公开(公告)号：US10720227B2

公开(公告)日：2020-07-21

申请号：US15159546

申请日：2016-05-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Garima Agarwal ,  Srikanth Rama Mallavarapu ,  Ajit Shyamsunder Bopardikar ,  Taejin Ahn

IPC: G16H10/60 ,  G16B30/00 ,  G16H10/20 ,  G06N5/02

Abstract: Provided are methods and devices for mutation prioritization, which are helpful in personalized therapy of a patient. Also, provided are methods and devices for generating a disease knowledgebase. Information present in various categories of knowledge sources with respect to a particular association of set may be identified. The identified information is ranked with respect to the disease knowledgebase to find out the most relevant ones for the treatment of a particular Disease/Gene/Mutation of a patient, thereby enabling medical experts to personalize a therapy to be administered to a patient.

公开(公告)号：US09690844B2

公开(公告)日：2017-06-27

申请号：US14604433

申请日：2015-01-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Subhankar Mukherjee ,  Taejin Ahn ,  Ajit S. Bopardikar ,  Anirban Bhaduri ,  Srikanth Rama Mallavarapu

IPC: G06F17/30

CPC classification number: G06F17/30601

Abstract: Methods and devices for clustering a plurality of sub-networks of a larger interaction network using an enhanced hierarchical clustering algorithm are disclosed. The methods provide expression based sub-network generation using differentially expressed markers. The enhanced hierarchical clustering algorithm clusters the generated sub-networks based on a user defined customizable similarity coefficient. The methods use non-Boolean links to cluster similar sub-networks. This provides consideration of indirect relationships among sub-networks. The customizable similarity coefficient enables the methods to be used for diverse applications such as biomarker detection, patient stratification, personalized therapy, drug efficacy prediction, genetic similarity analysis in genetic diseases. The methods enable patient grouping based on the enhanced hierarchical clustering algorithm.

公开(公告)号：US20150213115A1

公开(公告)日：2015-07-30

申请号：US14604433

申请日：2015-01-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Subhankar Mukherjee ,  Taejin Ahn ,  Ajit S. Bopardikar ,  Anirban Bhaduri ,  Srikanth Rama Mallavarapu

IPC: G06F17/30

CPC classification number: G06F17/30601

Abstract: Methods and devices for clustering a plurality of sub-networks of a larger interaction network using an enhanced hierarchical clustering algorithm are disclosed. The methods provide expression based sub-network generation using differentially expressed markers. The enhanced hierarchical clustering algorithm clusters the generated sub-networks based on a user defined customizable similarity coefficient. The methods use non-Boolean links to cluster similar sub-networks. This provides consideration of indirect relationships among sub-networks. The customizable similarity coefficient enables the methods to be used for diverse applications such as biomarker detection, patient stratification, personalized therapy, drug efficacy prediction, genetic similarity analysis in genetic diseases. The methods enable patient grouping based on the enhanced hierarchical clustering algorithm.

Abstract translation: 公开了使用增强层次聚类算法对较大交互网络的多个子网进行聚类的方法和装置。 该方法提供使用差异表达标记的基于表达的子网生成。 增强层次聚类算法基于用户定义的可定制相似系数对生成的子网进行聚类。 这些方法使用非布尔链接来聚类类似的子网络。 这提供了子网之间间接关系的考虑。 可定制的相似系数使得该方法可用于多种应用，如生物标志物检测，患者分层，个性化治疗，药物功效预测，遗传疾病中的遗传相似性分析。 该方法使得基于增强层次聚类算法的患者分组。