首页> 外文会议>International Meeting on Computational Intelligence Methods for Bioinformatics and Biostatistics >Cancer Mutational Signatures Identification with Sparse Dictionary Learning
【24h】

Cancer Mutational Signatures Identification with Sparse Dictionary Learning

机译:癌症突变签名用稀疏的字典学习识别

获取原文

摘要

Somatic DNA mutations are a characteristic of cancerous cells, being usually key in the origin and development of cancer. In the last few years, somatic mutations have been studied in order to understand which processes or conditions may generate them, with the purpose of developing prevention and treatment strategies. In this work we propose a novel sparse regularised method that aims at extracting mutational signatures from somatic mutations. We developed a pipeline that extracts the dataset from raw data and performs the analysis returning the signatures and their relative usage frequencies. A thorough comparison between our method and the state of the art procedure reveals that our pipeline can be used alternatively without losing information and possibly gaining more interpretability and precision.
机译:体细胞DNA突变是癌细胞的特征,通常是癌症起源和发育的关键。在过去的几年中,已经研究了体细胞突变,以了解哪些过程或条件可能产生它们,目的是发展预防和治疗策略。在这项工作中,我们提出了一种新颖的稀疏正规方法,旨在提取来自体细胞突变的突变签名。我们开发了一种管道,从原始数据中提取数据集,并执行返回签名及其相对使用频率的分析。我们的方法和最先进的方法之间的彻底比较揭示了我们的管道可以替代地使用,而不会丢失信息并可能获得更多的可解释性和精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号