MSDRP: a deep learning model based on multisource data for predicting drug response

最新推荐文章于 2024-06-02 23:09:50 发布
最新推荐文章于 2024-06-02 23:09:50 发布
阅读量818 收藏 1
点赞数
文章标签： 深度学习 人工智能
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/qq_51014805/article/details/134503394
版权

数据源

cell

在这里插入图片描述
细胞系数据一共有四个矩阵数据，分别是，基因表达，体细胞突变，拷贝数变异三种类型，比如说，基因表达是该种细胞系与700个癌症基因在基因表达上的关系，其余类似。
在这里插入图片描述

记下来对每个细胞系矩阵数据通过切比雪夫进行相似度处理，分别得到四个580*580的数据。

drug data

药物数据一共有六种指纹图谱，五种药物与生物体的关系，一种药物与细胞系的关系
在这里插入图片描述
在这里插入图片描述
对12种药物矩阵数据进行相似度处理
在这里插入图片描述

fusion vector

对12个药物矩阵进行混合处理
在这里插入图片描述

model step

在这里插入图片描述
在这里插入图片描述
设计了一个交互模块，包括外积和内积单元，以捕获di和cj之间的细粒度和粗粒度交互。在外积单元中，首先在变换后的di向量和变换后的cj向量之间进行外积运算。可以得到48个(12×4)不同的外部相互作用图来表示di-cj。然后利用CNN网络从多个外部交互图中学习外部交互嵌入。CNN网络由两个残差块和一个CNN层组成，可以有效地利用di和cj交互的局部特征。最后，使用最大池化层从提取的交互嵌入中捕获全局信息。在内积单元中，首先进行内积运算，然后利用MLPInner模块（全连接层）学习嵌入。

在这里插入图片描述

overall

在这里插入图片描述

何以解忧，唯有睡觉
关注
  • 0
    点赞
  • 踩
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
PEDLA: predicting enhancers with a deep learning-based algorithmic framework.
02-11
PEDLA: predicting enhancers with a deep learning-based algorithmic framework.
A hybrid model based on rough sets theory and genetic algorithms for stock price
04-25
In the stock market, technical analysis is a useful method for predicting stock prices. Although, professional stock analysts and fund managers usually make subjective judgments, based on objective technical indicators, it is difficult for non-professionals to apply this forecasting technique because there are too many complex technical indicators to be considered. Moreover, two drawbacks have been found in many of the past forecasting models: (1) statistical assumptions about variables are required for time series models, such as the autoregressive moving average model (ARMA) and the autoregressive conditional heteroscedasticity (ARCH), to produce forecasting models of mathematical equations, and these are not easily understood by stock investors; and (2) the rules mined from some artificial intelligence (AI) algorithms, such as neural networks (NN), are not easily realized.
文章2：全文Identifying and Predicting Autism Spectrum Disorder Based on Multi-Site Structural MRI With Machine Learning.pdf
04-23
文章2：全文Identifying and Predicting Autism Spectrum Disorder Based on Multi-Site Structural MRI With Machine Learning.pdf
Improving Deep Neural Networks Tensorflow Homework
生物医学信息学博客
09-24 8595
TensorFlow TutorialWelcome to this week’s programming assignment. Until now, you’ve always used numpy to build neural networks. Now we will step you through a deep learning framework that will allow yo
每日学术速递4.14
与君共勉，一起学习
04-14 904
标题：大规模深度强化学习：使用移动机械手对办公楼中的垃圾进行分类作者：Mengyuan Yan Jessica Lin Montserrat Gonzalez Arenas Ted Xiao Daniel Kappler Daniel Ho文章链接：https://rl-at-scale.github.io/assets/rl_at_scale.pdf项目代码：https://rl-at-scale.github.io/摘要： 我们描述了一个用于深度强化学习机器人操作技能的系统，该系统应用于大
msdrp.cab
iteye_7128的博客
05-08 65
[u][/u]
Paper reading (二十)：Deep Learning for Genomics: A Concise Overview
wxw060709的专栏
09-29 1028
论文题目：Deep Learning for Genomics: A Concise Overview scholar 引用：19 页数：40 发表时间：2018.05 发表刊物：Genomics 作者：Tianwei Yue,Haohan Wang 摘要： This data explosion driven by advancements in genomic research...
A Computational Method Based on the Integration of Heterogeneous Networks for Predicting Disease-Gene Associations
02-11
A Computational Method Based on the Integration of Heterogeneous Networks for Predicting Disease-Gene Associations
Deep generative model with domain adversarial training for predicting arteri.pdf
08-07
Deep generative model with domain adversarial training for predicting arterial blood pressure waveform from photoplethysmogram signal
吴恩达深度学习第一课第三周作业
wanfuchun的博客
08-11 1185
Planar data classification with one hidden layer Welcome to your week 3 programming assignment. It’s time to build your first neural network, which will have a hidden layer. You will see a big differe...
【CTR预估】The Wide and Deep Learning Model（译文+Tensorlfow源码解析）
热门推荐
快来学习鸭～～～
11-03 1万+
Author: DivinerShi本文主要讲解Google的Wide and Deep Learning 模型。本文先从原始论文开始，先一步步分析论文，把论文看懂。再去分析官方开源的Tensorflow源码，解析各个特征的具体实现方法，以及模型的具体构造方法等。先上图1.论文翻译ABSTRACTGeneralized linear models with nonlinear feature tra
【论文阅读】A Hybrid Model Integrating Local and Global...Traffic Prediction[一种融合局部和全局空间相关性的交通预测混合模型]（2）
weixin_43360025的博客
09-14 755
【论文阅读】A Hybrid Model Integrating Local and Global Spatial Correlation for Traffic Prediction[一种融合局部和全局空间相关性的交通预测混合模型]（2） 2. Related Work（相关工作）Abstract
深度学习文本分类文献综述（翻译自Deep Learning Based Text Classification: A Comprehensive Review）
qq_41978896的博客
02-01 4531
深度学习文本分类文献综述摘要介绍1. 文本分类任务2．文本分类中的深度模型2.1 Feed-Forward Neural Networks2.2 RNN-Based Models2.3 CNN-Based Models2.4 Capsule Neural Networks2.5 Models with Attention Mechanism2.6 Memory-Augmented Networks2.7 Transformers2.8 Graph Neural Networks2.9 Siamese Neu
[论文翻译]Deep learning
风信子的博客
08-02 1489
【论文翻译】Deep learning 论文题目：Deep Learning 论文来源:Deep Learning_2015_Nature 翻译人：BDML@CQUT实验室 Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These met
RK3568笔记二十八：CRNN车牌识别部署
05-31 747
1、训练平台：Autodl2、运行板子：ATK-DLRK3568。
06_深度学习历史的里程碑--重读AlexNet
https://github.com/foxpup11?tab=repositories
06-02 904
https://www.bilibili.com/video/BV1r7411X7LC?p=3&vd_source=7dace3632125a1ef7fd32c285eb2fbac
区间预测 | Matlab实现QRCNN-BiLSTM-Attention分位数回归卷积双向长短期记忆网络注意力机制时序区间预测
最新发布
关注并私信文章链接，获取对应文章源码和数据，机器学习之心的博客。
06-02 607
区间预测 | Matlab实现QRCNN-BiLSTM-Attention分位数回归卷积双向长短期记忆网络注意力机制时序区间预测
DALL-E 2之学习心得
七夜的博客
05-31 691
DALL-E 2是 OpenAI 开发的一款人工智能图像生成器，它可以根据自然语言的文本描述创建图像和艺术形式。这是一个根据文本生成图像的人工智能系统，是 DALL-E 模型的升级版。DALL-E 2图像生成：能够从文本描述中创建原创、逼真的图像和艺术作品。概念组合：可以结合概念、属性和风格。图像扩展：能够扩展原始画布中的图像，创造新的构图。图像编辑：可以对现有图像进行逼真的编辑，添加或移除元素，同时考虑阴影、反射和纹理。图像变体：能够获取一幅图像并创造出受原始图像启发的不同变体。
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
05-11
Convolutional LSTM (Long Short-Term Memory) network is a machine learning approach used for precipitation nowcasting. It combines the strengths of convolutional neural networks (CNNs) and LSTMs to make accurate predictions of precipitation in the near future. CNNs are good at understanding spatial features in images, while LSTMs are good at understanding temporal dependencies in time-series data. By combining these two networks, the Convolutional LSTM network is able to learn both spatial and temporal features of precipitation data. The network takes in a sequence of radar images and predicts the precipitation intensity for the next few minutes. The output of the network is a sequence of precipitation maps that show the predicted intensity of precipitation over time. This approach has shown promising results in accurately predicting precipitation in the near future, which can have significant applications in weather forecasting and disaster management.

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值