adjust confidence interval names

cambiotraining · Mar 28, 2024 · cfff04e · cfff04e
1 parent 4c3dfa0
commit cfff04e
Show file tree

Hide file tree

Showing 8 changed files with 15 additions and 15 deletions.
diff --git a/_freeze/materials/04-wastewater/03-ww_visualisation/execute-results/html.json b/_freeze/materials/04-wastewater/03-ww_visualisation/execute-results/html.json
diff --git a/_freeze/materials/04-wastewater/04-ww_mutations/execute-results/html.json b/_freeze/materials/04-wastewater/04-ww_mutations/execute-results/html.json
diff --git a/course_files/r_demo/lineage_abundances.csv b/course_files/r_demo/lineage_abundances.csv
@@ -1,4 +1,4 @@
-sample,name,abundance,boot_lo,boot_hi,date,country,city,latitude,longitude
+sample,name,abundance,boot_lo,boot_up,date,country,city,latitude,longitude
 SRR18541074,AY.44,0.26583286,0.22062022336636045,0.2971052371373705,2021-12-01,United States,San Diego,32.719875,-117.170082
 SRR18541074,AY.3,0.17287380,0.15684817412629423,0.19134365770536377,2021-12-01,United States,San Diego,32.719875,-117.170082
 SRR18541074,AY.100,0.06591169,0.0621177963944036,0.07690953917545072,2021-12-01,United States,San Diego,32.719875,-117.170082

diff --git a/course_files/r_demo/vocs_abundances.csv b/course_files/r_demo/vocs_abundances.csv
@@ -1,4 +1,4 @@
-sample,name,abundance,boot_lo,boot_hi,date,country,city,latitude,longitude
+sample,name,abundance,boot_lo,boot_up,date,country,city,latitude,longitude
 SRR18541074,Delta,0.9640087907444956,0.9596984293917038,0.9682214940819226,2021-12-01,United States,San Diego,32.719875,-117.170082
 SRR18541074,Omicron,0.019682409750709555,0.013233836060878133,0.02276906228234253,2021-12-01,United States,San Diego,32.719875,-117.170082
 SRR18541074,Other,0.0012202492036713667,0.0,0.008722550206162935,2021-12-01,United States,San Diego,32.719875,-117.170082

diff --git a/materials/04-wastewater/03-ww_visualisation.qmd b/materials/04-wastewater/03-ww_visualisation.qmd
@@ -313,7 +313,7 @@ lineages |>
   mutate(name = fct_reorder(name, abundance)) |> 
   # make the plot
   ggplot(aes(x = name, y = abundance, colour = abundance < 0.05)) +
-  geom_pointrange(aes(ymin = boot_lo, ymax = boot_hi)) +
+  geom_pointrange(aes(ymin = boot_lo, ymax = boot_up)) +
   labs(x = "Lineage", y = "Abundance (95% CI)", colour = "< 5%")
 ```
 
@@ -340,7 +340,7 @@ lineages |>
   filter(sample == "SRR18541092") |> 
   mutate(name = fct_reorder(name, abundance)) |> 
   ggplot(aes(x = name, y = abundance, colour = abundance < 0.05)) +
-  geom_pointrange(aes(ymin = boot_lo, ymax = boot_hi)) +
+  geom_pointrange(aes(ymin = boot_lo, ymax = boot_up)) +
   scale_x_discrete(guide = guide_axis(angle = 45)) +
   labs(x = "Lineage", y = "Abundance (95% CI)", colour = "< 5%", 
        main = "Sample: SRR18541092")
@@ -349,7 +349,7 @@ lineages |>
   filter(sample == "SRR18541114") |> 
   mutate(name = fct_reorder(name, abundance)) |> 
   ggplot(aes(x = name, y = abundance, colour = abundance < 0.05)) +
-  geom_pointrange(aes(ymin = boot_lo, ymax = boot_hi)) +
+  geom_pointrange(aes(ymin = boot_lo, ymax = boot_up)) +
   scale_x_discrete(guide = guide_axis(angle = 45)) +
   labs(x = "Lineage", y = "Abundance (95% CI)", colour = "< 5%",
        main = "Sample: SRR18541114")
@@ -375,7 +375,7 @@ sandiego |>
   filter(sample %in% c("SRR18541092", "SRR18541114")) |> 
   # make the plot
   ggplot(aes(x = name, y = abundance, colour = sample)) +
-  geom_pointrange(aes(ymin = boot_lo, ymax = boot_hi), 
+  geom_pointrange(aes(ymin = boot_lo, ymax = boot_up), 
                   position = position_dodge(width = 0.5))
 ```
 

diff --git a/materials/04-wastewater/04-ww_mutations.qmd b/materials/04-wastewater/04-ww_mutations.qmd
@@ -236,7 +236,7 @@ In R, we can calculate this as follows:
 ```{r}
 missense <- missense |> 
   mutate(af_lo = qbeta(0.025, alt_dp + 0.5, (dp - alt_dp) + 0.5),
-         af_hi = qbeta(0.975, alt_dp + 0.5, (dp - alt_dp) + 0.5))
+         af_up = qbeta(0.975, alt_dp + 0.5, (dp - alt_dp) + 0.5))
 ```
 
 One possible visualisation is to consider the mutations in individual samples, shown as a plot across the genome:
@@ -245,7 +245,7 @@ One possible visualisation is to consider the mutations in individual samples, s
 missense |> 
   filter(sample == "SRR18541114") |> 
   ggplot(aes(pos, af, colour = gene)) + 
-  geom_pointrange(aes(ymin = af_lo, ymax = af_hi)) +
+  geom_pointrange(aes(ymin = af_lo, ymax = af_up)) +
   scale_y_continuous(limits = c(0, 1))
 ```
 
@@ -255,7 +255,7 @@ Or, we can focus on an individual mutation and plot it over time:
 missense |> 
   filter(aa_change == "p.K856R") |> 
   ggplot(aes(date, af)) +
-  geom_pointrange(aes(ymin = af_lo, ymax = af_hi)) +
+  geom_pointrange(aes(ymin = af_lo, ymax = af_up)) +
   scale_y_continuous(limits = c(0, 1))
 ```
 

diff --git a/materials/04-wastewater/ww_notes.md b/materials/04-wastewater/ww_notes.md
@@ -199,4 +199,4 @@ pagetitle: "SARS Genomic Surveillance"
 Trainers:
 
 - Amanda Qvesel (bioinformatics) - [email protected]
-- 
+
diff --git a/utils/wastewater/tidy_freyja_viralrecon.py b/utils/wastewater/tidy_freyja_viralrecon.py
@@ -135,7 +135,7 @@ def parse_bootstrap(file_path):
     # zip them up
     boot = list(zip(lineage_names, q1, q7))
     # convert to data frame
-    boot_df = pd.DataFrame(boot, columns=["name", "boot_lo", "boot_hi"])
+    boot_df = pd.DataFrame(boot, columns=["name", "boot_lo", "boot_up"])
 
     return boot_df
Original file line number	Diff line number	Diff line change
Expand Up		@@ -199,4 +199,4 @@ pagetitle: "SARS Genomic Surveillance"
		Trainers:

		- Amanda Qvesel (bioinformatics) - [email protected]
		-