merge Orr's changes into base

.gitignore

@@ -0,0 +1,5 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+*.Rproj

quality_control/QualityControl.Rmd

@@ -7,19 +7,25 @@
 title: "Quality Control"
 output: html_document
 params:
-  PROJECT_ID: "PROJECT_ID"
-  DATASET_DESCRIPTION: "Brief description of the single-cell dataset."
+  PROJECT_ID: "scalable-analysis-playground"
+  DATASET_DESCRIPTION: "Retinal Bipolar Neurons http://www.cell.com/cell/pdf/S0092-8674(16)31007-8.pdf"
   # This table must exist.
-  RAW_DATA_TABLE: "PROJECT_ID_THE_DATA_IS_IN.DATASET_NAME.TABLE_NAME"
+  RAW_DATA_TABLE: "scalable-analysis-playground.mouse_retinal_bipolar.scrna_seq"
   # These tables will be created.
-  CELL_METRICS_TABLE: "DESTINATION_DATASET_NAME.TABLE_NAME"
-  PASSING_CELLS_TABLE: "DESTINATION_DATASET_NAME.TABLE_NAME"
-  GENE_METRICS_TABLE: "DESTINATION_DATASET_NAME.TABLE_NAME"
-  PASSING_GENES_TABLE: "DESTINATION_DATASET_NAME.TABLE_NAME"
+  CELL_METRICS_TABLE: "orr_bp.cell_metrics"
+  PASSING_CELLS_TABLE: "orr_bp.passing_cells"
+  GENE_METRICS_TABLE: "orr_bp.gene_metrics"
+  PASSING_GENES_TABLE: "orr_bp.passing_genes"
+  MT_GENE_TABLE: "orr_bp.gene_table"
+  PASSING_MT_FRACTION: 0.1
+  MIN_GENES: 501  # SQL BETWEEN operator is inclusive for range, want > 500 genes/cell
+  MAX_GENES: 23000
+  MIN_CELLS: 30
+  MIN_COUNTS: 60
   # Only create the tables if they do not already exist.  For other options, see
   # https://cloud.google.com/dataflow/model/bigquery-io#writing-to-bigquery
-  WRITE_DISPOSITION: "WRITE_EMPTY"
-
+  CREATE_DISPOSITION: "CREATE_IF_NEEDED"
+  WRITE_DISPOSITION: "WRITE_TRUNCATE"  # CHANGE THIS TO WRITE_EMPTY SO USERS DO NOT OVERWRITE TABLE
 # This RMarkdown is a parameterized report.  See
 # http://rmarkdown.rstudio.com/developer_parameterized_reports.html
 # for more detail.
@@ -191,4 +197,5 @@ perform_bqquery(sql_path = "passing_genes.sql",
 
 ```{r passing_counts, comment=NA}
 perform_bqquery(sql_path = "passing_data_counts.sql")
+sessionInfo()
 ```

quality_control/cell_metrics.sql

@@ -5,7 +5,7 @@
 SELECT
   cell,
   SUM(trans_cnt) AS alltrans,
-  SUM(IF(gene LIKE "mt-%",
+  SUM(IF(gene IN (SELECT gene FROM `{{ MT_GENE_TABLE }}`),
       trans_cnt,
       0)) AS mttrans,
   COUNT(DISTINCT gene) AS gene_cnt

quality_control/gene_table.csv

@@ -0,0 +1,30 @@
+gene
+mt-Nd3
+mt-Tp
+mt-Tn
+mt-Atp6
+mt-Co1
+mt-Co2
+mt-Tf
+mt-Te
+mt-Co3
+mt-Tl2
+mt-Tl1
+mt-Tm
+mt-Ti
+mt-Rnr1
+mt-Tw
+mt-Ts2
+mt-Tv
+mt-Nd4
+mt-Tc
+mt-Nd1
+mt-Ty
+mt-Rnr2
+mt-Ta
+mt-Nd6
+mt-Tt
+mt-Nd2
+mt-Cytb
+mt-Tq
+mt-Nd5

quality_control/passing_cells.sql

@@ -9,5 +9,5 @@ SELECT
 FROM
   `{{ CELL_METRICS_TABLE }}`
 WHERE
-  .10 > mttrans/alltrans
-  AND 500 < gene_cnt
+  {{ PASSING_MT_FRACTION }} > mttrans/alltrans
+  AND gene_cnt BETWEEN {{ MIN_GENES }} AND {{ MAX_GENES }}

quality_control/passing_genes.sql

@@ -9,5 +9,5 @@ SELECT
 FROM
   `{{ GENE_METRICS_TABLE }}`
 WHERE
-  30 < cell_cnt
-  AND 60 < alltrans
+  {{ MIN_CELLS }} < cell_cnt
+  AND {{ MIN_COUNTS }} < alltrans

scalable_analytics.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX