-
Notifications
You must be signed in to change notification settings - Fork 0
/
R_script_gemmule_microbiome.R
1630 lines (1142 loc) · 68 KB
/
R_script_gemmule_microbiome.R
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
#### Project name : S.lacustris_gemmules_microbiome ####
#### Description of the project ####
#Sponges and their microbiome are playing important role in their ecosystems, such as the cycling of the organic matter.
#However, the mechanisms associated with the transmission of the bacterial community from one generation to another is still unexplored, especially for freshwater sponges.
#Spongilla lacustris is a model widely distributed in European rivers and lakes, producing before winter dormant cysts (named gemmules) for their asexual reproduction.
#Through an in vitro experiment, this study aims to describe the dynamics of the bacterial community and its transmission modes following the hatching of these gemmules.
#### Objective of the script ####
# To analyse the 16S rRNA gene metabarcoding reads obtained from the DADA2 pipeline.
# The main package used for this analysis will be phyloseq (for more details see tutorials such as https://joey711.github.io/phyloseq/index.html)
#### Author of the script : Dr. Benoît PAIX
#### Citation : not yet available (paper submitted)
#### 1. Setting the working directory ####
setwd("C:/Users/benoit.paix/Mon Drive/2021_2023 Postdoc/8. Gemmules growth project/4. Lab notebook/3. Metabarcoding analyses/4. Phyloseq analysis v2 with 2")
#### 2. Installation and loading of the packages ####
# example of few package installations :
#install.packages("randomcoloR")
#install.packages("ggplot2")
#source('http://bioconductor.org/biocLite.R')
#biocLite('phyloseq')
#install.packages("stringi")
#install.packages("Rcpp")
#if (!require("BiocManager", quietly = TRUE))
# install.packages("BiocManager")
#BiocManager::install(version='devel')
#BiocManager::install("microbiome")
#install.packages("hrbrthemes")
#install.packages("ggthemes")
#install.packages("RColorBrewer")
#library(devtools)
#install_github("pmartinezarbizu/pairwiseAdonis/pairwiseAdonis")
library(stringi)
library(vegan)
library(Rcpp)
library(ggplot2)
library(randomcoloR)
library(rlang)
library(phyloseq)
library(ape)
library(dplyr)
library(agricolae) #for statistical tests
library(RVAideMemoire) #for statistical tests
library(microbiome)
library(hrbrthemes)
library(cowplot) #for figures
#library(ggthemes)
library(RColorBrewer) #for figures
library(decontam) #for decontamination of the dataset
library(ggrepel) #for figures
library(microbiomeMarker) #for lefse analysis
library(multcompView)
library(rcompanion)
library(pairwiseAdonis)
library(ggpubr)
library(ggh4x)
#### 3. Creation of the output folders
#dir.create("1. Data_prep results")
#dir.create("2. Alpha_div results")
#dir.create("3. Beta_div results")
#dir.create("4. Compositional results")
#### 4. Reading of the csv files (ASV, Taxonomy and Metadata tables) ####
ASV_table = read.csv(file = "ASV_table.csv" , header = TRUE , sep = ";" , row.names = 1)
dim(ASV_table)
TAX_table = read.csv(file = "Taxonomy_table.csv" , sep = ";" , header = T , row.names = 1)
dim(TAX_table)
META_table = read.csv(file = "Metadata_table.csv" , header = TRUE , sep = ";" , row.names = 1)
dim(META_table)
TAX_table = as.data.frame(TAX_table)
TAX_table
TAX_table.v2 <- TAX_table
TAX_table.v2$Kingdom <- TAX_table.v2$Kingdom
TAX_table.v2$Phylum <- paste(TAX_table.v2$Kingdom,"|" ,TAX_table$Phylum)
TAX_table.v2$Class <- paste(TAX_table.v2$Phylum,"|" ,TAX_table$Class)
TAX_table.v2$Order <- paste(TAX_table.v2$Class ,"|" ,TAX_table$Order)
TAX_table.v2$Family <- paste(TAX_table.v2$Order,"|" ,TAX_table$Family)
TAX_table.v2$Genus <- paste(TAX_table.v2$Family,"|" ,TAX_table$Genus)
head(TAX_table.v2)
#### 5. Creation of the main phyloseq object ####
ASV_phylo = otu_table(ASV_table, taxa_are_rows = TRUE)
dim(ASV_phylo)
TAX_table = as.matrix(TAX_table.v2)
TAX_phylo = tax_table(TAX_table)
dim(TAX_phylo)
META_phylo = sample_data(META_table)
dim(META_phylo)
physeq_raw = phyloseq(ASV_phylo, TAX_phylo, META_phylo)
physeq_raw
#### 6. Decontamination of the dataset #####
#inspection of the library sizes
df <- as.data.frame(sample_data(physeq_raw)) # Put sample_data into a ggplot-friendly data.frame
df$LibrarySize <- sample_sums(physeq_raw)
df <- df[order(df$LibrarySize),]
df$Index <- seq(nrow(df))
plot_lib_size = ggplot(data=df, aes(x=Index, y=LibrarySize, color=Sample_or_Control))
plot_lib_size = plot_lib_size + geom_point()
plot_lib_size
ggsave(filename = "Plot_lib_size.pdf",
plot = plot_lib_size,
device = "pdf" ,
width = 15 , height = 10, units = "cm",
path = "./1. Data_prep results")
#identification of the contaminants (prevalence method)
sample_data(physeq_raw)$is.neg <- sample_data(physeq_raw)$Sample_or_Control == "Control"
contamdf.prev05 <- isContaminant(physeq_raw, method="prevalence", neg="is.neg", threshold=0.5)
table(contamdf.prev05$contaminant)
contamdf.prev05 = cbind(as.data.frame(tax_table(physeq_raw)) , contamdf.prev05)
contamdf.prev05
write.csv(contamdf.prev05, file.path("./1. Data_prep results" , "Contamination_table_prev05.csv"))
# Make phyloseq object of presence-absence in negative controls and true samples
ps.pa <- transform_sample_counts(physeq_raw, function(abund) 1*(abund>0))
ps.pa.neg <- prune_samples(sample_data(ps.pa)$Sample_or_Control == "Control", ps.pa)
ps.pa.pos <- prune_samples(sample_data(ps.pa)$Sample_or_Control == "True sample", ps.pa)
# Make data.frame of prevalence in positive and negative samples
df.pa <- data.frame(pa.pos=taxa_sums(ps.pa.pos), pa.neg=taxa_sums(ps.pa.neg),
contaminant=contamdf.prev05$contaminant)
plot_prevalence = ggplot(data=df.pa, aes(x=pa.neg, y=pa.pos, color=contaminant))
plot_prevalence = plot_prevalence + geom_point()
plot_prevalence = plot_prevalence + xlab("Prevalence (Negative Controls)") + ylab("Prevalence (True Samples)")
plot_prevalence
ggsave(filename = "Plot_prevalence.pdf",
plot = plot_prevalence,
device = "pdf" ,
width = 15 , height = 10, units = "cm",
path = "./1. Data_prep results")
#create a phyloseq_decontam object without the contaminants
physeq_decontam = prune_taxa(!contamdf.prev05$contaminant, physeq_raw)
physeq_decontam
#### 7. Removing unwanted taxa (EuK, Chloroplast, Mitochondria) ####
physeq_filtered = subset_taxa(physeq_decontam,
(Kingdom != "Eukaryota" | is.na(Kingdom)) &
(Order!= "Bacteria | Cyanobacteria | Cyanobacteriia | Chloroplast"| is.na(Order)) &
(Family != "Bacteria | Proteobacteria | Alphaproteobacteria | Rickettsiales | Mitochondria"| is.na(Family)))
physeq_filtered
#### 8. Verification of the rarefaction curves ######
as.data.frame(t(otu_table(physeq_filtered)))
rarecurve(as.data.frame(t(otu_table(physeq_filtered))), step = 20, cex = 0.5)
#save manually the plot to ./1. Data_prep results
#set a minimum reads threshold based on the rarefaction curves results
#### 9. Removing unwanted samples for the analysis (control samples and those below the threshold) ######
sample_sums(physeq_filtered)
physeq_subsampled = prune_samples(sample_sums(physeq_filtered)>=10000, physeq_filtered)
physeq_subsampled
saveRDS(physeq_subsampled, "Physeq_subsampled.RDS")
#### 10. Creating phylose_subsampled objects ######
physeq_subsampled = readRDS("Physeq_subsampled.RDS") #######
physeq_subsampled
sample_sums(physeq_subsampled)
physeq_subsampled_t0 = subset_samples(physeq_subsampled, Sampling_time == "04. T0")
physeq_subsampled_t1 = subset_samples(physeq_subsampled, Sampling_time == "05. T1" & Sample_type == "Cultivated sponge")
physeq_subsampled_t2 = subset_samples(physeq_subsampled, Sampling_time == "06. T2" & Sample_type == "Cultivated sponge")
physeq_subsampled_t3 = subset_samples(physeq_subsampled, Sampling_time == "07. T3" & Sample_type == "Cultivated sponge")
physeq_subsampled_t4 = subset_samples(physeq_subsampled, Sampling_time == "08. T4" & Sample_type == "Cultivated sponge")
physeq_subsampled_t5 = subset_samples(physeq_subsampled, Sampling_time == "09. T5" & Sample_type == "Cultivated sponge")
physeq_subsampled_t6 = subset_samples(physeq_subsampled, Sampling_time == "10. T6" & Sample_type == "Cultivated sponge")
#### 11. ALPHA DIVERSITY ANALYSES ##################
# Create a phyloseq rarefied objects for alpha div analyses
physeq_rarefied = rarefy_even_depth(physeq_subsampled)
physeq_rarefied
sample_sums(physeq_rarefied)
# ALPHA DIVERSITY INDEX
data_alpha = estimate_richness(physeq_rarefied , measures = c("Observed", "Shannon", "Chao1"))
data_alpha
Pielou = data_alpha$Shannon / log(data_alpha$Observed)
Pielou
data_alpha = cbind(sample_data(physeq_rarefied), data_alpha , Pielou)
data_alpha = data_alpha[, c("Sample_type","Sampling_time" , "Cross_conditions", "Washing" , "Medium", "Shannon" ,"Chao1","Pielou")]
data_alpha
data_alpha$Sample_type[data_alpha$Sample_type == "Gemmule"] <- "2. Gemmules"
data_alpha$Sample_type[data_alpha$Sample_type == "Cultivated sponge"] <- "3. Cultivated sponges"
data_alpha$Sample_type[data_alpha$Sample_type == "In situ maternal sponge"] <- "1. In situ maternal sponge"
data_alpha$Sample_type[data_alpha$Sample_type == "Filtered freshwater"] <- "4. Filtered freshwater"
data_alpha
#Q1 : differences per samples types
color_vector_1 = c("G+EM" = "lightcoral",
"G+EM_F-PB" = "plum3",
"G+EM_F+PB" = "sandybrown",
"G-EM" = "lightgreen",
"G-EM_F-PB" = "mediumaquamarine",
"G-EM_F+PB" = "yellow1")
plot_chao1_Q1 = ggplot(data_alpha, aes(Cross_conditions ,Chao1, fill = Cross_conditions))
plot_chao1_Q1 = plot_chao1_Q1 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sample_type, scales="free", space = "free")
plot_chao1_Q1 = plot_chao1_Q1 + theme_bw(base_size = 15)
plot_chao1_Q1 = plot_chao1_Q1 + theme(legend.position="none") + theme(axis.text.x=element_blank())
plot_chao1_Q1 = plot_chao1_Q1 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_chao1_Q1 = plot_chao1_Q1 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_chao1_Q1 = plot_chao1_Q1 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_chao1_Q1
plot_shannon_Q1 = ggplot(data_alpha, aes(Cross_conditions ,Shannon, fill = Cross_conditions))
plot_shannon_Q1 = plot_shannon_Q1 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sample_type, scales="free", space = "free")
plot_shannon_Q1 = plot_shannon_Q1 + theme_bw(base_size = 15)
plot_shannon_Q1 = plot_shannon_Q1 + theme(legend.position="none") + theme(axis.text.x=element_blank())
plot_shannon_Q1 = plot_shannon_Q1 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_shannon_Q1 = plot_shannon_Q1 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_shannon_Q1 = plot_shannon_Q1 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_shannon_Q1
plot_pielou_Q1 = ggplot(data_alpha, aes(Cross_conditions ,Pielou, fill = Cross_conditions))
plot_pielou_Q1 = plot_pielou_Q1 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sample_type, scales="free", space = "free")
plot_pielou_Q1 = plot_pielou_Q1 + theme_bw(base_size = 15)
plot_pielou_Q1 = plot_pielou_Q1 + theme(legend.position="none") + theme(axis.text.x=element_text(angle = 45, hjust = 1))
plot_pielou_Q1 = plot_pielou_Q1 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_pielou_Q1 = plot_pielou_Q1 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_pielou_Q1 = plot_pielou_Q1 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_pielou_Q1
plot_alpha_Q1 = plot_grid( plot_chao1_Q1, plot_shannon_Q1 ,plot_pielou_Q1 , labels=c("A", "B", "C"),rel_heights = c(1, 1, 1.6) , ncol = 1, nrow = 3 ,label_size = 20)
plot_alpha_Q1
ggsave(filename = "Plot_alpha_Q1.pdf",
plot = plot_alpha_Q1,
device = "pdf" ,
width = 30 , height = 25, units = "cm",
path = "./2. Alpha_div results")
#Q2 : within gemmules & cultivated gemmules : per time ###########
data_alpha_Q2 = subset(data_alpha, Sample_type == "3. Cultivated sponges" | Sample_type == "2. Gemmules" )
data_alpha_Q2
plot_chao1_Q2 = ggplot(data_alpha_Q2, aes(Cross_conditions ,Chao1, fill = Cross_conditions))
plot_chao1_Q2 = plot_chao1_Q2 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sampling_time, scales="free", space = "free")
plot_chao1_Q2 = plot_chao1_Q2 + theme_bw(base_size = 15)
plot_chao1_Q2 = plot_chao1_Q2 + theme(legend.position="none") + theme(axis.text.x=element_blank())
plot_chao1_Q2 = plot_chao1_Q2 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_chao1_Q2 = plot_chao1_Q2 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_chao1_Q2 = plot_chao1_Q2 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_chao1_Q2
plot_shannon_Q2 = ggplot(data_alpha_Q2, aes(Cross_conditions ,Shannon, fill = Cross_conditions))
plot_shannon_Q2 = plot_shannon_Q2 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sampling_time, scales="free", space = "free")
plot_shannon_Q2 = plot_shannon_Q2 + theme_bw(base_size = 15)
plot_shannon_Q2 = plot_shannon_Q2 + theme(legend.position="none") + theme(axis.text.x=element_text(angle = 90, hjust = 1))
plot_shannon_Q2 = plot_shannon_Q2 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_shannon_Q2 = plot_shannon_Q2 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_shannon_Q2 = plot_shannon_Q2 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_shannon_Q2
plot_pielou_Q2 = ggplot(data_alpha_Q2, aes(Cross_conditions ,Pielou, fill = Cross_conditions))
plot_pielou_Q2 = plot_pielou_Q2 + geom_boxplot(alpha = 0.8, size = 1 ) + facet_grid( ~ Sampling_time, scales="free", space = "free")
plot_pielou_Q2 = plot_pielou_Q2 + theme_bw(base_size = 15)
plot_pielou_Q2 = plot_pielou_Q2 + theme(legend.position="none") + theme(axis.text.x=element_text(angle = 90, hjust = 1))
plot_pielou_Q2 = plot_pielou_Q2 + theme(axis.title.x = element_blank(),axis.title.y = element_blank())
plot_pielou_Q2 = plot_pielou_Q2 + scale_fill_manual(values = c(color_vector_1), na.value = c("pink3","slateblue"))
plot_pielou_Q2 = plot_pielou_Q2 + geom_point(fill = "white" , size = 3, alpha = 0.5, pch = 21, stroke = 1)
plot_pielou_Q2
plot_shannon_Q2
ggsave(filename = "Plot_shannon_Q2.pdf",
plot = plot_shannon_Q2,
device = "pdf" ,
width = 25 , height = 15, units = "cm",
path = "./2. Alpha_div results")
plot_chao1_pielou_Q2 = plot_grid( plot_chao1_Q2 ,plot_pielou_Q2 , labels=c("A", "B"),rel_heights = c(1, 1.6) , ncol = 1, nrow = 2 ,label_size = 20)
plot_chao1_pielou_Q2
ggsave(filename = "Plot_chao1_pielou_Q2.pdf",
plot = plot_chao1_pielou_Q2,
device = "pdf" ,
width = 30 , height = 20, units = "cm",
path = "./2. Alpha_div results")
### Univariate statistics for alpha div(anova) ####
#Q1 : differences between sample types
#Shapiro tests from the checking of the normal distribution
shapiro_data_shannon_Q1 = shapiro.test(data_alpha$Shannon)
shapiro_data_shannon_Q1$p.value
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
shapiro_data_chao1_Q1 = shapiro.test(data_alpha$Chao1)
shapiro_data_chao1_Q1
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
shapiro_data_pielou_Q1 = shapiro.test(data_alpha$Pielou)
shapiro_data_pielou_Q1
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
#writing a table with the results from the shapiro tests with the 3 indexes
shapiro_data_alpha_Q1 <- matrix(nrow = 3 , ncol=2, byrow=TRUE)
colnames(shapiro_data_alpha_Q1) = c("W","p-value")
rownames(shapiro_data_alpha_Q1) = c("Shannon","Chao1","Pielou")
shapiro_data_alpha_Q1[,1] <- c(shapiro_data_shannon_Q1$statistic,
shapiro_data_chao1_Q1$statistic,
shapiro_data_pielou_Q1$statistic)
shapiro_data_alpha_Q1[,2]<- c(shapiro_data_shannon_Q1$p.value,
shapiro_data_chao1_Q1$p.value,
shapiro_data_pielou_Q1$p.value)
shapiro_data_alpha_Q1
write.csv(shapiro_data_alpha_Q1, file.path("./2. Alpha_div results" , "Shapiro_data_alpha_Q1.csv"))
# Kruskal tests (non parametric anova) with Sample type factor : Q1
krustal_data_shannon_Q1 = kruskal.test(Shannon ~ Sample_type, data_alpha)
krustal_data_shannon_Q1
krustal_data_chao1_Q1 = kruskal.test(Chao1 ~ Sample_type, data_alpha)
krustal_data_chao1_Q1
krustal_data_pielou_Q1 = kruskal.test(Pielou ~ Sample_type, data_alpha)
krustal_data_pielou_Q1
kruskal_data_alpha_Q1 <- matrix(nrow = 3 , ncol=3, byrow=TRUE)
colnames(kruskal_data_alpha_Q1) = c("Chi-square","Df","p-value")
rownames(kruskal_data_alpha_Q1) = c("Shannon","Chao1","Pielou")
kruskal_data_alpha_Q1
kruskal_data_alpha_Q1[,1] <- c(krustal_data_shannon_Q1$statistic,
krustal_data_chao1_Q1$statistic,
krustal_data_pielou_Q1$statistic)
kruskal_data_alpha_Q1[,2]<- c(krustal_data_shannon_Q1$parameter,
krustal_data_chao1_Q1$parameter,
krustal_data_pielou_Q1$parameter)
kruskal_data_alpha_Q1[,3]<- c(krustal_data_shannon_Q1$p.value,
krustal_data_chao1_Q1$p.value,
krustal_data_pielou_Q1$p.value)
kruskal_data_alpha_Q1
write.csv(kruskal_data_alpha_Q1, file.path("./2. Alpha_div results" , "Kruskal_data_alpha_Q1.csv"))
# Wilcox pairwise comparison test for anova with p < 0.05 : here for Pielou
data_wilcox_pielou_Q1 = pairwise.wilcox.test(data_alpha$Pielou, data_alpha$Sample_type, p.adjust.method = "bonf")
data_wilcox_pielou_Q1
data_wilcox_pielou_Q1$p.value
data_wilcox_pielou_Q1_full = fullPTable(data_wilcox_pielou_Q1$p.value)
data_wilcox_pielou_Q1_full
indices_wilcox_pielou_Q1 = multcompLetters(data_wilcox_pielou_Q1_full,
compare="<",
threshold=0.05,
Letters=letters,
reversed = FALSE)
indices_wilcox_pielou_Q1$Letters
data_wilcox_pielou_Q1_full2 = cbind(data_wilcox_pielou_Q1_full, indices_wilcox_pielou_Q1$Letters )
data_wilcox_pielou_Q1_full2
write.csv(data_wilcox_pielou_Q1_full2, file.path("./2. Alpha_div results" , "Wilcox_data_pielou_Q1.csv"))
#Q2 : differences between conditions over time
#Shapiro tests
shapiro_data_shannon_Q2 = shapiro.test(data_alpha_Q2$Shannon)
shapiro_data_shannon_Q2
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
shapiro_data_chao1_Q2 = shapiro.test(data_alpha_Q2$Chao1)
shapiro_data_chao1_Q2
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
shapiro_data_pielou_Q2 = shapiro.test(data_alpha_Q2$Pielou)
shapiro_data_pielou_Q2
#writing a table with the results from the shapiro tests with the 3 indexes
shapiro_data_alpha_Q2 <- matrix(nrow = 3 , ncol=2, byrow=TRUE)
colnames(shapiro_data_alpha_Q2) = c("W","p-value")
rownames(shapiro_data_alpha_Q2) = c("Shannon","Chao1","Pielou")
shapiro_data_alpha_Q2[,1] <- c(shapiro_data_shannon_Q2$statistic,
shapiro_data_chao1_Q2$statistic,
shapiro_data_pielou_Q2$statistic)
shapiro_data_alpha_Q2[,2]<- c(shapiro_data_shannon_Q2$p.value,
shapiro_data_chao1_Q2$p.value,
shapiro_data_pielou_Q2$p.value)
shapiro_data_alpha_Q2
write.csv(shapiro_data_alpha_Q2, file.path("./2. Alpha_div results" , "Shapiro_data_alpha_Q2.csv"))
#From the output, the p-value < 0.05 implying that the distribution of the data is significantly different from normal distribution. In other words, we cannot assume the normality.
#for Q2 I need to create a new factor column in the dataset : Sampling_time_cross_condition. This factor will be used for the Kruskal-wallis tests
# --> solution used : or (to simplify the analysis, but harder to justify in m&m ) a factor Sampling_time_washing (since the medium type seems to have no effect)
St_Cc = paste(data_alpha_Q2$Sampling_time ,
data_alpha_Q2$Washing)
St_Cc
data_alpha_Q2.2 = cbind(data_alpha_Q2, St_Cc)
head(data_alpha_Q2.2)
# Kruskal tests (non parametric anova) with Sample_time and Cross_conditions factors : Q2
krustal_data_chao1_Q2 = kruskal.test(Chao1 ~ St_Cc , data_alpha_Q2.2)
krustal_data_chao1_Q2
krustal_data_shannon_Q2 = kruskal.test(Shannon ~ St_Cc , data_alpha_Q2.2)
krustal_data_shannon_Q2
krustal_data_pielou_Q2 = kruskal.test(Pielou ~ St_Cc , data_alpha_Q2.2)
krustal_data_pielou_Q2
kruskal_data_alpha_Q2 <- matrix(nrow = 3 , ncol=3, byrow=TRUE)
colnames(kruskal_data_alpha_Q2) = c("Chi-square","Df","p-value")
rownames(kruskal_data_alpha_Q2) = c("Shannon","Chao1","Pielou")
kruskal_data_alpha_Q2
kruskal_data_alpha_Q2[,1] <- c(krustal_data_shannon_Q2$statistic,
krustal_data_chao1_Q2$statistic,
krustal_data_pielou_Q2$statistic)
kruskal_data_alpha_Q2[,2]<- c(krustal_data_shannon_Q2$parameter,
krustal_data_chao1_Q2$parameter,
krustal_data_pielou_Q2$parameter)
kruskal_data_alpha_Q2[,3]<- c(krustal_data_shannon_Q2$p.value,
krustal_data_chao1_Q2$p.value,
krustal_data_pielou_Q2$p.value)
kruskal_data_alpha_Q2
write.csv(kruskal_data_alpha_Q2, file.path("./2. Alpha_div results" , "Kruskal_data_alpha_Q2.csv"))
data_wilcox_shannon_Q2 = pairwise.wilcox.test(data_alpha_Q2.2$Shannon, data_alpha_Q2.2$St_Cc, p.adjust.method = "bonferroni")
data_wilcox_shannon_Q2
data_wilcox_shannon_Q2$p.value
data_wilcox_chao1_Q2 = pairwise.wilcox.test(data_alpha_Q2.2$Chao1, data_alpha_Q2.2$St_Cc, p.adjust.method = "bonferroni")
data_wilcox_chao1_Q2
data_wilcox_chao1_Q2$p.value
data_wilcox_pielou_Q2 = pairwise.wilcox.test(data_alpha_Q2.2$Pielou, data_alpha_Q2.2$St_Cc, p.adjust.method = "bonferroni")
data_wilcox_pielou_Q2
data_wilcox_pielou_Q2$p.value
data_wilcox_shannon_Q2_full = fullPTable(data_wilcox_shannon_Q2$p.value)
data_wilcox_shannon_Q2_full
indices_wilcox_shannon_Q2 = multcompLetters(data_wilcox_shannon_Q2_full,
compare="<",
threshold=0.05,
Letters=letters,
reversed = FALSE)
indices_wilcox_shannon_Q2$Letters
data_wilcox_shannon_Q2_full2 = cbind(data_wilcox_shannon_Q2_full, indices_wilcox_shannon_Q2$Letters )
data_wilcox_shannon_Q2_full2
write.csv(data_wilcox_shannon_Q2_full2, file.path("./2. Alpha_div results" , "Wilcox_data_shannon_Q2.csv"))
data_wilcox_chao1_Q2_full = fullPTable(data_wilcox_chao1_Q2$p.value)
data_wilcox_chao1_Q2_full
indices_wilcox_chao1_Q2 = multcompLetters(data_wilcox_chao1_Q2_full,
compare="<",
threshold=0.05,
Letters=letters,
reversed = FALSE)
indices_wilcox_chao1_Q2$Letters
data_wilcox_chao1_Q2_full2 = cbind(data_wilcox_chao1_Q2_full, indices_wilcox_chao1_Q2$Letters )
data_wilcox_chao1_Q2_full2
write.csv(data_wilcox_chao1_Q2_full2, file.path("./2. Alpha_div results" , "Wilcox_data_chao1_Q2.csv"))
data_wilcox_pielou_Q2_full = fullPTable(data_wilcox_pielou_Q2$p.value)
data_wilcox_pielou_Q2_full
indices_wilcox_pielou_Q2 = multcompLetters(data_wilcox_pielou_Q2_full,
compare="<",
threshold=0.05,
Letters=letters,
reversed = FALSE)
indices_wilcox_pielou_Q2$Letters
data_wilcox_pielou_Q2_full2 = cbind(data_wilcox_pielou_Q2_full, indices_wilcox_pielou_Q2$Letters )
data_wilcox_pielou_Q2_full2
write.csv(data_wilcox_pielou_Q2_full2, file.path("./2. Alpha_div results" , "Wilcox_data_pielou_Q2.csv"))
#### 12. BETA DIVERSITY : NMDS ############
physeq_compo = transform(physeq_subsampled, "compositional")
physeq_compo
nmds_Q1 = ordinate(physeq_compo, "NMDS", "bray")
nmds_Q1$points
nmds_Q1$stress
#write.csv(nmds$points , file = "nmds.points.t3.csv")
### Sample plot with phyloseq with all samples
palette_nmdsplot = c("pink",
"pink3",
"tan4",
"orchid",
"cornflowerblue" ,
"aquamarine3" ,
"green" ,
"yellow" ,
"darkorange" ,
"brown1")
palette_nmdsplot
data_nmds = plot_ordination(physeq_compo, nmds_Q1, type="samples", justDF = TRUE)
data_nmds
plot_nmds_Q1_samples = ggplot(data_nmds, aes(NMDS1, NMDS2))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + geom_point(aes(fill = Sampling_time, pch = Sample_type) , stroke = 1.5 , size = 7, alpha = 0.7, color = "black" , show.legend = T)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + scale_shape_manual(values = c(21, 25 ,22, 23))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + theme_bw(base_size = 20)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + guides(fill = guide_legend(override.aes = list(shape = 21)))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + scale_fill_manual(values = palette_nmdsplot)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + annotate("text", label="2D stress = 0.15", x=-3.4, y=1.6, size = 5)
plot_nmds_Q1_time_samples = plot_nmds_Q1_samples
plot_nmds_Q1_time_samples
ggsave(filename = "Plot_NMDS_Q1_time_samples.pdf",
plot = plot_nmds_Q1_time_samples,
device = "pdf" ,
width = 35 , height = 20, units = "cm",
path = "./3. Beta_div_results")
#same plot but to visualize the different cross-conditions
color_vector_1
plot_nmds_Q1_samples = ggplot(data_nmds, aes(NMDS1, NMDS2))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + geom_point(aes(fill = Cross_conditions, pch = Sample_type) , stroke = 1.5 , size = 7, alpha = 0.7, color = "black" , show.legend = T)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + scale_shape_manual(values = c(21, 25 ,22, 23))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + theme_bw(base_size = 20)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + guides(fill = guide_legend(override.aes = list(shape = 21)))
plot_nmds_Q1_samples = plot_nmds_Q1_samples + scale_fill_manual(values = color_vector_1)
plot_nmds_Q1_samples = plot_nmds_Q1_samples + annotate("text", label="2D stress = 0.16", x=-3.4, y=1.6, size = 5)
plot_nmds_Q1_crossco_samples = plot_nmds_Q1_samples
plot_nmds_Q1_crossco_samples
ggsave(filename = "Plot_NMDS_Q1_crossco_samples.pdf",
plot = plot_nmds_Q1_crossco_samples,
device = "pdf" ,
width = 35 , height = 20, units = "cm",
path = "./3. Beta_div_results")
# ASVs plots all samples (Q1) : is it necessary?
sum_taxa = taxa_sums(physeq_compo)
sum_taxa
select.taxa = plot_ordination(physeq_compo, nmds, type="taxa", justDF = TRUE)
select.taxa
select.taxa.2 = cbind(select.taxa, sum_taxa)
select.taxa.2
select.taxa.4 = subset(select.taxa.2, sum_taxa > 0.1 )
select.taxa.4
check_asv_names <- select.taxa.4[order(select.taxa.4$sum_taxa,decreasing=TRUE),]
head(check_asv_names)
head(select.taxa.4)
select.taxa.4$Phylum
levels(factor(select.taxa.4$Phylum))
colorpal_phylum = c( "Bacteria | Acidobacteriota" ="darkgoldenrod1",
"Bacteria | Actinobacteriota" ="darkslateblue",
"Bacteria | Armatimonadota" = "orchid4",
"Bacteria | Bacteroidota" = "yellow1",
"Bacteria | Bdellovibrionota" = "olivedrab1",
"Bacteria | Cyanobacteria" = "plum1",
"Bacteria | Gemmatimonadota" ="orangered1",
"Bacteria | Myxococcota" ="slategray2",
"Bacteria | Patescibacteria" = "darkblue",
"Bacteria | Planctomycetota" ="aquamarine4",
"Bacteria | Proteobacteria" ="dodgerblue",
"Bacteria | Spirochaetota" ="peachpuff",
"Bacteria | Verrucomicrobiota" = "brown")
plot_nmds_Q1_ASV = ggplot(select.taxa.4, aes(NMDS1, NMDS2))
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + geom_point(aes(fill = Phylum, size = sum_taxa), stroke = 1 , color = "black", alpha = 0.6, pch = 21) #+ facet_wrap(vars(Family))
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + scale_size_continuous(range = c(1, 15))
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + scale_fill_manual(values = colorpal_phylum)
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + theme_bw(base_size = 17) + theme(legend.position="right")
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + guides(fill = guide_legend(override.aes = list(size = 5)))
plot_nmds_Q1_ASV = plot_nmds_Q1_ASV + geom_point(data = data_nmds, aes(data_nmds$NMDS1, data_nmds$NMDS2), pch = 22 , size = 7, alpha = 0)
plot_nmds_Q1_ASV
ggsave(filename = "Plot_NMDS_Q1_ASV.pdf",
plot = plot_nmds_Q1_ASV,
device = "pdf" ,
width = 35 , height = 20, units = "cm",
path = "./3. Beta_div_results")
##### TEST STAT PERMANOVA et pairwise for Q1.1
metadata <- as(sample_data(physeq_compo), "data.frame")
metadata
data_distbeta = as.matrix(distance(physeq_compo, method="bray"))
data_distbeta
metadata$Sample_type
data_permnova_Q1.1 = adonis2(data_distbeta ~ Sample_type, data = metadata)
data_permnova_Q1.1
write.csv(as.data.frame(data_permnova_Q1.1),
file.path("./3. Beta_div_results" , "Permanova_Q1.1_sampletype.csv"))
data_pairwiseadonis_Q1.1 = pairwise.adonis(data_distbeta, metadata$Sample_type)
data_pairwiseadonis_Q1.1
write.csv(data_pairwiseadonis_Q1.1,
file.path("./3. Beta_div_results" , "Pairwise_adonis_Q1.1_sampletype.csv"))
# dataset for Q1.2 : cross condition * time comparison, so only cultivated juveniles sponges
metadata
physeq_subsampled
physeq_subsampled_cultivated = subset_samples(physeq_subsampled, Sample_type == "Cultivated sponge")
physeq_subsampled_cultivated
physeq_subsampled_cultivated_compo = transform(physeq_subsampled_cultivated, "compositional")
physeq_subsampled_cultivated_compo
metadata <- as(sample_data(physeq_subsampled_cultivated_compo), "data.frame")
metadata
head(metadata)
data_distbeta = as.matrix(distance(physeq_subsampled_cultivated_compo, method="bray"))
data_distbeta
data_permnova_Q1.2 = adonis2(data_distbeta ~ Sampling_time*Washing*Medium , data = metadata)
data_permnova_Q1.2
write.csv(as.data.frame(data_permnova_Q1.2),
file.path("./3. Beta_div_results" , "Permanova_Q1.2_sampletime_crossco.csv"))
data_pairwiseadonis_Q1.2 = pairwise.adonis(data_distbeta, metadata$Sampling_time)
data_pairwiseadonis_Q1.2
write.csv(data_pairwiseadonis_Q1.2,
file.path("./3. Beta_div_results" , "Pairwise_adonis_Q1.2_sampletime.csv"))
data_pairwiseadonis_Q1.2 = pairwise.adonis(data_distbeta, metadata$Cross_conditions)
data_pairwiseadonis_Q1.2
write.csv(data_pairwiseadonis_Q1.2,
file.path("./3. Beta_div_results" , "Pairwise_adonis_Q1.2_crossco.csv"))
### NMDS for Q2 : Sample plot with phyloseq by time
color_vector_1 = c("G+EM" = "lightcoral",
"G+EM_F-PB" = "plum3",
"G+EM_F+PB" = "sandybrown",
"G-EM" = "lightgreen",
"G-EM_F-PB" = "mediumaquamarine",
"G-EM_F+PB" = "yellow1")
# phyloseq compo object for all sampling times
physeq_compo_t0 = transform(physeq_subsampled_t0, "compositional")
physeq_compo_t1 = transform(physeq_subsampled_t1, "compositional")
physeq_compo_t2 = transform(physeq_subsampled_t2, "compositional")
physeq_compo_t3 = transform(physeq_subsampled_t3, "compositional")
physeq_compo_t4 = transform(physeq_subsampled_t4, "compositional")
physeq_compo_t5 = transform(physeq_subsampled_t5, "compositional")
physeq_compo_t6 = transform(physeq_subsampled_t6, "compositional")
#just for a test
physeq_compo_maternal_and_t0 = transform(physeq_subsampled_maternal_and_t0, "compositional")
physeq_compo_maternal_and_t0
nmds_t1 = ordinate(physeq_compo_t1, "NMDS", "bray")
nmds_t1$points
nmds_t1$stress
data_nmds_t1 = plot_ordination(physeq_compo_t1, nmds_t1, type="samples", justDF = TRUE)
data_nmds_t1
plot.nmds = ggplot(data_nmds_t1, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t1 = plot.nmds
nmds_t2 = ordinate(physeq_compo_t2, "NMDS", "bray")
nmds_t2$points
nmds_t2$stress
data_nmds_t2 = plot_ordination(physeq_compo_t2, nmds_t2, type="samples", justDF = TRUE)
data_nmds_t2
plot.nmds = ggplot(data_nmds_t2, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t2 = plot.nmds
nmds_t3 = ordinate(physeq_compo_t3, "NMDS", "bray")
nmds_t3$points
nmds_t3$stress
data_nmds_t3 = plot_ordination(physeq_compo_t3, nmds_t3, type="samples", justDF = TRUE)
data_nmds_t3
plot.nmds = ggplot(data_nmds_t3, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t3 = plot.nmds
nmds_t4 = ordinate(physeq_compo_t4, "NMDS", "bray")
nmds_t4$points
nmds_t4$stress
data_nmds_t4 = plot_ordination(physeq_compo_t4, nmds_t4, type="samples", justDF = TRUE)
data_nmds_t4
plot.nmds = ggplot(data_nmds_t4, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t4 = plot.nmds
nmds_t5 = ordinate(physeq_compo_t5, "NMDS", "bray")
nmds_t5$points
nmds_t5$stress
data_nmds_t5 = plot_ordination(physeq_compo_t5, nmds_t5, type="samples", justDF = TRUE)
data_nmds_t5
plot.nmds = ggplot(data_nmds_t5, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t5 = plot.nmds
nmds_t6 = ordinate(physeq_compo_t6, "NMDS", "bray")
nmds_t6$points
nmds_t6$stress
data_nmds_t6 = plot_ordination(physeq_compo_t6, nmds_t6, type="samples", justDF = TRUE)
data_nmds_t6
plot.nmds = ggplot(data_nmds_t6, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 21, stroke = 1.5 , alpha = 0.8, size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
legend_t1.6 = as_ggplot(get_legend(plot.nmds+ theme_bw(base_size = 11)))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())
plot.nmds
plot.nmds.t6 = plot.nmds
legend_t1.6
nmds_t0 = ordinate(physeq_compo_t0, "NMDS", "bray")
nmds_t0$points
nmds_t0$stress
data_nmds_t0 = plot_ordination(physeq_compo_t0, nmds_t0, type="samples", justDF = TRUE)
data_nmds_t0
plot.nmds = ggplot(data_nmds_t0, aes(NMDS1, NMDS2))
plot.nmds = plot.nmds + geom_point(aes(fill = Cross_conditions) , pch = 22, stroke = 1.5 , alpha = 0.8,size = 5, color = "black" , show.legend = T)
plot.nmds = plot.nmds + theme_bw(base_size = 12)
plot.nmds = plot.nmds + scale_fill_manual(values = color_vector_1)
#plot.nmds = plot.nmds + guides(fill = guide_legend(override.aes = list(shape = 21)))
#plot.nmds = plot.nmds + scale_fill_manual(values = palette.boxplot.2)
#plot.nmds = plot.nmds + annotate("text", label="2D stress = 0.129 ", x=-0.4, y=0.4, size = 6)
#plot.nmds = plot.nmds + geom_text_repel(aes(label = Samples_name))
legend_t0 = as_ggplot(get_legend(plot.nmds+ theme_bw(base_size = 11)))
plot.nmds = plot.nmds + theme(legend.position="none",
axis.title=element_blank())