المؤلفون: Randolph, Gregory W, Sosa, Julie Ann, Hao, Yangyang, Angell, Trevor E, Shonka, David C, LiVolsi, Virginia A, Ladenson, Paul W, Blevins, Thomas C, Duh, Quan-Yang, Ghossein, Ronald, Harrell, Mack, Patel, Kepal Narendra, Shanik, Michael H, Traweek, S Thomas, Walsh, P Sean, Yeh, Michael W, Ahmed, Amr H Abdelhamid, Ho, Allen S, Wong, Richard J, Klopper, Joshua P, Huang, Jing, Kennedy, Giulia C, Kloos, Richard T, Sadow, Peter M

المصدر: Thyroid. 32(9)

مصطلحات موضوعية: Biomedical and Clinical Sciences, Clinical Sciences, Genetics, Cancer, Clinical Research, Rare Diseases, Biopsy, Fine-Needle, Carcinoma, Neuroendocrine, Gene Expression Profiling, Humans, RNA, Retrospective Studies, Thyroid Cancer, Papillary, Thyroid Neoplasms, Thyroid Nodule, indeterminate cytology, machine learning, medullary thyroid cancer, molecular diagnostics, molecular testing, thyroid nodule, Endocrinology & Metabolism, Clinical sciences

الوصف: Background: Cytopathological evaluation of thyroid fine-needle aspiration biopsy (FNAB) specimens can fail to raise preoperative suspicion of medullary thyroid carcinoma (MTC). The Afirma RNA-sequencing MTC classifier identifies MTC among FNA samples that are cytologically indeterminate, suspicious, or malignant (Bethesda categories III-VI). In this study we report the development and clinical performance of this MTC classifier. Methods: Algorithm training was performed with a set of 483 FNAB specimens (21 MTC and 462 non-MTC). A support vector machine classifier was developed using 108 differentially expressed genes, which includes the 5 genes in the prior Afirma microarray-based MTC cassette. Results: The final MTC classifier was blindly tested on 211 preoperative FNAB specimens with subsequent surgical pathology, including 21 MTC and 190 non-MTC specimens from benign and malignant thyroid nodules independent from those used in training. The classifier had 100% sensitivity (21/21 MTC FNAB specimens correctly called positive; 95% confidence interval [CI] = 83.9-100%) and 100% specificity (190/190 non-MTC FNAs correctly called negative; CI = 98.1-100%). All positive samples had pathological confirmation of MTC, while all negative samples were negative for MTC on surgical pathology. Conclusions: The RNA-sequencing MTC classifier accurately identified MTC from preoperative thyroid nodule FNAB specimens in an independent validation cohort. This identification may facilitate an MTC-specific preoperative evaluation and resulting treatment.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/5mg1q2p5Test

المؤلفون: Pinto, Jessica O., Livhits, Masha J., Yeh, Michael W., Kaykov, Atanas, Klopper, Joshua P., Kloos, Richard T., Alshalalfa, Mohammed, Hao, Yangyang, Huang, Jing, Endo, Mayumi

المصدر: Journal of Clinical & Translational Endocrinology ; volume 35, page 100329 ; ISSN 2214-6237

مصطلحات موضوعية: Endocrinology, Endocrinology, Diabetes and Metabolism

الإتاحة: https://doi.org/10.1016/j.jcte.2023.100329Test
https://api.elsevier.com/content/article/PII:S2214623723000170?httpAccept=text/xmlTest
https://api.elsevier.com/content/article/PII:S2214623723000170?httpAccept=text/plainTest

المؤلفون: Shao, Zhiwen, Zhu, Hengliang, Tan, Xin, Hao, Yangyang, Ma, Lizhuang

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-ExtensionTest.
Comment: This paper has been accepted by Neurocomputing

الوصول الحر: http://arxiv.org/abs/1808.01558Test

المؤلفون: Zhu, Hengliang, Hao, Yangyang, Ma, Lizhuang, Li, Ruixing, Wang, Hua

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: We participated the Task 1: Lesion Segmentation. The paper describes our algorithm and the final result of validation set for the ISIC Challenge 2018 - Skin Lesion Analysis Towards Melanoma Detection.

الوصول الحر: http://arxiv.org/abs/1807.08471Test

المؤلفون: Hao, Yangyang

مرشدي الرسالة: Liu, Yunlong, Edenberg, Howard J., Li, Lang, Nakshatr, Harikrishna

مصطلحات موضوعية: Low-frequency variants, Machine-learning, Next generation sequencing, SNVs, Somatic mutations, Statistical modeling, Cancer, Genetic aspects, Nucleotide sequence, Statistical methods, Genetics, Statistics, Genomics, Machine learning, Mathematical models, Mathematical optimization, Biopsy, Population genetics

الوصف: Indiana University-Purdue University Indianapolis (IUPUI)
Reliable detection of low-frequency single nucleotide variants (SNVs) carries great significance in many applications. In cancer genetics, the frequencies of somatic variants from tumor biopsies tend to be low due to contamination with normal tissue and tumor heterogeneity. Circulating tumor DNA monitoring also faces the challenge of detecting low-frequency variants due to the small percentage of tumor DNA in blood. Moreover, in population genetics, although pooled sequencing is cost-effective compared with individual sequencing, pooling dilutes the signals of variants from any individual. Detection of low frequency variants is difficult and can be cofounded by multiple sources of errors, especially next-generation sequencing artifacts. Existing methods are limited in sensitivity and mainly focus on frequencies around 5%; most fail to consider differential, context-specific sequencing artifacts. To face this challenge, we developed a computational and experimental framework, RareVar, to reliably identify low-frequency SNVs from high-throughput sequencing data. For optimized performance, RareVar utilized a supervised learning framework to model artifacts originated from different components of a specific sequencing pipeline. This is enabled by a customized, comprehensive benchmark data enriched with known low-frequency SNVs from the sequencing pipeline of interest. Genomic-context-specific sequencing error model was trained on the benchmark data to characterize the systematic sequencing artifacts, to derive the position-specific detection limit for sensitive low-frequency SNV detection. Further, a machine-learning algorithm utilized sequencing quality features to refine SNV candidates for higher specificity. RareVar outperformed existing approaches, especially at 0.5% to 5% frequency. We further explored the influence of statistical modeling on position specific error modeling and showed zero-inflated negative binomial as the best-performed statistical distribution. When replicating analyses on an Illumina MiSeq benchmark dataset, our method seamlessly adapted to technologies with different biochemistries. RareVar enables sensitive detection of low-frequency SNVs across different sequencing platforms and will facilitate research and clinical applications such as pooled sequencing, cancer early detection, prognostic assessment, metastatic monitoring, and relapses or acquired resistance identification.

الإتاحة: https://hdl.handle.net/1805/8891Test

المؤلفون: Hao, Yangyang, Duh, Quan-Yang, Kloos, Richard T, Babiarz, Joshua, Harrell, R Mack, Traweek, S Thomas, Kim, Su Yeon, Fedorowicz, Grazyna, Walsh, P Sean, Sadow, Peter M, Huang, Jing, Kennedy, Giulia C

المصدر: BMC systems biology. 13(Suppl 2)

مصطلحات موضوعية: Mitochondria, Oxyphil Cells, Humans, Neoplasms, Gene Expression Profiling, Sequence Analysis, Genomics, Heterozygote, Machine Learning, Algorithm, Genomic, Hürthle, Machine learning, Personalized healthcare, RNA-seq, Thyroid cancer, Hurthle, Bioinformatics, Biochemistry and Cell Biology, Other Medical and Health Sciences, Computer Software

الوصف: BackgroundIdentification of Hürthle cell cancers by non-operative fine-needle aspiration biopsy (FNAB) of thyroid nodules is challenging. Resultingly, non-cancerous Hürthle lesions were conventionally distinguished from Hürthle cell cancers by histopathological examination of tissue following surgical resection. Reliance on histopathological evaluation requires patients to undergo surgery to obtain a diagnosis despite most being non-cancerous. It is highly desirable to avoid surgery and to provide accurate classification of benignity versus malignancy from FNAB preoperatively. In our first-generation algorithm, Gene Expression Classifier (GEC), we achieved this goal by using machine learning (ML) on gene expression features. The classifier is sensitive, but not specific due in part to the presence of non-neoplastic benign Hürthle cells in many FNAB.ResultsWe sought to overcome this low-specificity limitation by expanding the feature set for ML using next-generation whole transcriptome RNA sequencing and called the improved algorithm the Genomic Sequencing Classifier (GSC). The Hürthle identification leverages mitochondrial expression and we developed novel feature extraction mechanisms to measure chromosomal and genomic level loss-of-heterozygosity (LOH) for the algorithm. Additionally, we developed a multi-layered system of cascading classifiers to sequentially triage Hürthle cell-containing FNAB, including: 1. presence of Hürthle cells, 2. presence of neoplastic Hürthle cells, and 3. presence of benign Hürthle cells. The final Hürthle cell Index utilizes 1048 nuclear and mitochondrial genes; and Hürthle cell Neoplasm Index leverages LOH features as well as 2041 genes. Both indices are Support Vector Machine (SVM) based. The third classifier, the GSC Benign/Suspicious classifier, utilizes 1115 core genes and is an ensemble classifier incorporating 12 individual models.ConclusionsThe accurate algorithmic depiction of this complex biological system among Hürthle subtypes results in a dramatic improvement of classification performance; specificity among Hürthle cell neoplasms increases from 11.8% with the GEC to 58.8% with the GSC, while maintaining the same sensitivity of 89%.

وصف الملف: application/pdf

الوصول الحر: https://escholarship.org/uc/item/3636g1wrTest

المؤلفون: Ladenson, Paul W., Klopper, Joshua P., Hao, Yangyang, Kaushik, Praveen, Walsh, P. Sean, Huang, Jing, Kloos, Richard T., Ali, Syed Z.

المصدر: Cancer Cytopathology ; volume 131, issue 10, page 609-613 ; ISSN 1934-662X 1934-6638

الوصف: Molecular analysis of thyroid nodules can provide diagnostic and prognostic information as well as indicate opportunities for targeted therapy. Whole RNA exome analysis offers information that can be leveraged to predict tumor behavior.

الإتاحة: https://doi.org/10.1002/cncy.22744Test

المؤلفون: Zhang, Yuanfu, Sun, Shu, Qi, Yue, Dai, Yifan, Hao, Yangyang, Xin, Mengyu, Xu, Rongji, Chen, Hongyan, Wu, Xiaoting, Liu, Qian, Kong, Congcong, Zhang, Guangmei, Wang, Peng, Guo, Qiuyan

المساهمون: National Natural Science Foundation of China, University Nursing Program for Young Scholars with Creative Talents in Heilongjiang Province

المصدر: Journal of Ovarian Research ; volume 16, issue 1 ; ISSN 1757-2215

مصطلحات موضوعية: Obstetrics and Gynecology, Oncology

الوصف: Background Patients with epithelial ovarian carcinoma (EOC) are usually diagnosed at an advanced stage with tumour cell invasion. However, identifying the underlying molecular mechanisms and biomarkers of EOC proliferation and invasion remains challenging. Results Herein, we explored the relationship between tumour microenvironment (TME) reprogramming and tissue invasion based on single-cell RNA sequencing (scRNA-seq) datasets. Interestingly, hypoxia, oxidative phosphorylation (OXPHOS) and glycolysis, which have biologically active trajectories during epithelial mesenchymal transition (EMT), were positively correlated. Moreover, energy metabolism and anti-apoptotic activity were found to be critical contributors to intratumor heterogeneity. In addition, HMGA1, EGR1 and RUNX1 were found to be critical drivers of the EMT process in EOC. Experimental validation revealed that suppressing EGR1 expression inhibited tumour cell invasion, significantly upregulated the expression of E-cadherin and decreased the expression of N-cadherin. In cell components analysis, cancer-associated fibroblasts (CAFs) were found to significantly contribute to immune infiltration and tumour invasion, and the accumulation of CAFs was associated with poorer patient survival. Conclusion We revealed the molecular mechanism and biomarkers of tumour invasion and TME reprogramming in EOC, which provides effective targets for the suppression of tumour invasion.

الإتاحة: https://doi.org/10.1186/s13048-023-01270-7Test

المؤلفون: Hao, Yangyang, Qiu, Zhaoyi, Xu, Qiner, He, Qiuhong, Fang, Xuemo, Wang, Chuyun

المساهمون: The Reality Review and Development Path Research of Sports Industry Empowering Rural Revitalization

المصدر: Journal of Cloud Computing ; volume 12, issue 1 ; ISSN 2192-113X

مصطلحات موضوعية: Computer Networks and Communications, Software

الوصف: Public sports service is an important component of the modern government construction service system. They play an important role in strengthening the national physique, improving people’s satisfaction with public services, and improving people’s welfare. With the implementation of the national sports strategy, the quality of sports has continuously improved, and significant progress has been made in the construction of sports facilities, sports service mechanisms, sports service projects, and sports service personnel. Due to the inclination of national development centers and differences in regional economic levels, the effectiveness and implementation of public sports service governance may be affected. In order to solve the current problems of unbalanced development of public SS and insufficient social security, this article used cloud computing to conduct an innovative design for public SS governance and surveyed the satisfaction of residents in the community with public SS governance under the innovative design. Through comparative experiments, it studied the service quality and implementation effect of cloud computing on public SS governance. Through experimental analysis, it was found that the service quality and implementation effect of the public SS governance innovation strategy were higher than the original public SS service system. The service quality of the edge computing public SS innovation system was about 10.6% higher than the original public SS system, and the implementation effect was about 8.1% higher than the original public SS system. Experiments have verified the feasibility of sports service innovation strategies under cloud computing.

الإتاحة: https://doi.org/10.1186/s13677-023-00448-0Test

المؤلفون: Du, Yuwei, Li, Yao, Chen, Jiancai, Hao, Yangyang, Liu, Jiao

المساهمون: Realistic review and development path research of sports industry enabling rural revitalization

المصدر: Journal of Cloud Computing ; volume 12, issue 1 ; ISSN 2192-113X

مصطلحات موضوعية: Computer Networks and Communications, Software

الوصف: With the great development of Internet of Things (IoT) and edge computing, the development of sports activities depends on the development of information technology and it is inevitable to pay attention to the combination and optimization of resources. The combination of IoT and edge computing will be critical in sports activities. This paper elaborates on the application of network skill in sports event information management, that is, through the effective gathering of sports event data, to realize the use of sports event information, to achieve the purpose of information and digitization. Furthermore, the goal is to investigate the effect of sports event in the era of IoT. The impact of sports events on the economy and culture of the hosting city is investigated using IoT concept of edge computing. By analyzing the advantages and disadvantages of traditional centralized optimization method, we present a series of performance indicators and utility functions and show that the method is effective and achieves the optimal purpose. Through vital research, it is found that with the development of the edge computing and IoT industry, the scale of sports events is constantly expanding. By 2019, there has been a scale of 1,271 billion yuan. An increase of 981 billion yuan, compared with 290 billion yuan in 2013. Therefore, the use of the IoT technology in combination with edge computing to manage sports events will greatly encourage the expansion of sports activities. Furthermore, the holding of sporting events reflects a city’s overall strength and enhances the city’s exposure and fame. The investigation offers a certain reference point for cities looking to increase their influence through events.

الإتاحة: https://doi.org/10.1186/s13677-023-00419-5Test