Update list of accepted assays and bump schema to 2.0.1 (#1117)

chanzuckerberg · May 8, 2024 · 15b8c19 · 15b8c19
1 parent cf3d18e
commit 15b8c19
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 22 deletions.
diff --git a/docs/cellxgene_census_schema.md b/docs/cellxgene_census_schema.md
@@ -1,6 +1,6 @@
 # CZ CELLxGENE Discover Census Schema
 
-**Version**: 2.0.0
+**Version**: 2.0.1
 
 **Last edited**: March, 2024.
 

diff --git a/docs/census_accepted_assays.csv b/docs/census_accepted_assays.csv
@@ -1,9 +1,4 @@
 EFO:0003755,FL-cDNA
-EFO:0004158,random RNA-Seq across whole transcriptome
-EFO:0005684,RNA-seq of coding RNA from single cells
-EFO:0005685,RNA-seq of non coding RNA from single cells
-EFO:0008440,tag based single cell RNA sequencing
-EFO:0008441,full length single cell RNA sequencing
 EFO:0008640,3'T-fill
 EFO:0008641,3’-end-seq
 EFO:0008643,3′-Seq
@@ -43,7 +38,6 @@ EFO:0008897,RNAtag-Seq
 EFO:0008898,RNET-seq
 EFO:0008903,SC3-seq
 EFO:0008908,SCI-seq
-EFO:0008913,single-cell RNA sequencing
 EFO:0008919,Seq-Well
 EFO:0008929,SMA
 EFO:0008930,Smart-seq
@@ -63,9 +57,6 @@ EFO:0008975,TRAP-Seq
 EFO:0008978,TSS Sequencing
 EFO:0008980,UMI Method
 EFO:0009309,Div-Seq
-EFO:0009809,single nucleus RNA sequencing
-EFO:0009810,full length single nucleus RNA sequencing
-EFO:0009811,tag based single nucleus RNA sequencing
 EFO:0009899,10x 3' v2
 EFO:0009900,10x 5' v2
 EFO:0009901,10x 3' v1
@@ -100,7 +91,6 @@ EFO:0030031,SCOPE-chip
 EFO:0030061,mcSCRB-seq
 EFO:0030074,SORT-seq
 EFO:0030078,droplet-based single-cell RNA library preparation
-EFO:0030080,10x transcription profiling
 EFO:0700003,BD Rhapsody Whole Transcriptome Analysis
 EFO:0700004,BD Rhapsody Targeted mRNA
 EFO:0700010,TruDrop

diff --git a/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/globals.py b/tools/cellxgene_census_builder/src/cellxgene_census_builder/build_soma/globals.py
@@ -11,7 +11,7 @@
 # DataFrame columns. True is enabled, False is disabled.
 USE_ARROW_DICTIONARY = True
 
-CENSUS_SCHEMA_VERSION = "2.0.0"
+CENSUS_SCHEMA_VERSION = "2.0.1"
 
 CXG_SCHEMA_VERSION = "5.0.0"  # the CELLxGENE schema version supported
 
@@ -252,11 +252,7 @@
 # terms are excluded from the Census.
 RNA_SEQ = [
     "EFO:0003755",  # FL-cDNA
-    "EFO:0004158",  # random RNA-Seq across whole transcriptome
-    "EFO:0005684",  # RNA-seq of coding RNA from single cells
-    "EFO:0005685",  # RNA-seq of non coding RNA from single cells
-    "EFO:0008440",  # tag based single cell RNA sequencing
-    "EFO:0008441",  # full length single cell RNA sequencing
+    "EFO:0008440",  #
     "EFO:0008640",  # 3'T-fill
     "EFO:0008641",  # 3’-end-seq
     "EFO:0008643",  # 3′-Seq
@@ -296,7 +292,6 @@
     "EFO:0008898",  # RNET-seq
     "EFO:0008903",  # SC3-seq
     "EFO:0008908",  # SCI-seq
-    "EFO:0008913",  # single-cell RNA sequencing
     "EFO:0008919",  # Seq-Well
     "EFO:0008929",  # SMA
     "EFO:0008930",  # Smart-seq
@@ -316,9 +311,6 @@
     "EFO:0008978",  # TSS Sequencing
     "EFO:0008980",  # UMI Method
     "EFO:0009309",  # Div-Seq
-    "EFO:0009809",  # single nucleus RNA sequencing
-    "EFO:0009810",  # full length single nucleus RNA sequencing
-    "EFO:0009811",  # tag based single nucleus RNA sequencing
     "EFO:0009899",  # 10x 3' v2
     "EFO:0009900",  # 10x 5' v2
     "EFO:0009901",  # 10x 3' v1
@@ -353,7 +345,6 @@
     "EFO:0030061",  # mcSCRB-seq
     "EFO:0030074",  # SORT-seq
     "EFO:0030078",  # droplet-based single-cell RNA library preparation
-    "EFO:0030080",  # 10x transcription profiling
     "EFO:0700003",  # BD Rhapsody Whole Transcriptome Analysis
     "EFO:0700004",  # BD Rhapsody Targeted mRNA
     "EFO:0700010",  # TruDrop