检索结果-内蒙古大学图书馆

Assessment of CYP2D6 gene expression in liver tissue: Variability in CYP2D6 mRNA levels within genotype-predicted metabolizer phenotype groups

学校读者我要写书评

暂无评论

Chemico-Biological Interactions 2025年 416卷

作者： Meaddough, Erika L. Sarasua, Sara M. Kunkel, Deborah Boccuto, Luigi Ganakammal, Satishkumar R. Moersen, Matt Farrell, Christopher L. School of Nursing Healthcare Genetics & Genomics Program College of Behavioral Social and Health Sciences Clemson University Clemson SC United States School of Mathematical and Statistical Sciences College of Science Clemson University Clemson SC United States Research Computing & Data Clemson Computing and Information Technology Clemson University Clemson SC United States

Pharmacogenetic (PGx) testing can be used to help guide drug therapy and decrease or avoid the risk of adverse drug reactions. CYP2D6 is an important pharmacogene in pharmacogenomics testing panels. However, phenoconversion, whereby an individual's ability to metabolize a drug does not match the genotype-predicted metabolizer status, is a confounding factor to the accurate application of PGx testing results to patient care. To address this issue, CYP2D6 expression between and within genotype-predicted CYP2D6 metabolizer phenotype groups was compared using WGS and RNA-Seq data from 134 normal liver tissue donors obtained from the GTEx program. Wide variability in CYP2D6 mRNA levels was observed within metabolizer phenotype groups. The median expression level for ultrarapid metabolizers (UMs) was 738.9 TPM (transcripts per million;196.8–778.9 TPM), 212.5 TPM (32.1–666.5 TPM) for normal metabolizers (NMs), 219.6 TPM for intermediate metabolizers (IMs) (22–389.8 TPM), and 121.2 TPM for poor metabolizers (PMs) (9.3–298.2 TPM). The PM and UM phenotypes were significant predictors of CYP2D6 expression (p = 0.0004 and p = 0.019, respectively). Interestingly, expression of the gene encoding human serum albumin (ALB) was also a significant predictor of CYP2D6 expression (p = 0.0003). data from 50 patients with hepatocellular carcinoma obtained from the TCGA program showed no significant difference in expression between tumor tissue (median = 119.7 TPM, range 0.16–817.7 TPM) and normal matched tissue (median = 143.3 TPM, range 26.2–810.7 TPM). Transcriptional regulation of CYP2D6 expression may contribute to differences in drug response and risk for CYP2D6 phenoconversion. Efforts to understand the role of gene expression to predict CYP2D6 phenoconversion may inform the use of PGx testing in the clinical setting. © 2025 The Authors

关键词： CYP2D6 Drug-metabolizing enzymes Gene expression Hepatocellular carcinoma Metabolizer phenotype Pharmacogenetics Phenoconversion

BENCHMARKING COMMUNITY DRUG RESPONSE PREDICTION MODELS: dataSETS, MODELS, TOOLS, AND METRICS FOR CROSS-dataSET GENERALIZATION ANALYSIS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Partin, Alexander Vasanthakumari, Priyanka Narykov, Oleksandr Wilke, Andreas Koussa, Natasha Jones, Sara E. Zhu, Yitan Overbeek, Jamie C. Jain, Rajeev Fernando, Gayara Demini Sanchez-Villalobos, Cesar Garcia-Cardona, Cristina Mohd-Yusof, Jamaludin Chia, Nicholas Wozniak, Justin M. Ghosh, Souparno Pal, Ranadip Brettin, Thomas S. Weil, M. Ryan Stevens, Rick L. Division of Data Science and Learning Argonne National Laboratory LemontIL United States Frederick National Laboratory for Cancer Research Cancer Data Science Initiatives Cancer Research Technology Program FrederickMD United States Department of Statistics University of Nebraska–Lincoln LincolnNE United States Department of Electrical & Computer Engineering Texas Tech University LubbockTX United States Division of Computer Computational and Statistical Sciences Los Alamos National Laboratory Los AlamosNM United States Department of Computer Science The University of Chicago ChicagoIL United States

Deep learning (DL) and machine learning (ML) models have shown promise in drug response prediction (DRP), yet their ability to generalize across datasets remains an open question, raising concerns about their real-world applicability. Due to the lack of standardized benchmarking approaches, model evaluations and comparisons often rely on inconsistent datasets and evaluation criteria, making it difficult to assess true predictive capabilities. In this work, we introduce a benchmarking framework for evaluating cross-dataset prediction generalization in DRP models. Our framework incorporates five publicly available drug screening datasets, six standardized DRP models, and a scalable workflow for systematic evaluation. To assess model generalization, we introduce a set of evaluation metrics that quantify both absolute performance (e.g., predictive accuracy across datasets) and relative performance (e.g., performance drop compared to within-dataset results), enabling a more comprehensive assessment of model transferability. Our results reveal substantial performance drops when models are tested on unseen datasets, underscoring the importance of rigorous generalization assessments. While several models demonstrate relatively strong cross-dataset generalization, no single model consistently outperforms across all datasets. Furthermore, we identify CTRPv2 as the most effective source dataset for training, yielding higher generalization scores across target datasets. By sharing this standardized evaluation framework with the community, our study aims to establish a rigorous foundation for model comparison, and accelerate the development of robust DRP models for real-world applications. © 2025, CC BY.

关键词： Prediction models

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

学校读者我要写书评

暂无评论

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

Improving structure evaluation through automatic hierarchy expansion 20

学校读者我要写书评

暂无评论

Improving structure evaluation through automatic hierarchy e...

20th International Society for Music Information Retrieval Conference, ISMIR 2019

作者： McFee, Brian Kinnaird, Katherine M. Music and Audio Research Lab Center for Data Science New York University United States Department of Computer Science Statistical and Data Sciences Program Smith College United States

ISBN: (纸本)9781732729919

Structural segmentation is the task of partitioning a recording into non-overlapping time intervals, and labeling each segment with an identifying marker such as A, B, or verse. Hierarchical structure annotation expands this idea to allow an annotator to segment a song with multiple levels of granularity. While there has been recent progress in developing evaluation criteria for comparing two hierarchical annotations of the same recording, the existing methods have known deficiencies when dealing with inexact label matchings and sequential label repetition. In this article, we investigate methods for automatically enhancing structural annotations by inferring (and expanding) hierarchical information from the segment labels. The proposed method complements existing techniques for comparing hierarchical structural annotations by coarsening or refining labels with variation markers to either collapse similarly labeled segments together, or separate identically labeled segments from each other. Using the multi-level structure annotations provided in the SALAMI dataset, we demonstrate that automatic hierarchy expansion allows structure comparison methods to more accurately assess similarity between annotations. © 2020 International Society for Music Information Retrieval. All rights reserved.

关键词： Coarsening

A Grammar for Reproducible and Painless Extract-Transform-Load Operations on Medium data

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Baumer, Benjamin S. Program in Statistical and Data Sciences Smith College

Many interesting data sets available on the Internet are of a medium size—too big to fit into a personal computer’s memory, but not so large that they won’t fit comfortably on its hard disk. In the coming years, data sets of this magnitude will inform vital research in a wide array of application domains. However, due to a variety of constraints they are cumbersome to ingest, wrangle, analyze, and share in a reproducible fashion. These obstructions hamper thorough peer-review and thus disrupt the forward progress of science. We propose a predictable and pipeable framework for R (the state-of-the-art statistical computing environment) that leverages SQL (the venerable database architecture and query language) to make reproducible research on medium data a painless reality.62-07, 68U99 Copyright © 2017, The Authors. All rights reserved.

关键词： Query languages

"playing the whole game": A data collection and analysis exercise with Google Calendar

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kim, Albert Y. Hardin, Johanna Program in Statistical and Data Sciences Smith College Statistical and Data Sciences NorthamptonMA01063 United States

We provide an exercise suitable for early introduction in an undergraduate statistics or data science course that allows students to 'play the whole game' of data science: performing both data collection and data analysis. While many teaching resources exist for data analysis, such resources are not as abundant for data collection given the inherent difficulty of the task. Our proposed exercise centers around student use of Google Calendar to collect data with the goal of answering the question 'How do I spend my time?' On the one hand, the exercise involves answering a question with near universal appeal, but on the other hand, the data collection mechanism is not beyond the reach of a modal undergraduate student. A further benefit of this exercise is that it provides an opportunity for discussions on ethical questions and considerations that data providers and data analysts face in today's age of large-scale internet-based data collection. Copyright © 2020, The Authors. All rights reserved.

关键词： Students

Method for modelling the number of HIV and AIDS cases using least square spline Biresponse nonparametric negative binomial regression

学校读者我要写书评

暂无评论

MethodsX 2025年 14卷 103336页

作者： Ramadan, Arip Chamidah, Nur Budiantara, I Nyoman Lestari, Budi Aydin, Dursun Doctoral Study Program of Mathematics and Natural Sciences Faculty of Science and Technology Airlangga University Surabaya 60115 Indonesia Information System Study Program Department of Industrial and System Engineering Telkom University Surabaya Campus Surabaya 60231 Indonesia Department of Mathematics Faculty of Science and Technology Airlangga University Surabaya 60115 Indonesia Research Group of Statistical Modeling in Life Science Faculty of Science and Technology Airlangga University Surabaya 60115 Indonesia Statistics Department Faculty of Science and Data Analytics Sepuluh Nopember Institute of Technology Surabaya 60111 Indonesia Department of Mathematics Faculty of Mathematics and Natural Sciences The University of Jember Jember 68121 Indonesia Department of Statistics Faculty of Science Muğla Sıtkı Koçman University Muğla 48000 Turkey Research Scholar at Department of Mathematics University of Wisconsin Oshkosh Algoma Blvd Oshkosh 54901 WI United States

We propose a new statistical modeling method to analyze functional relationship between predictor variables and correlated response variables, and apply it for modeling the number of HIV and AIDS cases influenced by early-age marriages and contraceptive users. The proposed method is LS-Spline BNNBR that is a Biresponse Nonparametric Negative Binomial Regression (BNNBR) based on least squares spline (LS-Spline). To validate the proposed method, we compare it with classical method, namely Ordinary Least Square Biresponse Parametric Negative Binomial Regression (OLS-BPNBR). The results show that the LS-Spline BNNBR method provided deviance value of 7.542334 which is smaller than that of OLS-BPNBR method, namely 7.993935. Thus, the proposed method has better prediction fit than the classical method. • This study discusses new statistical modeling method for the number of HIV and AIDS cases influenced by early-age marriages and contraceptive users where the response variables are correlated with each other. • The model estimation results show that the number of HIV and AIDS cases in Indonesia will decrease if the early-age marriages percentage increases and the contraceptive users percentage decreases. • The results are useful to provide a scientific basis for making policies to control the number of HIV and AIDS cases in Indonesia. © 2025 The Authors

关键词： AIDS BLSSNNBR model Contraceptive user Early-age marriage HIV Least square spline

A general semi-parametric elliptical distribution model for semi-supervised learning

学校读者我要写书评

暂无评论

Journal of Nonparametric Statistics 2025年第2期37卷

作者： Chin-Tsang Chiang Sheng-Hsin Fan Ming-Yueh Huang Jen-Chieh Teng Alvin Lim a Institute of Applied Mathematical Sciences National Taiwan University Taipei Taiwan b Department of Mathematics National Taiwan University Taipei Taiwan c Institute of Statistical Science Academia Sinica Taipei Taiwan d Data Science Degree Program National Taiwan University Taipei Taiwan e Data Science Department Measured Inc. Austin TX USAf Goizueta Business School Emory University Atlanta GA USA

ABSTRACTThis research proposes a novel semi-parametric elliptical distribution model for application in semi-supervised learning tasks. We use labelled and unlabelled data to develop a pseudo maximum likelihood method for estimation and classification. The proposed estimator outperforms the estimator based solely on labelled data and achieves the semi-parametric efficiency bound with a suitable size of unlabelled data. We efficiently maximise the objective function by utilising low-dimensional groupwise pseudo-likelihood functions in a block coordinate descent manner while ensuring numerical stability and convergence through appropriate bandwidth selectors and initial parameter estimates. Additionally, the study comprehensively investigates the impact of labelled and unlabelled data on the pseudo maximum likelihood estimator and classifier. Simulation studies and empirical data applications illustrate the superiority of our methodology.

关键词： elliptical distribution posterior group probability pseudo maximum likelihood method semi-parametric efficiency semi-supervised learning

A Consensus Privacy Metrics Framework for Synthetic data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pilgram, Lisa Dankar, Fida K. Drechsler, Jörg Elliot, Mark Domingo-Ferrer, Josep Francis, Paul Kantarcioglu, Murat Kong, Linglong Malin, Bradley Muralidhar, Krishnamurty Myles, Puja Prasser, Fabian Raisaro, Jean Louis Yan, Chao El Emam, Khaled School of Epidemiology and Public Health University of Ottawa ON Canada CHEO Research Institute ON Canada Department of Nephrology and Medical Intensive Care Charité – Universitätsmedizin Berlin Berlin Germany Department for Statistical Methods Institute for Employment Research Nuernberg Germany Institute for Statistics Ludwig-Maximilians-Universität Munich Germany Joint Program in Survey Methodology University of Maryland United States The Cathie Marsh Institute Research School of Social Sciences University of Manchester Manchester United Kingdom Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Catalonia Tarragona Spain Max Planck Institute for Software Systems Germany Department of Computer Science Virginia Tech United States Department of Mathematical and Statistical Sciences University of Alberta Alberta Canada Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Biostatistics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Department of Marketing and Supply Chain Management University of Oklahoma Oklahoma United States Medicines and Healthcare products Regulatory Agency London United Kingdom Berlin Institute of Health at Charité Universitätsmedizin Berlin Medical Informatics Group Berlin Germany Biomedical Data Science Center University Hospital Lausanne Lausanne Switzerland

Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals’ privacy is adequately protected. There is no consolidated standard for measuring privacy in synthetic data. Through an expert panel and consensus process, we developed a framework for evaluating privacy in synthetic data. Our findings indicate that current similarity metrics fail to measure identity disclosure, and their use is discouraged. For differentially private synthetic data, a privacy budget other than close to zero was not considered interpretable. There was consensus on the importance of membership and attribute disclosure, both of which involve inferring personal information about an individual without necessarily revealing their identity. The resultant framework provides precise recommendations for metrics that address these types of disclosures effectively. Our findings further present specific opportunities for future research that can help with widespread adoption of synthetic data. © 2025, CC BY.

关键词： Differential privacy