首页> 外文会议>International conference on applications of natural language to information systems >Using Machine Reading to Aid Cancer Understanding and Treatment
【24h】

Using Machine Reading to Aid Cancer Understanding and Treatment

机译:使用机器阅读帮助癌症的理解和治疗

获取原文

摘要

PubMed, a repository and search engine for biomedical literature, now indexes more than 1 million articles each year. This is clearly beyond the processing capacity of human domain experts, which hinders our capacity to truly understand many diseases. In this talk, I will introduce an effort that teaches computers to "read" millions of cancer-research publications to have a holistic understanding of the disease. Our approach extracts and assembles protein signaling pathways, which are partly responsible for causing cancer, into a large model, which allows researchers to come up with new hypotheses for understanding and treating the disease. I will show that, not only does our automated approach perform comparably with human experts at the task of reading papers, but also that the generated knowledge is able to produce new explanations for several types of cancer.
机译:PubMed是生物医学文献的存储库和搜索引擎,现在每年索引超过100万篇文章。这显然超出了领域专家的处理能力,这妨碍了我们真正了解许多疾病的能力。在本次演讲中,我将介绍一项旨在教会计算机“阅读”数百万篇癌症研究出版物的方法,以全面了解这种疾病。我们的方法将部分导致癌症的蛋白质信号传导途径提取并组装成一个大模型,这使研究人员能够提出新的假设来理解和治疗该疾病。我将证明,在阅读论文的任务中,我们的自动化方法不仅可以与人类专家媲美,而且所产生的知识也能够为几种类型的癌症提供新的解释。

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