Background:: Ultrasound test is one of the routine tests for the diagnosis of thyroid cancer. The diagnosis accuracy depends largely on the correct interpretation of ultrasound images of thyroid nodules. However, human eye-based image recognition is usually subjective and sometimes error-prone especially for less experienced doctors, which presents a need for computeraided diagnostic systems. Objective: : To our best knowledge, there is no well-maintained ultrasound image database for the Chinese population. In addition, though there are several computational methods for image-based thyroid cancer detection, a comparison among them is missing. Finally, the effects of features like the choice of distance measures have not been assessed. The study aims to give the improvement of these limitations and proposes a highly accurate image-based thyroid cancer diagnosis system, which can better assist doctors in the diagnosis of thyroid cancer. Methods:: We first establish a novel thyroid nodule ultrasound image database consisting of 508 images collected from the Third Hospital of Hebei Medical University in China. The clinical information for the patients is also collected from the hospital, where 415 patients are diagnosed to be benign and 93 are malignant by doctors following a standard diagnosis procedure. We develop and apply five machine learning methods to the dataset including deep neural network, support vector machine, the center clustering method, k-nearest neighbor, and logistic regression. Results:: Experimental results show that deep neural network outperforms other diagnosis methods with an average cross-validation accuracy of 0.87 in 10 runs. Meanwhile, we also explore the performance of four image distance measures including the Euclidean distance, the Manhattan distance, the Chebyshev distance, and the Minkowski distance, among which the Chebyshev distance is the best. The resource can be directly used to aid doctors in thyroid cancer diagnosis and treatment. Conclusions: : The paper establishes a novel thyroid nodule ultrasound image database and develops a high accurate image-based thyroid cancer diagnosis system which can better assist doctors in the diagnosis of thyroid cancer.

RNAs may act as competing endogenous RNAs (ceRNAs), a critical mechanism in determining gene expression regulations in many cancers. However, the roles of ceRNAs in thyroid carcinoma remains elusive. In this study, we have developed a novel pipeline called Molecular Network-based Identification of ceRNA (MNIceRNA) to identify ceRNAs in thyroid carcinoma. MNIceRNA first constructs micro RNA (miRNA)–messenger RNA (mRNA)long non-coding RNA (lncRNA) networks from miRcode database and weighted correlation network analysis (WGCNA), based on which to identify key drivers of differentially expressed RNAs between normal and tumor samples. It then infers ceRNAs of the identified key drivers using the long non-coding competing endogenous database (lnCeDB). We applied the pipeline into The Cancer Genome Atlas (TCGA) thyroid carcinoma data. As a result, 598 lncRNAs, 1025 mRNAs, and 90 microRNA (miRNAs) were inferred to be differentially expressed between normal and thyroid cancer samples. We then obtained eight key driver miRNAs, among which hsa-mir-221 and hsa-mir-222 were key driver RNAs identified by both miRNA–mRNA–lncRNA and WGCNA network. In addition, hsa-mir-375 was inferred to be significant for patients’ survival with 34 associated ceRNAs, among which RUNX2, DUSP6 and SEMA3D are known oncogenes regulating cellular proliferation and differentiation in thyroid cancer. These ceRNAs are critical in revealing the secrets behind thyroid cancer progression and may serve as future therapeutic biomarkers.

As a common malignant tumor disease, thyroid cancer lacks effective preventive and therapeutic drugs. Thus, it is crucial to provide an effective drug selection method for thyroid cancer patients. The connectivity map (CMAP) project provides an experimental validated strategy to repurpose and optimize cancer drugs, the rationale behind which is to select drugs to reverse the gene expression variations induced by cancer. However, it has a few limitations. Firstly, CMAP was performed on cell lines, which are usually different from human tissues. Secondly, only gene expression information was considered, while the information about gene regulations and modules/pathways was more or less ignored. In this study, we first measured comprehensively the perturbations of thyroid cancer on a patient including variations at gene expression level, gene co-expression level and gene module level. After that, we provided a drug selection pipeline to reverse the perturbations based on drug signatures derived from tissue studies. We applied the analyses pipeline to the cancer genome atlas (TCGA) thyroid cancer data consisting of 56 normal and 500 cancer samples. As a result, we obtained 812 up-regulated and 213 down-regulated genes, whose functions are significantly enriched in extracellular matrix and receptor localization to synapses. In addition, a total of 33,778 significant differentiated co-expressed gene pairs were found, which form a larger module associated with impaired immune function and low immunity. Finally, we predicted drugs and gene perturbations that could reverse the gene expression and co-expression changes incurred by the development of thyroid cancer through the Fisher’s exact test. Top predicted drugs included validated drugs like baclofen, nevirapine, glucocorticoid, formaldehyde and so on. Combining our analyses with literature mining, we inferred that the regulation of thyroid hormone secretion might be closely related to the inhibition of the proliferation of thyroid cancer cells.

No abstract

Drug-disease correlations play an important role in revealing the mechanism of disease, finding new indications of available drugs, or drug repositioning. A variety of computational approaches were proposed to find drug-disease correlations and achieve good performances. However, these methods used a variety of network information, but integrated networks were rarely used. In addition, the role of known drug-disease association data has not been fully played. In this work, we designed a combination algorithm of random walk and supervised learning to find the drug-disease correlations. We used an integrated network to update the model and selected a gene set as the start of random walk based on the known drug-disease correlations data. The experimental results show that the proposed method can effectively find the correlation between drugs and diseases, and the prediction accuracy is 82.7%. We found that there are 8 pairs of drug-disease relationships that have not yet been reported, and 5 of them have pharmacodynamic effects on Parkinson’s disease. We also found that a key linkage between Parkinson’s disease and phenylhexol, a drug for the treatment of Parkinson’s disease α-synuclein and tau protein, provides a useful exploration for the effectiveness of the treatment of Parkinson’s disease.