检索结果-内蒙古大学图书馆

Chimeric transcripts observed in non-canonical FGFR2 fusions with partner genes' breakpoint located in intergenic region in intrahepatic cholangiocarcinoma

引用

Cancer Genetics 2022年第0期266-267卷 39-43页

作者： Yin, Lei Han, Zhijun Feng, Meilin Wang, Jie Xie, Zhenghua Yu, Wenlong Fu, Xiaohui Shen, Ningjia Wang, Xiang Duan, Anqi Zhang, Yongjie Ma, Jing 2nd Department of Biliary Truct Surgery Eastern Hepatobiliary surgery hospital 225#Changhai Road Shanghai China Department of Bioinformatics 3D Medicines Inc Shanghai China Department of Data System 3D Medicines Inc Shanghai China Department of Research and Development 3D Medicines Inc Shanghai China

Intrahepatic cholangiocarcinoma (ICC) is a fatal bile duct cancer with dismal prognosis and limited therapeutic options. FGFR family fusion have been identified in many diseases, and FGFR2 fusion is a validated oncogenic driver in ICC. At present, a variety of fusion forms have been reported, including gene-gene, gene-intergenic, and intergenic-intergenic fusion. Here, by performing RNA- and DNA-sequencing analysis, FGFR2 fusions were found in 10.1% of ICC, including 4 gene-intergenic fusions. We confirmed that the non-canonical rearrangements can generate chimeric transcripts, and used conventional splicing mechanism to explain the event. Our study provides possible target therapy for these 4 patients and possibility analysis scheme for similar situation. © 2022

关键词： Breakpoint FGFR2 fusion Gene-intergenic Intrahepatic cholangiocarcinoma NGS

来源：评论

学校读者我要写书评

暂无评论

An Accurate Prediction of Coronary Heart Disease Using Ensemble Algorithms 1

An Accurate Prediction of Coronary Heart Disease Using Ensem...

引用

1st IEEE International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics, AIKIIE 2023

作者： Joshi, Kambham Pratap Prasad, M Lakshmi Natchadalingam, R. Reddy, Pundru Chandra Shaker Mukherjee, Saptarshi Babu, G Charles Hyderabad Dundigal India Institute of Aeronautical Engineering Computer Science and Engineering Telangana Dundigal India R.L.Jalappa Institute of Technology CSE-Data Science Karnataka Bengaluru India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India Maulana Abul Kalam Azad University of Technology M. Tech-Bioinformatics West Bengal India Gokaraju Rangaraju Institute of Engineering and Technology Computing Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350316469

Coronary Heart-disease (CHD) is one the foremost causes of death globally, making the accurate recognition of it vital. Machine-learning (ML) and deep-learning (DL) are two of the newest technologies being put to use in the healthcare industry. This paper uses a risk factor method to examine how CHD can be predicted. K-Nearest-Neighbors, Binary-Logistic Classification, and Naïve-Bayes are only few of the predictive methods that are measured by accuracy, recall, and receiver operating characteristic (ROC) curves for evaluation. Ensemble modeling strategies including bagging, boosting, and stacking are contrasted to these foundational classifiers. The efficacy of using ensemble approaches to enhance coronary heart disease prediction was investigated using a comparative analytical methodology. The 'Cardiovascular-Disease dataset,' which includes 80,000 records of patient data for CHD, is used to evaluate the modeling techniques. It is demonstrated that bagged models, on average, are more accurate than their non-bagged counterparts by the margin of 1.99 percentage points. The highest accuracy of all models was 76.5%, but the AUC for the boosted models was 0.78. Accuracy of 75.1% was achieved by the stacked model consisting of KNN, random-forest classifier, and SVM. In addition, data-analytic methods and K-Folds cross-validation were used to verify the tested models' performance. © 2023 IEEE.

关键词： Artificial intelligence CHD Ensemble techniques Heart-disease Hybrid modeling Machine-learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for TikTok Review Using VADER Sentiment and SVM Model

引用

Procedia Computer Science 2023年 227卷 168-175页

作者： Mahmud Isnan Gregorius Natanael Elwirehardja Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

TikTok, a social networking site for uploading short videos, has become one of the most popular. Despite this, not all users are happy with the app; there are criticisms and suggestions, one of which is reviewed via the TikTok app on the Google Play Store. The reviews were extracted and then used for training a sentiment analysis model. The VADER sentiment method was utilized to offer the review's initial labeling (positive, neutral, and negative). The result revealed that most reviews were classified as positive, meaning that the data were imbalanced and challenging to handle in further analysis. Therefore, Random Under-sampling (RUS) and Random Over-sampling (ROS) methods were deployed to deal with that condition. The labeled reviews were subsequently pre-processed using tools such as case folding, noise removal, normalization, and stopwords before being used for training a Support Vector Machine (SVM) model for sentiment classification. The SVM trained without resampling produced the most favorable results, with an F1-score of 0.80.

关键词： Sentiment Analysis TikTok SVM VADER Sentiment Google Play Store

来源：评论

学校读者我要写书评

暂无评论

Less is More: Reducing Overfitting in Deep Learning for EEG Classification 50

Less is More: Reducing Overfitting in Deep Learning for EEG ...

引用

50th Computing in Cardiology, CinC 2023

作者： Zhou, Songchi Geng, Shijia Li, Jun Zhang, Deyun Xie, Ziqian Cheng, Chuandong Hong, Shenda Shanghai Jiao Tong University Department of Bioinformatics and Biostatistics Shanghai China HeartVoice Medical Technology Hefei China College of Electronic Science and Engineering Jilin University Changchun China University of Texas Health Science Center HoustonTX United States The First Affiliated Hospital of Ustc Department of Neurosurgery Hefei China National Institute of Health Data Science Peking University Beijing China Institute of Medical Technology Health Science Center of Peking University Beijing China

ISBN: (纸本)9798350382525

Although most of the patients' recordings includes large scale long-term physiological time series, the patient-level quantity is relatively small, posing great challenges for machine learning methods. As part of the George B. Moody PhysioNet Challenge 2023, we aim to propose a series of Reducing Overfitting techniques in Deep learning for EEG (coined as RODE) in this scenario, for neurological recovery prognosis. RODE is a simple yet effective machine-learning method, which is mostly powered by generalizable deep-learning features. Specifically, we first pre-train a convolutional neural network on the segment level with a margin-based and mining-based loss, and extract deep features from it. Then we decrease the deep features' complexity using dimensionality reduction methods, which prove to be quite significant for reducing overfitting in deep learning. Finally, we combine the reduced features with static features in patient level, and put them into an ensemble model for classification. Our team, PKU_NIHDS, receives a Challenge score of 0.821 on the hidden validation set and 0.708 on the hidden test set. © 2023 CinC.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

scAI-SNP: a method for inferring ancestry from single-cell data

引用

BMC methods 2025年第1期2卷 10页

作者： Sung Chul Hong Francesc Muyas Isidro Cortés-Ciriano Sahand Hormoz Department of Data Science Dana-Farber Cancer Institute Boston MA 02215 USA. European Molecular Biology Laboratory European Bioinformatics Institute Hinxton Cambridge CB10 1SD UK. Department of Systems Biology Harvard Medical School Boston MA 02115 USA. Broad Institute of MIT and Harvard Cambridge MA 02142 USA.

Background:Collaborative efforts, such as the Human Cell Atlas, are rapidly accumulating large amounts of single-cell data. To ensure that single-cell atlases are representative of human genetic diversity, we need to determine the ancestry of the donors from whom single-cell data are generated. Self-reporting of race and ethnicity, although important, can be biased and is not always available for the datasets already collected. Methods:Here, we introduce scAI-SNP, a tool to infer ancestry directly from single-cell genomics data. To train scAI-SNP, we identified 4.5 million ancestry-informative single-nucleotide polymorphisms (SNPs) in the 1000 Genomes Project dataset across 3201 individuals from 26 population groups. For a query single-cell dataset, scAI-SNP uses these ancestry-informative SNPs to compute the contribution of each of the 26 population groups to the ancestry of the donor from whom the cells were obtained. Results:Using diverse single-cell datasets with matched whole-genome sequencing data, we show that scAI-SNP is robust to the sparsity of single-cell data, can accurately and consistently infer ancestry from samples derived from diverse types of tissues and cancer cells, and can be applied to different modalities of single-cell profiling assays, such as single-cell RNA-seq and single-cell ATAC-seq. Discussion:Finally, we argue that ensuring that single-cell atlases represent diverse ancestry, ideally alongside race and ethnicity, is ultimately important for improved and equitable health outcomes by accounting for human diversity. Supplementary Information:The online version contains supplementary material available at 10.1186/s44330-025-00029-4.

关键词： Ancestry SNP Single-cell transcriptomics The 1000 Genomes Project scAI-SNP

来源：评论

学校读者我要写书评

暂无评论

iPiDA-LGE: a local and global graph ensemble learning framework for identifying piRNA-disease associations

引用

BMC Biology 2025年第1期23卷 1-14页

作者： Wei, Hang Hou, Jialu Liu, Yumeng Shaytan, Alexey K. Liu, Bin Wu, Hao School of Computer Science and Technology Xidian University Shaanxi Xi’an 710126 China SMBU-MSU-BIT Joint Laboratory On Bioinformatics and Engineering Biology Shenzhen MSU-BIT University Guangdong Shenzhen 518172 China School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China College of Big Data and Internet Shenzhen Technology University Guangdong Shenzhen 518118 China Department of Biology Lomonosov Moscow State University Moscow 119234 Russian Federation International Laboratory of Bioinformatics AI and Digital Sciences Institute Faculty of Computer Science HSE University Moscow 109028 Russian Federation Zhongguancun Academy Beijing 100094 China

Background: Exploring piRNA-disease associations can help discover candidate diagnostic or prognostic biomarkers and therapeutic targets. Several computational methods have been presented for identifying associations between piRNAs and diseases. However, the existing methods encounter challenges such as over-smoothing in feature learning and overlooking specific local proximity relationships, resulting in limited representation of piRNA-disease pairs and insufficient detection of association patterns. Results: In this study, we propose a novel computational method called iPiDA-LGE for piRNA-disease association identification. iPiDA-LGE comprises two graph convolutional neural network modules based on local and global piRNA-disease graphs, aimed at capturing specific and general features of piRNA-disease pairs. Additionally, it integrates their refined and macroscopic inferences to derive the final prediction result. Conclusions: The experimental results show that iPiDA-LGE effectively leverages the advantages of both local and global graph learning, thereby achieving more discriminative pair representation and superior predictive performance. © The Author(s) 2025.

关键词： Graph ensemble learning Local context graph piRNA-disease association identification

来源：评论

学校读者我要写书评

暂无评论

data mining for epidemiology: The correlation of typhoid fever occurrence and environmental factors

引用

Procedia Computer Science 2023年 216卷 284-292页

作者： Faisal Asadi Joko Pebrianto Trinugroho Alam Ahmad Hidayat Reza Rahutomo Bens Pardamean Bioinformatics & Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Information System Department School of Information System Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Typhoid fever is an endemic disease that burdens Indonesia and has a potentially fatal infection multisystem. Salmonella typhi bacterium is responsible for typhoid fever disease. Poor sanitation, crowding, and slums are the main factors of increasing typhoid fever incidences. Environmental factors directly connected to meteorological factors are the main factor in breeding the Salmonella typhi bacterium. This study aims to identify the correlation between meteorological parameters and typhoid fever disease occurrence. The study was carried out in Jakarta, Indonesia, and the Bureau of Meteorological, Climatology, and Geophysics (BMKG) provided the meteorological parameter data. In addition, the Jakarta health surveillance office provided information on typhoid fever hospitalizations from 2019 to 2021. Pearson's concept was utilized d to investigate the correlation between typhoid fever incidences and the meteorological parameters. Humidity, precipitation, and wind speed are the meteorological parameters that significantly affect in contribute to the occurrence of typhoid fever disease. These findings might be used as a reference for Indonesia's government in making public policy to prevent typhoid fever in Indonesia.

关键词： typhoid fever salmonella typhi endemic disease meteorological factors

来源：评论

学校读者我要写书评

暂无评论

An Efficient System to Collect data for AI Training on Multi-Category Object Counting Task 1

An Efficient System to Collect Data for AI Training on Multi...

引用

1st International Conference on Computer Science and Artificial Intelligence, ICCSAI 2021

作者： Haessel, Brian Abdul Rahman, Munif Faisol Andry, Steven Cenggoro, Tjeng Wawan Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Bioinformatics and Data Science Research Center Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

This study focused on the problem of collecting data to train AI for a multi-category object counting task, which is like a standard object counting task, where we need to count the number of a particular type of object, for instance, counting how many people in an image. In multi-category object counting, we need to count more than one type of object by keeping track of the number of each type of object. Although in the real object counting case, we often find that AI needs to count objects with multiple categories, the dataset for that particular task is not publicly available. Meanwhile, to have a robust AI for this task, it needs to be trained with a massive amount of data. Therefore, in this study, we developed a system to efficiently facilitate massive data collection for multi-category object counting. This aim was achieved by a careful design of the user experience in the system. The system has been proved to be useful via Technology Acceptance Model (TAM). © 2021 IEEE.

关键词： data acquisition

来源：评论

学校读者我要写书评

暂无评论

Model of learning management system based on artificial intelligence in team-based learning framework 6

Model of learning management system based on artificial inte...

引用

6th International Conference on Information Management and Technology, ICIMTech 2021

作者： Pardamean, Bens Suparyanto, Teddy Cenggoro, Tjeng Wawan Sudigyo, Digdo Anugrahana, Andri Anugraheni, Indri Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia Sanata Dharma University Elementary School Teacher Education Yogyakarta Indonesia Satya Wacana Christian University Elementary School Teacher Education Salatiga Indonesia

ISBN: (纸本)9781665449373

The presence of various innovations and technology of Artificial Intelligence (AI) has now begun to be adopted by Indonesia in many aspects including in the industrial sector. The utilization of AI also can offer a new paradigm in learning and teaching strategies. The development of learning strategies continues also performed to obtain the variations of learning that involve student activity. Team-Based Learning (TBL) is one of the teaching strategies that can improve the quality of the learning process and student activity in groups. By starting to integrate digital-based learning resources in the learning and teaching process, the TBL strategy can potentially be an alternative to new learning strategies that are relevant to be applied in the era of the educational revolution 4.0. The main focus of this research is to develop and evaluate the application of AI in a digital-based TBL strategy that will be implemented in the form of personalized learning about student learning styles. This research was developed based on the learning strategy development of the research method. However, this article more focuses on developing the AI application design that will be applied. The application design was developed based on the agile development method, especially SCRUM. The result of this study is an additional feature that was implemented on a Learning Management System (LMS) based on the Modular Object-Oriented Dynamic Learning Environment (MOODLE). © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm

arXiv

引用

arXiv 2024年

作者： Li, Jingyang Cai, T. Tony Xia, Dong Zhang, Anru R. Department of Statistics Department of Mathematics University of Michigan Ann Arbor United States Department of Statistics and Data Science University of Pennsylvania United States Department of Mathematics Hong Kong University of Science and Technology Hong Kong Department of Biostatistics & Bioinformatics Department of Computer Science Duke University United States

Federated Learning (FL) has gained significant recent attention in machine learning for its enhanced privacy and data security, making it indispensable in fields such as healthcare, finance, and personalized services. This paper investigates federated PCA and estimation for spiked covariance matrices under distributed differential privacy constraints. We establish minimax rates of convergence, with a key finding that the central server’s optimal rate is the harmonic mean of the local clients’ minimax rates. This guarantees consistent estimation at the central server as long as at least one local client provides consistent results. Notably, consistency is maintained even if some local estimators are inconsistent, provided there are enough clients. These findings highlight the robustness and scalability of FL for reliable statistical inference under privacy constraints. To establish minimax lower bounds, we derive a matrix version of van Trees’ inequality, which is of independent interest. Furthermore, we propose an efficient algorithm that preserves differential privacy while achieving near-optimal rates at the central server, up to a logarithmic factor. We address significant technical challenges in analyzing this algorithm, which involves a three-layer spectral decomposition. Numerical performance of the proposed algorithm is investigated using both simulated and real data. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：