forked from YuLab-SMU/clusterProfiler-book
-
Notifications
You must be signed in to change notification settings - Fork 0
/
references.bib
301 lines (279 loc) · 17 KB
/
references.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
@article{yu_reactomepa_2016,
title = {{ReactomePA}: an R/Bioconductor package for reactome pathway analysis and visualization},
volume = {12},
issn = {1742-2051},
url = {http://pubs.rsc.org.eproxy2.lib.hku.hk/en/content/articlelanding/2016/mb/c5mb00663e},
doi = {10.1039/C5MB00663E},
shorttitle = {{ReactomePA}},
abstract = {Reactome is a manually curated pathway annotation database for unveiling high-order biological pathways from high-throughput data. {ReactomePA} is an R/Bioconductor package providing enrichment analyses, including hypergeometric test and gene set enrichment analyses. A functional analysis can be applied to the genomic coordination obtained from a sequencing experiment to analyze the functional significance of genomic loci including cis-regulatory elements and non-coding regions. Comparison among different experiments is also supported. Moreover, {ReactomePA} provides several visualization functions to produce highly customizable, publication-quality figures. The source code and documents of {ReactomePA} are freely available through Bioconductor (http://www.bioconductor.org/packages/{ReactomePA}).},
pages = {477--479},
number = {2},
journaltitle = {Molecular {BioSystems}},
shortjournal = {Mol. {BioSyst}.},
author = {Yu, Guangchuang and He, Qing-Yu},
urldate = {2016-02-17},
date = {2016-01-26},
langid = {english}
}
@article{yu_chipseeker_2015,
title = "ChIPseeker: an R/Bioconductor package for ChIP peak annotation, comparison and visualization",
author = {Yu, Guangchuang and Wang, Li-Gen and He, Qing-Yu},
journal = "Bioinformatics",
year = "2015",
volume = "31",
number = "14",
pages = "2382-2383",
PMID = "25765347",
url = {http://bioinformatics.oxfordjournals.org/content/31/14/2382.abstract},
doi = "10.1093/bioinformatics/btv145",
}
@article{yu_dose_2015,
title = {{DOSE}: an R/Bioconductor package for disease ontology semantic and enrichment analysis},
volume = {31},
issn = {1367-4803, 1460-2059},
url = {http://bioinformatics.oxfordjournals.org/content/31/4/608},
doi = {10.1093/bioinformatics/btu684},
shorttitle = {{DOSE}},
abstract = {Summary: Disease ontology ({DO}) annotates human genes in the context of disease. {DO} is important annotation in translating molecular findings from high-throughput data to clinical relevance. {DOSE} is an R package providing semantic similarity computations among {DO} terms and genes which allows biologists to explore the similarities of diseases and of gene functions in disease perspective. Enrichment analyses including hypergeometric model and gene set enrichment analysis are also implemented to support discovering disease associations of high-throughput biological data. This allows biologists to verify disease relevance in a biological experiment and identify unexpected disease associations. Comparison among gene clusters is also supported.
Availability and implementation: {DOSE} is released under Artistic-2.0 License. The source code and documents are freely available through Bioconductor (http://www.bioconductor.org/packages/release/bioc/html/{DOSE}.html).
Supplementary information: Supplementary data are available at Bioinformatics online.
Contact: [email protected] or [email protected]},
pages = {608--609},
number = {4},
journaltitle = {Bioinformatics},
shortjournal = {Bioinformatics},
author = {Yu, Guangchuang and Wang, Li-Gen and Yan, Guang-Rong and He, Qing-Yu},
urldate = {2015-02-13},
date = {2015-02-15},
langid = {english}
}
@Article{yu2012,
title = {clusterProfiler: an R package for comparing biological themes among gene clusters},
volume = {16},
issn = {1536-2310},
number ={5},
url = {http://online.liebertpub.com/doi/abs/10.1089/omi.2011.0118},
doi = {10.1089/omi.2011.0118},
journal = {OMICS: A Journal of Integrative Biology},
author = {Guangchuang Yu and Le-Gen Wang and Yanyan Han and Qing-Yu He},
year = {2012},
month = may,
note = {},
keywords = {clusterProfiler, Gene Ontology, KEGG, Enrichment analysis, R package, Cluster comparison},
pages = {284-287}
}
@article{yu2011,
title = {Functional similarity analysis of human virus-encoded {miRNAs}},
volume = {1},
issn = {2043-9113},
url = {http://www.jclinbioinformatics.com/content/1/1/15},
doi = {10.1186/2043-9113-1-15},
number = {1},
journal = {Journal of Clinical Bioinformatics},
author = {Yu, Guangchuang and He, {Qing-Yu}},
month = may,
year = {2011},
pages = {15}
}
@article{yu_new_2011,
title = {A new method for measuring functional similarity of {microRNAs}},
volume = {1},
issn = {2182-0287},
url = {http://www.jiomics.com/index.php/jio/article/view/21},
doi = {10.5584/jiomics.v1i1.21},
number = {1},
journal = {Journal of Integrated {OMICS}},
author = {Yu, Guangchuang and Xiao, {Chuan-Le} and Bo, Xiaochen and Lu, {Chun-Hua} and Qin, Yide and Zhan, Sheng and He, {Qing-Yu}},
month = feb,
year = {2011},
keywords = {Clustering, Gene, {microRNA;}, Ontology;, Semantic, Similarity;},
pages = {49--54}
}
@Article{yu2010,
title = {GOSemSim: an R package for measuring semantic similarity among GO terms and gene products},
volume = {26},
issn = {1367-4803},
number= {7},
url = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/26/7/976},
doi = {10.1093/bioinformatics/btq064},
journal = {Bioinformatics},
author = {Guangchuang Yu and Fei Li and Yide Qin and Xiaochen Bo and Yibo Wu and Shengqi Wang},
month = April,
year = {2010},
note = {PMID: 20179076},
keywords = {Gene Ontology, Semantic Similarity, Bioconductor},
pages = {976-978}
}
@Article{schmidt2008,
title = {The Humoral Immune System Has a Key Prognostic Impact in Node-Negative Breast Cancer},
volume = {68},
url = {http://cancerres.aacrjournals.org/content/68/13/5405.abstract},
doi = {10.1158/0008-5472.CAN-07-5206},
number = {13},
journal = {Cancer Research},
author = {Schmidt, Marcus and B?hm, Daniel and von T?rne, Christian and Steiner, Eric and Puhl, Alexander and Pilch, Henryk and Lehr, {Hans-Anton} and Hengstler, Jan G. and K?lbl, Heinz and Gehrmann, Mathias},
month = jul,
year = {2008},
pages = {5405 --5413}
}
@article{boyle2004,
title = {{GO::TermFinder--open} source software for accessing Gene Ontology information and finding significantly enriched Gene Ontology terms associated with a list of genes},
volume = {20},
issn = {1367-4803},
shorttitle = {{GO}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/15297299},
doi = {10.1093/bioinformatics/bth456},
number = {18},
journal = {Bioinformatics (Oxford, England)},
author = {Boyle, Elizabeth I and Weng, Shuai and Gollub, Jeremy and Jin, Heng and Botstein, David and Cherry, J Michael and Sherlock, Gavin},
month = dec,
year = {2004},
note = {PMID: 15297299},
keywords = {Abstracting and Indexing as Topic, Database Management Systems, Databases, Protein, Gene Expression Profiling, Information Storage and Retrieval, Natural Language Processing, Oligonucleotide Array Sequence Analysis, Programming Languages, Software, {User-Computer} Interface, Vocabulary, Controlled},
pages = {3710--3715}
}
@article{luo_pathview,
title = {Pathview: an {R/Bioconductor} package for pathway-based data integration and visualization},
volume = {29},
issn = {1367-4803, 1460-2059},
url = {http://bioinformatics.oxfordjournals.org/content/29/14/1830},
doi = {10.1093/bioinformatics/btt285},
shorttitle = {Pathview},
language = {en},
issue = {14},
pages = {1830-1831},
journaltitle = {Bioinformatics},
shortjournal = {Bioinformatics},
author = {Luo, Weijun and Brouwer, Cory},
urldate = {2013-10-21},
date = {2013-07-15},
note = {{PMID:} 23740750},
}
@article{subramanian_gene_2005,
title = {Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles},
volume = {102},
shorttitle = {Gene set enrichment analysis},
url = {http://www.pnas.org/content/102/43/15545.abstract},
doi = {10.1073/pnas.0506580102},
abstract = {Although genomewide {RNA} expression analysis has become a routine tool in biomedical research, extracting biological insight from such information remains a major challenge. Here, we describe a powerful analytical method called Gene Set Enrichment Analysis ({GSEA)} for interpreting gene expression data. The method derives its power by focusing on gene sets, that is, groups of genes that share common biological function, chromosomal location, or regulation. We demonstrate how {GSEA} yields insights into several cancer-related data sets, including leukemia and lung cancer. Notably, where single-gene analysis finds little similarity between two independent studies of patient survival in lung cancer, {GSEA} reveals many biological pathways in common. The {GSEA} method is embodied in a freely available software package, together with an initial database of 1,325 biologically defined gene sets.},
number = {43},
urldate = {2010-03-12},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
author = {Subramanian, Aravind and Tamayo, Pablo and Mootha, Vamsi K. and Mukherjee, Sayan and Ebert, Benjamin L. and Gillette, Michael A. and Paulovich, Amanda and Pomeroy, Scott L. and Golub, Todd R. and Lander, Eric S. and Mesirov, Jill P.},
month = oct,
year = {2005},
pages = {15545--15550}
}
@article{huang_david_2007,
title = {The {DAVID} Gene Functional Classification Tool: a novel biological module-centric algorithm to functionally analyze large gene lists},
volume = {8},
issn = {14656906},
url = {http://genomebiology.com/2007/8/9/R183},
doi = {10.1186/gb-2007-8-9-r183},
shorttitle = {The {DAVID} Gene Functional Classification Tool},
pages = {R183},
number = {9},
journaltitle = {Genome Biology},
author = {Huang, Da and Sherman, Brad T and Tan, Qina and Collins, Jack R and Alvord, W Gregory and Roayaei, Jean and Stephens, Robert and Baseler, Michael W and Lane, H Clifford and Lempicki, Richard A},
urldate = {2015-03-06},
date = {2007}
}
@article{fresno_rdavidwebservice_2013,
title = {{RDAVIDWebService}: a versatile R interface to {DAVID}},
volume = {29},
issn = {1367-4803, 1460-2059},
url = {http://bioinformatics.oxfordjournals.org.eproxy1.lib.hku.hk/content/29/21/2810},
doi = {10.1093/bioinformatics/btt487},
shorttitle = {{RDAVIDWebService}},
abstract = {Summary: The {RDAVIDWebService} package provides a class-based interface from R programs/scripts to fully access/control the database for annotation, visualization and integrated discovery, without the need for human interaction on its Web site (http://david.abcc.ncifcrf.gov). The library enhances the database for annotation, visualization and integrated discovery capabilities for Gene Ontology analysis by means of {GOstats}-based direct acyclic graph conversion methods, in addition to the usual many-genes-to-many-terms visualization.
Availability and implementation: {RDAVIDWebService} is available as an R package from the Bioconductor project (www.bioconductor.org) and on the authors’ Web site (www.bdmg.com.ar) under {GPL}-2 license, subjected to the terms of use of {DAVID} (http://david.abcc.ncifcrf.gov/content.jsp?file={WS}.html).
Contact: [email protected] or [email protected]},
pages = {2810--2811},
number = {21},
journaltitle = {Bioinformatics},
shortjournal = {Bioinformatics},
author = {Fresno, Cristóbal and Fernández, Elmer A.},
urldate = {2015-03-06},
date = {2013-11-01},
langid = {english},
pmid = {23958726}
}
@article{paranjpe_genome_wide_2013,
title = {A genome-wide survey of maternal and embryonic transcripts during Xenopus tropicalis development},
volume = {14},
issn = {1471-2164},
url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3907017/},
doi = {10.1186/1471-2164-14-762},
abstract = {Background
Dynamics of polyadenylation vs. deadenylation determine the fate of several developmentally regulated genes. Decay of a subset of maternal {mRNAs} and new transcription define the maternal-to-zygotic transition, but the full complement of polyadenylated and deadenylated coding and non-coding transcripts has not yet been assessed in Xenopus embryos.
Results
To analyze the dynamics and diversity of coding and non-coding transcripts during development, both polyadenylated {mRNA} and ribosomal {RNA}-depleted total {RNA} were harvested across six developmental stages and subjected to high throughput sequencing. The maternally loaded transcriptome is highly diverse and consists of both polyadenylated and deadenylated transcripts. Many maternal genes show peak expression in the oocyte and include genes which are known to be the key regulators of events like oocyte maturation and fertilization. Of all the transcripts that increase in abundance between early blastula and larval stages, about 30\% of the embryonic genes are induced by fourfold or more by the late blastula stage and another 35\% by late gastrulation. Using a gene model validation and discovery pipeline, we identified novel transcripts and putative long non-coding {RNAs} ({lncRNA}). These {lncRNA} transcripts were stringently selected as spliced transcripts generated from independent promoters, with limited coding potential and a codon bias characteristic of noncoding sequences. Many {lncRNAs} are conserved and expressed in a developmental stage-specific fashion.
Conclusions
These data reveal dynamics of transcriptome polyadenylation and abundance and provides a high-confidence catalogue of novel and long non-coding {RNAs}.},
pages = {762},
journaltitle = {{BMC} Genomics},
shortjournal = {{BMC} Genomics},
author = {Paranjpe, Sarita S and Jacobi, Ulrike G and van Heeringen, Simon J and C Veenstra, Gert Jan},
urldate = {2015-03-06},
date = {2013-11-06},
pmid = {24195446},
pmcid = {PMC3907017}
}
@article{omer_ncg,
title = {NCG 5.0: updates of a manually curated repository of cancer genes and associated properties from cancer mutational screenings},
volume = {44},
issn = {0305-1048, 1362-4962},
shorttitle = {Network of Cancer Gene},
url = {http://nar.oxfordjournals.org/content/44/D1/D992},
doi = {10.1093/nar/gkv1123},
number = {D1},
urldate = {},
journal = {Nucleic Acids Research},
author = {Omer A. and Giovanni M. D. and Thanos P. M. and Francesca D. C.},
month = jan,
year = {2016},
pages = {D992--D999}
}
@article{janet_disgenet,
title = {DisGeNET: a discovery platform for the dynamical exploration of human diseases and their genes},
volume = {2015},
issn = {1758-0463},
shorttitle = {DisGeNET},
url = {http://database.oxfordjournals.org/content/2015/bav028.long},
doi = {10.1093/database/bav028},
number = {},
urldate = {},
journal = {Database},
author = {Janet, P. and Núria Q.R. and Àlex B. and Jordi D.P. and Anna B.M. and Martin B. and Ferran S. and Laura I. F.},
month = mar,
year = {2015},
pages = {bav028}
}
@Article{Du15062009,
author = {Du, Pan and Feng, Gang and Flatow, Jared and Song, Jie and Holko, Michelle and Kibbe, Warren A. and Lin, Simon M.},
title = {From disease ontology to disease-ontology lite: statistical methods to adapt a general-purpose ontology for the test of gene-ontology associations},
volume = {25},
number = {12},
pages = {i63-i68},
year = {2009},
doi = {10.1093/bioinformatics/btp193},
abstract ={Subjective methods have been reported to adapt a general-purpose ontology for a specific application. For example, Gene Ontology (GO) Slim was created from GO to generate a highly aggregated report of the human-genome annotation. We propose statistical methods to adapt the general purpose, OBO Foundry Disease Ontology (DO) for the identification of gene-disease associations. Thus, we need a simplified definition of disease categories derived from implicated genes. On the basis of the assumption that the DO terms having similar associated genes are closely related, we group the DO terms based on the similarity of gene-to-DO mapping profiles. Two types of binary distance metrics are defined to measure the overall and subset similarity between DO terms. A compactness-scalable fuzzy clustering method is then applied to group similar DO terms. To reduce false clustering, the semantic similarities between DO terms are also used to constrain clustering results. As such, the DO terms are aggregated and the redundant DO terms are largely removed. Using these methods, we constructed a simplified vocabulary list from the DO called Disease Ontology Lite (DOLite). We demonstrated that DOLite results in more interpretable results than DO for gene-disease association tests. The resultant DOLite has been used in the Functional Disease Ontology (FunDO) Web application at http://www.projects.bioinformatics.northwestern.edu/fundo.Contact: [email protected]},
URL = {http://bioinformatics.oxfordjournals.org/content/25/12/i63.abstract},
eprint = {http://bioinformatics.oxfordjournals.org/content/25/12/i63.full.pdf+html},
journal = {Bioinformatics}
}
@article{alex_fgsea,
title = {An algorithm for fast preranked gene set enrichment analysis using cumulative statistic calculation},
volume = {},
issn = {},
shorttitle = {fgsea},
url = {http://biorxiv.org/content/early/2016/06/20/060012},
doi = {10.1101/060012},
number = {},
urldate = {},
journal = {biorxiv},
author = {Alexey S.},
month = {},
year = {},
pages = {}
}