Supplemental Figure: Protocol optimization
E. coli ORBIT 2022
Scott H. Saunders
Notes
This figure contains data from many different experiments that were used to optimize the protocol for ORBIT.
Setup packages and plotting for the notebook:
# Check packages
source("../tools/package_setup.R")
# Load packages
library(tidyverse)
library(cowplot)
library(kableExtra)
# Code display options
knitr::opts_chunk$set(tidy.opts=list(width.cutoff=60),tidy=FALSE, echo = TRUE, message=FALSE, warning=FALSE, fig.align="center", fig.retina = 2)
# Load plotting tools
source("../tools/plotting_tools.R")
#Modify the plot theme
theme_set(theme_notebook())Fig. 2A - Helper plasmid induction conditions
Read in the data.
df_po <- read_csv("../../data/low_throughput_experiments/2022_09_15_PO_bonds_orbit.csv") %>% mutate(eff = Kan_count / LB_count)
df_po## # A tibble: 12 × 6
## condition replicate PO_bonds LB_count Kan_count eff
## <chr> <dbl> <chr> <dbl> <dbl> <dbl>
## 1 p265 1 0 740000 550 0.000743
## 2 p265 2 0 840000 1140 0.00136
## 3 p265 3 0 800000 1510 0.00189
## 4 p386 1 2 740000 1140 0.00154
## 5 p386 2 2 830000 1500 0.00181
## 6 p386 3 2 620000 1670 0.00269
## 7 p387 1 4 610000 930 0.00152
## 8 p387 2 4 540000 1170 0.00217
## 9 p387 3 4 500000 1100 0.0022
## 10 pInt only control 1 control 720000 40 0.0000556
## 11 pInt only control 2 control 710000 19 0.0000268
## 12 pInt only control 3 control 780000 26 0.0000333po_control <- mean((df_po %>% filter(PO_bonds == 'control'))$eff)
plot_po <- ggplot(df_po %>% filter(PO_bonds != 'control'), aes(x = factor(PO_bonds), y = eff)) +
geom_hline(yintercept = po_control, color = 'light gray', linetype = 2) +
geom_jitter(shape = 21, width = 0.1, height = 0) +
stat_summary(geom = 'point', fun = 'mean')+
scale_y_continuous(labels = scales::label_percent(accuracy = 0.01))+
#scale_y_log10(breaks = c(0.0001, 0.001, 0.01), limits = c(0.00003, 0.01), labels = scales::label_percent(accuracy = 0.01))+
scale_x_discrete(labels = c('none', "2x 5' PO", "2x 5' PO\n2x 3' PO"))+
labs(x = 'Targeting oligo PO bonds', y = 'Efficiency')+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
plot_po
df_pur <- read_csv("../../data/low_throughput_experiments/2022_09_07_TO_purification.csv") %>% mutate(eff = Kan_count / LB_count) %>%
mutate(purification = factor(purification, levels = c('desalt','cartridge','HPLC','PAGE','control')))
df_pur## # A tibble: 10 × 6
## condition purification replicate LB_count Kan_count eff
## <chr> <fct> <dbl> <dbl> <dbl> <dbl>
## 1 p265 desalt 1 640000 800 0.00125
## 2 p265 desalt 2 680000 700 0.00103
## 3 p395 cartridge purified cartridge 1 640000 620 0.000969
## 4 p395 cartridge purified cartridge 2 560000 1110 0.00198
## 5 p396 HPLC purified HPLC 1 730000 1090 0.00149
## 6 p396 HPLC purified HPLC 2 490000 880 0.00180
## 7 p397 PAGE purified PAGE 1 600000 1550 0.00258
## 8 p397 PAGE purified PAGE 2 690000 2000 0.00290
## 9 pInt only control 1 770000 18 0.0000234
## 10 pInt only control 2 970000 28 0.0000289pur_control <- mean((df_pur %>% filter(purification == 'control'))$eff)
plot_pur <- ggplot(df_pur %>% filter(purification != 'control'), aes(x = purification, y = eff)) +
geom_hline(yintercept = pur_control, color = 'light gray', linetype = 2) +
geom_jitter(shape = 21, width = 0.1, height = 0) +
stat_summary(geom = 'point', fun = 'mean')+
scale_y_continuous(labels = scales::label_percent(accuracy = 0.01))+
#scale_y_log10(breaks = c(0.0001, 0.001, 0.01), limits = c(0.00002, 0.01), labels = scales::label_percent(accuracy = 0.01))+
#scale_x_discrete(labels = c('none', "2x 5' PO", "2x 5' PO + 2x 3' PO"))+
labs(x = 'Targeting oligo purification method', y = 'Efficiency')+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
plot_pur
df_co <- read_csv("../../data/low_throughput_experiments/2022_10_10_oligo_supplier.csv") %>% mutate(eff = Kan_count / LB_count) %>%
mutate(locus = factor(locus, levels = c('galK','hisA','metA','leuD'))) %>%
group_by(supplier, locus) %>%
mutate(avg_eff = mean(eff))
df_co## # A tibble: 24 × 9
## # Groups: supplier, locus [12]
## condition supplier locus replica…¹ targe…² LB_co…³ Kan_c…⁴ eff avg_eff
## <chr> <chr> <fct> <dbl> <chr> <dbl> <dbl> <dbl> <dbl>
## 1 galK - IDT IDT galK 1 p177 1070000 910 8.50e-4 1.01e-3
## 2 galK - IDT IDT galK 2 p177 1170000 1380 1.18e-3 1.01e-3
## 3 hisA - IDT IDT hisA 1 p229 1250000 240 1.92e-4 1.28e-4
## 4 hisA - IDT IDT hisA 2 p229 1570000 100 6.37e-5 1.28e-4
## 5 metA - IDT IDT metA 1 p230 1010000 30 2.97e-5 5.84e-5
## 6 metA - IDT IDT metA 2 p230 1000000 87 8.7 e-5 5.84e-5
## 7 leuD - IDT IDT leuD 1 p231 1310000 107 8.17e-5 7.80e-5
## 8 leuD - IDT IDT leuD 2 p231 1210000 90 7.44e-5 7.80e-5
## 9 galK - Sigma Sigma galK 1 p264 1250000 260 2.08e-4 5.33e-4
## 10 galK - Sigma Sigma galK 2 p264 1060000 910 8.58e-4 5.33e-4
## # … with 14 more rows, and abbreviated variable names ¹replicates,
## # ²targeting_oligo, ³LB_count, ⁴Kan_countplot_co <- ggplot(df_co, aes(x = supplier, y = eff, color = locus, group = locus)) +
geom_jitter(shape = 21, width = 0.1, height = 0, alpha = 0.4) +
geom_point(aes(y = avg_eff))+
geom_line(aes(y = avg_eff))+
#scale_y_continuous(labels = scales::label_percent(accuracy = 0.01))+
scale_y_log10( labels = scales::label_percent(accuracy = 0.001))+
scale_color_viridis_d()+
labs(x = 'Targeting oligo supplier', y = 'Efficiency')+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
plot_co
theme_set(theme_figure())
supp_protocol <- plot_grid(plot_po, plot_pur, plot_co + guides(color = 'none'), nrow = 1,
align = 'hv', axis = 'lr', scale = 1.0,
labels = 'AUTO')
supp_protocol
#save_plot("../../figures/r_pdf_figs/supp_figs/supp_protocol_optimization.pdf", plot = supp_protocol, base_height = 3, base_width = 7)## R version 4.2.0 (2022-04-22)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Big Sur/Monterey 10.16
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] ggrastr_1.0.1 kableExtra_1.3.4 cowplot_1.1.1 viridis_0.6.2
## [5] viridisLite_0.4.1 knitr_1.41 forcats_0.5.2 stringr_1.5.0
## [9] dplyr_1.1.0 purrr_0.3.5 readr_2.1.3 tidyr_1.2.1
## [13] tibble_3.1.8 ggplot2_3.4.0 tidyverse_1.3.2
##
## loaded via a namespace (and not attached):
## [1] httr_1.4.4 sass_0.4.4 bit64_4.0.5
## [4] vroom_1.6.0 jsonlite_1.8.3 modelr_0.1.10
## [7] bslib_0.4.1 assertthat_0.2.1 highr_0.9
## [10] vipor_0.4.5 googlesheets4_1.0.1 cellranger_1.1.0
## [13] yaml_2.3.6 pillar_1.8.1 backports_1.4.1
## [16] glue_1.6.2 digest_0.6.30 rvest_1.0.3
## [19] colorspace_2.0-3 htmltools_0.5.4 pkgconfig_2.0.3
## [22] broom_1.0.1 haven_2.5.1 scales_1.2.1
## [25] webshot_0.5.4 svglite_2.1.0 tzdb_0.3.0
## [28] timechange_0.1.1 googledrive_2.0.0 farver_2.1.1
## [31] generics_0.1.3 ellipsis_0.3.2 cachem_1.0.6
## [34] withr_2.5.0 cli_3.4.1 magrittr_2.0.3
## [37] crayon_1.5.2 readxl_1.4.1 evaluate_0.18
## [40] fs_1.5.2 fansi_1.0.3 xml2_1.3.3
## [43] beeswarm_0.4.0 tools_4.2.0 hms_1.1.2
## [46] gargle_1.2.1 lifecycle_1.0.3 munsell_0.5.0
## [49] reprex_2.0.2 compiler_4.2.0 jquerylib_0.1.4
## [52] systemfonts_1.0.4 rlang_1.1.1 grid_4.2.0
## [55] rstudioapi_0.14 labeling_0.4.2 rmarkdown_2.18
## [58] gtable_0.3.1 DBI_1.1.3 R6_2.5.1
## [61] gridExtra_2.3 lubridate_1.9.0 fastmap_1.1.0
## [64] bit_4.0.5 utf8_1.2.2 stringi_1.7.8
## [67] ggbeeswarm_0.7.1 parallel_4.2.0 vctrs_0.5.2
## [70] dbplyr_2.2.1 tidyselect_1.2.0 xfun_0.35