Building Classification Trees on Japanese Stock Groups Partitioned by Network Clustering

2017 ◽  
Vol 137 (10) ◽  
pp. 1387-1392
Author(s):  
Takashi Isogai ◽  
Hieu Chi Dam
Keyword(s):  
Classification Trees ◽  
Network Clustering

Biomarker Identification for Liver Hepatocellular Carcinoma and Cholangiocarcinoma Based on Gene Regulatory Network Analysis

2020 ◽  
Vol 15 ◽  
Author(s):  
Qiuyan Huo ◽  
Yuying Ma ◽  
Yu Yin ◽  
Guimin Qin
Keyword(s):  
Hepatocellular Carcinoma ◽  
Regulatory Networks ◽  
Primary Liver Cancer ◽  
Endocrine Resistance ◽  
Molecular Characteristics ◽  
Network Clustering ◽  
Resistance Pathway ◽  
Gene Regulatory ◽  
Tf Gene ◽  
Liver Hepatocellular Carcinoma

Aims: We aimed to find common and distinct molecular characteristics between LIHC and CHOL based on miRNA-TF-gene FFL. Background: Liver hepatocellular carcinoma (LIHC) and cholangiocarcinoma (CHOL) are two main histological subtypes of primary liver cancer with a unified molecular landscape, and feed-forward loops (FFLs) have been shown to be relevant in these complex diseases. Objective: To date, there has been no comparative analysis of the pathogenesis of LIHC and CHOL based on regulatory relationships. Therefore, we investigated the common and distinct regulatory properties of LIHC and CHOL in terms of gene regulatory networks. Method: Based on identified FFLs and an analysis of pathway enrichment, we constructed pathway-specific co-expression networks and further predicted biomarkers for these cancers by network clustering. Resul: We identified 20 and 36 candidate genes for LIHC and CHOL, respectively. The literature from PubMed supports the reliability of our results. Conclusion: Our results indicated that the hsa01522-Endocrine resistance pathway was associated with both LIHC and CHOL. Additionally, six genes (SPARC, CTHRC1, COL4A1, EDIL3, LAMA4 and OLFML2B) were predicted to be highly associated with both cancers, of which SPARC was significantly highly ranked. Other: In addition, we inferred that the Collagen gene family, which appeared more frequently in our overall prediction results, might be closely related to cancer development.

scholarly journals Development of a biomarker database toward performing disease classification and finding disease interrelations

Database ◽  
2021 ◽  
Vol 2021 ◽  
Author(s):  
Shaikh Farhad Hossain ◽  
Ming Huang ◽  
Naoaki Ono ◽  
Aki Morita ◽  
Shigehiko Kanaya ◽  
...  
Keyword(s):  
Rapid Detection ◽  
Molecular Mechanisms ◽  
Clustering Algorithm ◽  
Disease Diagnosis ◽  
Disease Classification ◽  
Network Clustering ◽  
Medical Field ◽  
Database Development ◽  
Abnormal State ◽  
Comprehensive Information

Abstract A biomarker is a measurable indicator of a disease or abnormal state of a body that plays an important role in disease diagnosis, prognosis and treatment. The biomarker has become a significant topic due to its versatile usage in the medical field and in rapid detection of the presence or severity of some diseases. The volume of biomarker data is rapidly increasing and the identified data are scattered. To provide comprehensive information, the explosively growing data need to be recorded in a single platform. There is no open-source freely available comprehensive online biomarker database. To fulfill this purpose, we have developed a human biomarker database as part of the KNApSAcK family databases which contain a vast quantity of information on the relationships between biomarkers and diseases. We have classified the diseases into 18 disease classes, mostly according to the National Center for Biotechnology Information definitions. Apart from this database development, we also have performed disease classification by separately using protein and metabolite biomarkers based on the network clustering algorithm DPClusO and hierarchical clustering. Finally, we reached a conclusion about the relationships among the disease classes. The human biomarker database can be accessed online and the inter-disease relationships may be helpful in understanding the molecular mechanisms of diseases. To our knowledge, this is one of the first approaches to classify diseases based on biomarkers. Database URL:  http://www.knapsackfamily.com/Biomarker/top.php

A semi-supervised approach to growing classification trees

2020 ◽  
Author(s):  
Sudarsun Santhiappan ◽  
Balaraman Ravindran
Keyword(s):  
Classification Trees

Multi-Step Classification Trees

2012 ◽  
Vol 41 (9) ◽  
pp. 1728-1744 ◽  
Author(s):  
Youngjae Chang
Keyword(s):  
Classification Trees

Non-binary classification trees

1996 ◽  
Vol 6 (3) ◽  
pp. 231-243 ◽  
Author(s):  
Stanislav Keprta
Keyword(s):  
Binary Classification ◽  
Classification Trees

New Glaucoma Classification Method Based on Standard Heidelberg Retina Tomograph Parameters by Bagging Classification Trees

2003 ◽  
Vol 12 (4) ◽  
pp. 340-346 ◽  
Author(s):  
Christian Y. Mardin ◽  
Torsten Hothorn ◽  
Andrea Peters ◽  
Anselm G. J??nemann ◽  
Nhung X. Nguyen ◽  
...  
Keyword(s):  
Classification Trees ◽  
Classification Method ◽  
Heidelberg Retina Tomograph

scholarly journals The Role of Steps and Game Elements in Gamified Fitness Tracker Apps: A Systematic Review

2021 ◽  
Vol 5 (2) ◽  
pp. 5
Author(s):  
Aatish Neupane ◽  
Derek Hansen ◽  
Jerry Alan Fails ◽  
Anud Sharma
Keyword(s):  
Social Influence ◽  
Design Space ◽  
Real Life ◽  
Network Clustering ◽  
And Performance ◽  
Fitness Tracker ◽  
Game Elements ◽  
The Relationship ◽  
Contingent Rewards

This article reviews 103 gamified fitness tracker apps (Android and iOS) that incorporate step count data into gameplay. Games are labeled with a set of 13 game elements as well as meta-data from the app stores (e.g., avg rating, number of reviews). Network clustering and visualizations are used to identify the relationship between game elements that occur in the same games. A taxonomy of how steps are used as rewards is provided, along with example games. An existing taxonomy of how games use currency is also mapped to step-based games. We show that many games use the triad of Social Influence, Competition, and Challenges, with Social Influence being the most common game element. We also identify holes in the design space, such as games that include a Plot element (e.g., Collaboration and Plot only co-occur in one game). Games that use Real-Life Incentives (e.g., allow you to translate steps into dollars or discounts) were surprisingly common, but relatively simple in their gameplay. We differentiate between task-contingent rewards (including completion-contingent and engagement-contingent) and performance-contingent rewards, illustrating the differences with fitness apps. We also demonstrate the value of treating steps as currency by mapping an existing currency-based taxonomy onto step-based games and providing illustrations of nine different categories.

Sign in / Sign up

Export Citation Format

Share Document