Advanced Interdisciplinary Projects Lab(AIPLab) 討論區

Please login or register.

請輸入帳號, 密碼以及預計登入時間

新聞:

[慶賀]恭喜張清貿醫師升任北榮傳醫科主治醫師-20170201

  列出文章 - admin
* View Member Posts | View Member Topics | View Member Attachments
頁: [1] 2 3 ... 115
1  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / DESeq2 於: 十月 04, 2018, 01:33:41 am
http://bioconductor.org/packages/devel/bioc/vignettes/DESeq2/inst/doc/DESeq2.html
2  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / GenCode 於: 十月 04, 2018, 01:20:29 am
https://www.gencodegenes.org/releases/current.html
https://www.gencodegenes.org/stats/current.html
3  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / SequenceOntology 於: 十月 04, 2018, 01:14:43 am
http://www.sequenceontology.org
4  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / Definitions and classifications of lncRNA and lincRNA 於: 十月 04, 2018, 01:01:50 am
https://www.nature.com/articles/nrm.2017.104/tables/1

LincRNA   LncRNA not overlapping a protein-coding transcript
5  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / biomaRt 於: 十月 04, 2018, 12:56:50 am
Interface to BioMart databases (e.g. Ensembl, COSMIC, Wormbase and Gramene)

https://bioconductor.org/packages/release/bioc/html/biomaRt.html


程式碼: [Select]
library(biomaRt)
ensembl <- useMart("ensembl",dataset="hsapiens_gene_ensembl")
my.genes <- c("ENSG00000284190", "ENSG00000171658", "Something else")
out <- getBM(attributes=c("ensembl_gene_id", "gene_biotype"),
    filters="ensembl_gene_id", values=my.genes, mart=ensembl)
out <- out[match(my.genes, out$ensembl_gene_id),] # now in correct order/length.
https://support.bioconductor.org/p/104800/
6  107學年(上)課程2018Autumn / 107-1 中醫資料庫的建置與應用 / GDCRNATools 於: 十月 04, 2018, 12:54:58 am
http://bioconductor.org/packages/devel/bioc/vignettes/GDCRNATools/inst/doc/GDCRNATools.html

GDCRNATools is an R package which provides a standard, easy-to-use and comprehensive pipeline for downloading, organizing, and integrative analyzing RNA expression data in the GDC portal with an emphasis on deciphering the lncRNA-mRNA related ceRNAs regulatory network in cancer.
7  Top Category / Math Basics / 基礎統計檢定 ( t-test, ANOVA) 於: 五月 20, 2018, 10:06:10 pm
R/Excel/SPSS/Matlab

T檢驗:
https://bioant.blogspot.tw/2009/12/excelstudent-t-testp-value.html
http://charngro.blogspot.tw/2016/01/t_86.html

(1)單一樣本(One-sample t-test)
one-sample t-test is used to compare the mean of one sample to a known standard (or theoretical/hypothetical) mean (μ).
假說檢定(Hypothesis Testing)
H0:m=μ
R      http://www.instantr.com/2012/12/29/performing-a-one-sample-t-test-in-r/
Excel http://charngro.blogspot.tw/2016/01/t.html

(2)成對樣本t檢定 (Paired samples t-test)

假說檢定(Hypothesis Testing)
H0:the true mean difference is zero
R    https://www.r-bloggers.com/paired-students-t-test/

(3) 獨立樣本t檢定 (Independent sample t-test)
假說檢定(Hypothesis Testing)
SPSShttps://www.yongxi-stat.com/independent-sample-t-test/
http://www.r-web.com.tw/stat/step1.php?method=two_sample_independent_t_test


(4) 單因子變異數分析(One-way ANOVA)
(H0):u1 = u2 = u3 =……= uk
http://r97846001.blog.ntu.edu.tw/2010/05/03/sas-analysis-of-variance-anova/
https://www.yongxi-stat.com/one-way-anova-indenpedent/

(5) 二因子變異數分析(Two-way ANOVA)
https://www.yongxi-stat.com/two-way-anova/
8  Top Category / GitHub / Signal Processing 於: 五月 20, 2018, 12:07:36 am
benpolletta/HHT-Tutorial https://github.com/benpolletta/HHT-Tutorial/
9  106學年齡(下)課程2018Spring / 106(下)中西醫結合的大數據分析 / 在Jupyter notebook中寫Matlab程式 於: 五月 15, 2018, 04:39:16 am
https://ww2.mathworks.cn/help/matlab/matlab-engine-for-python.html
https://github.com/Calysto/matlab_kernel

程式碼: [Select]
On Windows systems —
cd "C:\Program Files\MATLAB\R2017b\extern\engines\python"
python setup.py install

程式碼: [Select]
$ pip install matlab_kernel
10  106學年齡(下)課程2018Spring / 106(下)中西醫結合的大數據分析 / 在Jupyter notebook中寫R程式 於: 五月 09, 2018, 09:52:32 pm
(1) 安裝R/R-Studio
https://cran.r-project.org/bin/windows/base/
https://www.rstudio.com/products/rstudio/download/
(2) 安裝Anaconda
https://www.anaconda.com/download/
(3) 更新Anaconda(命令列)
程式碼: [Select]
conda update anaconda
conda install -c r r-essentials
(4) 更新 jupyter_core jupyter_client(命令列)
程式碼: [Select]
conda update jupyter_core jupyter_client(5) Install IRkernel (用R或RStudio)
程式碼: [Select]
install.packages(c('repr', 'IRdisplay', 'evaluate', 'crayon', 'pbdZMQ', 'devtools', 'uuid', 'digest'))
devtools::install_github('IRkernel/IRkernel')
IRkernel::installspec(user = FALSE)

參考
https://stackoverflow.com/questions/48372019/importerror-cannot-import-name-ensure-dir-exists
11  106學年齡(下)課程2018Spring / 106(下)中西醫結合的大數據分析 / DEG比較 於: 五月 07, 2018, 11:51:13 am
程式碼: [Select]
#Merge HT-Seq count files
basedir <- "D:/SRP073050-Monocytes-counts"
setwd(basedir)
sample = c("S080","S081","S082","S083","S084","S085")
for (i in 1:length(sample) ) {
    filename <- paste(sample[i], '.counts', sep = "", collapse = "")
    exp_table <-read.table(filename, header = F, stringsAsFactors = FALSE)
    if (i==1){#read only once
        df<-read.table(filename, header = F, stringsAsFactors = FALSE)
        names(df) <- c("Gene", sample[i])
    }
    else{
        df2<-read.table(filename, header = F, stringsAsFactors = FALSE)
        df[sample[i]] <-df2[2]
    }
}
 write.csv(df, file = "SRP073050.csv")
程式碼: [Select]
#Run Deseg2
library("DESeq2")
files=paste0(sample, rep(".counts", length(sample)))
cond = c("A","A","A","B","A","A")
sTable = data.frame(sampleName = files, fileName = files, condition = cond)
dds <-DESeqDataSetFromHTSeqCount(sampleTable=sTable, directory = "D:/SRP073050-Monocytes-counts", design = ~condition)
dds <- DESeq(dds)
res <- results(dds)
summary(res)
write.csv(as.data.frame(res),file="SRP073050-de.csv")
DESeq2::plotDispEsts(dds, main="Dispersion Estimates")
plotMA(res, main="Differentially Expressed Genes ", ylim=c(-2,2))
程式碼: [Select]
#Transform 這個步驟會比較久.....
library("annotables")
library("AnnotationDbi")
library("org.Hs.eg.db")
res$symbol = mapIds(org.Hs.eg.db,
                     keys=rownames(res),
                     column="SYMBOL",
                     keytype="SYMBOL",
                     multiVals="first")
res$entrez = mapIds(org.Hs.eg.db,
                     keys=row.names(res),
                     column="ENTREZID",
                     keytype="SYMBOL",
                     multiVals="first")
res$name =   mapIds(org.Hs.eg.db,
                     keys=row.names(res),
                     column="GENENAME",
                     keytype="SYMBOL",
                     multiVals="first")
程式碼: [Select]
#GAG
library("dplyr")
library(pathview)
library(gage)
library(gageData)
data(kegg.sets.hs)
data(sigmet.idx.hs)
foldchanges = res$log2FoldChange
names(foldchanges) = res$entrez
kegg.sets.hs = kegg.sets.hs[sigmet.idx.hs]
# Get the results
keggres = gage(foldchanges, gsets=kegg.sets.hs, same.dir=TRUE)
# Look at both up (greater), down (less), and statatistics.
lapply(keggres, head)

# Get the pathways
keggrespathways = data.frame(id=rownames(keggres$greater), keggres$greater) %>%
  tbl_df() %>%
  filter(row_number()<=5) %>%
  .$id %>%
  as.character()
keggrespathways
程式碼: [Select]
#Plot KEGG pathways
detach("package:dplyr", unload=TRUE) #dplyr會和sapply衝突
keggresids = substr(keggrespathways, start=1, stop=8)
# Define plotting function for applying later
plot_pathway = function(pid) pathview(gene.data=foldchanges, pathway.id=pid, species="hsa", new.signature=FALSE)

# plot multiple pathways (plots saved to disk and returns a throwaway list object)
tmp = sapply(keggresids, function(pid) pathview(gene.data=foldchanges, pathway.id=pid, species="hsa"))

12  106學年齡(下)課程2018Spring / 106(下) 機器學習 / Develop Your First XGBoost Model in Python with scikit-learn 於: 五月 06, 2018, 08:41:20 pm
https://machinelearningmastery.com/develop-first-xgboost-model-python-scikit-learn/

XGBoost is an implementation of gradient boosted decision trees designed for speed and performance that is dominative competitive machine learning.

  • How to install XGBoost on your system for use in Python.
    How to prepare data and train your first XGBoost model.
    How to make predictions using your XGBoost model.
13  106學年齡(下)課程2018Spring / 106(下) 機器學習 / Cuda, CuDNN 於: 五月 06, 2018, 05:41:07 am
Prerequisites
Ensure you meet the following requirements before you install cuDNN.
(1)A GPU of compute capability 3.0 or higher. To understand the compute capability of the GPU on your system, see: CUDA GPUs.
(2)
One of the following supported CUDA versions and NVIDIA graphics driver:
NVIDIA graphics driver R377 or newer for CUDA 8
NVIDIA graphics driver R384 or newer for CUDA 9
NVIDIA graphics driver R390 or newer for CUDA 9.1
(3)
Installing NVIDIA Graphics Drivers
Installing CUDA

14  106學年齡(下)課程2018Spring / 106(下) 機器學習 / CUDA 9 and cuDNN 7 於: 五月 06, 2018, 05:34:35 am
Install instructions for TensorFlow and Keras using CUDA 9 and cuDNN 7 with GPU enabled, on Windows 10

https://github.com/rohit-patel/Install_Instructions-Win10-Deeplearning-Keras-Tensorflow

有AVX (i3-7100) pip install tensorflow-gpu==1.8
沒有AVX(G4600) pip install tensorflow-gpu==1.5

CUDA 9.0 compatible GPU
CUDA 9.0 (9.1 or later versions are NOT compatible)
cuDNN v7.0.5 (Dec 5, 2017), for CUDA 9.0
15  106學年齡(下)課程2018Spring / 106(下) 機器學習 / Caffe2、TensorFlow、MXnet 於: 五月 06, 2018, 05:15:07 am
Caffe2
A New Lightweight, Modular, and Scalable Deep Learning Framework
https://caffe2.ai/

TensorFlow
An open source machine learning framework for everyone
https://www.tensorflow.org/

MXnet
A Scalable Deep Learning Framework
https://mxnet.incubator.apache.org/
頁: [1] 2 3 ... 115
SimplePortal Classic 2.0.5