前言

在DisGeNET数据库的第一篇推文；DisGeNET数据库：人类疾病相关基因研究的百科全书中，Immugent介绍了它跨越十年的发展历程。如今，作为最权威的人类疾病基因相关数据库之一，DisGeNET数据库已经发展成一个集整合资源，网页，数据分析软件为一体的综合型数据库。

此外，在另一篇推文：disgenet2r:一个R包解决人类疾病分子功能的全部研究中，Immugent大致介绍了如何在自己的PC上构建disgenet2r包的资源，本期推文开始，生信宝库将会推出系列推文，通过代码实操的方式来演示如何将disgenet2r包运用在我们的数据分析中。

代码实操

此教程的代码需要延续上一篇推文来进行。

data1 <- gene2disease( gene = 3953, vocabulary = "ENTREZ",
                       database = "CURATED")
                       
class(data1)
## [1] "DataGeNET.DGN"
## attr(,"package")
## [1] "disgenet2r"

data1
## Object of class 'DataGeNET.DGN'
##  . Search:      single 
##  . Type:        gene-disease 
##  . Database:     CURATED 
##  . Score:        0-1 
##  . Term:        3953 
##  . Results:  89

results <- extract(data1)
head( results, 3 )
##   year_initial protein_class     el disease_type
## 1         1998  DTO:05007599 strong      disease
## 2         1966  DTO:05007599             disease
## 3         1966  DTO:05007599             disease
##                                                                      disease_class_name protein_class_name gene_dpi year_final
## 1                                                                                                Signaling    0.434       2019
## 2    Pathological Conditions, Signs and Symptoms;    Nutritional and Metabolic Diseases          Signaling    0.434       2021
## 3                      Nutritional and Metabolic Diseases;    Endocrine System Diseases          Signaling    0.434       2020
##   score disease_class disease_semantic_type    ei gene_symbol  source gene_dsi                             disease_name geneid
## 1  0.82                 Disease or Syndrome 1.000        LEPR CURATED  0.99475               LEPTIN RECEPTOR DEFICIENCY   3953
## 2  0.80       C23;C18   Disease or Syndrome 0.937        LEPR CURATED  0.99475                                  Obesity   3953
## 3  0.60       C18;C19   Disease or Syndrome 0.975        LEPR CURATED  0.99475 Diabetes Mellitus, Non-Insulin-Dependent   3953
##   gene_pli uniprotid diseaseid
## 1     0.84    P48357  C3554225
## 2     0.84    P48357  C0028754
## 3     0.84    P48357  C0011860

plot( data1,
      class = "Network",
      prop = 20)

image.png

plot( data1,      class = "DiseaseClass",      prop = 3)

image.png

data1 <- gene2evidence( gene = "LEPR",
                        vocabulary = "HGNC",
               disease ="C3554225",
                       database = "ALL",
                       score =c(0.3,1))
data1
results <- extract(data1)

探索多个基因的疾病相关性。

myListOfGenes <- c( "KCNE1", "KCNE2", "KCNH1", "KCNH2", "KCNG1")
data2 <- gene2disease(
  gene     = myListOfGenes,
  score =c(0.2, 1),
  verbose  = TRUE)
  
plot( data2,
      class = "Network",
      prop = 10)

image.png

plot( data2,      class  ="Heatmap",      limit  = 100, nchars = 50 )

image.png

plot( data2,      class="DiseaseClass", nchars=60)

image.png

以疾病为研究对象的使用方式。

data3 <- disease2gene( disease  = "C0036341",
                          database = "CURATED",
                          score    = c( 0.4,1 ) )
data4 <- disease2gene( disease  = "181500", vocabulary = "OMIM",
                          database = "CURATED",
                          score    = c(0.4,1 ) )  
                          
plot( data3,  class="ProteinClass")

image.png

探索与疾病相关的证据。。。

data3 <- disease2evidence( disease  = "C0036341",
                           type = "GDA",
                          database = "CURATED",
                          score    = c( 0.4,1 ) )
                          
data3 <- disease2evidence( disease  = "C0036341",
                           gene = c("DRD2", "DRD3"),
                           type = "GDA",
                          database = "CURATED",
                          score    = c( 0.4,1 ) )

results <- extract(data3)

image.png

同时搜索多种疾病。。。

diseasesOfInterest <- c("C0036341", "C0002395", "C0030567","C0005586")

data5 <- disease2gene(
  disease = diseasesOfInterest,
  database = "CURATED",
  score =c(0.4,1),
  verbose  = TRUE )
  
plot( data5,
      class="ProteinClass" )

image.png

说在最后

从上述流程我们可以看出disgenet2r包，高度集和了DisGeNET数据库的资源，而且和多种分析流程进行无缝衔接，这样使用起来就很方便。并且更加难能可贵的是，disgenet2r包输出的图都很高达上，可以直接用于我们发表的文章中。当然，disgenet2r包的功能远不止如此，Immmugent将会在下期介绍如何将突变位点和疾病相关联，敬请期待！

好啦，本期分享到这里就结束了，我们下期再会~~