aboutsummaryrefslogtreecommitdiff
path: root/gn3/db
diff options
context:
space:
mode:
authorFrederick Muriuki Muriithi2021-09-27 04:48:53 +0300
committerFrederick Muriuki Muriithi2021-09-27 04:48:53 +0300
commit19783a18c2bc7941fc5980e593f19fb1d18c3623 (patch)
treef3a6e241be3c6224b9647c8258c516a7b741a28c /gn3/db
parent8d9bc0f29ce9208306915b079818e6f0c31785e2 (diff)
downloadgenenetwork3-19783a18c2bc7941fc5980e593f19fb1d18c3623.tar.gz
Update terminology: `strain` to `sample`
Issue: https://github.com/genenetwork/gn-gemtext-threads/blob/main/topics/gn1-migration-to-gn2/clustering.gmi * Update the terminology used: use `sample` in place of `strain` according to Zachary's direction at https://github.com/genenetwork/genenetwork3/pull/37#issuecomment-926043306
Diffstat (limited to 'gn3/db')
-rw-r--r--gn3/db/genotypes.py8
-rw-r--r--gn3/db/traits.py44
2 files changed, 26 insertions, 26 deletions
diff --git a/gn3/db/genotypes.py b/gn3/db/genotypes.py
index 9987320..8f18cac 100644
--- a/gn3/db/genotypes.py
+++ b/gn3/db/genotypes.py
@@ -14,16 +14,16 @@ def build_genotype_file(
def load_genotype_samples(genotype_filename: str, file_type: str = "geno"):
"""
- Load sample of strains from genotype files.
+ Load sample of samples from genotype files.
DESCRIPTION:
- Traits can contain a varied number of strains, some of which do not exist in
+ Traits can contain a varied number of samples, some of which do not exist in
certain genotypes. In order to compute QTLs, GEMMAs, etc, we need to ensure
- to pick only those strains that exist in the genotype under consideration
+ to pick only those samples that exist in the genotype under consideration
for the traits used in the computation.
This function loads a list of samples from the genotype files for use in
- filtering out unusable strains.
+ filtering out unusable samples.
PARAMETERS:
diff --git a/gn3/db/traits.py b/gn3/db/traits.py
index 4fc47c3..c9d05d7 100644
--- a/gn3/db/traits.py
+++ b/gn3/db/traits.py
@@ -445,7 +445,7 @@ def retrieve_temp_trait_data(trait_info: dict, conn: Any):
query,
{"trait_name": trait_info["trait_name"]})
return [dict(zip(
- ["strain_name", "value", "se_error", "nstrain", "id"], row))
+ ["sample_name", "value", "se_error", "nstrain", "id"], row))
for row in cursor.fetchall()]
return []
@@ -484,7 +484,7 @@ def retrieve_geno_trait_data(trait_info: Dict, conn: Any):
"species_id": retrieve_species_id(
trait_info["db"]["riset"], conn)})
return [dict(zip(
- ["strain_name", "value", "se_error", "id"], row))
+ ["sample_name", "value", "se_error", "id"], row))
for row in cursor.fetchall()]
return []
@@ -515,7 +515,7 @@ def retrieve_publish_trait_data(trait_info: Dict, conn: Any):
{"trait_name": trait_info["trait_name"],
"dataset_id": trait_info["db"]["dataset_id"]})
return [dict(zip(
- ["strain_name", "value", "se_error", "nstrain", "id"], row))
+ ["sample_name", "value", "se_error", "nstrain", "id"], row))
for row in cursor.fetchall()]
return []
@@ -548,7 +548,7 @@ def retrieve_cellid_trait_data(trait_info: Dict, conn: Any):
"trait_name": trait_info["trait_name"],
"dataset_id": trait_info["db"]["dataset_id"]})
return [dict(zip(
- ["strain_name", "value", "se_error", "id"], row))
+ ["sample_name", "value", "se_error", "id"], row))
for row in cursor.fetchall()]
return []
@@ -577,29 +577,29 @@ def retrieve_probeset_trait_data(trait_info: Dict, conn: Any):
{"trait_name": trait_info["trait_name"],
"dataset_name": trait_info["db"]["dataset_name"]})
return [dict(zip(
- ["strain_name", "value", "se_error", "id"], row))
+ ["sample_name", "value", "se_error", "id"], row))
for row in cursor.fetchall()]
return []
-def with_strainlist_data_setup(strainlist: Sequence[str]):
+def with_samplelist_data_setup(samplelist: Sequence[str]):
"""
- Build function that computes the trait data from provided list of strains.
+ Build function that computes the trait data from provided list of samples.
PARAMETERS
- strainlist: (list)
- A list of strain names
+ samplelist: (list)
+ A list of sample names
RETURNS:
Returns a function that given some data from the database, computes the
- strain's value, variance and ndata values, only if the strain is present
- in the provided `strainlist` variable.
+ sample's value, variance and ndata values, only if the sample is present
+ in the provided `samplelist` variable.
"""
def setup_fn(tdata):
- if tdata["strain_name"] in strainlist:
+ if tdata["sample_name"] in samplelist:
val = tdata["value"]
if val is not None:
return {
- "strain_name": tdata["strain_name"],
+ "sample_name": tdata["sample_name"],
"value": val,
"variance": tdata["se_error"],
"ndata": tdata.get("nstrain", None)
@@ -607,19 +607,19 @@ def with_strainlist_data_setup(strainlist: Sequence[str]):
return None
return setup_fn
-def without_strainlist_data_setup():
+def without_samplelist_data_setup():
"""
Build function that computes the trait data.
RETURNS:
Returns a function that given some data from the database, computes the
- strain's value, variance and ndata values.
+ sample's value, variance and ndata values.
"""
def setup_fn(tdata):
val = tdata["value"]
if val is not None:
return {
- "strain_name": tdata["strain_name"],
+ "sample_name": tdata["sample_name"],
"value": val,
"variance": tdata["se_error"],
"ndata": tdata.get("nstrain", None)
@@ -627,7 +627,7 @@ def without_strainlist_data_setup():
return None
return setup_fn
-def retrieve_trait_data(trait: dict, conn: Any, strainlist: Sequence[str] = tuple()):
+def retrieve_trait_data(trait: dict, conn: Any, samplelist: Sequence[str] = tuple()):
"""
Retrieve trait data
@@ -650,23 +650,23 @@ def retrieve_trait_data(trait: dict, conn: Any, strainlist: Sequence[str] = tupl
if results:
# do something with mysqlid
mysqlid = results[0]["id"]
- if strainlist:
+ if samplelist:
data = [
item for item in
- map(with_strainlist_data_setup(strainlist), results)
+ map(with_samplelist_data_setup(samplelist), results)
if item is not None]
else:
data = [
item for item in
- map(without_strainlist_data_setup(), results)
+ map(without_samplelist_data_setup(), results)
if item is not None]
return {
"mysqlid": mysqlid,
"data": dict(map(
lambda x: (
- x["strain_name"],
- {k:v for k, v in x.items() if x != "strain_name"}),
+ x["sample_name"],
+ {k:v for k, v in x.items() if x != "sample_name"}),
data))}
return {}