Non-negative tensor factorization workflow for time series biomedical data

被引：0

作者：

Tsuyuzaki, Koki ^{[1
,2
]}

Yoshida, Naoki ^{[3
]}

Ishikawa, Tetsuo ^{[3
,4
,5
]}

Goshima, Yuki ^{[4
]}

Kawakami, Eiryo ^{[3
,4
,6
,7
]}

机构：

[1] RIKEN Ctr Biosyst Dynam Res, Lab Bioinformat Res, Wako, Saitama 3510198, Japan

[2] Japan Sci & Technol Agcy, PRESTO, 7 Gobancho,Chiyoda ku, Tokyo 1020075, Japan

[3] Chiba Univ, Grad Sch Med, Dept Artificial Intelligence Med, Chiba 2608670, Japan

[4] RIKEN Informat R&D & Strategy Headquarters, Adv Data Sci Project ADSP, Yokohama, Kanagawa 2300045, Japan

[5] Keio Univ, Dept Extended Intelligence Med, Ishii Ishibashi Lab, Sch Med, Shinjuku Ku, Tokyo 1608582, Japan

[6] Japanese Fdn Canc Res JFCR, NEXT Ganken Program, Tokyo 1358550, Japan

[7] Chiba Univ, Inst Adv Acad Res IAAR, Chiba 2608670, Japan

来源：

STAR PROTOCOLS | 2023年 / 4卷 / 03期

基金：

日本科学技术振兴机构;

关键词：

Bioinformatics; Computer sciences; Health Sciences;

D O I：

10.1016/j.xpro.2023.102318

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

Non-negative tensor factorization (NTF) enables the extraction of a small number of latent components from high-dimensional biomedical data. However, NTF requires many steps, which is a hurdle to implementation. Here, we provide a protocol for TensorLyCV, an easy to run and reproducible NTF analysis pipeline using Snake make workflow management system and Docker container. Using vaccine adverse reaction data as an example, we describe steps for data processing, tensor decomposition, optimal rank parameter estimation, and visualization of factor matrices. For complete details on the use and execution of this protocol, please refer to Kei Ikeda et al.1

引用

页数：16

共 50 条

[21] CLASSIFICATION OF POLSAR IMAGE WITH NON-NEGATIVE TENSOR FACTORIZATION APPROACH
Gou, Shuiping
Chen, Wenshuai
Liu, Yizhou
Li, Pengcheng
Jiao, Licheng
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2016, : 1150 - 1153
[22] Non-negative Matrix Factorization for Binary Data
Larsen, Jacob Sogaard
Clemmensen, Line Katrine Harder
2015 7TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT (IC3K), 2015, : 555 - 563
[23] Non-negative Einstein tensor factorization for unmixing hyperspectral images
El Hachimi, Anas
Jbilou, Khalide
Ratnani, Ahmed
NUMERICAL ALGORITHMS, 2025,
[24] Non-Negative Tensor Factorization Applied to Music Genre Classification
Benetos, Emmanouil
Kotropoulos, Constantine
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (08): : 1955 - 1967
[25] QUASI-ORTHOGONALIZATION FOR ALTERNATING NON-NEGATIVE TENSOR FACTORIZATION
Grasedyck, Lars
Klever, Maren
Kraemer, Sebastian
ELECTRONIC TRANSACTIONS ON NUMERICAL ANALYSIS, 2024, 62 : 22 - 57
[26] A sufficient condition for the unique solution of non-negative tensor factorization
Sumi, Toshio
Sakata, Toshio
INDEPENDENT COMPONENT ANALYSIS AND SIGNAL SEPARATION, PROCEEDINGS, 2007, 4666 : 113 - +
[27] Ensemble Non-negative Matrix Factorization for Clustering Biomedical Documents
Zhu, Shanfeng
Yuan, Wei
Wang, Fei
OPTIMIZATION AND SYSTEMS BIOLOGY, PROCEEDINGS, 2008, 9 : 358 - 364
[28] NEIGHBORHOOD PRESERVING NON-NEGATIVE TENSOR FACTORIZATION FOR IMAGE REPRESENTATION
Wang, Yu-Xiong
Gui, Liang-Yan
Zhang, Yu-Jin
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 3389 - 3392
[29] VARIATIONAL BAYESIAN PARTIALLY OBSERVED NON-NEGATIVE TENSOR FACTORIZATION
Hinrich, Jesper L.
Nielsen, Soren F. V.
Madsen, Kristoffer H.
Morup, Morten
2018 IEEE 28TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2018,
[30] Time Series Electricity Consumption Analysis using Non-negative Matrix Factorization
Gakushuin University, Computer Centre, Tokyo, Japan
不详
IEEE Int. Conf. Aware. Sci. Technol., iCAST - Proc., 2019,

← 1 2 3 4 5 →