one-class logistic regression (OCLR)

最新推荐文章于 2019-11-02 17:19:01 发布

weixin_30767921

最新推荐文章于 2019-11-02 17:19:01 发布

阅读量1.2k

点赞数

CC 4.0 BY-SA版权

文章标签：人工智能数据结构与算法 r语言

原文链接：http://www.cnblogs.com/leezx/p/8794744.html

本文介绍了一种使用机器学习方法来识别肿瘤样本中特定细胞类型的技术。通过建立单类别预测模型，该方法能够在包含多种未知比例细胞类型的样本中准确地鉴定目标细胞。实验证明，这种方法相较于二元分类模型更有效，并且能够揭示干细胞特征与侵袭性乳腺癌亚型之间的关联。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

ONE-CLASS DETECTION OF CELL STATES IN TUMOR SUBTYPES

Machine Learning Identifies Stemness Features Associated with Oncogenic Dedifferentiation

PanCanStem Web

However, the challenge is to find them within samples containing mixtures of cell types of unknown proportions.

需要从一堆混合有未知细胞的细胞群中鉴定出我们想要的细胞。

We demonstrate that one-class models are able to identify specific cell types in heterogeneous cell populations better than their binary predictor counterparts.

We derive one-class predictors for the major breast and bladder subtypes and reaffirm the connection between these two tissues.

In addition, we use a one-class predictor to quantitatively associate an embryonic stem cell signature with an aggressive breast cancer subtype that reveals shared stemness pathways potentially important for treatment.

The resulting machine learning task is to build a model that can correctly rank the background samples containing the stemness signal above those that do not.

The accuracy is evaluated via Area under the ROC curve (AUC), which can be interpreted as the probability that the predictor correctly ranks a mixture sample above a non-mixture sample.

问题：

1. 到底什么是one class？

2. 与其他算法相比，有什么优点？

3. 我能应用到我的分析当中吗？

转载于:https://www.cnblogs.com/leezx/p/8794744.html