Multiple instance neural networks based on sparse attention for cancer detection using T-cell receptor sequences.
Multiple instance neural networks based on sparse attention for cancer detection using T-cell receptor sequences.
复制标题
DOI：
10.1186/s12859-022-05012-2
复制
发表时间：
2022-11-08
影响因子：
3
通讯作者：
中科院分区：
文献类型：
--
作者：
癌症的早期检测由于其在生物医学领域中的至高无上的重要性而得到了广泛的探索。在用于回答这一生物学问题的不同类型的数据中，基于T细胞受体(TCR)的研究最近受到关注，因为越来越多的人认识到宿主免疫系统在肿瘤生物学中的作用。然而，一个患者和多个TCR序列之间的一对多对应关系阻碍了研究人员简单地采用经典的统计/机器学习方法。最近有人尝试在多实例学习(MIL)的背景下对这种类型的数据进行建模。尽管MIL在使用TCR序列的癌症检测中有了新的应用，并且在几种肿瘤类型中表现出了足够的性能，但仍有改进的空间，特别是对于某些癌症类型。此外，对于这一应用，可解释的神经网络模型还没有得到充分的研究。在本文中，我们提出了基于稀疏注意的多实例神经网络(Minn-SA)来提高癌症检测的性能和可解释性。稀疏注意结构在每个包中丢弃了没有信息的实例，与跳过连接相结合，实现了可解释性和更好的预测性能。我们的实验表明，与现有的MIL方法相比，Minn-SA在10种不同类型的癌症中平均测量的ROC曲线下区域得分最高。此外，我们从估计的关注度观察到，Minn-SA可以识别同一T细胞库中针对肿瘤抗原的TCR。
Early detection of cancers has been much explored due to its paramount importance in biomedical fields. Among different types of data used to answer this biological question, studies based on T cell receptors (TCRs) are under recent spotlight due to the growing appreciation of the roles of the host immunity system in tumor biology. However, the one-to-many correspondence between a patient and multiple TCR sequences hinders researchers from simply adopting classical statistical/machine learning methods. There were recent attempts to model this type of data in the context of multiple instance learning (MIL). Despite the novel application of MIL to cancer detection using TCR sequences and the demonstrated adequate performance in several tumor types, there is still room for improvement, especially for certain cancer types. Furthermore, explainable neural network models are not fully investigated for this application. In this article, we propose multiple instance neural networks based on sparse attention (MINN-SA) to enhance the performance in cancer detection and explainability. The sparse attention structure drops out uninformative instances in each bag, achieving both interpretability and better predictive performance in combination with the skip connection. Our experiments show that MINN-SA yields the highest area under the ROC curve scores on average measured across 10 different types of cancers, compared to existing MIL approaches. Moreover, we observe from the estimated attentions that MINN-SA can identify the TCRs that are specific for tumor antigens in the same T cell repertoire.
登录
查看更多内容
在肿瘤浸润淋巴细胞上表达的孤儿T细胞受体的抗原鉴定。
影响因子：
64.5
作者：
Gee MH;Han A;Lofgren SM;Beausang JF;Mendoza JL;Birnbaum ME;Bethune MT;Fischer S;Yang X;Gomez-Eerland R;Bingham DB;Sibener LV;Fernandes RA;Velasco A;Baltimore D;Schumacher TN;Khatri P;Quake SR;Davis MM;Garcia KC
通讯作者：
Garcia KC
DOI：
10.1073/pnas.0408677102
发表时间：
2005-05-03
影响因子：
11.1
作者：
Atchley, WR;Zhao, JP;Drüke, T
通讯作者：
Drüke, T
影响因子：
14.4
作者：
Amores, Jaume
通讯作者：
Amores, Jaume
影响因子：
8
作者：
Cheplygina, Veronika;Tax, David M. J.;Loog, Marco
通讯作者：
Loog, Marco
影响因子：
8
作者：
Carbonneau, Marc-Andre;Cheplygina, Veronika;Gagnon, Ghyslain
通讯作者：
Gagnon, Ghyslain