语雀：左手柳叶刀右手炭火烧
微信公众号：研平方 | 简书：研平方
关注可了解更多的科研教程及技巧。如有问题或建议，请留言。
欢迎关注我：一起学习，一起进步！
最近，小编“扫荡”文献时，发现一个令我十分感兴趣的应用，利用文本文本挖掘技术可以评估选定基因与癌症之间的关联。提到文本挖掘这类技术，小编当然要一探究竟了。
1.原文如下
Literature evidence for the identified target genes in cancer
We used OncoScore, a text mining tool to assess the associations between each gene and specific cancers based on the literature. A cutoff value of 21.09 was suggested to determine true positives and the true negatives in cancer gene identification.
2.查找资料
习惯性的打开浏览器，准备打破砂锅问到底，惊喜的发现，OncoScore竟然是一个写好的R包，而且放在了Bioconductor网页，可直接进行安装、使用。虽然文章发在了Sci Rep杂志上，但是小编认为还是值得一试。
image
image
3.它能干什么
The OncoScore analysis consists of two parts. One can estimate a score to asses the
oncogenic potential of a set of genes, given the lecterature knowledge, at the time of the
analysis, or one can study the trend of such score over time.
可见，OncoScore不仅可以依据文献中的知识，对一组设定目标基因列表的致癌能力进行评分，还可以研究这个分数随时间的趋势。
4.开始表演，拿好小板凳看戏
4.1 准备工作
if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
BiocManager::install("OncoScore")
# load the library
library(OncoScore)
# Define a query
query = perform.query(c("ASXL1","IDH1","IDH2","SETBP1","TET2"))
### Starting the queries for the selected genes.
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 923
Number of papers found in PubMed for IDH1 was: 3691
Number of papers found in PubMed for IDH2 was: 1318
Number of papers found in PubMed for SETBP1 was: 177
Number of papers found in PubMed for TET2 was: 1609
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 1018
Number of papers found in PubMed for IDH1 was: 3902
Number of papers found in PubMed for IDH2 was: 1499
Number of papers found in PubMed for SETBP1 was: 229
Number of papers found in PubMed for TET2 was: 2117
以上我们可以发现，通过检索，得到了癌症相关研究的文献数量，以及所有与检索基因相关文献数量。
OncoScore provides a function to merge gene names if requested by the user. This function is useful when there are aliases in the gene list.
combine.query.results(query, c('IDH1', 'IDH2'), 'new_gene')
CitationsGene CitationsGeneInCancer
ASXL1 1018 923
SETBP1 229 177
TET2 2117 1609
new_gene 5401 5009
当然，OncoScore还可以依据染色体信息检索基因。这里不再演示。
4.2 重点来啦
4.2.1 开始计算基因的致癌评分
result = compute.oncoscore(query)
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 81.59349
IDH1 -> 86.66355
IDH2 -> 79.59096
SETBP1 -> 67.43283
TET2 -> 69.12424
4.2.2 时间趋势分析（OncoScore timeline analysis）
query.timepoints = perform.query.timeseries(c("ASXL1","IDH1","IDH2","SETBP1","TET2"),
c("2012/03/01", "2013/03/01", "2014/03/01", "2015/03/01", "2016/03/01"))
### Starting the queries for the selected genes.
### Quering PubMed for timepoint 2012/03/01
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 86
Number of papers found in PubMed for IDH1 was: 409
Number of papers found in PubMed for IDH2 was: 173
Number of papers found in PubMed for SETBP1 was: 5
Number of papers found in PubMed for TET2 was: 173
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 92
Number of papers found in PubMed for IDH1 was: 489
Number of papers found in PubMed for IDH2 was: 235
Number of papers found in PubMed for SETBP1 was: 10
Number of papers found in PubMed for TET2 was: 197
### Quering PubMed for timepoint 2013/03/01
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 135
Number of papers found in PubMed for IDH1 was: 662
Number of papers found in PubMed for IDH2 was: 267
Number of papers found in PubMed for SETBP1 was: 11
Number of papers found in PubMed for TET2 was: 258
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 150
Number of papers found in PubMed for IDH1 was: 753
Number of papers found in PubMed for IDH2 was: 336
Number of papers found in PubMed for SETBP1 was: 18
Number of papers found in PubMed for TET2 was: 303
### Quering PubMed for timepoint 2014/03/01
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 188
Number of papers found in PubMed for IDH1 was: 904
Number of papers found in PubMed for IDH2 was: 365
Number of papers found in PubMed for SETBP1 was: 29
Number of papers found in PubMed for TET2 was: 347
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 209
Number of papers found in PubMed for IDH1 was: 1003
Number of papers found in PubMed for IDH2 was: 440
Number of papers found in PubMed for SETBP1 was: 36
Number of papers found in PubMed for TET2 was: 431
### Quering PubMed for timepoint 2015/03/01
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 257
Number of papers found in PubMed for IDH1 was: 1198
Number of papers found in PubMed for IDH2 was: 468
Number of papers found in PubMed for SETBP1 was: 51
Number of papers found in PubMed for TET2 was: 461
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 286
Number of papers found in PubMed for IDH1 was: 1304
Number of papers found in PubMed for IDH2 was: 551
Number of papers found in PubMed for SETBP1 was: 66
Number of papers found in PubMed for TET2 was: 583
### Quering PubMed for timepoint 2016/03/01
### Performing queries for cancer literature
Number of papers found in PubMed for ASXL1 was: 323
Number of papers found in PubMed for IDH1 was: 1506
Number of papers found in PubMed for IDH2 was: 569
Number of papers found in PubMed for SETBP1 was: 68
Number of papers found in PubMed for TET2 was: 587
### Performing queries for all the literature
Number of papers found in PubMed for ASXL1 was: 359
Number of papers found in PubMed for IDH1 was: 1625
Number of papers found in PubMed for IDH2 was: 661
Number of papers found in PubMed for SETBP1 was: 89
Number of papers found in PubMed for TET2 was: 745
perform.query.timeseries ()函数检索了几个设定时间的文献数据信息。
result.timeseries = compute.oncoscore.timeseries(query.timepoints)
### Computing oncoscore for timepoint 2012/03/01
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 79.14893
IDH1 -> 74.27776
IDH2 -> 64.27063
SETBP1 -> 34.9485
TET2 -> 76.29579
### Computing oncoscore for timepoint 2013/03/01
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 77.54983
IDH1 -> 78.71551
IDH2 -> 69.99559
SETBP1 -> 46.4559
TET2 -> 74.81894
### Computing oncoscore for timepoint 2014/03/01
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 78.28121
IDH1 -> 81.08963
IDH2 -> 73.50788
SETBP1 -> 64.97398
TET2 -> 71.31087
### Computing oncoscore for timepoint 2015/03/01
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 78.84769
IDH1 -> 82.99363
IDH2 -> 75.60886
SETBP1 -> 64.48853
TET2 -> 70.46695
### Computing oncoscore for timepoint 2016/03/01
### Processing data
### Computing frequencies scores
### Estimating oncogenes
### Results:
ASXL1 -> 79.37202
IDH1 -> 83.9881
IDH2 -> 76.89328
SETBP1 -> 64.60591
TET2 -> 70.53378
4.2.3 可视化
## Oncogenetic potential of the considered genes
plot.oncoscore(result, col = 'darkblue')
## Absolute values of the oncogenetic potential of the considered genes over times
plot.oncoscore.timeseries(result.timeseries)
## Variations of the oncogenetic potential of the considered genes over times
plot.oncoscore.timeseries(result.timeseries,
incremental = TRUE,
ylab='absolute variation')
## Variations as relative values of the oncogenetic potential of the considered genes over times
plot.oncoscore.timeseries(result.timeseries,
incremental = TRUE,
relative = TRUE,
ylab='relative variation')
plot1.png
plot2.png
plot3.png
plot4.png
