|
表型数据分析中的多任务学习
Multi-task learning in the analysis of phenotypic data |
|
| |
| 课程网址: |
http://videolectures.net/icgeb_arany_phenotypic_data/
|
| 主讲教师: |
Adam Arany
|
| 开课单位: |
KU鲁汶
|
| 开课时间: |
2019-06-28
|
| 课程语种: |
英语
|
| 中文简介: |
多任务学习是一种有效的机器学习方法，它结合了几个相关任务的数据，与单独解决每个任务相比，提高了精度。考虑到大型生物问题的特殊要求，我们的研究小组开发了一种可扩展的贝叶斯矩阵分解方法Macau及其基于非线性深度学习的后续SparseFlow。在这次演讲中，我将说明这些方法在与表型数据分析相关的两个应用领域中的应用。第一个应用是概念验证工作，证明单个高通量成像分析的数据可以重新用于预测数百种针对无关路径或生物过程的分析中化合物的生物活性。我们的结果表明，来自高含量屏幕的数据是丰富的信息来源，可用于预测和取代定制的生物检测。这些结果也证明了基于图像的药物发现学习的进一步研究是正确的。在第二个应用领域中，我们使用矩阵分解法，通过细胞类型（基因表达）和药物靶向对给定细胞系药物作用的影响来衡量癌症治疗效果的机制。
|
| 课程简介: |
Multi-task learning is an efficient approach of machine learning which combines data from several related tasks, improving accuracy compared to solving each task separately. With the special requirements of large biological problems in mind, our research group developed a scalable Bayesian matrix factorization method Macau, and its nonlinear deep learning based successor SparseFlow. In this talk I will illustrate the application of these methods in two application area related to phenotypic data analysis. The first application is a proof-of-concept work demonstrating that data from a single high-throughput imaging assay can be repurposed to predict the biological activity of compounds in hundreds of assays targeting unrelated pathways or biological processes. Our results suggest that data from high-content screens are a rich source of information that can be used to predict and replace customized biological assays. These results also justify further work on image-based learning for drug discovery. In the second application area we used the matrix factorization method to gain insight about the mechanisms underlying treatment efficacy in cancer, measured by the effect of cell type (gene expression) and drug targets to the effect of drugs on a given cell-line.
|
| 关 键 词: |
表型数据分析; 数据科学; 多任务学习; 后续SparseFlow非线性深度学习; 机器学习方法
|
| 课程来源: |
视频讲座网
|
| 数据采集: |
2022-10-14：cyh
|
| 最后编审: |
2022-10-14：cyh
|
| 阅读次数: |
31
|
|
图 书 馆