Merge pull request #42 from broadinstitute/add-new-batches

Add new batches

1.run-workflows/3.select_images_to_print.Rmd

@@ -21,7 +21,7 @@ load_data <-
     recursive = T
   )  %>%
   map_df(function(filename) {
-    df <- read_csv(filename)
+    df <- read_csv(filename, show_col_types = FALSE)
     df <- df %>% mutate(Metadata_Batch = str_split(filename, "/")[[1]][2])
   })
 
@@ -59,9 +59,11 @@ datasets <-
   tribble(
     ~batch, ~plate,
     "NCP_STEM_1", "BR_NCP_STEM_1",
-    "NCP_PROGENITORS_1", "BR_NCP_PROGENITORS_1",
-    "NCP_PILOT_3", "BR_NCP_PILOT_3",
-    "NCP_PILOT_3B", "MAtt_ICC_test"
+    "NCP_PROGENITORS_1", "BR00127194",
+    "2022_03_03_NCP_NEURONS_2_20x", "BR00132672",
+    "2022_03_03_NCP_NEURONS_2_20x", "BR00132673",
+    "2022-08-07_batch", "Plate1_PE_PP96",
+    "2022-08-07_batch", "PE_PP_Plate2"
   )
 
 metadata <-
@@ -70,6 +72,7 @@ metadata <-
           function(batch, plate) {
             read_tsv(
               file.path("metadata", glue("{batch}/platemap/{plate}.txt")),
+              show_col_types = FALSE
             ) %>%
               mutate(Batch = batch) %>%
               distinct()
@@ -96,7 +99,7 @@ set.seed(5)
 
 metadata_sampled <-
   metadata %>%
-  group_by(Metadata_Batch, Metadata_line_ID, Metadata_line_condition, Metadata_compound_ID, Metadata_plating_density) %>%
+  group_by(Metadata_Batch, Metadata_line_ID, Metadata_line_condition, Metadata_plating_density) %>%
   sample_n(1) %>%
   ungroup()
 ```
@@ -115,7 +118,7 @@ filenames_header <- paste0("FileName_Orig", channels)
 images <- 
   load_data %>%
   select(Metadata_Batch, Metadata_Plate, Metadata_Well, Metadata_Row, Metadata_FieldID, matches("^URL_"), one_of(filenames_header)) %>%
-  inner_join(metadata_sampled, by = c("Metadata_Plate", "Metadata_Well")) %>%
+  inner_join(metadata_sampled, by = c("Metadata_Batch", "Metadata_Plate", "Metadata_Well")) %>%
   filter(Metadata_FieldID %in% fieldIDs) %>%
   select(matches("^Metadata"), matches("^URL"), matches("^FileName_Orig"))
 
@@ -137,6 +140,20 @@ images %>%
   write_csv("data/sample_images_metadata.csv")
 ```
 
+```{r}
+images %>% 
+  distinct(Metadata_Batch, Metadata_Plate, Metadata_Well, Metadata_line_ID, Metadata_line_condition, Metadata_plating_density) %>% 
+  group_by(Metadata_Batch, Metadata_Plate, Metadata_line_ID, Metadata_line_condition, Metadata_plating_density) %>% 
+  tally() %>%
+  group_by(n) %>%
+  tally(name = "n_unique_conditions")
+```
+
+```{r}
+metadata_sampled %>% count()
+```
+
+
 Run this on command line to download the images:
 
 ```{sh eval=FALSE}
@@ -176,11 +193,11 @@ E.g. if the pipeline was configured differently, we'd have different values in `
 
 Only `NCP_PILOT_3B` and `NCP_PILOT_1` have 3 planes
 
-```{r}
+```{r eval=FALSE}
 load_data %>% distinct(Metadata_Batch, Metadata_PlaneID) %>% filter(Metadata_PlaneID > 1)
 ```
 
-```{r}
+```{r eval=FALSE}
 plane_batch <-
   tribble(~Metadata_Batch, ~ Metadata_PlaneID_outline,
            "NCP_PILOT_3B", 3,
@@ -224,7 +241,7 @@ outline_images %>%
   write_csv("data/sample_images_outline.csv")
 ```
 
-```{r results='asis'}
+```{r eval=FALSE, results='asis'}
 outline_images %>%
   mutate(URL_Outline = str_c("[Outline](", URL_Outline, ")")) %>% 
   select(Metadata_Batch, Metadata_plating_density, Metadata_line_condition, Metadata_compound_ID, URL_Outline, everything()) %>%

1.run-workflows/metadata/2022-08-07_batch/barcode_platemap.csv

@@ -0,0 +1,3 @@
+Assay_Plate_Barcode,Plate_Map_Name
+PE_PP_Plate2,2022-08-07_batch_METADATA
+Plate1_PE_PP96,2022-08-07_batch_METADATA

1.run-workflows/metadata/2022-08-07_batch/platemap/2022-08-07_batch_METADATA.txt

@@ -0,0 +1,97 @@
+plate_map_name	well_position	METADATA_SAMPLE_ID	METADATA_DENSITY	METADATA_CONDITION	METADATA_SOURCE
+2022-08-07_batch_METADATA	A01	1	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A02	30	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	A03	9	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A04	26	5000	DELETION	ISOGENIC
+2022-08-07_batch_METADATA	A05	4	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A06	34	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	A07	15	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A08	36	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	A09	2	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A10	16	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A11	20	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	A12	12	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B01	17	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B02	39	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B03	37	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B04	42	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B05	7	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B06	29	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B07	11	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B08	38	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B09	43	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	B10	18	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B11	6	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	B12	29	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C01	27	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C02	41	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C03	32	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C04	46	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C05	1	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	C06	33	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	C07	14	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	C08	9	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	C09	23	5000	CONTROL	ISOGENIC
+2022-08-07_batch_METADATA	C10	22	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	C11	3	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	C12	28	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	D01	5	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D02	35	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	D03	13	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D04	19	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D05	24	5000	CONTROL	ISOGENIC
+2022-08-07_batch_METADATA	D06	17	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D07	21	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D08	28	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	D09	31	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	D10	10	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	D11	45	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	D12	11	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	E01	24	5000	CONTROL	ISOGENIC
+2022-08-07_batch_METADATA	E02	38	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E03	44	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E04	47	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E05	20	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	E06	12	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	E07	47	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E08	5	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	E09	40	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E10	27	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E11	42	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	E12	19	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	F01	6	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	F02	40	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F03	41	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F04	2	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	F05	26	5000	DELETION	ISOGENIC
+2022-08-07_batch_METADATA	F06	48	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F07	39	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F08	48	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F09	30	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F10	8	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	F11	46	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	F12	32	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G01	14	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	G02	36	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G03	43	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G04	16	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	G05	45	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G06	4	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	G07	25	5000	DELETION	ISOGENIC
+2022-08-07_batch_METADATA	G08	34	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G09	44	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G10	15	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	G11	37	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	G12	7	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H01	10	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H02	25	5000	DELETION	ISOGENIC
+2022-08-07_batch_METADATA	H03	8	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H04	31	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	H05	18	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H06	21	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H07	3	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H08	23	5000	CONTROL	ISOGENIC
+2022-08-07_batch_METADATA	H09	33	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	H10	13	5000	CONTROL	HUMAN
+2022-08-07_batch_METADATA	H11	35	5000	DELETION	HUMAN
+2022-08-07_batch_METADATA	H12	22	5000	CONTROL	HUMAN

1.run-workflows/metadata/2022-08-07_batch/platemap/PE_PP_Plate2.txt

@@ -0,0 +1,97 @@
+plate_map_name	well_position	line_ID	plating_density	line_condition	line_source
+PE_PP_Plate2	A01	1	5000	control	human
+PE_PP_Plate2	A02	30	5000	deletion	human
+PE_PP_Plate2	A03	9	5000	control	human
+PE_PP_Plate2	A04	26	5000	deletion	isogenic
+PE_PP_Plate2	A05	4	5000	control	human
+PE_PP_Plate2	A06	34	5000	deletion	human
+PE_PP_Plate2	A07	15	5000	control	human
+PE_PP_Plate2	A08	36	5000	deletion	human
+PE_PP_Plate2	A09	2	5000	control	human
+PE_PP_Plate2	A10	16	5000	control	human
+PE_PP_Plate2	A11	20	5000	control	human
+PE_PP_Plate2	A12	12	5000	control	human
+PE_PP_Plate2	B01	17	5000	control	human
+PE_PP_Plate2	B02	39	5000	deletion	human
+PE_PP_Plate2	B03	37	5000	deletion	human
+PE_PP_Plate2	B04	42	5000	deletion	human
+PE_PP_Plate2	B05	7	5000	control	human
+PE_PP_Plate2	B06	29	5000	deletion	human
+PE_PP_Plate2	B07	11	5000	control	human
+PE_PP_Plate2	B08	38	5000	deletion	human
+PE_PP_Plate2	B09	43	5000	deletion	human
+PE_PP_Plate2	B10	18	5000	control	human
+PE_PP_Plate2	B11	6	5000	control	human
+PE_PP_Plate2	B12	29	5000	deletion	human
+PE_PP_Plate2	C01	27	5000	deletion	human
+PE_PP_Plate2	C02	41	5000	deletion	human
+PE_PP_Plate2	C03	32	5000	deletion	human
+PE_PP_Plate2	C04	46	5000	deletion	human
+PE_PP_Plate2	C05	1	5000	control	human
+PE_PP_Plate2	C06	33	5000	deletion	human
+PE_PP_Plate2	C07	14	5000	control	human
+PE_PP_Plate2	C08	9	5000	control	human
+PE_PP_Plate2	C09	23	5000	control	isogenic
+PE_PP_Plate2	C10	22	5000	control	human
+PE_PP_Plate2	C11	3	5000	control	human
+PE_PP_Plate2	C12	28	5000	deletion	human
+PE_PP_Plate2	D01	5	5000	control	human
+PE_PP_Plate2	D02	35	5000	deletion	human
+PE_PP_Plate2	D03	13	5000	control	human
+PE_PP_Plate2	D04	19	5000	control	human
+PE_PP_Plate2	D05	24	5000	control	isogenic
+PE_PP_Plate2	D06	17	5000	control	human
+PE_PP_Plate2	D07	21	5000	control	human
+PE_PP_Plate2	D08	28	5000	deletion	human
+PE_PP_Plate2	D09	31	5000	deletion	human
+PE_PP_Plate2	D10	10	5000	control	human
+PE_PP_Plate2	D11	45	5000	deletion	human
+PE_PP_Plate2	D12	11	5000	control	human
+PE_PP_Plate2	E01	24	5000	control	isogenic
+PE_PP_Plate2	E02	38	5000	deletion	human
+PE_PP_Plate2	E03	44	5000	deletion	human
+PE_PP_Plate2	E04	47	5000	deletion	human
+PE_PP_Plate2	E05	20	5000	control	human
+PE_PP_Plate2	E06	12	5000	control	human
+PE_PP_Plate2	E07	47	5000	deletion	human
+PE_PP_Plate2	E08	5	5000	control	human
+PE_PP_Plate2	E09	40	5000	deletion	human
+PE_PP_Plate2	E10	27	5000	deletion	human
+PE_PP_Plate2	E11	42	5000	deletion	human
+PE_PP_Plate2	E12	19	5000	control	human
+PE_PP_Plate2	F01	6	5000	control	human
+PE_PP_Plate2	F02	40	5000	deletion	human
+PE_PP_Plate2	F03	41	5000	deletion	human
+PE_PP_Plate2	F04	2	5000	control	human
+PE_PP_Plate2	F05	26	5000	deletion	isogenic
+PE_PP_Plate2	F06	48	5000	deletion	human
+PE_PP_Plate2	F07	39	5000	deletion	human
+PE_PP_Plate2	F08	48	5000	deletion	human
+PE_PP_Plate2	F09	30	5000	deletion	human
+PE_PP_Plate2	F10	8	5000	control	human
+PE_PP_Plate2	F11	46	5000	deletion	human
+PE_PP_Plate2	F12	32	5000	deletion	human
+PE_PP_Plate2	G01	14	5000	control	human
+PE_PP_Plate2	G02	36	5000	deletion	human
+PE_PP_Plate2	G03	43	5000	deletion	human
+PE_PP_Plate2	G04	16	5000	control	human
+PE_PP_Plate2	G05	45	5000	deletion	human
+PE_PP_Plate2	G06	4	5000	control	human
+PE_PP_Plate2	G07	25	5000	deletion	isogenic
+PE_PP_Plate2	G08	34	5000	deletion	human
+PE_PP_Plate2	G09	44	5000	deletion	human
+PE_PP_Plate2	G10	15	5000	control	human
+PE_PP_Plate2	G11	37	5000	deletion	human
+PE_PP_Plate2	G12	7	5000	control	human
+PE_PP_Plate2	H01	10	5000	control	human
+PE_PP_Plate2	H02	25	5000	deletion	isogenic
+PE_PP_Plate2	H03	8	5000	control	human
+PE_PP_Plate2	H04	31	5000	deletion	human
+PE_PP_Plate2	H05	18	5000	control	human
+PE_PP_Plate2	H06	21	5000	control	human
+PE_PP_Plate2	H07	3	5000	control	human
+PE_PP_Plate2	H08	23	5000	control	isogenic
+PE_PP_Plate2	H09	33	5000	deletion	human
+PE_PP_Plate2	H10	13	5000	control	human
+PE_PP_Plate2	H11	35	5000	deletion	human
+PE_PP_Plate2	H12	22	5000	control	human