle was arrested in the G0/G1 and S phases, with a significantly increased proportion of cells in the G0/G1 phase and a significantly decreased proportion of cells in the S phase, as compared with the blank control group (P<0.05). The expression levels of PI3K, AKT, p-AKT, mTOR, p-mTOR, p70 S6K, and p-p70 S6K proteins decreased significantly compared with the blank control group (P<0.05). CONCLUSIONS: Polydatin can effectively inhibit the proliferation, block the cell cycle, and induce the apoptosis of THP-1 cells, which may be related to inhibition of the PI3K/AKT/mTOR signaling pathway.

Transforming OMIC features for classification using siamese convolutional networks.

Modern biotechnologies have generated huge amount of OMIC data, among which transcriptomes and methylomes are two major OMIC types. Transcriptomes measure the expression levels of all the transcripts while methylomes depict the cytosine methylation levels across a genome. Both OMIC data types could be generated by array or sequencing. And some studies deliver many more features (the number of features is denoted as [Formula: see text]) for a sample than the number [Formula: see text] of samples in a cohort, which induce the "large [Formula: see text] small [Formula: see text]" paradigm. This study focused on the classification problem about OMIC with "large [Formula: see text] small [Formula: see text]" paradigm. A Siamese convolutional network was utilized to transform the OMIC features into a new space with minimized intra-class distances and maximized inter-class distances between the samples. The proposed feature engineering algorithm SiaCo was comprehensively evaluated using both transcriptome and methylome datasets. The experimental data showed that SiaCo generated SiaCo features with improved classification accuracies for binary classification problems, and achieved improvements on the independent test dataset. The individual SiaCo features did not show better inter-class discrimination powers than the original OMIC features. This may be due to that the Siamese convolutional network optimized the collective performances of the SiaCo features, instead of the individual feature's discrimination power. The inherent transformation nature of the Siamese twin network also makes the SiaCo features lack of interpretability. The source code of SiaCo is freely available at http://www.healthinformaticslab.org/supp/resources.php.

AcneGrader: An ensemble pruning of the deep learning base models to grade acne.

BACKGROUND: Acne is one of the most common skin lesions in adolescents. Some severe or inflammatory acne leads to scars, which may have major impacts on patients' quality of life or even job prospects. Grading acne plays an important role in diagnosis, and the diagnosis is made by counting the number of acne. It is a labor-intensive job and it is easy for dermatologists to make mistakes, so it is very important to develop automatic diagnosis methods. Ensemble learning may improve the prediction results of the base models, but its time complexity is relatively high. The ensemble pruning strategy may solve this computational challenge by removing the redundant base models. MATERIALS AND METHODS: This study proposed a novel ensemble pruning framework of deep learning models to accurately detect and grade acne using images. First, we train multi-base models and prune the redundancy models according to the performance and diversity of the models. Then, we construct the new features of the training data by the base models we select in the previous step. Next, we remove the redundancy models further by a feature selection algorithm. Finally, we integrate all the base models by classifiers. The ensemble pruning algorithm was proposed to prune the deep learning base models. RESULTS: The experimental data showed that the ensemble pruned framework achieved a prediction accuracy of 85.82% on the acne dataset, better than the existing studies. To verify our method's effectiveness, we test our method in a skin cancer dataset and greatly outperform the state-of-the-art methods. CONCLUSION: The method we proposed is used to grade acne. Our method's performance outperforms state-of-the-art methods on two datasets, and it can also remove redundancy models to reduce computational complexity.

COVID19XrayNet: A Two-Step Transfer Learning Model for the COVID-19 Detecting Problem Based on a Limited Number of Chest X-Ray Images.

The novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a major pandemic outbreak recently. Various diagnostic technologies have been under active development. The novel coronavirus disease (COVID-19) may induce pulmonary failures, and chest X-ray imaging becomes one of the major confirmed diagnostic technologies. The very limited number of publicly available samples has rendered the training of the deep neural networks unstable and inaccurate. This study proposed a two-step transfer learning pipeline and a deep residual network framework COVID19XrayNet for the COVID-19 detection problem based on chest X-ray images. COVID19XrayNet firstly tunes the transferred model on a large dataset of chest X-ray images, which is further tuned using a small dataset of annotated chest X-ray images. The final model achieved 0.9108 accuracy. The experimental data also suggested that the model may be improved with more training samples being released. COVID19XrayNet, a two-step transfer learning framework designed for biomedical images.

Spatiotemporal scale and integrative methods matter for quantifying the driving forces of land cover change.

Land cover change (LCC) is a major part of environmental change. Exploring the spatiotemporal differences in LCC and the driving factors is the basis for comprehensive research on landscape planning, and it is of great significance for future effective and sustainable landscape management. In this respect, cross-scale research with integrated methods is worthy of more attention, although some studies have discussed the driving forces of LCCs at either regional or local scale. We combined a structural equation model and a mixed-effects model for quantifying the driving forces of LCCs across different scales in the Loess Plateau (China), which is a typical region that has experienced significant LCCs over recent decades. The impacts of biophysical and socioeconomic factors on different change trajectories (agricultural intensification, urbanization and ecological restoration) were found to be inconsistent at different temporal and spatial scales. We found that topography had a negative effect on agricultural intensification during 1990-2010 and on urbanization during 1990-2000, but it had a positive effect on ecological restoration during 2000-2015 at the regional scale. Moreover, although there was no significant impact from economic development on any type of LCCs at the regional scale, its important influence could be seen in some of the township categories. Therefore, the path and scale dependence of driving forces is an important consideration in landscape planning and management to accommodate local conditions and fine-tuned analysis as decision-making supports.

Gender specificity improves the early-stage detection of clear cell renal cell carcinoma based on methylomic biomarkers.

AIM: The two genders are different ranging from the molecular to the phenotypic levels. But most studies did not use this important information. We hypothesize that the integration of gender information may improve the overall prediction accuracy. MATERIALS & METHODS: A comprehensive comparative study was carried out to test the hypothesis. The classification of the stages I + II versus III + IV of the clear cell renal cell carcinoma samples was formulated as an example. RESULTS & CONCLUSION: In most cases, female-specific model significantly outperformed both-gender model, as similarly for the male-specific model. Our data suggested that gender information is essential for building biomedical classification models and even a simple strategy of building two gender-specific models may outperform the gender-mixed model.

Proteomic biomarkers for lung cancer progression.

AIM: Lung adenocarcinoma (LUAD) and lung squamous-cell carcinoma (LUSC) are two major subtypes of lung cancer and constitute about 70% of all the lung cancer cases. The patient's lifespan and living quality will be significantly improved if they are diagnosed at an early stage and adequately treated. METHODS & RESULTS: This study comprehensively screened the proteomic dataset of both LUAD and LUSC, and proposed classification models for the progression stages of LUAD and LUSC with accuracies 86.51 and 89.47%, respectively. DISCUSSION & CONCLUSION: A comparative analysis was also carried out on related transcriptomic datasets, which indicates that the proposed biomarkers provide discerning power for accurate stage prediction, and will be improved when larger-scale proteomic quantitative technologies become available.