文献阅读--A systematic approach to identify novel cancer drug targets using machine learning, inhibitor
来源:互联网 发布:淘宝详情页模板图 编辑:程序博客网 时间:2024/05/15 11:33
最近找了一些,预测肿瘤药物靶点的文献看看,这篇我挺感兴趣。
我主要阅读了靶点预测部分,一些专业的东西还不理解,暂粗浅的记录下
用机器学习算法,找新的癌症药物靶点
中心思想:用已知的训练集学习得出一个分类器(模型),再对未知的数据集进行分类
特征
收集癌症药物靶点的基因级信息,包括:
作为机器学习的特征空间
原始数据集
1. 已知药物靶点数据集2.未知药物靶点数据集
已知药物靶点数据集:collecting anti-BrCa, -PaCa and -OvCa drugs, their targets were identified from DrugBank [31] and the Therapeutic Target Database. In total, 62 known BrCa drug targets, 69 known PaCa targets and known 45 OvCa targets constituted the positive dataset。
未知药物靶点数据集:相关蛋白,在DrugBank和Therapeutic Target Database 没有记录;没有注释为癌症相关蛋白;不与肿瘤药物靶点相互影响;没有分享Pfam功能域;与已知靶点序列相似。
用文本挖掘的方法,挖掘在肿瘤研究文献中的所研究的15663个基因,统计出5169个基因可作为未知药物靶点数据集。
机器学习和特征选择
算法:支持向量机(SVM)
目的:将要预测的数据集,分为有癌症药物靶点或无癌症药物靶点两类。
特征选择:用SVM-REF方法,对13个特征评分,根据评分,最终得到5个相关的特征,包括:Average gene essentiality,Average mRNA expression,Average DNA copy number,Mutation occurrence,Clustering coefficient。
在用最优的特征集,训练集来得出最优的预测模型。
BrCa prediction model
PaCa prediction model
OvCa prediction model
靶点预测
用生成的预测模型,对15663个人基因分类.
预测结果:1655个基因作为假定靶点,对不同的癌型有不同的预测分值,可根据分值选取后续验证的靶点。
- 文献阅读--A systematic approach to identify novel cancer drug targets using machine learning, inhibitor
- A novel approach to neural machine translation
- 【文献阅读】Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- [文献阅读] The Alignment Template Approach to Statistical Machine Translation
- A novel approach to monitor rehabilitation outcomes in stroke survivors using wearable technology被引文
- A machine learning approach for non-blind image deconvolution(泛读)
- 文献阅读-Actionable pathways: interactive discovery of therapeutic targets using signaling pathway model
- Using Machine Learning to Name Malware
- 阅读A Discriminative Feature Learning Approach for Deep Face Recognition
- A Novel Approach to Improvingthe Efficiency of Storing and Accessing Small Files on Hadoop: a Case S
- Exploratory Analysis of Spatial and Temporal Data: A Systematic Approach
- 文献阅读-Identifying driver mutations in sequenced cancer genomes
- Iterative Quantization: A Procrustean Approach to Learning Binary Codes (ITQ)
- A Fuzzing Approach to Credentials Discovery using Burp Intruder
- Nature文献解读:Machine-learning-assisted materials discovery using failed experiments
- Course学习之旅--UW的Machine Learning Foundations: A Case Study Approach--Lession 1
- Machine Learning Foundations: A Case Study Approach-Regression-Assignment: Predicting House Prices
- 学习摘要:convolutional-lstm-network-a-machine-learning-approach-for-precipitation-nowcasting
- 斐波那契三种求法
- 第九周LeetCode
- python _缺省参数及赋值
- 加法编程
- cocos mac 环境问题记录
- 文献阅读--A systematic approach to identify novel cancer drug targets using machine learning, inhibitor
- 电脑登录云主机服务器
- ResNet--Deep Residual Learning for Image Recognition
- 常见的内联和块状元素
- 循环语句的使用
- 5G:非正交多址接入技术(NOMA)
- 受检异常
- bzoj3275: Number
- Db2中,为什么ALTER TABLE需要X类型的internal Plan lock?