forked from microbiome/OMA
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbook.bib
1012 lines (875 loc) · 41.6 KB
/
book.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
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@Article{Huang2021,
author = {Ruizhu Huang and Charlotte Soneson and Felix
G.M. Ernst and others},
title = {TreeSummarizedExperiment: a S4 class for data with
hierarchical structure [version 2; peer review: 3
approved]},
journal = {F1000Research},
volume = 9,
pages = 1246,
doi = {https://doi.org/10.12688/f1000research.26669.2},
year = 2021,
annote = {TreeSE reference},
keywords = {bioscience}
}
@Article{Quast2013,
author = {Quast, C and Pruesse, E and Yilmaz, P and Gerken, J
and Schweer, T and Yarza, P and Peplies, J and
Glöckner, FO},
title = {The SILVA ribosomal RNA gene database project:
improved data processing and web-based tools},
journal = {Nucleic Acids Research},
volume = 41,
issue = {D1},
pages = D590-D596,
year = 2013,
annote = {SILVA database reference},
keywords = {bioscience}
}
@Article{MorenoIndias2021,
author = {Isabel Moreno-Indias and Leo Lahti and Miroslava
Nedyalkova and Ilze Elbere and Gennady
V. Roshchupkin and Muhamed Adilovic and Onder
Aydemir and Burcu Bakir-Gungor and Enrique
Carrillo-de Santa Pau and Domenica D'Elia and Magesh
S. Desai and Laurent Falquet and Aycan Gundogdu and
Karel Hron and Thomas Klammsteiner and Marta
B. Lopes and Laura J. Marcos Zambrano and Cláudia
Marques and Michael Mason and Patrick May and Lejla
Pašić and Gianvito Pio and Sándor Pongor and Vasilis
J. Promponas and Piotr Przymus and Julio
Sáez-Rodríguez and Alexia Sampri and Rajesh Shigdel
and Blaz Stres and Ramona Suharoschi and Jaak Truu
and Ciprian-Octavian Truică and Baiba Vilne and
Dimitrios P. Vlachakis and Ercüment Yılmaz and Georg
Zeller and Aldert Zomer and David Gómez-Cabrero and
Marcus Claesson},
title = {Statistical and machine learning techniques in human
microbiome studies: contemporary challenges and
solutions},
journal = {Frontiers in Microbiology},
volume = 12,
pages = 277,
month = {February},
year = 2021,
doi = {10.3389/fmicb.2021.635781},
keywords = {bioscience}
}
@Book{Amezquita2020,
author = {Robert Amezquita and Aaron Lun and Stephanie Hicks
and Raphael Gottardo},
title = {Orchestrating Single-Cell Analysis with
Bioconductor},
publisher = {Bioconductor},
year = 2020,
url = {https://bioconductor.org/books/release/OSCA/}
}
@Article{Amezquita2020natmeth,
author = {Robert A. Amezquita and Aaron T.L. Lun and Etienne
Becht and Vince J. Carey and Lindsay N. Carpp and
Ludwig Geistlinger and Federico Marini and Kevin
Rue-Albrecht and Davide Risso and Charlotte Soneson
and Levi Waldron and Hervé Pagès and Mike L. Smith
and Wolfgang Huber and Martin Morgan and Raphael
Gottardo and Stephanie C. Hicks},
title = {Orchestrating single-cell analysis with
Bioconductor},
journal = {Nature Methods},
year = 2020,
volume = 17,
pages = {137--145},
doi = {10.1038/s41592-019-0654-x}
}
@article{Anderson2001,
author = {Anderson, Marti J.},
title = {A new method for non-parametric multivariate
analysis of variance},
journal = {Austral Ecology},
volume = 26,
number = 1,
pages = {32--46},
doi = {10.1111/j.1442-9993.2001.01070.pp.x},
year = 2001
}
@article{Anderson2006,
author = {Anderson, Marti J.},
title = {Distance-based tests for homogeneity of multivariate
dispersions},
journal = {Biometrics},
volume = 62,
pages = {245--253},
doi = {10.1111/j.1541-0420.2005.00440.x},
year = 2006
}
@article{Argelaguet2018,
author = {Argelaguet, Ricard et al.},
title = {Multi-Omics Factor Analysis—a framework for unsupervised integration of multi-omics data sets},
journal = {Molecular Systems Biology},
volume = 14,
number = 6,
pages = {e8124},
doi = {10.15252/msb.20178124},
year = 2018
}
@Article{Callahan2016workflow,
author = {Ben J. Callahan and Kris Sankaran and Julia
A. Fukuyama and Paul J. McMurdie and Susan
P. Holmes},
title = {Bioconductor Workflow for Microbiome Data Analysis:
from raw reads to community analyses [version 2;
peer review: 3 approved]},
journal = {F1000Research},
year = 2016,
volume = 5,
pages = 1492,
doi = {10.12688/f1000research.8986.2}
}
@article{Chao1984,
author = {Chao A},
title = {Non-parametric estimation of the number of classes in a population},
journal = {Scandinavian Journal of Statistics},
volume = {11},
number = {4},
pages = {265-270},
url = {https://www.jstor.org/stable/4615964},
year = {1984}
}
@article{Chao1992,
author = {Chao A and Lee SM},
title = {Estimating the number of classes via sample coverage},
journal = {Journal of the American statistical Association},
volume = {87},
number = {417},
pages = {210-217},
doi = {https://doi.org/10.1080/01621459.1992.10475194},
url = {https://amstat.tandfonline.com/doi/abs/10.1080/01621459.1992.10475194#.YHFw5egzaHu},
year = {1992}
}
@Article{DECIPHER2016,
title = {Using DECIPHER v2.0 to Analyze Big Biological Sequence Data in R},
author = {Erik S. Wright},
journal = {The R Journal},
year = {2016},
volume = {8},
number = {1},
pages = {352-359},
}
@article{Faith1992,
author = {Faith, D. P.},
title = {Conservation evaluation and phylogenetic diversity},
journal = {Biological Conservation},
volume = {61},
number = {1},
pages = {10},
doi = {https://doi.org/10.1016/0006-3207(92)91201-3},
url = {https://www.sciencedirect.com/science/article/pii/0006320792912013?via%3Dihub},
year = {1992}
}
@Article{Friedman2012,
author = {Friedman, J and Alm, EJ},
title = {Inferring Correlation Networks from Genomic Survey
Data},
journal = {{PLoS Computational Biology}},
year = 2012,
volume = 8,
number = 9,
pages = {e1002687},
annote = {SparCC},
doi = {10.1371/journal.pcbi.1002687}
}
@Article{GenomicRanges2013,
title = {Software for Computing and Annotating Genomic Ranges},
author = {Michael Lawrence and Wolfgang Huber and Herv\'e Pag\`es and Patrick Aboyoun and Marc Carlson and Robert Gentleman and Martin Morgan and Vincent Carey},
year = {2013},
journal = {{PLoS} Computational Biology},
volume = {9},
issue = {8},
doi = {10.1371/journal.pcbi.1003118},
url = {http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003118},
}
@Article{Gentleman2004,
author = {Robert C Gentleman and Vincent J Carey and Douglas M
Bates and Ben Bolstad and Marcel Dettling and
Sandrine Dudoit and Byron Ellis and Laurent Gautier
and Yongchao Ge and Jeff Gentry and Kurt Hornik and
Torsten Hothorn and Wolfgang Huber and Stefano Iacus
and Rafael Irizarry and Friedrich Leisch and Cheng
Li and Martin Maechler and Anthony J Rossini and
Gunther Sawitzki and Colin Smith and Gordon Smyth
and Luke Tierney and Jean YH Yang and Jianhua Zhang},
title = {Bioconductor: open software development for
computational biology and bioinformatics},
journal = {Genome Biology},
year = 2004,
volume = 5,
pages = {R80},
annote = {Original Bioconductor reference}
}
@Book{Grolemund2017,
author = {Garret Grolemund and Hadley Wickham},
title = {R for Data Science},
publisher = {O’Reilly},
year = 2017,
url = {https://r4ds.had.co.nz/}
}
@Book{Holmes2019,
author = {Susan Holmes and Wolfgang Huber},
title = {Modern Statistics for Modern Biology},
publisher = {Cambridge University Press},
address = {New York, NY},
year = 2019,
url = {https://www.huber.embl.de/msmb/}
}
@Article{Huber2015,
author = {W. Huber and V. J. Carey and R. Gentleman and
S. Anders and M. Carlson and B. S. Carvalho and
H. C. Bravo and S. Davis and L. Gatto and T. Girke
and R. Gottardo and F. Hahne and K. D. Hansen and
R. A. Irizarry and M. Lawrence and M. I. Love and
J. MacDonald and V. Obenchain and A. K. {Ole's} and
H. {Pag`es} and A. Reyes and P. Shannon and
G. K. Smyth and D. Tenenbaum and L. Waldron and
M. Morgan},
title = {{O}rchestrating high-throughput genomic analysis
with {B}ioconductor},
journal = {Nature Methods},
year = 2015,
volume = 12,
number = 2,
pages = {115--121},
annote = {Was with key: Biobase2015 / BiocGenerics2015},
url =
{http://www.nature.com/nmeth/journal/v12/n2/full/nmeth.3252.html}
}
@Article{IRanges2013,
title = {Software for Computing and Annotating Genomic Ranges},
author = {Michael Lawrence and Wolfgang Huber and Herv\'e Pag\`es and Patrick Aboyoun and Marc Carlson and Robert Gentleman and Martin Morgan and Vincent Carey},
year = {2013},
journal = {{PLoS} Computational Biology},
volume = {9},
issue = {8},
doi = {10.1371/journal.pcbi.1003118},
url = {http://www.ploscompbiol.org/article/info%3Adoi%2F10.1371%2Fjournal.pcbi.1003118},
}
@article{Kembel2010,
author = {Kembel Steven W and Cowan Peter D and Helmus Matthew R and Cornwell William K and Morlon Helene and Ackerly David D and Blomberg Simon P and Webb Campbell O},
title = {Picante: R tools for integrating phylogenies and ecology},
journal = {Bioinformatics},
volume = {26},
number = {11},
pages = {1463-1464},
doi = {https://doi.org/10.1093/bioinformatics/btq166},
url = {https://academic.oup.com/bioinformatics/article/26/11/1463/203321},
year = {2010}
}
@Article{Kurtz2015,
author = {Kurtz, ZD and Müller, CL and Miraldi, ER and
Littman, DR and Blaser, MJ and Bonneau RA},
title = {Sparse and Compositionally Robust Inference of
Microbial Ecological Networks},
journal = {{PLoS Computational Biology}},
year = 2015,
volume = 11,
number = 5,
pages = {e1004226},
annote = {SPIEC-EASI},
doi = {10.1371/journal.pcbi.1004226}
}
@article{Lahti2014,
author = {Leo Lahti and Jarkko Salojärvi and Anne Salonen and Marten Scheffer and Willem M. de Vos},
title = {Tipping elements in the human intestinal ecosystem},
journal = {Nature Communications},
volume = {2014},
issue = {5},
pages = {1-10},
doi = {https://doi.org/10.1038/ncomms5344},
year = {2014}
}
@Article{Lahti2021bioc,
author = {Leo Lahti, Felix G.M. Ernst, Sudarshan A. Shetty and
others},
title = {Microbiome data science in the {\it SummarizedExperiment}
universe},
journal = {F1000Research},
year = 2021,
volume = 10,
number = 748,
note = {(slides); version 1; not peer reviewed},
doi = {10.7490/f1000research.1118712.1}
}
@Book{McElreath2020,
author = {Richard McElreath},
title = {Statistical Rethinking},
publisher = {Chapman and Hall/CRC},
year = 2020,
note = {with implementation by Solomon Kurz: https://bookdown.org/ajkurz/Statistical\_Rethinking\_recoded/}
}
@article{McInnes2018,
author = {{McInnes}, Leland and {Healy}, John and {Melville}, James},
title = "{UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction}",
journal = {arXiv e-prints},
year = 2018,
pages = {arXiv:1802.03426},
url = {https://arxiv.org/abs/1802.03426},
}
@article{McMurdie2013,
author = {Paul J McMurdie and Susan Holmes},
title = {{\it phyloseq:} An R Package for Reproducible
Interactive Analysis and Graphics of Microbiome
Census Data},
journal = {PLoS ONE},
volume = 8,
issue = 4,
pages = {e61217},
doi = {10.1371/journal.pone.0061217},
year = 2013
}
@Article{MultiAssayExperiment2017,
title = {Software For The Integration Of Multi-Omics Experiments In Bioconductor},
author = {Marcel Ramos and Lucas Schiffer and Angela Re and Rimsha Azhar and Azfar Basunia and Carmen Rodriguez Cabrera and Tiffany Chan and Philip Chapman and Sean Davis and David Gomez-Cabrero and Aedin C. Culhane and Benjamin Haibe-Kains and Kasper Hansen and Hanish Kodali and Marie Stephie Louis and Arvind Singh Mer and Markus Reister and Martin Morgan and Vincent Carey and Levi Waldron},
journal = {Cancer Research},
year = {2017},
volume = {77(21); e39-42},
}
@Book{OMA,
author = {Leo Lahti and Sudarshan Shetty and Felix M Ernst and others},
title = {Orchestrating Microbiome Analysis with Bioconductor [beta version]},
year = 2021,
url = {microbiome.github.io/oma/}
}
@Article{Pasolli2017,
author = {E Pasolli and L Schiffer and P Manghi and A Renson
and V Obenchain and D Truong and F Beghini and F
Malik and M Ramos and J Dowd and C Huttenhower and M
Morgan and N Segata and Waldron L},
title = {Accessible, curated metagenomic data through
ExperimentHub},
journal = {Nature Methods},
volume = 14,
issue = 11,
pages = {1023–1024},
year = 2017,
doi = {10.1038/nmeth.4468}
}
@article{Pons2006,
author = {Pons, Pascal and Latapy, Matthieu},
year = {2006},
month = {01},
pages = {191-218},
title = {Computing Communities in Large Networks Using Random Walks},
volume = {10},
journal = {Journal of Graph Algorithms and Applications},
doi = {10.7155/jgaa.00124}
}
@Article{Quinn2017,
author = {Quinn, T.P. and Richardson, M.F. and Lovell, D. and
Tamsyn M. Crowley},
title = {{\it propr}: An {R}-package for Identifying
Proportionally Abundant Features Using Compositional
Data Analysis},
journal = {Scientific Reports},
year = 2017,
volume = 7,
pages = 16252,
doi = {10.1038/s41598-017-16520-0}
}
@Manual{R-Biobase,
title = {Biobase: Base functions for Bioconductor},
author = {R. Gentleman and V. Carey and M. Morgan and S. Falcon},
year = {2020},
note = {R package version 2.50.0},
url = {https://bioconductor.org/packages/Biobase},
}
@Manual{R-BiocGenerics,
title = {BiocGenerics: S4 generic functions used in Bioconductor},
author = {The Bioconductor Dev Team},
year = {2020},
note = {R package version 0.36.0},
url = {https://bioconductor.org/packages/BiocGenerics},
}
@Manual{R-Biostrings,
title = {Biostrings: Efficient manipulation of biological strings},
author = {H. Pagès and P. Aboyoun and R. Gentleman and S. DebRoy},
year = {2020},
note = {R package version 2.58.0},
url = {https://bioconductor.org/packages/Biostrings},
}
@Manual{R-DECIPHER,
title = {DECIPHER: Tools for curating, analyzing, and manipulating biological
sequences},
author = {Erik Wright},
year = {2020},
note = {R package version 2.18.1},
}
@Manual{R-GenomeInfoDb,
title = {GenomeInfoDb: Utilities for manipulating chromosome names, including modifying
them to follow a particular naming style},
author = {Sonali Arora and Martin Morgan and Marc Carlson and H. Pagès},
year = {2020},
note = {R package version 1.26.2},
url = {https://bioconductor.org/packages/GenomeInfoDb},
}
@Manual{R-GenomicRanges,
title = {GenomicRanges: Representation and manipulation of genomic intervals},
author = {P. Aboyoun and H. Pagès and M. Lawrence},
year = {2020},
note = {R package version 1.42.0},
url = {https://bioconductor.org/packages/GenomicRanges},
}
@Manual{R-IRanges,
title = {IRanges: Foundation of integer range manipulation in Bioconductor},
author = {H. Pagès and P. Aboyoun and M. Lawrence},
year = {2020},
note = {R package version 2.24.0},
url = {https://bioconductor.org/packages/IRanges},
}
@Manual{R-MatrixGenerics,
title = {MatrixGenerics: S4 Generic Summary Statistic Functions that Operate on
Matrix-Like Objects},
author = {Constantin Ahlmann-Eltze and Peter Hickey and Hervé Pagès},
year = {2020},
note = {R package version 1.2.0},
url = {https://bioconductor.org/packages/MatrixGenerics},
}
@Manual{R-MultiAssayExperiment,
title = {MultiAssayExperiment: Software for the integration of multi-omics experiments in
Bioconductor},
author = {Marcel Ramos and Levi Waldron},
year = {2020},
note = {R package version 1.16.0},
url = {http://waldronlab.io/MultiAssayExperiment/},
}
@Manual{R-S4Vectors,
title = {S4Vectors: Foundation of vector-like and list-like containers in
Bioconductor},
author = {H. Pagès and M. Lawrence and P. Aboyoun},
year = {2020},
note = {R package version 0.28.0},
url = {https://bioconductor.org/packages/S4Vectors},
}
@Manual{R-SingleCellExperiment,
title = {SingleCellExperiment: S4 Classes for Single Cell Data},
author = {Aaron Lun and Davide Risso},
year = {2020},
note = {R package version 1.12.0},
}
@Manual{R-SummarizedExperiment,
title = {SummarizedExperiment: SummarizedExperiment container},
author = {Martin Morgan and Valerie Obenchain and Jim Hester and Hervé Pagès},
year = {2020},
note = {R package version 1.20.0},
url = {https://bioconductor.org/packages/SummarizedExperiment},
}
@Manual{R-TreeSummarizedExperiment,
title = {TreeSummarizedExperiment: a S4 Class for Data with Tree
Structures},
author = {Ruizhu Huang},
year = {2020},
note = {R package version 1.6.2},
}
@Manual{R-XVector,
title = {XVector: Foundation of external vector representation and manipulation in
Bioconductor},
author = {Hervé Pagès and Patrick Aboyoun},
year = {2020},
note = {R package version 0.30.0},
url = {https://bioconductor.org/packages/XVector},
}
@Manual{R-base,
title = {R: A Language and Environment for Statistical Computing},
author = {{R Core Team}},
organization = {R Foundation for Statistical Computing},
address = {Vienna, Austria},
year = {2020},
url = {https://www.R-project.org/},
}
@Manual{R-bluster,
title = {{bluster: Clustering Algorithms for Bioconductor}},
author = {Aaron Lun},
year = {2021},
note = {R package version 1.3.0},
url = {https://bioconductor.org/packages/3.14/bioc/html/bluster.html},
}
@Manual{R-bookdown,
title = {bookdown: Authoring Books and Technical Documents with R Markdown},
author = {Yihui Xie},
year = {2020},
note = {R package version 0.21},
url = {https://github.com/rstudio/bookdown},
}
@Manual{R-dada2,
title = {dada2: Accurate, high-resolution sample inference
from amplicon sequencing data},
author = {Benjamin Callahan and Paul McMurdie and Susan
Holmes},
year = 2020,
note = {R package version 1.18.0},
url = {http://benjjneb.github.io/dada2/},
}
@Article{Callahan2016dada2,
title = {DADA2: High-resolution sample inference from
Illumina amplicon data},
author = {Benjamin J Callahan and Paul J McMurdie and Michael
J Rosen and Andrew W Han and Amy Jo A Johnson and
Susan P Holmes},
journal = {Nature Methods},
volume = 13,
pages = {581-583},
year = 2016,
doi = {10.1038/nmeth.3869},
}
@Manual{R-ggpubr,
title = {ggpubr: ggplot2 Based Publication Ready Plots},
author = {Alboukadel Kassambara},
year = {2020},
note = {R package version 0.4.0},
url = {https://rpkgs.datanovia.com/ggpubr/},
}
@Manual{R-knitr,
title = {knitr: A General-Purpose Package for Dynamic Report Generation in R},
author = {Yihui Xie},
year = {2020},
note = {R package version 1.30},
url = {https://yihui.org/knitr/},
}
@Manual{R-matrixStats,
title = {matrixStats: Functions that Apply to Rows and Columns of Matrices (and to
Vectors)},
author = {Henrik Bengtsson},
year = {2020},
note = {R package version 0.57.0},
url = {https://github.com/HenrikBengtsson/matrixStats},
}
@Manual{R-mia,
title = {mia: Microbiome analysis},
author = {Felix G.M. Ernst and Sudarshan Shetty and Leo Lahti},
year = {2020},
note = {R package version 0.98.15},
}
@Manual{R-picante,
title = {Picante: R tools for integrating phylogenies and ecology},
author = {Steven W Kembel and Peter D Cowan and Matthew R Helmus and William K Cornwell and Helene Morlon and David D Ackerly and Simon P Blomberg and Campbell O Webb},
year = {2010},
note = {R package version 1.8.2},
url = {https://cran.r-project.org/web/packages/picante},
}
@Manual{R-rmarkdown,
title = {rmarkdown: Dynamic Documents for R},
author = {JJ Allaire and Yihui Xie and Jonathan McPherson and Javier Luraschi and Kevin Ushey and Aron Atkins and Hadley Wickham and Joe Cheng and Winston Chang and Richard Iannone},
year = {2020},
note = {R package version 2.5},
url = {https://github.com/rstudio/rmarkdown},
}
@Manual{R-scater,
title = {scater: Single-Cell Analysis Toolkit for Gene Expression Data in R},
author = {Davis McCarthy and Kieran Campbell and Aaron Lun and Quin Wills},
year = {2020},
note = {R package version 1.18.3},
url = {http://bioconductor.org/packages/scater/},
}
@Manual{R-vegan,
title = {vegan: Community Ecology Package},
author = {Jari Oksanen and F. Guillaume Blanchet and Michael Friendly and Roeland Kindt and Pierre Legendre and Dan McGlinn and Peter R. Minchin and R. B. O'Hara and Gavin L. Simpson and Peter Solymos and M. Henry H. Stevens and Eduard Szoecs and Helene Wagner},
year = {2020},
note = {R package version 2.5-7},
url = {https://CRAN.R-project.org/package=vegan},
}
@article{Rousseeuw1987,
author = {Peter J. Rousseeuw},
title = {Silhouettes: A graphical aid to the interpretation and validation of cluster analysis},
journal = {Journal of Computational and Applied Mathematics},
volume = {20},
pages = {53-65},
year = {1987},
doi = {https://doi.org/10.1016/0377-0427(87)90125-7},
url = {https://www.sciencedirect.com/science/article/pii/0377042787901257},
}
@article{Salosensaari2021,
author = {Salosensaari, Aaro and Laitinen, Ville and Havulinna, Aki and Méric, Guillaume and Cheng, Susan and Perola, Markus and Valsta, Liisa and Alfthan, Georg and Inouye, Michael and Watrous, Jeramie and Long, Tao and Salido, Rodolfo and Sanders, Karenina and Brennan, Caitriona and Humphrey, Gregory and Sanders, Jon and Jain, Mohit and Jousilahti, Pekka and Salomaa, Veikko and Niiranen, Teemu},
title = {Taxonomic signatures of cause-specific mortality risk in human gut microbiome},
journal = {Nature Communications},
volume = {12},
issue = {1},
pages = {1-8},
url = {https://www.nature.com/articles/s41467-021-22962-y},
year = {2021}
}
@Article{Shen2021,
author = {Yunyi Shen and Claudia Solis-Lemus},
title = {{CARlasso}: An {R} package for the estimation of sparse
microbial networks with predictors},
journal = {{arXiv} preprint},
year = 2021,
note = {arXiv:2107.13763 [stat.AP]},
url = {https://arxiv.org/abs/2107.13763}
}
@Article{Shetty2019,
author = {Sudarshan Shetty and Leo Lahti},
title = {Microbiome data science},
journal = {Journal of Biosciences},
year = 2019,
volume = 44,
pages = 115,
month = {October},
doi = {10.1007/s12038-019-9930-2},
note = {Preprint: https://github.com/openresearchlabs/openresearchlabs.github.io/blob/master/public/publication\_resources/papers/2019-Shetty-MDS.pdf},
status = {bioscience},
keywords = {review}
}
@Article{SingleCellExperiment2020,
title = {Orchestrating single-cell analysis with Bioconductor},
author = {Robert Amezquita and Aaron Lun and Etienne Becht and Vince Carey and Lindsay Carpp and Ludwig Geistlinger and Federico Marini and Kevin Rue-Albrecht and Davide Risso and Charlotte Soneson and Levi Waldron and Herve Pages and Mike Smith and Wolfgang Huber and Martin Morgan and Raphael Gottardo and Stephanie Hicks},
year = {2020},
volume = {17},
pages = {137--145},
journal = {Nature Methods},
url = {https://www.nature.com/articles/s41592-019-0654-x},
}
@Article{Vatanen2016,
author = {Tommi Vatanen and Aleksandar D. Kostic and Eva
d’Hennezel and Heli Siljander and Eric A. Franzosa
and Moran Yassour and Raivo Kolde and Hera Vlamakis
and Timothy D. Arthur and Anu-Maaria Hämäläinen and
Aleksandr Peet and Vallo Tillmann and Raivo Uibo and
Sergei Mokurov and Natalya Dorshakova and Jorma
Ilonen and Suvi M. Virtanen and Susanne J. Szabo and
Jeffrey A. Porter and Harri Lähdesmäki and Curtis
Huttenhower and Dirk Gevers and Thomas W. Cullen and
Mikael Knip and and Ramnik J. Xavier},
title = {Variation in Microbiome LPS Immunogenicity
Contributes to Autoimmunity in Humans},
journal = {Cell},
year = 2016,
volume = 165,
pages = {842--853},
month = {May},
doi = {10.1016/j.cell.2016.04.007},
status = {bioscience}
}
@article{Whittaker1960,
author = {Whittaker, R. H.},
title = {Vegetation of the Siskiyou Mountains, Oregon and California},
journal = {Ecological Monographs},
volume = {30},
number = {3},
pages = {279-338},
doi = {https://doi.org/10.2307/1943563},
url = {https://esajournals.onlinelibrary.wiley.com/doi/abs/10.2307/1943563},
eprint = {https://esajournals.onlinelibrary.wiley.com/doi/pdf/10.2307/1943563},
year = {1960}
}
@Book{bookdown2016,
title = {bookdown: Authoring Books and Technical Documents with {R} Markdown},
author = {Yihui Xie},
publisher = {Chapman and Hall/CRC},
address = {Boca Raton, Florida},
year = {2016},
note = {ISBN 978-1138700109},
url = {https://github.com/rstudio/bookdown},
}
@InCollection{knitr2014,
booktitle = {Implementing Reproducible Computational Research},
editor = {Victoria Stodden and Friedrich Leisch and Roger D. Peng},
title = {knitr: A Comprehensive Tool for Reproducible Research in {R}},
author = {Yihui Xie},
publisher = {Chapman and Hall/CRC},
year = {2014},
note = {ISBN 978-1466561595},
url = {http://www.crcpress.com/product/isbn/9781466561595},
}
@Book{knitr2015,
title = {Dynamic Documents with {R} and knitr},
author = {Yihui Xie},
publisher = {Chapman and Hall/CRC},
address = {Boca Raton, Florida},
year = {2015},
edition = {2nd},
note = {ISBN 978-1498716963},
url = {https://yihui.org/knitr/},
}
@Book{rmarkdown2018,
title = {R Markdown: The Definitive Guide},
author = {Yihui Xie and J.J. Allaire and Garrett Grolemund},
publisher = {Chapman and Hall/CRC},
address = {Boca Raton, Florida},
year = {2018},
note = {ISBN 9781138359338},
url = {https://bookdown.org/yihui/rmarkdown},
}
@Book{rmarkdown2020,
title = {R Markdown Cookbook},
author = {Yihui Xie and Christophe Dervieux and Emily Riederer},
publisher = {Chapman and Hall/CRC},
address = {Boca Raton, Florida},
year = {2020},
note = {ISBN 9780367563837},
url = {https://bookdown.org/yihui/rmarkdown-cookbook},
}
@Article{scater2017,
author = {Davis J. McCarthy and Kieran R. Campbell and Aaron T. L. Lun and Quin F. Willis},
title = {Scater: pre-processing, quality control, normalisation and visualisation of single-cell {R}{N}{A}-seq data in {R}},
journal = {Bioinformatics},
year = {2017},
volume = {33},
issue = {8},
pages = {1179-1186},
doi = {10.1093/bioinformatics/btw777},
}
@Book{xie2015,
title = {Dynamic Documents with {R} and knitr},
author = {Yihui Xie},
publisher = {Chapman and Hall/CRC},
address = {Boca Raton, Florida},
year = {2015},
edition = {2nd},
note = {ISBN 978-1498716963},
url = {http://yihui.org/knitr/},
}
@article{Quinn2021,
title = {A {{Critique}} of {{Differential Abundance Analysis}}, and {{Advocacy}} for an {{Alternative}}},
author = {Quinn, Thomas P. and {Gordon-Rodriguez}, Elliott and Erb, Ionas},
year = {2021},
month = apr,
journal = {arXiv:2104.07266 [q-bio, stat]},
eprint = {2104.07266},
eprinttype = {arxiv},
primaryclass = {q-bio, stat},
abstract = {It is largely taken for granted that differential abundance analysis is, by default, the best first step when analyzing genomic data. We argue that this is not necessarily the case. In this article, we identify key limitations that are intrinsic to differential abundance analysis: it is (a) dependent on unverifiable assumptions, (b) an unreliable construct, and (c) overly reductionist. We formulate an alternative framework called ratio-based biomarker analysis which does not suffer from the identified limitations. Moreover, ratio-based biomarkers are highly flexible. Beyond replacing DAA, they can also be used for many other bespoke analyses, including dimension reduction and multi-omics data integration.},
archiveprefix = {arXiv},
langid = {english},
keywords = {Quantitative Biology - Genomics,Statistics - Methodology},
file = {/Users/henrikeckermann/Zotero/storage/TQGUMRYU/Quinn et al. - 2021 - A Critique of Differential Abundance Analysis, and.pdf}
}
@article{Nearing2022,
title = {Microbiome Differential Abundance Methods Produce Different Results across 38 Datasets},
author = {Nearing, Jacob T. and Douglas, Gavin M. and Hayes, Molly G. and MacDonald, Jocelyn and Desai, Dhwani K. and Allward, Nicole and Jones, Casey M. A. and Wright, Robyn J. and Dhanani, Akhilesh S. and Comeau, Andr{\'e} M. and Langille, Morgan G. I.},
year = {2022},
month = dec,
journal = {Nature Communications},
volume = {13},
number = {1},
pages = {342},
issn = {2041-1723},
doi = {10.1038/s41467-022-28034-z},
abstract = {Abstract Identifying differentially abundant microbes is a common goal of microbiome studies. Multiple methods are used interchangeably for this purpose in the literature. Yet, there are few large-scale studies systematically exploring the appropriateness of using these tools interchangeably, and the scale and significance of the differences between them. Here, we compare the performance of 14 differential abundance testing methods on 38 16S rRNA gene datasets with two sample groups. We test for differences in amplicon sequence variants and operational taxonomic units (ASVs) between these groups. Our findings confirm that these tools identified drastically different numbers and sets of significant ASVs, and that results depend on data pre-processing. For many tools the number of features identified correlate with aspects of the data, such as sample size, sequencing depth, and effect size of community differences. ALDEx2 and ANCOM-II produce the most consistent results across studies and agree best with the intersect of results from different approaches. Nevertheless, we recommend that researchers should use a consensus approach based on multiple differential abundance methods to help ensure robust biological interpretations.},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/RL7S8KYH/Nearing et al. - 2022 - Microbiome differential abundance methods produce .pdf}
}
@article{Huang2020,
title = {Analysis of Compositions of Microbiomes with Bias Correction},
author = {Lin, Huang and Peddada, Shyamal Das},
year = {2020},
month = dec,
journal = {Nat Commun},
volume = {11},
number = {1},
pages = {3514},
issn = {2041-1723},
doi = {10.1038/s41467-020-17041-7},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/DHDQWYVW/Lin and Peddada - 2020 - Analysis of compositions of microbiomes with bias .pdf}
}
@article{Mandal2015,
title = {Analysis of Composition of Microbiomes: A Novel Method for Studying Microbial Composition},
shorttitle = {Analysis of Composition of Microbiomes},
author = {Mandal, Siddhartha and Van Treuren, Will and White, Richard A. and Eggesb{\o}, Merete and Knight, Rob and Peddada, Shyamal D.},
year = {2015},
month = may,
journal = {Microbial Ecology in Health \& Disease},
volume = {26},
number = {0},
issn = {1651-2235},
doi = {10.3402/mehd.v26.27663},
abstract = {Background: Understanding the factors regulating our microbiota is important but requires appropriate statistical methodology. When comparing two or more populations most existing approaches either discount the underlying compositional structure in the microbiome data or use probability models such as the multinomial and Dirichlet-multinomial distributions, which may impose a correlation structure not suitable for microbiome data. Objective: To develop a methodology that accounts for compositional constraints to reduce false discoveries in detecting differentially abundant taxa at an ecosystem level, while maintaining high statistical power. Methods: We introduced a novel statistical framework called analysis of composition of microbiomes (ANCOM). ANCOM accounts for the underlying structure in the data and can be used for comparing the composition of microbiomes in two or more populations. ANCOM makes no distributional assumptions and can be implemented in a linear model framework to adjust for covariates as well as model longitudinal data. ANCOM also scales well to compare samples involving thousands of taxa. Results: We compared the performance of ANCOM to the standard t-test and a recently published methodology called Zero Inflated Gaussian (ZIG) methodology (1) for drawing inferences on the mean taxa abundance in two or more populations. ANCOM controlled the false discovery rate (FDR) at the desired nominal level while also improving power, whereas the t-test and ZIG had inflated FDRs, in some instances as high as 68\% for the t-test and 60\% for ZIG. We illustrate the performance of ANCOM using two publicly available microbial datasets in the human gut, demonstrating its general applicability to testing hypotheses about compositional differences in microbial communities. Conclusion: Accounting for compositionality using log-ratio analysis results in significantly improved inference in microbiota survey data.},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/Z2JYHTAK/Mandal et al. - 2015 - Analysis of composition of microbiomes a novel me.pdf}
}
@article{sprockettMicrobiotaAssemblyStructure2020,
title = {Microbiota Assembly, Structure, and Dynamics among {{Tsimane}} Horticulturalists of the {{Bolivian Amazon}}},
author = {Sprockett, Daniel D. and Martin, Melanie and Costello, Elizabeth K. and Burns, Adam R. and Holmes, Susan P. and Gurven, Michael D. and Relman, David A.},
year = {2020},
month = dec,
journal = {Nat Commun},
volume = {11},
number = {1},
pages = {3772},
issn = {2041-1723},
doi = {10.1038/s41467-020-17541-6},
abstract = {Abstract Selective and neutral forces shape human microbiota assembly in early life. The Tsimane are an indigenous Bolivian population with infant care-associated behaviors predicted to increase mother-infant microbial dispersal. Here, we characterize microbial community assembly in 47 infant-mother pairs from six Tsimane villages, using 16S rRNA gene amplicon sequencing of longitudinal stool and tongue swab samples. We find that infant consumption of dairy products, vegetables, and chicha (a fermented drink inoculated with oral microbes) is associated with stool microbiota composition. In stool and tongue samples, microbes shared between mothers and infants are more abundant than non-shared microbes. Using a neutral model of community assembly, we find that neutral processes alone explain the prevalence of 79\% of infant-colonizing microbes, but explain microbial prevalence less well in adults from river villages with more regular access to markets. Our results underscore the importance of neutral forces during microbiota assembly. Changing lifestyle factors may alter traditional modes of microbiota assembly by decreasing the role of neutral processes.},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/D59QN8JL/Sprockett et al. - 2020 - Microbiota assembly, structure, and dynamics among.pdf}
}
@article{Sprockett2020,
title = {Microbiota Assembly, Structure, and Dynamics among {{Tsimane}} Horticulturalists of the {{Bolivian Amazon}}},
author = {Sprockett, Daniel D. and Martin, Melanie and Costello, Elizabeth K. and Burns, Adam R. and Holmes, Susan P. and Gurven, Michael D. and Relman, David A.},
year = {2020},
month = dec,
journal = {Nat Commun},
volume = {11},
number = {1},
pages = {3772},
issn = {2041-1723},
doi = {10.1038/s41467-020-17541-6},
abstract = {Abstract Selective and neutral forces shape human microbiota assembly in early life. The Tsimane are an indigenous Bolivian population with infant care-associated behaviors predicted to increase mother-infant microbial dispersal. Here, we characterize microbial community assembly in 47 infant-mother pairs from six Tsimane villages, using 16S rRNA gene amplicon sequencing of longitudinal stool and tongue swab samples. We find that infant consumption of dairy products, vegetables, and chicha (a fermented drink inoculated with oral microbes) is associated with stool microbiota composition. In stool and tongue samples, microbes shared between mothers and infants are more abundant than non-shared microbes. Using a neutral model of community assembly, we find that neutral processes alone explain the prevalence of 79\% of infant-colonizing microbes, but explain microbial prevalence less well in adults from river villages with more regular access to markets. Our results underscore the importance of neutral forces during microbiota assembly. Changing lifestyle factors may alter traditional modes of microbiota assembly by decreasing the role of neutral processes.},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/D59QN8JL/Sprockett et al. - 2020 - Microbiota assembly, structure, and dynamics among.pdf}
}
@article{davis2018simple,
title={Simple statistical identification and removal of contaminant sequences in marker-gene and metagenomics data},
author={Davis, Nicole M and Proctor, Diana M and Holmes, Susan P and Relman, David A and Callahan, Benjamin J},
journal={Microbiome},
volume={6},
number={1},
pages={1--14},
year={2018},
publisher={Springer}
}
@article{mcmurdie2014waste,
title={Waste not, want not: why rarefying microbiome data is inadmissible},
author={McMurdie, Paul J and Holmes, Susan},
journal={PLoS computational biology},
volume={10},
number={4},
pages={e1003531},
year={2014},
publisher={Public Library of Science San Francisco, USA}
}
@Manual{patchwork2022,
title = {patchwork: The Composer of Plots},
author = {Thomas Lin Pedersen},
year = {2022},
note = {https://patchwork.data-imaginist.com,
https://github.com/thomasp85/patchwork},
}
@article{Gloor2016,
title = {Displaying {{Variation}} in {{Large Datasets}}: {{Plotting}} a {{Visual Summary}} of {{Effect Sizes}}},
shorttitle = {Displaying {{Variation}} in {{Large Datasets}}},
author = {Gloor, Gregory B. and Macklaim, Jean M. and Fernandes, Andrew D.},
year = {2016},
month = jul,
journal = {Journal of Computational and Graphical Statistics},
volume = {25},
number = {3},
pages = {971--979},
issn = {1061-8600, 1537-2715},
doi = {10.1080/10618600.2015.1131161},
abstract = {Displaying the component-wise between-group differences high-dimensional datasets is problematic because widely used plots such as Bland-Altman and Volcano plots do not show what they are colloquially believed to show. Thus, it is difficult for the experimentalist to grasp why the between-group difference of one component is `significant' while that of another component is not. Here we propose a type of `Effect Plot' that displays between-group differences in relation to respective underlying variability for every component of a high-dimensional dataset. We use synthetic data to show that such a plot captures the essence of what determines `significance' for between-group differences in each component, and provide guidance in the interpretation of the plot. Supplementary online materials contain the code and data for this paper, and includes simple R functions to produce an effect plot from suitable datasets.},
langid = {english},
file = {/Users/henrikeckermann/Zotero/storage/RE6XBPGQ/Gloor et al. - 2016 - Displaying Variation in Large Datasets Plotting a.pdf}
}
@article{Zhou2022,
title = {{{LinDA}}: Linear Models for Differential Abundance Analysis of Microbiome Compositional Data},
shorttitle = {{{LinDA}}},
author = {Zhou, Huijuan and He, Kejun and Chen, Jun and Zhang, Xianyang},