aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPjotr Prins2016-07-21 12:55:23 +0600
committerPjotr Prins2016-07-21 12:55:23 +0600
commit48af807b4d8eabb0fac53451333fe7e85d38855b (patch)
treeb32e04e0a68c17753c84cc8017d12482883ca0a7
parent56636bf3fabedd3fb581ddc4a95fcf3e586fd607 (diff)
downloadgenenetwork2-48af807b4d8eabb0fac53451333fe7e85d38855b.tar.gz
Doc: SNP handling
-rw-r--r--doc/database.org50
1 files changed, 49 insertions, 1 deletions
diff --git a/doc/database.org b/doc/database.org
index 9c8c89f2..624174a4 100644
--- a/doc/database.org
+++ b/doc/database.org
@@ -945,7 +945,7 @@ INFO:base.data_set:.sql: get_trait_info:
(that is a bug!).
-** Fetch phenotypes
+** Fetch phenotype information
*** Through the trait page
When hitting the trait page, e.g.
@@ -1165,3 +1165,51 @@ select * from ProbeSetData limit 5;
5 rows in set (0.00 sec)
linked by ProbeSetXRef.dataid.
+** Fetch genotype information
+
+*** SNPs
+
+The SNP count info for the BXD is calculated like this
+
+#+begin_src python
+ while startMb<endMb:
+ snp_count = g.db.execute("""
+ select
+ count(*) from BXDSnpPosition
+ where
+ Chr = '%s' AND Mb >= %2.6f AND Mb < %2.6f AND
+ StrainId1 = %d AND StrainId2 = %d
+ """ % (chrName, startMb, startMb+stepMb, strainId1, strainId2)).fetchone()[0]
+ SNPCounts.append(snp_count)
+ startMb += stepMb
+#+end_src
+
+select * from BXDSnpPosition limit 5;
++------+-----------+-----------+----------+
+| Chr | StrainId1 | StrainId2 | Mb |
++------+-----------+-----------+----------+
+| 1 | 2 | 3 | 0.002477 |
+| 1 | 2 | 3 | 0.002592 |
+| 1 | 2 | 3 | 0.00283 |
+| 1 | 2 | 3 | 0.002994 |
+| 1 | 2 | 3 | 0.003299 |
++------+-----------+-----------+----------+
+
+Other SNP tables containing
+
+select * from SnpSource limit 5;
+Empty set (0.00 sec)
+
+select * from SnpAll limit 5;
+Empty set (0.00 sec)
+
+mysql> select * from SnpAll limit 5;
+Empty set (0.00 sec)
+
+mysql> select * from SnpPattern limit 5;
+Empty set (0.00 sec)
+
+mysql> select * from SnpSource limit 5;
+Empty set (0.00 sec)
+
+Hmmm. This is the test database. Then there are the plink files and VCF files.