-
Notifications
You must be signed in to change notification settings - Fork 0
/
Hunt_Creek_16S.R
2512 lines (2337 loc) · 158 KB
/
Hunt_Creek_16S.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
#Analysis of 16S microbial communities at Hunt Creek 2014-2016
#########################################
#Load packages
library(reshape)
library(ggplot2)
library(vegan)
library(plyr)
library(dplyr)
library(indicspecies)
library(doBy)
library(ggpubr)
library(lme4)
library(VennDiagram)
library(devtools)
library(gplots)
library(venn)
library(RColorBrewer)
library(gridExtra)
library(grid)
library(lattice)
library(gridExtra)
library(pastecs)
library(MASS)
library(extrafont)
font_import()
#Functions
as.numeric.factor <- function(x) {as.numeric(levels(x))[x]}
is.wholenumber <- function(x, tol = .Machine$double.eps^0.5) abs(x - round(x)) < tol
## Summarizes data.
## Gives count, mean, standard deviation, standard error of the mean, and confidence
## interval (default 95%).
## data: a data frame.
## measurevar: the name of a column that contains the variable to be summariezed
## groupvars: a vector containing names of columns that contain grouping variables
## na.rm: a boolean that indicates whether to ignore NA's
## conf.interval: the percent range of the confidence interval (default is 95%)
summarySE <- function(data=NULL, measurevar, groupvars=NULL, na.rm=FALSE, conf.interval=.95) {
library(doBy)
# New version of length which can handle NA's: if na.rm==T, don't count them
length2 <- function (x, na.rm=FALSE) {
if (na.rm) sum(!is.na(x))
else length(x)
}
# Collapse the data
formula <- as.formula(paste(measurevar, paste(groupvars, collapse=" + "), sep=" ~ "))
datac <- summaryBy(formula, data=data, FUN=c(length2,mean,sd), na.rm=na.rm)
# Rename columns
names(datac)[ names(datac) == paste(measurevar, ".mean", sep="") ] <- measurevar
names(datac)[ names(datac) == paste(measurevar, ".sd", sep="") ] <- "sd"
names(datac)[ names(datac) == paste(measurevar, ".length2", sep="") ] <- "N"
datac$se <- datac$sd / sqrt(datac$N) # Calculate standard error of the mean
# Confidence interval multiplier for standard error
# Calculate t-statistic for confidence interval:
# e.g., if conf.interval is .95, use .975 (above/below), and use df=N-1
ciMult <- qt(conf.interval/2 + .5, datac$N-1)
datac$ci <- datac$se * ciMult
return(datac)
}
#color vectors
BFColor<-"#66c2a5"
two_col_vec <- c("black", "bisque3")
two_col_vec_reach<-c("skyblue3", "tomato3")
two_col_vec_taxa<-c("#33a02c", "#1f78b4")
two_col_vec_bfcar<-c("#66c2a5", "#fc8d62")
two_col_vec_baecar<-c("#8da0cb","#fc8d62")
two_col_vec_carsi<-c("#fc8d62","#666666")
three_col_vec<- c("#1b9e77", "#d95f02", "#fc8d62")
three_col_vec_bfcari<-c("#8da0cb","#66c2a5","#fc8d62")
three_col_vec_conttreatcar<-c("#984ea3","#1b9e77","#fc8d62")
three_col_vec_CBaeS<-c("#fc8d62","#8da0cb","#666666")
four_col_vec<-c("#7fc97f", "#beaed4", "#fdc086", "#ffff99")
four_col_vec_BfCBS<-c("#66c2a5","#fc8d62","#8da0cb","#666666")
four_col_vec_BBfCS<-c("#8da0cb","#66c2a5","#fc8d62","#666666")
four_col_vec_CBfBS<-c("#fc8d62","#66c2a5","#8da0cb","#666666")
four_col_vec_y1conttreatcar<-c("#e6ab02","#984ea3","#1b9e77","#fc8d62")
four_col_vec_CBf1SBf2SBf2C<-c("#fc8d62","#034e7b","#66c2a5","#f7fcb9")
four_col_vec_CBa1SBa2SBa2C<-c("#fc8d62","#4a1486","#8da0cb","#005824")
four_col_vec_CS1SS2SS2C<-c("#fc8d62","#386cb0","#666666","#ffff99")
five_col_vec<- c("#7fc97f", "#beaed4", "#fdc086", "#ffff99", "#386cb0")
five_col_vec_babchs<-c("#66c2a5","#fc8d62","#8da0cb","#f0027f","#666666")
five_col_vec_CBBaSH<-c("#fc8d62","#66c2a5","#8da0cb","#666666","#f0027f")
six_col_vec<- c("#e41a1c", "#377eb8", "green", "#984ea3", "#ff7f00", "#ffff33")
six_col_vec_cont<-c("#fee5d9", "#fcbba1", "#fc9272", "#fb6a4a", "#de2d26", "#a50f15")
seven_col_vec<-c("#1b9e77","#d95f02","#7570b3","#e7298a","#66a61e","#e6ab02","#a6761d")
blue_scale_white_zero<-brewer.pal(9, "Blues")
blue_scale_white_zero[1]<-"white"
#First work with rarefication plots
#Shannon diversity
HC_Shannon_q2<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_shannon_q2.txt", sep="\t", header=T)
rownames(HC_Shannon_q2)<-HC_Shannon_q2[,1]
HC_Shannon_q2[,1]<-NULL
HC_Shannon<-data.frame(t(HC_Shannon_q2))
HC_Shannon$iteration<-NULL
str(HC_Shannon)
HC_Sh_m<-melt(HC_Shannon, id.vars="sequences.per.sample")
any(is.na(HC_Sh_m))
HC_Sh_c_m<-cast(HC_Sh_m, variable ~ sequences.per.sample, fun.aggregate=mean, na.omit=TRUE)
HC_Sh_c_m$Calculation<-rep("mean",175)
HC_Sh_c_var<-cast(HC_Sh_m, variable ~ sequences.per.sample, fun.aggregate=var)
HC_Sh_c_var$Calculation<-rep("variance",175)
HC_Sh_c_m_var<-rbind(HC_Sh_c_m,HC_Sh_c_var)
names(HC_Sh_c_m_var)[names(HC_Sh_c_m_var)=="variable"] <- "SampleID"
HC_Sh_c_m_var$Calculation<-as.factor(HC_Sh_c_m_var$Calculation)
HC_Sh_c_m_var<-as.data.frame(HC_Sh_c_m_var)
HC_Sh_c_m_var_m<-melt(HC_Sh_c_m_var, id.vars=c("Calculation","SampleID"))
HC_Sh_c_m_var_c<-cast(HC_Sh_c_m_var_m, variable + SampleID ~ Calculation)
#Get metadata through mapping file
Hunt_Creek_16S_map <- read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/Hunt_Creek_Map_Filtered_R.txt", header=T)
#Merge metadata onto rarefication file
HC_Sh_map <-merge(Hunt_Creek_16S_map, HC_Sh_c_m_var_c, by="SampleID")
names(HC_Sh_map)[names(HC_Sh_map)=="variable"] <- "Sequences_per_sample"
any(is.na(HC_Sh_map))
HC_Sh_map$Sequences_per_sample<-as.numeric(as.character(HC_Sh_map$Sequences_per_sample))
HC_Sh_map$Source<-factor(revalue(HC_Sh_map$Source, c("Stegopterna"="S. mutata", "Baetis"="B. brunneicolor", "Heptagenia"="H. flavescens")), levels =c("Biofilm", "Carcass", "B. brunneicolor", "H. flavescens", "S. mutata"))
HC_Sh_map_sum_m <- summarySE(HC_Sh_map, measurevar=c("mean"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_Sh_map_sum_v <- summarySE(HC_Sh_map, measurevar=c("variance"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_Sh_map_sum_v$StandDev<-sqrt(HC_Sh_map_sum_v$variance)
HC_Sh_map_sum_v$StandEr<-HC_Sh_map_sum_v$StandDev/sqrt(HC_Sh_map_sum_v$N)
HC_Sh_sum_m_sd<-merge(HC_Sh_map_sum_m,HC_Sh_map_sum_v, by=0)
#make rarefication plots
ggplot(HC_Sh_sum_m_sd, aes(x=Sequences_per_sample.x, y=mean, colour=Source.x)) +
geom_errorbar(aes(ymin=mean-StandEr, ymax=mean+StandEr), width=1) +
geom_line(size=1.5) +
geom_point(size=1.5) +
xlab("Number of reads sampled") +
ylab("Mean Shannon H' diversity") +
labs(colour = "Source") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=five_col_vec_babchs)
#Faith's diversity
HC_Faith_q2<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_Faith_q2.txt", sep="\t", header=T)
rownames(HC_Faith_q2)<-HC_Faith_q2[,1]
HC_Faith_q2[,1]<-NULL
HC_Faith<-data.frame(t(HC_Faith_q2))
HC_Faith$iteration<-NULL
str(HC_Faith)
HC_F_m<-melt(HC_Faith, id.vars="sequences.per.sample")
HC_F_c_m<-cast(HC_F_m, variable ~ sequences.per.sample, fun.aggregate=mean)
HC_F_c_m$Calculation<-rep("mean",175)
HC_F_c_var<-cast(HC_F_m, variable ~ sequences.per.sample, fun.aggregate=var)
HC_F_c_var$Calculation<-rep("variance",175)
HC_F_c_m_var<-rbind(HC_F_c_m,HC_F_c_var)
names(HC_F_c_m_var)[names(HC_F_c_m_var)=="variable"] <- "SampleID"
HC_F_c_m_var$Calculation<-as.factor(HC_F_c_m_var$Calculation)
HC_F_c_m_var<-as.data.frame(HC_F_c_m_var)
HC_F_c_m_var_m<-melt(HC_F_c_m_var, id.vars=c("Calculation","SampleID"))
HC_F_c_m_var_c<-cast(HC_F_c_m_var_m, variable + SampleID ~ Calculation)
#Merge metadata onto rarefication file
HC_F_map <-merge(Hunt_Creek_16S_map, HC_F_c_m_var_c, by="SampleID")
names(HC_F_map)[names(HC_F_map)=="variable"] <- "Sequences_per_sample"
HC_F_map$Sequences_per_sample<-as.numeric(as.character(HC_F_map$Sequences_per_sample))
HC_F_map$Source<-factor(revalue(HC_F_map$Source, c("Stegopterna"="S. mutata", "Baetis"="B. brunneicolor", "Heptagenia"="H. flavescens")), levels =c("Biofilm", "Carcass", "B. brunneicolor", "H. flavescens", "S. mutata"))
HC_F_map_sum_m <- summarySE(HC_F_map, measurevar=c("mean"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_F_map_sum_v <- summarySE(HC_F_map, measurevar=c("variance"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_F_map_sum_v$StandDev<-sqrt(HC_F_map_sum_v$variance)
HC_F_map_sum_v$StandEr<-HC_F_map_sum_v$StandDev/sqrt(HC_F_map_sum_v$N)
HC_F_sum_m_sd<-merge(HC_F_map_sum_m,HC_F_map_sum_v, by=0)
#make rarefication plots
ggplot(HC_F_sum_m_sd, aes(x=Sequences_per_sample.x, y=mean, colour=Source.x)) +
geom_errorbar(aes(ymin=mean-StandEr, ymax=mean+StandEr), width=1) +
geom_line(size=1.5) +
geom_point(size=1.5) +
xlab("Number of reads sampled") +
ylab("Mean Faith's phylogenetic diversity") +
labs(colour = "Source") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=five_col_vec_babchs)
#Observed OTUs
HC_Ob_q2<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_Obs_q2.txt", sep="\t", header=T)
rownames(HC_Ob_q2)<-HC_Ob_q2[,1]
HC_Ob_q2[,1]<-NULL
HC_Ob<-data.frame(t(HC_Ob_q2))
HC_Ob$iteration<-NULL
str(HC_Ob)
HC_o_m<-melt(HC_Ob, id.vars="sequences.per.sample")
HC_o_c_m<-cast(HC_o_m, variable ~ sequences.per.sample, fun.aggregate=mean)
HC_o_c_m$Calculation<-rep("mean",175)
HC_o_c_var<-cast(HC_o_m, variable ~ sequences.per.sample, fun.aggregate=var)
HC_o_c_var$Calculation<-rep("variance",175)
HC_o_c_m_var<-rbind(HC_o_c_m,HC_o_c_var)
names(HC_o_c_m_var)[names(HC_o_c_m_var)=="variable"] <- "SampleID"
HC_o_c_m_var$Calculation<-as.factor(HC_o_c_m_var$Calculation)
HC_o_c_m_var<-as.data.frame(HC_o_c_m_var)
HC_o_c_m_var_m<-melt(HC_o_c_m_var, id.vars=c("Calculation","SampleID"))
HC_o_c_m_var_c<-cast(HC_o_c_m_var_m, variable + SampleID ~ Calculation)
#Merge metadata onto rarefication file
HC_o_map <-merge(Hunt_Creek_16S_map, HC_o_c_m_var_c, by="SampleID")
names(HC_o_map)[names(HC_o_map)=="variable"] <- "Sequences_per_sample"
HC_o_map$Sequences_per_sample<-as.numeric(as.character(HC_o_map$Sequences_per_sample))
HC_o_map$Source<-factor(revalue(HC_o_map$Source, c("Stegopterna"="S. mutata", "Baetis"="B. brunneicolor", "Heptagenia"="H. flavescens")), levels =c("Biofilm", "Carcass", "B. brunneicolor", "H. flavescens", "S. mutata"))
HC_o_map_sum_m <- summarySE(HC_o_map, measurevar=c("mean"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_o_map_sum_v <- summarySE(HC_o_map, measurevar=c("variance"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_o_map_sum_v$StandDev<-sqrt(HC_o_map_sum_v$variance)
HC_o_map_sum_v$StandEr<-HC_o_map_sum_v$StandDev/sqrt(HC_o_map_sum_v$N)
HC_o_sum_m_sd<-merge(HC_o_map_sum_m,HC_o_map_sum_v, by=0)
#make rarefication plots
ggplot(HC_o_sum_m_sd, aes(x=Sequences_per_sample.x, y=mean, colour=Source.x)) +
geom_errorbar(aes(ymin=mean-StandEr, ymax=mean+StandEr), width=1) +
geom_line(size=1.5) +
geom_point(size=1.5) +
xlab("Number of reads sampled") +
ylab("Mean observed OTUs") +
labs(colour = "Source") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=five_col_vec_babchs)
#Chao1
HC_Ch_q2<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_Chao1_q2.txt", sep="\t", header=T)
rownames(HC_Ch_q2)<-HC_Ch_q2[,1]
HC_Ch_q2[,1]<-NULL
HC_Ch<-data.frame(t(HC_Ch_q2))
HC_Ch$iteration<-NULL
str(HC_Ch)
HC_c_m<-melt(HC_Ch, id.vars="sequences.per.sample")
HC_c_c_m<-cast(HC_c_m, variable ~ sequences.per.sample, fun.aggregate=mean)
HC_c_c_m$Calculation<-rep("mean",175)
HC_c_c_var<-cast(HC_c_m, variable ~ sequences.per.sample, fun.aggregate=var)
HC_c_c_var$Calculation<-rep("variance",175)
HC_c_c_m_var<-rbind(HC_c_c_m,HC_c_c_var)
names(HC_c_c_m_var)[names(HC_c_c_m_var)=="variable"] <- "SampleID"
HC_c_c_m_var$Calculation<-as.factor(HC_c_c_m_var$Calculation)
HC_c_c_m_var<-as.data.frame(HC_c_c_m_var)
HC_c_c_m_var_m<-melt(HC_c_c_m_var, id.vars=c("Calculation","SampleID"))
HC_c_c_m_var_c<-cast(HC_c_c_m_var_m, variable + SampleID ~ Calculation)
#Merge metadata onto rarefication file
HC_c_map <-merge(Hunt_Creek_16S_map, HC_c_c_m_var_c, by="SampleID")
names(HC_c_map)[names(HC_c_map)=="variable"] <- "Sequences_per_sample"
HC_c_map$Sequences_per_sample<-as.numeric(as.character(HC_c_map$Sequences_per_sample))
HC_c_map$Source<-factor(revalue(HC_c_map$Source, c("Stegopterna"="S. mutata", "Baetis"="B. brunneicolor", "Heptagenia"="H. flavescens")), levels =c("Biofilm", "Carcass", "B. brunneicolor", "H. flavescens", "S. mutata"))
HC_c_map_sum_m <- summarySE(HC_c_map, measurevar=c("mean"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_c_map_sum_v <- summarySE(HC_c_map, measurevar=c("variance"), groupvars=c("Sequences_per_sample","Source"), na.rm=TRUE)
HC_c_map_sum_v$StandDev<-sqrt(HC_c_map_sum_v$variance)
HC_c_map_sum_v$StandEr<-HC_c_map_sum_v$StandDev/sqrt(HC_c_map_sum_v$N)
HC_c_sum_m_sd<-merge(HC_c_map_sum_m,HC_c_map_sum_v, by=0)
#make rarefication plots
ggplot(HC_c_sum_m_sd, aes(x=Sequences_per_sample.x, y=mean, colour=Source.x)) +
geom_errorbar(aes(ymin=mean-StandEr, ymax=mean+StandEr), width=1) +
geom_line(size=1.5) +
geom_point(size=1.5) +
xlab("Number of reads sampled") +
ylab("Mean Chao1 estimator") +
labs(colour = "Source") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=20),axis.title.y=element_text(size=20),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=five_col_vec_babchs)
#####Created facetted graph for manuscript
HC_Sh_sum_m_sd$alpha<-rep("A. Shannon Diveristy",50)
HC_F_sum_m_sd$alpha<-rep("B. Faith's Phylogenetic Diveristy",50)
HC_o_sum_m_sd$alpha<-rep("C. Observed OTUs",50)
HC_c_sum_m_sd$alpha<-rep("D. Chao1 Estimator",50)
HC_sum_m_sd<-rbind(HC_Sh_sum_m_sd,HC_F_sum_m_sd,HC_o_sum_m_sd,HC_c_sum_m_sd)
ggplot(HC_sum_m_sd, aes(x=Sequences_per_sample.x, y=mean, colour=Source.x)) +
geom_errorbar(aes(ymin=mean-StandEr, ymax=mean+StandEr), width=1) +
geom_line(size=1.5) +
geom_point(size=1.5) +
xlab("Number of Reads Sampled") +
ylab("Mean Alpha Diversity Value (+/- SEM)") +
labs(colour = "Source") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(family="Times New Roman", size=36, margin=margin(t=10,r=0,b=0,l=0)),
axis.title.y=element_text(family="Times New Roman", size=36, margin = margin(t = 0, r = 10, b = 0, l = 0)),
axis.text.x=element_text(family="Times New Roman", size=18),
axis.text.y = element_text(family="Times New Roman", size=18),
legend.position = 0,
strip.text.x = element_text(family="Times New Roman", face="bold", size = 24)) +
scale_color_manual(values=five_col_vec_CBBaSH,
limits=c("Carcass","Biofilm","B. brunneicolor","S. mutata","H. flavescens"),
labels=c("Carcass","Biofilm",expression(paste(italic('B. brunneicolor'))),expression(paste(italic('S. mutata'))),expression(paste(italic('H. flavescens'))))) +
facet_wrap(~alpha,scales="free_y")
#####################################
#Upload data tables generated in QIIME and manipulate to make "r friendly"
#####################################
#Get 16S OTU table
Hunt_Creek_16S<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_otu_table_q2.txt", sep="\t", header = T)
#Format data frame so the denovo is row name
row.names(Hunt_Creek_16S)<-Hunt_Creek_16S[,1]
#Delete otu id column, now that otu id is row name
Hunt_Creek_16S$ID<-NULL
#transpose
HC_16S_OTU_t<-t(Hunt_Creek_16S)
HC_16S_OTU_t<-data.frame(HC_16S_OTU_t, check.names = FALSE)
#Merge metadata onto data table
Hunt_Creek_16S_map_r<-Hunt_Creek_16S_map
row.names(Hunt_Creek_16S_map_r)<-Hunt_Creek_16S_map_r[,1]
HC_16S_OTU_map <-merge(Hunt_Creek_16S_map_r, HC_16S_OTU_t, by=0)
str(HC_16S_OTU_map)
HC_16S_OTU_t<-HC_16S_OTU_map[,18:ncol(HC_16S_OTU_map)]
#UNI-Do the following if you have unifrac distances ready
#UNI-Upload weighted unifrac distance matrix and remove samples with error
Hunt_Creek_16S_uni <- read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/weighted_unifrac_HC_q2.txt", header=T)
#UNI-Add metadata to unifrac table
Hunt_Creek_16S_uni_map <-merge(Hunt_Creek_16S_map_r, Hunt_Creek_16S_uni, by=0)
row.names(Hunt_Creek_16S_uni_map)<-Hunt_Creek_16S_uni_map[,1]
Hunt_Creek_16S_uni_map<-Hunt_Creek_16S_uni_map[,-c(1)]
Hunt_Creek_16S_uni<-Hunt_Creek_16S_uni_map[17:ncol(Hunt_Creek_16S_uni_map)]
H_C_16S_uni_com_samples<-as.vector(rownames(Hunt_Creek_16S_uni))
#UNI-use output of names to subset columns into rows to make square matrix
Hunt_Creek_16S_uni<-as.matrix(Hunt_Creek_16S_uni)
Hunt_Creek_16S_uni<-subset(Hunt_Creek_16S_uni, select=c(H_C_16S_uni_com_samples))
str(Hunt_Creek_16S_uni)
#Create overall environmental data matrix for community analysis with counts
HC_16S_env<-Hunt_Creek_16S_map
row.names(HC_16S_env)<-HC_16S_env[,1]
HC_16S_env<-HC_16S_env[,-c(1)]
#UNI-Create overall environmental data matrix for community analysis with uni distances
HC_16S_uni_env<-Hunt_Creek_16S_uni_map
row.names(HC_16S_uni_env)<-HC_16S_uni_env[,1]
HC_16S_uni_env<-HC_16S_uni_env[,1:16]
HC_16S_uni_env$Total_Biofilm_Growth_PostCarcass<-as.numeric(HC_16S_uni_env$Total_Biofilm_Growth_PostCarcass)
HC_16S_uni_env$Year<-as.factor(HC_16S_uni_env$Year)
#Analysis of all 16S community data
#############################################
#Overall permanova
adonis(HC_16S_OTU_t ~ Reach*Year*Source*Total_Biofilm_Growth_PostCarcass, data=HC_16S_env, method="jaccard", permutations=999)
#Significant factors are Reach, Year, Source, time, Reach:Source, Year:Source, Year:time, source:time, year:source:time and reach:year:source:time
#UNI-Overall permanova with unifrac distances
adonis(as.dist(Hunt_Creek_16S_uni) ~ Reach*Source*Total_Biofilm_Growth_PostCarcass*Year, data=HC_16S_uni_env, permutations=999)
#Significant factors are reach, source, time, year, reach:source, reach:time, source:time, reach:year, Source:year, Time:Year, reach:source:time, Source:time:Year
#Source has the largest impact on community structuring, so do analysis for each source individually
#UNI-Create carcass unifrac distance table with metadata
H_C_16S_uni_map_car<-subset(Hunt_Creek_16S_uni_map, Source=="Carcass")
H_C_16S_uni_car_env<-H_C_16S_uni_map_car[,1:16]
HC_16S_uni_car_Year<-as.factor(H_C_16S_uni_car_env$Year)
HC_16S_uni_car_Year<-gsub("1", "Year 1", HC_16S_uni_car_Year)
HC_16S_uni_car_Year<-gsub("2", "Year 2", HC_16S_uni_car_Year)
HC_16S_uni_car_Year<-as.factor(HC_16S_uni_car_Year)
H_C_16S_uni_car_com<-H_C_16S_uni_map_car[,17:ncol(H_C_16S_uni_map_car)]
H_C_16S_uni_car_com_samples<-as.vector(rownames(H_C_16S_uni_car_com))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_car_com<-as.matrix(H_C_16S_uni_car_com)
H_C_16S_uni_car_com<-subset(H_C_16S_uni_car_com, select=c(H_C_16S_uni_car_com_samples))
str(H_C_16S_uni_car_com)
#Create carcass otu table with metadata
HC_16S_OTU_map_car<-subset(HC_16S_OTU_map, Source=="Carcass")
#How many OTUs and gene amplicon sequences for carcasses?
#Delete OTUs with no observations
cols_to_drop_car = c(rep(TRUE, 17), colSums(HC_16S_OTU_map_car[,18:ncol(HC_16S_OTU_map_car)]) > 0)
HC_16S_OTU_map_car<-HC_16S_OTU_map_car[,cols_to_drop_car]
#There are 2819 OTUs (number of variables - 17 metadata variables)
sum(colSums(HC_16S_OTU_map_car[,18:ncol(HC_16S_OTU_map_car)]))
#37,500 total sequence reads
#Subset into environmental and community data frames
HC_16S_OTU_car_env<-HC_16S_OTU_map_car[,1:17]
HC_16S_OTU_car_com<-HC_16S_OTU_map_car[,18:ncol(HC_16S_OTU_map_car)]
#Year 1
HC_16S_OTU_map_car_Y1<-subset(HC_16S_OTU_map_car, Year=="1")
#Delete OTUs with no observations
cols_to_drop_car_Y1 = c(rep(TRUE, 17), colSums(HC_16S_OTU_map_car_Y1[,18:ncol(HC_16S_OTU_map_car_Y1)]) > 0)
HC_16S_OTU_map_car_Y1<-HC_16S_OTU_map_car_Y1[,cols_to_drop_car_Y1]
#There are 686 OTUs in year 1(number of variables - 17 metadata variables)
sum(colSums(HC_16S_OTU_map_car_Y1[,18:ncol(HC_16S_OTU_map_car_Y1)]))
#12,500 total sequence reads
#Year 2
HC_16S_OTU_map_car_Y2<-subset(HC_16S_OTU_map_car, Year=="2")
#Delete OTUs with no observations
cols_to_drop_car_Y2 = c(rep(TRUE, 17), colSums(HC_16S_OTU_map_car_Y2[,18:ncol(HC_16S_OTU_map_car_Y2)]) > 0)
HC_16S_OTU_map_car_Y2<-HC_16S_OTU_map_car_Y2[,cols_to_drop_car_Y2]
#There are 2196 OTUs in year 2(number of variables - 17 metadata variables)
sum(colSums(HC_16S_OTU_map_car_Y2[,18:ncol(HC_16S_OTU_map_car_Y2)]))
#25,000 total sequence reads
#UNI-carcass permanova with unifrac distances
adonis(as.dist(H_C_16S_uni_car_com) ~ Year, data=H_C_16S_uni_car_env, permutations=99999)
#Year is significant p=0.00027, R2 = .32
#NMDS carcass
HC_NMDS_uni_c<-metaMDS(as.dist(H_C_16S_uni_car_com), permutations=99999)
HC_NMDS_uni_c
#stress = 0.07
stressplot(HC_NMDS_uni_c)
ordiplot(HC_NMDS_uni_c, type="n")
with(HC_NMDS_uni_c, points(HC_NMDS_uni_c, display="sites", col = "black", pch=c(15,17)[HC_16S_uni_car_Year]))
with(HC_NMDS_uni_c, legend("topleft", legend=levels(HC_16S_uni_car_Year), bty="n", col="black",pch=c(15,17)))
with(HC_NMDS_uni_c, ordiellipse(HC_NMDS_uni_c, HC_16S_uni_car_Year, kind="se", conf=0.95, lwd=2, col="black", show.groups = "Year 1"))
with(HC_NMDS_uni_c, ordiellipse(HC_NMDS_uni_c, HC_16S_uni_car_Year, kind="se", conf=0.95, lwd=2, col="black", show.groups = "Year 2"))
with(HC_NMDS_uni_c, legend("topright", legend="2D Stress: 0.07", bty="n"))
#upload phyla level info and run indicator analysis for carcass/generate box plots
#Upload phyla level files for each run
Hunt_Creek_16S_P<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_Phyla_q2.txt", sep="\t", header = T)
#Clasify as data.frame
Hunt_Creek_16S_P<-data.frame(Hunt_Creek_16S_P)
#Format data frame so the taxonomy is row name
row.names(Hunt_Creek_16S_P)<-Hunt_Creek_16S_P[,1]
#Delete taxonomy column
Hunt_Creek_16S_P$ID<-NULL
#transpose
HC_16S_P_t<-t(Hunt_Creek_16S_P)
HC_16S_P_t<-data.frame(HC_16S_P_t)
str(HC_16S_P_t)
names(HC_16S_P_t)
#Merge metadata onto data table
HC_16S_P_map <-merge(Hunt_Creek_16S_map_r, HC_16S_P_t, by=0)
str(HC_16S_P_map)
head(sort(colSums(HC_16S_P_map[18:ncol(HC_16S_P_map)]),decreasing=TRUE))
#proteobacteria most abundant with 179270
sum((colSums(HC_16S_P_map[18:ncol(HC_16S_P_map)])))
#Total number of reachs = 415000
#subset phyla info into carcass
HC_16S_P_map_car<-subset(HC_16S_P_map, Source=="Carcass")
#determine how many phyla
cols_to_drop_car_P = c(rep(TRUE, 17), colSums(HC_16S_P_map_car[,18:ncol(HC_16S_P_map_car)]) > 0)
HC_16S_P_map_car<-HC_16S_P_map_car[,cols_to_drop_car_P]
HC_16S_P_map_car$k__Bacteria.__<-NULL
HC_16S_P_map_car$k__Bacteria.p__<-NULL
#29 total phyla (number of variables - 17 metadata columns)
HC_16S_P_map_car[,1:17]<-sapply(HC_16S_P_map_car[,1:17], as.factor)
HC_16S_P_map_car_env<-HC_16S_P_map_car[,1:17]
HC_16S_P_map_car_com<-HC_16S_P_map_car[,18:ncol(HC_16S_P_map_car)]
#find most abundant phyla
head(sort(colSums(HC_16S_P_map_car_com),decreasing=TRUE))
#Proteobacteria most abundant 20806
#Indicator analysis to see what phyla are driving this change
HC_p_car_indic<-signassoc(HC_16S_P_map_car_com, cluster=HC_16S_P_map_car_env$Year, mode=0, alternative = "two.sided",control = how(nperm=999))
HC_p_car_indic_sig<-subset(HC_p_car_indic, psidak<=0.05)
#3 phyla significant: k__Bacteria.p__Acidobacteria, k__Bacteria.p__Actinobacteria, k__Bacteria.p__Spirochaetes
#upload family level info and run indicator analysis for carcass
#Upload family level files for each run
Hunt_Creek_16S_F<-read.table("~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/HC_Family_q2.txt", sep="\t", header = T)
#Clasify as data.frame
Hunt_Creek_16S_F<-data.frame(Hunt_Creek_16S_F)
#Format data frame so the taxonomy is row name
row.names(Hunt_Creek_16S_F)<-Hunt_Creek_16S_F[,1]
#Delete taxonomy column
Hunt_Creek_16S_F$ID<-NULL
#transpose
HC_16S_F_t<-t(Hunt_Creek_16S_F)
HC_16S_F_t<-data.frame(HC_16S_F_t)
str(HC_16S_F_t)
names(HC_16S_F_t)
#Merge metadata onto data table
HC_16S_F_map <-merge(Hunt_Creek_16S_map_r, HC_16S_F_t, by=0)
#subset family info into carcass
HC_16S_F_map_car<-subset(HC_16S_F_map, Source=="Carcass")
HC_16S_F_map_car$k__Bacteria.__.__.__.__<-NULL
HC_16S_F_map_car$k__Bacteria.p__.c__.o__.f__<-NULL
#determine how many families
cols_to_drop_car_F = c(rep(TRUE, 17), colSums(HC_16S_F_map_car[,18:ncol(HC_16S_F_map_car)]) > 0)
HC_16S_F_map_car<-HC_16S_F_map_car[,cols_to_drop_car_F]
#349 (number of variables - 17 metadata columns)
HC_16S_F_map_car[,1:17]<-sapply(HC_16S_F_map_car[,1:17], as.factor)
HC_16S_F_map_car_env<-HC_16S_F_map_car[,1:17]
HC_16S_F_map_car_com<-HC_16S_F_map_car[,18:ncol(HC_16S_F_map_car)]
#find most abundant family
head(sort(colSums(HC_16S_F_map_car_com),decreasing=TRUE))
#k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Pseudomonadales.f__Moraxellaceae most abundant 5837
sum(HC_16S_F_map_car_com)
stat.desc(HC_16S_F_map_car_com$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Pseudomonadales.f__Moraxellaceae)
#Indicator analysis to see what families are driving this change
HC_f_car_indic<-signassoc(HC_16S_F_map_car_com, cluster=HC_16S_F_map_car_env$Year, mode=0, alternative = "two.sided",control = how(nperm=9999))
HC_f_car_indic_sig<-subset(HC_f_car_indic, psidak<=0.05)
#20 significant families
write.table(HC_f_car_indic_sig, "~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/16SCarIndSigQ2.txt", sep="\t")
#figure out which of the most significant are most abundant and or what abundance differences there are between years.
HC_16S_F_map_car_agg<-aggregate(HC_16S_F_map_car[18:ncol(HC_16S_F_map_car)], by=list(Year=HC_16S_F_map_car$Year), FUN=sum)
HC_16S_F_map_car_agg$k__Bacteria.p__Bacteroidetes.c__Bacteroidia.o__Bacteroidales.f__
#357 found first year, 0 in the second
HC_16S_F_map_car_agg$k__Bacteria.p__Cyanobacteria.c__4C0d.2.o__YS2.f__
#303 first year, 0 second
HC_16S_F_map_car_agg$k__Bacteria.p__Firmicutes.c__Clostridia.o__Clostridiales.f__Ruminococcaceae
#448 first year, 0 second
HC_16S_F_map_car_agg$k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae
#181 first year, 0 second
HC_16S_F_map_car_agg$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Aeromonadales.f__Succinivibrionaceae
#64 first year, 0 second
HC_16S_F_map_car_agg$k__Bacteria.p__Spirochaetes.c__Spirochaetes.o__Spirochaetales.f__Spirochaetaceae
#175 first year, 0 second
#only include indicator taxa in abundances
HC_f_car_indic_abund<-subset(HC_16S_F_map_car_agg, select=c(rownames(HC_f_car_indic_sig)))
tail(sort(colSums(HC_f_car_indic_abund)))
#most abundant is k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae
HC_16S_F_map_car_agg$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae
#2136 first year, 1574 second year
HC_16S_F_map_car_y1<-subset(HC_16S_F_map_car, Year=="1")
HC_16S_F_map_car_y2<-subset(HC_16S_F_map_car, Year=="2")
stat.desc(HC_16S_F_map_car_y1$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae)
stat.desc(HC_16S_F_map_car_y2$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae)
#############################################
#Separate data based on year of study (1 or 2)
###############################################
#UNI-Create Year 1 unifrac distance table with metadata
H_C_16S_uni_map_Y1<-subset(Hunt_Creek_16S_uni_map, Year=="1")
#Subset into environmental and community data frames
H_C_16S_uni_map_Y1_env<-H_C_16S_uni_map_Y1[,1:16]
H_C_16S_uni_map_Y1_com<-H_C_16S_uni_map_Y1[,17:ncol(H_C_16S_uni_map_Y1)]
H_C_16S_uni_Y1_com_samples<-as.vector(rownames(H_C_16S_uni_map_Y1_com))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_map_Y1_com<-as.matrix(H_C_16S_uni_map_Y1_com)
str(H_C_16S_uni_map_Y1_com)
H_C_16S_uni_map_Y1_com<-subset(H_C_16S_uni_map_Y1_com, select=c(H_C_16S_uni_Y1_com_samples))
H_C_16S_uni_map_Y1_Env<-as.factor(H_C_16S_uni_map_Y1_env$Env)
#UNI-Create Year 2 unifrac distance table with metadata
H_C_16S_uni_map_Y2<-subset(Hunt_Creek_16S_uni_map, Year=="2")
#Subset into environmental and community data frames
H_C_16S_uni_map_Y2_env<-H_C_16S_uni_map_Y2[,1:16]
H_C_16S_uni_map_Y2_com<-H_C_16S_uni_map_Y2[,17:ncol(H_C_16S_uni_map_Y2)]
H_C_16S_uni_Y2_com_samples<-as.vector(rownames(H_C_16S_uni_map_Y2_com))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_map_Y2_com<-as.matrix(H_C_16S_uni_map_Y2_com)
str(H_C_16S_uni_map_Y2_com)
H_C_16S_uni_map_Y2_com<-subset(H_C_16S_uni_map_Y2_com, select=c(H_C_16S_uni_Y2_com_samples))
H_C_16S_uni_map_Y2_Source<-factor(H_C_16S_uni_map_Y2_env$Source)
levels(H_C_16S_uni_map_Y2_Source)<-c("B. brunneicolor","Biofilm","Carcass","H. flavescens","S. mutata")
H_C_16S_uni_map_Y2_Source<- ordered(H_C_16S_uni_map_Y2_Source, levels = c("Biofilm", "Carcass", "B. brunneicolor","H. flavescens","S. mutata"))
H_C_16S_uni_map_Y2_Env<-factor(H_C_16S_uni_map_Y2_env$Env)
levels(H_C_16S_uni_map_Y2_Env)<-c("Control","Salmon","Control","Salmon","Salmon", "Salmon", "Control", "Salmon")
#Create year 1 otu table with metadata
HC_16S_OTU_map_Y1<-subset(HC_16S_OTU_map, Year=="1")
H_C_16S_map_Y1_env<-HC_16S_OTU_map_Y1[,1:17]
H_C_16S_map_Y1_com<-HC_16S_OTU_map_Y1[,18:ncol(HC_16S_OTU_map_Y1)]
#Create year2 otu table with metadata
HC_16S_OTU_map_Y2<-subset(HC_16S_OTU_map, Year=="2")
H_C_16S_map_Y2_env<-HC_16S_OTU_map_Y2[,1:17]
H_C_16S_map_Y2_com<-HC_16S_OTU_map_Y2[,18:ncol(HC_16S_OTU_map_Y2)]
#Visualize overall differences for year 1 and year 2 separately
#UNI-year 1 permanova with unifrac distances
adonis(as.dist(H_C_16S_uni_map_Y1_com) ~ Reach*Source*Total_Biofilm_Growth_PostCarcass, data=H_C_16S_uni_map_Y1_env, permutations=999)
#Reach, source, time, reach:source, reach:time are significant, source is most significant
#NMDS year 1
HC_NMDS_uni_y1<-metaMDS(as.dist(H_C_16S_uni_map_Y1_com))
#stress is nearly 0 - it appears that stegopterna samples are throwing this off because they are so different, so try again without those samples
#UNI-Create Year 1 unifrac distance table with metadata without any simuliidae
H_C_16S_uni_map_Y1ns<-subset(Hunt_Creek_16S_uni_map, Year=="1" & Source!="Stegopterna")
#Subset into environmental and community data frames
H_C_16S_uni_map_Y1ns_env<-H_C_16S_uni_map_Y1ns[,1:16]
H_C_16S_uni_map_Y1ns_com<-H_C_16S_uni_map_Y1ns[,17:ncol(H_C_16S_uni_map_Y1ns)]
H_C_16S_uni_Y1ns_com_samples<-as.vector(rownames(H_C_16S_uni_map_Y1ns_com))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_map_Y1ns_com<-as.matrix(H_C_16S_uni_map_Y1ns_com)
str(H_C_16S_uni_map_Y1ns_com)
H_C_16S_uni_map_Y1ns_com<-subset(H_C_16S_uni_map_Y1ns_com, select=c(H_C_16S_uni_Y1ns_com_samples))
H_C_16S_uni_map_Y1ns_Env<-factor(H_C_16S_uni_map_Y1ns_env$Env)
H_C_16S_uni_map_Y1ns_Source<-factor(H_C_16S_uni_map_Y1ns_env$Source)
levels(H_C_16S_uni_map_Y1ns_Source)<-c("B. brunneicolor", "Biofilm", "Carcass")
levels(H_C_16S_uni_map_Y1ns_Env)<-c("Control","Salmon","Control","Salmon","Salmon")
HC_NMDS_uni_y1ns<-metaMDS(as.dist(H_C_16S_uni_map_Y1ns_com))
HC_NMDS_uni_y1ns
#stress=0.13
stressplot(HC_NMDS_uni_y1ns)
ordiplot(HC_NMDS_uni_y1ns, type="n")
with(HC_NMDS_uni_y1ns, points(HC_NMDS_uni_y1ns, display="sites", col=three_col_vec_bfcari[H_C_16S_uni_map_Y1ns_Source], pch=c(15,17)[H_C_16S_uni_map_Y1ns_Env]))
with(HC_NMDS_uni_y1ns, legend("topleft", legend=c(levels(H_C_16S_uni_map_Y1ns_Source),levels(H_C_16S_uni_map_Y1ns_Env)), bty="n", col=c(three_col_vec_bfcari,"black","black"),pch=c(19,19,19,0,2),pt.bg="black"))
with(HC_NMDS_uni_y1ns, legend("topright", legend="2D Stress: 0.13", bty="n"))
#UNI-year 2 permanova with unifrac distances
adonis(as.dist(H_C_16S_uni_map_Y2_com) ~ Reach*Source*Total_Biofilm_Growth_PostCarcass, data=H_C_16S_uni_map_Y2_env, permutations=999)
#Reach, source, time, source:time reach:source:time significant
#NMDS year 2
HC_NMDS_uni_y2<-metaMDS(as.dist(H_C_16S_uni_map_Y2_com))
HC_NMDS_uni_y2
#stress=0.11
stressplot(HC_NMDS_uni_y2)
ordiplot(HC_NMDS_uni_y2, type="n")
with(HC_NMDS_uni_y2, points(HC_NMDS_uni_y2, display="sites", col=five_col_vec_babchs[H_C_16S_uni_map_Y2_Source], pch=c(15,17)[H_C_16S_uni_map_Y2_Env]))
with(HC_NMDS_uni_y2, legend("topleft", legend=c(levels(H_C_16S_uni_map_Y2_Source),levels(H_C_16S_uni_map_Y2_Env)), bty="n", col=c(five_col_vec_babchs,"black","black"),pch=c(19,19,19,19,19,0,2),pt.bg="black"))
with(HC_NMDS_uni_y2, legend("topright", legend="2D Stress: 0.11", bty="n"))
####################################################
#Biofilm sample analysis by year
############################################
#Create biofilm data tables by year
#Biofilm Year 1
#Create biofilm matrix for year 1 with metadata
H_C_16S_map_Y1_BF<-subset(HC_16S_OTU_map_Y1, Source=="Biofilm")
#how many OTUs BF Y1?
#Delete OTUs with no observations
cols_to_drop_BF_Y1 = c(rep(TRUE, 17), colSums(H_C_16S_map_Y1_BF[,18:ncol(H_C_16S_map_Y1_BF)]) > 0)
H_C_16S_map_Y1_BF<-H_C_16S_map_Y1_BF[,cols_to_drop_BF_Y1]
#There are 3118 OTUs (number of variables - 17 metadata variables)
sum(colSums(H_C_16S_map_Y1_BF[,18:ncol(H_C_16S_map_Y1_BF)]))
#90,000 total sequence reads
#without metadata for biofilms in year 1
H_C_16S_Y1_BF<-H_C_16S_map_Y1_BF[,18:ncol(H_C_16S_map_Y1_BF)]
H_C_16S_Y1_BF_samples<-as.vector(rownames(H_C_16S_Y1_BF))
#Biofilm year 1 environmental variable table
H_C_16S_env_Y1_BF<-H_C_16S_map_Y1_BF[,1:17]
Total_Biofilm_Growth_PostCarcass_Y1<-H_C_16S_env_Y1_BF$Total_Biofilm_Growth_PostCarcass
Reach_Y1<-as.factor(H_C_16S_env_Y1_BF$Reach)
#UNI-Create biofilm unifrac distance table for year 1 with metadata
H_C_16S_uni_map_Y1_BF<-subset(H_C_16S_uni_map_Y1, Source=="Biofilm")
#UNI-unifrac distance table without metadata for biofilms in year 1
H_C_16S_uni_Y1_BF<-H_C_16S_uni_map_Y1_BF[,17:ncol(H_C_16S_uni_map_Y1_BF)]
H_C_16S_uni_Y1_BF_samples<-as.vector(rownames(H_C_16S_uni_Y1_BF))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_Y1_BF<-as.matrix(H_C_16S_uni_Y1_BF)
H_C_16S_uni_Y1_BF<-subset(H_C_16S_uni_Y1_BF, select=c(H_C_16S_uni_Y1_BF_samples))
#UNI-Biofilm year 1 environmental variable table
H_C_16S_env_Y1_BF<-H_C_16S_uni_map_Y1_BF[,1:16]
Total_Biofilm_Growth_PostCarcass_Y1<-(H_C_16S_env_Y1_BF$Total_Biofilm_Growth_PostCarcass)
Reach_Y1<-as.factor(H_C_16S_env_Y1_BF$Reach)
BA_Y1<-as.factor(H_C_16S_env_Y1_BF$BA)
Env_Y1BF<-factor(revalue(H_C_16S_env_Y1_BF$Env, c("BiofilmSalmon"="Salmon", "BiofilmControl"="Control")), levels =c("Salmon", "Control"))
#Biofilm year 2
#Create biofilm matrix for year 2 with metadata
H_C_16S_map_Y2_BF<-subset(HC_16S_OTU_map_Y2, Source=="Biofilm")
#how many OTUs BF Y2?
#Delete OTUs with no observations
cols_to_drop_BF_Y2 = c(rep(TRUE, 17), colSums(H_C_16S_map_Y2_BF[,18:ncol(H_C_16S_map_Y2_BF)]) > 0)
H_C_16S_map_Y2_BF<-H_C_16S_map_Y2_BF[,cols_to_drop_BF_Y2]
#There are 4132 OTUs (number of variables - 17 metadata variables)
sum(colSums(H_C_16S_map_Y2_BF[,18:ncol(H_C_16S_map_Y2_BF)]))
#90,000 total sequence reads
#table without metadata for biofilms in year 2
H_C_16S_Y2_BF<-H_C_16S_map_Y2_BF[,18:ncol(H_C_16S_map_Y2_BF)]
H_C_16S_Y2_BF_samples<-as.vector(rownames(H_C_16S_Y2_BF))
#Biofilm year 2 environmental variable table
H_C_16S_env_Y2_BF<-H_C_16S_map_Y2_BF[,1:17]
Total_Biofilm_Growth_PostCarcass_Y2<-H_C_16S_env_Y2_BF$Total_Biofilm_Growth_PostCarcass
Reach_Y2<-as.factor(H_C_16S_env_Y2_BF$Reach)
#UNI-Create biofilm unifrac distance table for year 2 with metadata
H_C_16S_uni_map_Y2_BF<-subset(H_C_16S_uni_map_Y2, Source=="Biofilm")
#UNI_unifrac distance table without metadata for biofilms in year 2
H_C_16S_uni_Y2_BF<-H_C_16S_uni_map_Y2_BF[,17:ncol(H_C_16S_uni_map_Y2_BF)]
H_C_16S_uni_Y2_BF_samples<-as.vector(rownames(H_C_16S_uni_Y2_BF))
#UNI-use output of names to subset columns into rows to make square matrix
H_C_16S_uni_Y2_BF<-as.matrix(H_C_16S_uni_Y2_BF)
H_C_16S_uni_Y2_BF<-subset(H_C_16S_uni_Y2_BF, select=c(H_C_16S_uni_Y2_BF_samples))
#UNI-Biofilm year 2 environmental variable table
H_C_16S_env_Y2_BF<-H_C_16S_uni_map_Y2_BF[,1:16]
Total_Biofilm_Growth_PostCarcass_Y2<-H_C_16S_env_Y2_BF$Total_Biofilm_Growth_PostCarcass
Reach_Y2<-as.factor(H_C_16S_env_Y2_BF$Reach)
BA_Y2<-as.factor(H_C_16S_env_Y2_BF$BA)
Env_Y2BF<-factor(revalue(H_C_16S_env_Y2_BF$Env, c("BiofilmSalmon"="Salmon", "BiofilmControl"="Control")), levels =c("Salmon", "Control"))
#Year 1 biofilm permanova using counts
adonis(H_C_16S_Y1_BF ~ Reach_Y1*Total_Biofilm_Growth_PostCarcass_Y1, data=H_C_16S_env_Y1_BF, method="jaccard", permutations=999)
#Reach,time and reach:time interaction all significant
#Year 2 biofilm permanova using counts
adonis(H_C_16S_Y2_BF ~ Reach_Y2*Total_Biofilm_Growth_PostCarcass_Y2, data=H_C_16S_env_Y2_BF, method="jaccard", permutations=999)
#time significant
#UNI-Year 1 biofilm permanova using unfrac distance
adonis(as.dist(H_C_16S_uni_Y1_BF) ~ Reach_Y1*Total_Biofilm_Growth_PostCarcass_Y1, data=H_C_16S_env_Y1_BF, permutations=9999)
#Reach,time and reach:time interaction all significant
#UNI-Year 2 biofilm permanova using unifrac distance
adonis(as.dist(H_C_16S_uni_Y2_BF) ~ Reach_Y2*Total_Biofilm_Growth_PostCarcass_Y2, data=H_C_16S_env_Y2_BF, permutations=999)
#time significant
#Plot NMDS results for biofilms for each year
HC_NMDS_uni_y1bf<-metaMDS(as.dist(H_C_16S_uni_Y1_BF))
HC_NMDS_uni_y1bf
#stress=0.11
stressplot(HC_NMDS_uni_y1bf)
ordiplot(HC_NMDS_uni_y1bf, type="n")
with(HC_NMDS_uni_y1bf, points(HC_NMDS_uni_y1bf, display="sites", col="black", pch=c(16,5)[Env_Y1BF]))
with(HC_NMDS_uni_y1bf, ordiellipse(HC_NMDS_uni_y1bf, Env_Y1BF, kind="se", conf=0.95, lwd=2, col="black", draw="polygon", show.groups = "Salmon"))
with(HC_NMDS_uni_y1bf, ordiellipse(HC_NMDS_uni_y1bf, Env_Y1BF, kind="se", conf=0.95, lwd=2, col="black", show.groups = "Control"))
with(HC_NMDS_uni_y1bf, legend("topleft", legend=c("Salmon","Control"), bty="n", col="black",pch=c(16,5),pt.bg="black"))
with(HC_NMDS_uni_y1bf, legend("topright", legend="2D Stress: 0.11", bty="n"))
HC_NMDS_uni_y2bf<-metaMDS(as.dist(H_C_16S_uni_Y2_BF))
HC_NMDS_uni_y2bf
#stress=0.12
stressplot(HC_NMDS_uni_y2bf)
ordiplot(HC_NMDS_uni_y2bf, type="n")
with(HC_NMDS_uni_y2bf, points(HC_NMDS_uni_y2bf, display="sites", col="black", pch=c(16,5)[Env_Y2BF]))
with(HC_NMDS_uni_y2bf, ordiellipse(HC_NMDS_uni_y2bf, Env_Y2BF, kind="se", conf=0.95, lwd=2, col="black", draw="polygon", show.groups = "Salmon"))
with(HC_NMDS_uni_y2bf, ordiellipse(HC_NMDS_uni_y2bf, Env_Y2BF, kind="se", conf=0.95, lwd=2, col="black", show.groups = "Control"))
with(HC_NMDS_uni_y2bf, legend("topleft", legend=c("Salmon","Control"), bty="n", col="black",pch=c(16,5),pt.bg="black"))
with(HC_NMDS_uni_y2bf, legend("topright", legend="2D Stress: 0.12", bty="n"))
#indicator taxa analysis for biofilms
#subset phyla info into biofilms for each year
HC_16S_P_map_bf_y1<-subset(HC_16S_P_map, Source=="Biofilm" & Year=="1")
HC_16S_P_map_bf_y1$Unassigned.__<-NULL
HC_16S_P_map_bf_y1$k__Bacteria.__<-NULL
HC_16S_P_map_bf_y1$k__Bacteria.p__<-NULL
HC_16S_P_map_bf_y1[,1:17]<-sapply(HC_16S_P_map_bf_y1[,1:17], as.factor)
HC_16S_P_map_bf_y1_env<-HC_16S_P_map_bf_y1[,1:17]
HC_16S_P_map_bf_y1_com<-HC_16S_P_map_bf_y1[,18:ncol(HC_16S_P_map_bf_y1)]
#find most abundant phyla
head(sort(colSums(HC_16S_P_map_bf_y1_com),decreasing=TRUE))
#Proteobacteria most abundant with 39572
#subset phyla info into biofilms y2
HC_16S_P_map_bf_y2<-subset(HC_16S_P_map, Source=="Biofilm" & Year=="2")
HC_16S_P_map_bf_y2$Unassigned.__<-NULL
HC_16S_P_map_bf_y2$k__Bacteria.__<-NULL
HC_16S_P_map_bf_y2$k__Bacteria.p__<-NULL
HC_16S_P_map_bf_y2[,1:17]<-sapply(HC_16S_P_map_bf_y2[,1:17], as.factor)
HC_16S_P_map_bf_y2_env<-HC_16S_P_map_bf_y2[,1:17]
HC_16S_P_map_bf_y2_com<-HC_16S_P_map_bf_y2[,18:ncol(HC_16S_P_map_bf_y2)]
#find most abundant phyla
head(sort(colSums(HC_16S_P_map_bf_y2_com),decreasing=TRUE))
#Proteobacteria most abundant with 40010
#create clusters based on time and reach
BF_Y1_Reach<-HC_16S_P_map_bf_y1_env$Reach
BF_Y2_Reach<-HC_16S_P_map_bf_y2_env$Reach
BF_Y1_Time<-HC_16S_P_map_bf_y1_env$Total_Biofilm_Growth_PostCarcass
BF_Y2_Time<-HC_16S_P_map_bf_y2_env$Total_Biofilm_Growth_PostCarcass
BF_Y1_RT<-paste(BF_Y1_Reach, BF_Y1_Time)
BF_Y2_RT<-paste(BF_Y2_Reach, BF_Y2_Time)
#Indicator analysis of biofilms year 1 to see what phyla are driving this change
HC_p_bf_y1_indic<-signassoc(HC_16S_P_map_bf_y1_com, cluster=BF_Y1_Reach, mode=0, alternative = "two.sided",control = how(nperm=9999))
HC_p_bf_y1_indic_sig<-subset(HC_p_bf_y1_indic, psidak<=0.05)
#indicator analysis found 2 phyla: k__Bacteria.p__Proteobacteria, k__Bacteria.p__Spirochaetes,
#subset family info into biofilms for each year
HC_16S_F_map_bf_y1<-subset(HC_16S_F_map, Source=="Biofilm" & Year=="1")
HC_16S_F_map_bf_y1$Unassigned.__.__.__.__<-NULL
HC_16S_F_map_bf_y1$k__Bacteria.__.__.__.__<-NULL
HC_16S_F_map_bf_y1$k__Bacteria.p__.c__.o__.f__<-NULL
HC_16S_F_map_bf_y1[,1:17]<-sapply(HC_16S_F_map_bf_y1[,1:17], as.factor)
HC_16S_F_map_bf_y1_env<-HC_16S_F_map_bf_y1[,1:17]
HC_16S_F_map_bf_y1_com<-HC_16S_F_map_bf_y1[,18:ncol(HC_16S_F_map_bf_y1)]
#find most abundant family
head((sort(colSums(HC_16S_F_map_bf_y1_com),decreasing=TRUE)),n=5)
#k__Bacteria.p__Cyanobacteria.c__Chloroplast.o__Stramenopiles.f__ most abundant with 14734 reads
sum(HC_16S_F_map_bf_y1_com)
#87284 sequence reads
#subset family info into biofilms y2
HC_16S_F_map_bf_y2<-subset(HC_16S_F_map, Source=="Biofilm" & Year=="2")
HC_16S_F_map_bf_y2$Unassigned.__.__.__.__<-NULL
HC_16S_F_map_bf_y2$k__Bacteria.__.__.__.__<-NULL
HC_16S_F_map_bf_y2$k__Bacteria.p__.c__.o__.f__<-NULL
HC_16S_F_map_bf_y2[,1:17]<-sapply(HC_16S_F_map_bf_y2[,1:17], as.factor)
HC_16S_F_map_bf_y2_env<-HC_16S_F_map_bf_y2[,1:17]
HC_16S_F_map_bf_y2_com<-HC_16S_F_map_bf_y2[,18:ncol(HC_16S_F_map_bf_y2)]
#find most abundant family
head((sort(colSums(HC_16S_F_map_bf_y2_com),decreasing=TRUE)),n=5)
#k__Bacteria.p__Cyanobacteria.c__Chloroplast.o__Stramenopiles.f__ most abundant with 16015 reads
sum(HC_16S_F_map_bf_y2_com)
#88582 sequence reads
HC_16S_F_map_bf<-subset(HC_16S_F_map, Source=="Biofilm")
stat.desc(HC_16S_F_map_bf$k__Bacteria.p__Cyanobacteria.c__Chloroplast.o__Stramenopiles.f__)
#create clusters based on time and reach
BF_Y1_Reach<-HC_16S_F_map_bf_y1_env$Reach
BF_Y2_Reach<-HC_16S_F_map_bf_y2_env$Reach
BF_Y1_Time<-HC_16S_F_map_bf_y1_env$Total_Biofilm_Growth_PostCarcass
BF_Y2_Time<-HC_16S_F_map_bf_y2_env$Total_Biofilm_Growth_PostCarcass
BF_Y1_RT<-paste(BF_Y1_Reach, BF_Y1_Time)
BF_Y2_RT<-paste(BF_Y2_Reach, BF_Y2_Time)
BF_Y1_Env<-HC_16S_F_map_bf_y1_env$Env
BF_Y2_Env<-HC_16S_F_map_bf_y2_env$Env
#Indicator analysis of biofilms year 1 to see what families are driving this change
HC_f_bf_y1_indic<-signassoc(HC_16S_F_map_bf_y1_com, cluster=BF_Y1_Env, mode=0, alternative = "two.sided",control = how(nperm=9999))
HC_f_bf_y1_indic_sig<-subset(HC_f_bf_y1_indic, psidak<=0.05)
write.table(HC_f_bf_y1_indic_sig, "~/Documents/MSU/Research/Hunt_Creek_Salmon/Microbes/16S/16SBFY1IndSig.txt", sep="\t")
#indicator analysis found 15 families:
#Plot these families to visualize
HC_16S_F_map_bfcar<-subset(HC_16S_F_map, Source=="Biofilm" | Source== "Carcass")
HC_16S_F_map_bf<-subset(HC_16S_F_map, Source=="Biofilm")
HC_16S_F_map_bf$k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__)
BACP_BF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__", groupvars=c("Days_Since_Study_Start","Reach"))
BACP_BF$Reach<-factor(BACP_BF$Reach, c("Salmon", "Control"))
ggplot(BACP_BF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__-se, ymax=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__PK29.f__+se), width=.1) +
geom_point(size=3) +
geom_line(size=1.5, aes(linetype=Reach))+
xlab("Days since study start") +
ylab("Mean unnamed PK29 sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100))
HC_16S_F_map_bf$k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075)
BACREBF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075", groupvars=c("Days_Since_Study_Start","Reach"))
BACREBF$Reach<-factor(BACREBF$Reach, c("Salmon", "Control"))
ggplot(BACREBF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075-se, ymax=k__Bacteria.p__Acidobacteria.c__.Chloracidobacteria..o__RB41.f__Ellin6075+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach)) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean Ellin6075 sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae)
BBSSCBF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae", groupvars=c("Days_Since_Study_Start","Reach"))
BBSSCBF$Reach<-factor(BBSSCBF$Reach, c("Salmon", "Control"))
ggplot(BBSSCBF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae-se, ymax=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Chitinophagaceae+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach)) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean Chitinophagaceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae)
BBSSSBF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae", groupvars=c("Days_Since_Study_Start","Reach"))
BBSSSBF$Reach<-factor(BBSSSBF$Reach, c("Salmon", "Control"))
ggplot(BBSSSBF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae-se, ymax=k__Bacteria.p__Bacteroidetes.c__.Saprospirae..o__.Saprospirales..f__Saprospiraceae+se), width=.1, color=BFColor) +
geom_line(size=1.5, aes(linetype=Reach), color=BFColor) +
geom_point(size=3, color=BFColor) +
xlab("Days since study start") +
ylab("Mean Saprospiraceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$Stramenopiles.f__RA<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Cyanobacteria.c__Chloroplast.o__Stramenopiles.f__)/2500
BCCS_BF <- summarySE(HC_16S_F_map_bf, measurevar="Stramenopiles.f__RA", groupvars=c("Days_Since_Study_Start","Reach"))
BCCS_BF$Reach<-factor(BCCS_BF$Reach, c("Salmon", "Control"))
ggplot(BCCS_BF, aes(x=Days_Since_Study_Start, y=Stramenopiles.f__RA)) +
geom_errorbar(aes(ymin=Stramenopiles.f__RA-se, ymax=Stramenopiles.f__RA+se), width=.1, color=BFColor) +
geom_line(size=1.5, aes(linetype=Reach), color=BFColor) +
geom_point(size=3, color=BFColor) +
xlab("Days since study start") +
ylab("Mean Stramenopiles Rel. Abund. (±SE)") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=20,margin=margin(40,0,0,0)),axis.title.y=element_text(size=20),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae)
BPARHBF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae", groupvars=c("Days_Since_Study_Start","Reach"))
BPARHBF$Reach<-factor(BPARHBF$Reach, c("Salmon", "Control"))
ggplot(BPARHBF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae-se, ymax=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Rhizobiales.f__Hyphomicrobiaceae+se), width=.1, color=BFColor) +
geom_line(size=1.5, aes(linetype=Reach), color=BFColor) +
geom_point(size=3, color=BFColor) +
xlab("Days since study start") +
ylab("Mean Hyphomicrobiaceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae<-as.numeric(HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae)
BPASSBFC <- summarySE(HC_16S_F_map_bfcar, measurevar="k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae", groupvars=c("Days_Since_Study_Start","Reach","Source"))
BPASSBFC$Reach<-factor(BPASSBFC$Reach, c("Salmon", "Control"))
ggplot(BPASSBFC, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae, color=Source)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae-se, ymax=k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach), data=BPASSBFC[BPASSBFC$Source=="Biofilm",]) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean Sphingomonadaceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=two_col_vec_bfcar) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf_sal<-subset(HC_16S_F_map_bf, Reach=="Salmon")
HC_16S_F_map_bf_cont<-subset(HC_16S_F_map_bf, Reach=="Control")
stat.desc(HC_16S_F_map_bf_sal$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae)
stat.desc(HC_16S_F_map_bf_cont$k__Bacteria.p__Proteobacteria.c__Alphaproteobacteria.o__Sphingomonadales.f__Sphingomonadaceae)
HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__)
BPB__BF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__", groupvars=c("Days_Since_Study_Start","Reach"))
BPB__BF$Reach<-factor(BPB__BF$Reach, c("Salmon", "Control"))
ggplot(BPB__BF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__-se, ymax=k__Bacteria.p__Proteobacteria.c__Betaproteobacteria.o__.f__+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach)) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean unnamed Betaproteobacteria sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae<-as.numeric(HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae)
BPDDGBFC <- summarySE(HC_16S_F_map_bfcar, measurevar="k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae", groupvars=c("Days_Since_Study_Start","Reach","Source"))
BPDDGBFC$Reach<-factor(BPDDGBFC$Reach, c("Salmon", "Control"))
ggplot(BPDDGBFC, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae, color=Source)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae-se, ymax=k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach), data=BPDDGBFC[BPDDGBFC$Source=="Biofilm",]) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean Geobacteraceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=two_col_vec_bfcar) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
stat.desc(HC_16S_F_map_bf_sal$k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae)
stat.desc(HC_16S_F_map_bf_cont$k__Bacteria.p__Proteobacteria.c__Deltaproteobacteria.o__Desulfuromonadales.f__Geobacteraceae)
HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae<-as.numeric(HC_16S_F_map_bfcar$k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae)
BPECHBFC <- summarySE(HC_16S_F_map_bfcar, measurevar="k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae", groupvars=c("Days_Since_Study_Start","Reach","Source"))
BPECHBFC$Reach<-factor(BPECHBFC$Reach, c("Salmon", "Control"))
ggplot(BPECHBFC, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae, color=Source)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae-se, ymax=k__Bacteria.p__Proteobacteria.c__Epsilonproteobacteria.o__Campylobacterales.f__Helicobacteraceae+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach), data=BPECHBFC[BPECHBFC$Source=="Biofilm",]) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean Helicobacteraceae sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_color_manual(values=two_col_vec_bfcar) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__)
BPG__BF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__", groupvars=c("Days_Since_Study_Start","Reach"))
BPG__BF$Reach<-factor(BPG__BF$Reach, c("Salmon", "Control"))
ggplot(BPG__BF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__-se, ymax=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.__.__+se), width=.1) +
geom_line(size=1.5, aes(linetype=Reach)) +
geom_point(size=3) +
xlab("Days since study start") +
ylab("Mean unnamed Gammaproteobacteria sequence abundance") +
theme(panel.background = element_rect(fill = "white", colour = "grey50"),
axis.title.x=element_text(size=18),axis.title.y=element_text(size=18),
axis.text.x=element_text(size=14),axis.text.y = element_text(size=14),
legend.title=element_text(size=20),legend.text = element_text(size=16)) +
scale_x_continuous(breaks=seq(0,700,100)) +
geom_vline(xintercept = c(30,400), linetype = "dotted", colour = "black") +
scale_linetype_discrete(name="Treatment")
HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae<-as.numeric(HC_16S_F_map_bf$k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae)
BPGAABF <- summarySE(HC_16S_F_map_bf, measurevar="k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae", groupvars=c("Days_Since_Study_Start","Reach"))
BPGAABF$Reach<-factor(BPGAABF$Reach, c("Salmon", "Control"))
ggplot(BPGAABF, aes(x=Days_Since_Study_Start, y=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae)) +
geom_errorbar(aes(ymin=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae-se, ymax=k__Bacteria.p__Proteobacteria.c__Gammaproteobacteria.o__Alteromonadales.f__Alteromonadaceae+se), width=.1, color=BFColor) +