检索结果-内蒙古大学图书馆

A Design of Polygenic Risk Model with Deep Learning for Colorectal Cancer in Multiethnic Indonesians

Procedia Computer Science 2021年 179卷 632-639页

作者： Steven Amadeus Tjeng Wawan Cenggoro Arif Budiarto Bens Pardamean Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480

Recently, health management is emerging and attract attention to how to provide better prognostication and health management systems. The challenges in the prognostication are how to develop a model that can self-learn the prognostication features and how to get a high accuracy prediction. Prognostication in health disease involves SNPs which is a genetic marker. In this paper, we propose a polygenic risk model using deep learning: Transformer with self-attention mechanism and DeepLIFT. The use of these deep learning model allows us to predict the risk of colorectal cancer and see the correlation between SNPs.

关键词： Prognostication Polygenic Risk Model Transformer Model DeepLIFT Colorectal Cancer

来源：评论

学校读者我要写书评

暂无评论

Systematic Evaluation of Somatic Cis-Regulatory Mutations in Follicular Lymphoma

引用

BLOOD 2020年 136卷 26-27页

作者： Uyulur, Firat Bewicke-Copley, Findlay Anene, Chinedu Anthony Schlesner, Matthias Siebert, Reiner Okosun, Jessica Fitzgibbon, Jude Wang, Jun Centre for Cancer Genomics and Computational Biology Barts Cancer Institute Queen Mary University of London London United Kingdom Bioinformatics and Omics Data Analytics German Cancer Research Center (DKFZ) Heidelberg Germany Institute of Human Genetics Ulm University and Ulm University Medical Center Ulm Germany Centre for Haemato-Oncology Barts Cancer Institute Queen Mary University of London London United Kingdom

Background: Follicular lymphoma (FL) is an incurable indolent B cell malignancy characterized in the majority of cases by the t(14;18) translocation. While the mutational landscape of the coding genome is nearing completion, less is known about the characteristics of its noncoding genome. Our expectation is that the distribution of noncoding mutations will be non-random, determined by epigenomics features, such as chromatin modification and accessibility. Our strategy is therefore to integrate whole genome epigenomic marks and mutations in order to enrich for variants with regulatory potential and identify unique mutational processes specific to these cis -regulatory elements (CREs).Allele-specific expression (ASE) patterns allow further refinement to resolve functional CREs and bona fide mutations associated with changes in gene expression. Methods: The H3K27Ac consensus CREs were determined using the ChIP-Seq data of 9 FL patient primary cells (Koues et al., Immunity 2015). DNase I-hypersensitive sites (DHSs) and Hi-C of the B-lymphocyte cell line GM12878 was downloaded from ENCODE. Whole genome sequencing and RNA-Seq of 70 FL patients with relative high tumour cellularity (≥30% for DNA tumour purity and ≥25% for RNA B-cell content) were obtained from the International Cancer Genome Consortium project ICGC MMML-Seq. The mutation rate within CREs and DHSs in comparison to their flanking sequences was estimated using a previous pipeline (Sabarinathan et al., Nature 2016). We further developed cis -ASE, an integrated analytic pipeline for the identification of recurrent ASE genes, and significantly associated CREs and mutations (Fig1.A). Results: In total 1.04 million noncoding mutations, corresponding to 14.8K mutations per sample with a median of 9,991 noncoding mutations were identified in our series of 70 FL samples. 62K (6.0%) mutations were located within H3K27Ac bound CREs and there was an elevated mutation rate in H3K27Ac CREs compared to the corresponding fl

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cell2Sentence: Teaching Large Language Models the Language of Biology 41

Cell2Sentence: Teaching Large Language Models the Language o...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Levine, Daniel Rizvi, Syed Asad Lévy, Sacha Pallikkavaliyaveetil, Nazreen Zhang, David Chen, Xingyu Ghadermarzi, Sina Wu, Ruiming Zheng, Zihe Vrkic, Ivan Zhong, Anna Raskin, Daphne Han, Insu de Oliveira Fonseca, Antonio Henrique Caro, Josue Ortega Karbasi, Amin Dhodapkar, Rahul M. van Dijk, David Department of Computer Science Yale University New HavenCT United States School of Engineering Applied Science University of Pennsylvania PhiladelphiaPA United States School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Neuroscience Yale School of Medicine New HavenCT United States Wu Tsai Institute Yale University New HavenCT United States Google United States Yale Institute for Foundations of Data Science New HavenCT United States Yale School of Engineering and Applied Science New HavenCT United States Roski Eye Institute University of Southern California Los AngelesCA United States Yale School of Medicine New HavenCT United States Cardiovascular Research Center Yale School of Medicine New HavenCT United States Interdepartmental Program in Computational Biology & Bioinformatics Yale University New HavenCT United States

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into"cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the finetuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S finetuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications. Copyright 2024 by the author(s)

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Mobile Commerce Transaction Security Mechanisms Based on Mobile Agent

引用

Computers, Materials & Continua 2020年第12期65卷 2543-2555页

作者： Weijin Jiang Wei Liu Haolong Xia Yuhui Xu Dongbo Cao Guo Liang College of Computer and Information Engineering Hunan University of Technology and BusinessChangsha410205China Institute of Big Data and Internet Innovation Mobile E-business Collaborative Innovation Center of Hunan ProvinceHunan University of Technology and BusinessChangsha410205China Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Technology and BusinessChangsha410205China School of Bioinformatics University of MinnesotaTwin CitiesUSA

In networked mobile commerce network transactions,trust is the prerequisite and key to a smooth *** measurement of trust between entities involves factors such as transaction amount,transaction time,personal income of consumer entities and their risk attitude towards trust,etc.,so it is difficult to accurately calculate *** order to find out the essential characteristics of this trust relationship,based on the research background of mobile commerce in the mobile network environment,a dynamic trust mechanism is proposed through the research of trust in the mobile network environment,trust influencing factors and trust *** calculation model of mobile interactive services based on mobile service business *** model calculates feedback credibility through feedback deviation and feedback robustness,and combines transaction context factors and trust mapping mechanism to judge the seller’s *** model better reflects the degree of influence of subjective factors such as personal preferences and risk attitudes on trust calculations,And the sensitivity of trust algorithms and transaction attributes has been greatly *** a large number of experiments and theoretical analysis,this mechanism provides an effective explanation for solving the problem of network trust *** provides valuable new ideas for the study of secure transactions in the mobile Internet environment.

关键词： Mobile Internet mobile commerce dynamic trust model reputation management Mobile Agent System(MAS)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning as a Vector Embedding Model for Customer Churn

引用

Procedia Computer Science 2021年 179卷 624-631页

作者： Tjeng Wawan Cenggoro Raditya Ayu Wirastari Edy Rudianto Mochamad Ilham Mohadi Dinne Ratj Bens Pardamean Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

To face the tight competition in the telecommunication industry, it is important to minimize the rate of customers stopping their service subscription, which is known as customer churn. For that goal, an explainable predictive customer churn model is an essential tool to be owned by a telecommunication provider. In this paper, we developed the explainable model by utilizing the concept of vector embedding in Deep Learning. We show that the model can reveal churning customers that can potentially be converted back to use the previous telecommunication service. The generated vectors are also highly discriminative between the churning and loyal customers, which enable the developed models to be highly predictive for determining whether a customer would cease his/her service subscription or not. The best model in our experiment achieved a predictive performance of 81.16%, measured by the F1 Score. Further analysis on the clusters similarity and t-SNE plot also confirmed that the generated vectors are discriminative for churn prediction.

关键词： customer churn customer behavior deep learning vector embedding representation learning

来源：评论

学校读者我要写书评

暂无评论

Bovine Blastocyst Like Structures Derived From Stem Cell Cultures

SSRN

引用

SSRN 2023年

作者： Pinzón-Arteaga, Carlos A. Wang, Yinjuan Wei, Yulei Li, Leijie Orsi, Ana Elisa Ribeiro Scatolin, Giovanna Liu, Lizhong Sakurai, Masahiro Ye, Jianfeng Yu, Leqian Li, Bo Jiang, Zongliang Wu, Jun Department of Molecular Biology University of Texas Southwestern Medical Center DallasTX United States School of Animal Sciences AgCenter Louisiana State University Baton RougeLA70810 United States SJTU-Yale Joint Center for Biostatistics and Data Science School of Life Sciences and Biotechnology Shanghai Jiao Tong University Shanghai China Department of Genetics and Evolutionary Biology Institute of Biosciences University of São Paulo São Paulo Brazil Lyda Hill Department of Bioinformatics University of Texas Southwestern Medical Center DallasTX United States Department of Animal Sciences Genetics Institute University of Florida GainesvilleFL32610 United States Hamon Center for Regenerative Science and Medicine University of Texas Southwestern Medical Center DallasTX75390 United States Cecil H. and Ida Green Center for Reproductive Biology Sciences University of Texas Southwestern Medical Center DallasTX United States

Understanding blastocyst formation and implantation is critical for improving farm animal reproduction but is hampered by a limited supply of embryos. We developed an efficient method to generate bovine blastocyst-like structures (termed blastoids) via the assembly of trophoblast stem cells and expanded potential stem cells. Bovine blastoids resemble blastocysts in morphology, cell composition, single-cell transcriptomes, and represent an accessible in vitro model for studying bovine embryogenesis © 2023, The Authors. All rights reserved.

关键词： Stem cells

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes

引用

Procedia Computer Science 2023年 218卷 24-34页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai 602105 Tamil Nadu India

In the women's community, Breast Cancer (BC) is a severe disease. The World Health Organization reported in 2020 that 2.26 million deaths occur due to BC. BC is curable if detected early. Since thermal imaging is non-invasive and supports disease detection, it is commonly used in clinics. Compared to other methods, it keeps BC early and accurate. The proposed work aims to evaluate the performance of the Pretrained Deep-Learning Methods (PDLM) in detecting BC using the thermal images collected from the benchmark dataset. It includes the following stages: primary image processing, deep feature mining, handcrafted feature mining, feature optimization using Firefly-Algorithm (FA), classification and validation. Visual Lab thermal images were used in the study. The investigational outcome of this study authenticates that the VGG16, along with the DT, provides better detection accuracy (95.5%) compared to other classifiers used in this study. To justify the significance of the implemented technique, the proposed work not only improved accuracy, but also improved precision, sensitivity, specificity, and F1-Scores.

关键词： Breast cancer Thermal imaging Firefly algorithm Feature optimization Classification

来源：评论

学校读者我要写书评

暂无评论

CONCENTRATION INEQUALITIES AND OPTIMAL NUMBER OF LAYERS FOR STOCHASTIC DEEP NEURAL NETWORKS

arXiv

引用

arXiv 2022年

作者： Caprio, Michele Mukherjee, Sayan PRECISE Center Department of Computer and Information Science University of Pennsylvania 3330 Walnut Street PhiladelphiaPA19104 United States Center for Scalable Data Analytics and Artificial Intelligence Universität Leipzig Humboldtstraße 25 Leipzig04105 Germany The Max Planck Institute for Mathematics in the Sciences Inselstraße 22 Leipzig04103 Germany Departments of Statistical Science Mathematics Computer Science and Biostatistics & Bioinformatics Duke University DurhamNC27708 United States

We state concentration inequalities for the output of the hidden layers of a stochastic deep neural network (SDNN), as well as for the output of the whole SDNN. These results allow us to introduce an expected classifier (EC), and to give probabilistic upper bound for the classification error of the EC. We also state the optimal number of layers for the SDNN via an optimal stopping procedure. We apply our analysis to a stochastic version of a feedforward neural network with ReLU activation *** Codes Primary: 62M45, Secondary: 60G42 © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Effects of sickle trait on maternal and perinatal outcomes among pregnant women

Blood Vessels, Thrombosis & Hemostasis

引用

Blood Vessels, Thrombosis & Hemostasis 2025年第2期2卷 100049-100049页

作者： Sarah Sewaralthahab Jiling Chou Stephen Fernandez Nawar Shara Hedy P. Smith Department of Medicine College of Medicine King Saud University Riyadh Saudi Arabia Division of Hematology Oncology Center King Saud University Medical City Riyadh Saudi Arabia Department of Biostatistics Bioinformatics and Biomathematics Center of Biostatistics Informatics and Data Science Medstar Research Institute Hyattsville MD Depatment of Internal Medicine Medstar Washington Hospital Center Washington DC

Abstract The risk of multiple adverse pregnancy outcomes and perinatal outcomes among pregnant women with sickle cell trait (SCT) is not known. Our objective was to compare differences in adverse outcomes, specifically pregnancy-related hypertensive disease (PRHD), pyelonephritis/urinary tract infection (UTI), and low birth weight (LBW), between pregnant women with SCT and healthy controls. This was a retrospective cohort study of women who delivered between 2015 and 2020. We included all women with SCT, that is, hemoglobin electrophoresis AS. Women with SCT were matched in a 1:2 to women without SCT, controlling for age, gravidity, and parity. Our primary outcomes were PRHD, pyelonephritis/UTI, and LBW baby. Multivariable logistic regression modeling examined the associations between patients’ characteristics and the primary *** were 162 women with SCT, and 324 healthy control women were enrolled. Bivariate analysis revealed that women with SCT had a higher proportion of PRHD (38.9% vs 34.9%; P = .39), pyelonephritis/UTI (11.7% vs 7.1%; P = .09), but a lower proportion of LBW (10.5% vs 16.0%; P = .1). In multivariable analysis, after controlling for confounders, SCT was not an independent predictor of PRHD. However, SCT was an independent predictor of pyelonephritis/UTI (adjusted odds ratio [aOR], 1.98; 95% confidence interval [CI], 1.02-3.85) and of a lower risk of having a LBW baby (aOR, 0.48; 95% CI, 0.25-0.94). SCT is not associated with an increased risk of PRHD. However, SCT is associated with pregnancy outcomes, including higher risk of pyelonephritis/UTI but a lower risk of LBW babies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel strategy for disease risk prediction incorporating predicted gene expression and DNA methylation data:a multi-phased study of prostate cancer

引用

Cancer Communications 2021年第12期41卷 1387-1397页

作者： Chong Wu Jingjing Zhu Austin King Xiaoran Tong Qing Lu Jong Y.Park Liang Wang Guimin Gao Hong-Wen Deng Yaohua Yang Karen E.Knudsen Timothy R.Rebbeck Jirong Long Wei Zheng Wei Pan David V.Conti Christopher A Haiman Lang Wu Department of Statistics Florida State UniversityTallahasseeFL 32304USA Cancer Epidemiology Division Population Sciences in the Pacific ProgramUniversity of Hawaii Cancer CenterUniversity of Hawaii at ManoaHonoluluHI 96813USA Department of Epidemiology and Biostatistics Michigan State UniversityEast LansingMI 48824USA Department of Biostatistics University of FloridaGainesvilleFL 32603USA Department of Cancer Epidemiology H.Lee Moffitt Cancer Center and Research InstituteTampaFL 33612USA Department of Tumor Biology H.Lee Moffitt Cancer Center and Research InstituteTampaFL 33612USA Department of Public Health Sciences University of ChicagoChicagoIL 60637USA Center of Bioinformatics and Genomics Department of Global Biostatistics and Data ScienceTulane UniversityNew OrleansLA 70112USA Division of Epidemiology Department of MedicineVanderbilt Epidemiology CenterVanderbilt-Ingram Cancer CenterVanderbilt University Medical CenterNashvilleTN 37203USA Department of Cancer Biology Sidney Kimmel Cancer CenterThomas Jefferson UniversityPhiladelphiaPA 19107USA Department of Medical Oncology Dana-Farber Cancer InstituteBostonMA 02215USA Department of Epidemiology Harvard TH Chan School of Public HealthBostonMA 02115USA Division of Biostatistics University of MinnesotaMinneapolisMN 55455USA Department of Preventive Medicine Keck School of MedicineUniversity of Southern California/Norris Comprehensive Cancer CenterLos AngelesCA 90033USA

Background:DNA methylation and gene expression are known to play important roles in the etiology of human diseases such as prostate cancer(PCa).However,it has not yet been possible to incorporate information of DNA methylation and gene expression into polygenic risk scores(PRSs).Here,we aimed to develop and validate an improved PRS for PCa risk by incorporating genetically predicted gene expression and DNA methylation,and other genomic information using an integrative ***:Using data from the PRACTICAL consortium,we derived multiple sets of genetic scores,including those based on available single-nucleotide polymorphisms through widely used methods of pruning and thresholding,LDpred,LDpred-funt,AnnoPred,and EBPRS,as well as PRS constructed using the genetically predicted gene expression and DNA methylation through a revised pruning and thresholding *** the tuning step,using the UK Biobank data(1458 prevalent cases and 1467 controls),we selected PRSs with the best *** an independent set of data from the UK Biobank,we developed an integrative PRS combining information from individual ***,in the testing step,we tested the performance of the integrative PRS in another independent set of UK Biobank data of incident cases and ***:Our constructed PRS had improved performance(C statistics:76.1%)over PRSs constructed by individual benchmark methods(from 69.6%to 74.7%).Furthermore,our new PRS had much higher risk assessment power than family *** overall net reclassification improvement was 69.0%by adding PRS to the baseline model compared with 12.5%by adding family ***:We developed and validated a new PRS which may improve the utility in predicting the risk of developing *** innovative method can also be applied to other human diseases to improve risk prediction across multiple outcomes.

关键词： risk prediction polygenic risk scores predicted gene expression predicted DNA methylation integrative models prostate cancer

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：