def process():
logger.info("Processing data...")
df = pd.read_csv(os.path.join(dataDir, FILE), sep=",")
cleaned = clean_ids(df["Gwas.id"].values)
df["Gwas.id"] = cleaned
logger.info("\n{}", df.head())
df.rename(
columns={
"Gene.ensembl_id": "source",
"Gwas.id": "target",
"XQTL_MULTI_SNP_MR.b": "beta",
"XQTL_MULTI_SNP_MR.se": "se",
"XQTL_MULTI_SNP_MR.p": "p",
"XQTL_MULTI_SNP_MR.qtl_type": "qtl_type",
"XQTL_MULTI_SNP_MR.mr_method": "mr_method",
},
inplace=True,
)
logger.info(df.shape)
logger.info("\n{}", df.head())
df.drop_duplicates(inplace=True)
logger.info(df.shape)
logger.info("\n{}", df.head())
create_import(df=df, meta_id=meta_id)
def process_data():
logger.info("Processing mr data...")
col_names = [
"source",
"target",
"method",
"nsnp",
"b",
"se",
"ci_low",
"ci_upp",
"pval",
"selection",
"moescore",
]
data = os.path.join(dataDir, FILE)
df = pd.read_csv(data,header=None)
df.columns = col_names
logger.info(df.shape)
df.dropna(subset=['pval','se'])
df.drop_duplicates(inplace=True)
logger.info(df.shape)
logger.info(df.head())
create_import(df=df, meta_id=meta_id)
def gene():
FILE = get_source(meta_id, 1)
data = os.path.join(dataDir, FILE)
df = pd.read_csv(data, sep="\t")
# add column names
col_names = [
"chr",
"type",
"name",
"description",
"biomart_source",
"ensembl_id",
"start",
"end",
]
df.columns = col_names
df.drop_duplicates(inplace=True)
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (g:Gene) ASSERT g.ensembl_id IS UNIQUE",
"CREATE INDEX ON :Gene(name)",
"CREATE INDEX ON :Gene(chr)",
]
create_constraints(constraintCommands, meta_id)
def process():
# select the file
FILE = get_source(meta_id, 1)
logger.info("Reading {}", FILE)
df = pd.read_csv(os.path.join(dataDir, FILE))
# logger.info(df.columns)
logger.info(df.shape)
# drop some columns
df.drop(["access", "priority", "coverage", ""],
axis=1,
inplace=True,
errors="ignore")
logger.info(df.shape)
# create the csv and import data
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (g:Gwas) ASSERT g.id IS UNIQUE",
"CREATE index on :Gwas(trait)",
"CREATE index on :Gwas(filename)",
]
create_constraints(constraintCommands, meta_id)
def process():
logger.info("loading semrep data...{}", FILE)
sem_df = pd.read_csv(os.path.join(dataDir, FILE),
sep=",",
compression="gzip")
logger.info(sem_df)
#create new ids
logger.info('Dealing with IDs')
sub_id = sem_df.apply(lambda row: make_id(row, 'sub'), axis=1)
obj_id = sem_df.apply(lambda row: make_id(row, 'obj'), axis=1)
sem_df['sub_id_all'] = sub_id
sem_df['obj_id_all'] = obj_id
# need to split subject and object ids by ,
logger.info(sem_df.shape)
sem_df = (sem_df.assign(sub_id_all=sem_df.sub_id_all.str.split(
",")).explode("sub_id_all").reset_index(drop=True))
logger.info(sem_df.shape)
sem_df = (sem_df.assign(obj_id_all=sem_df.obj_id_all.str.split(
",")).explode("obj_id_all").reset_index(drop=True))
logger.info(sem_df.shape)
keep_cols = ["sub_id_all", "pred", "obj_id_all"]
sem_df = sem_df[keep_cols]
sem_df = pd.DataFrame({
"count": sem_df.groupby(keep_cols).size()
}).reset_index()
logger.info(sem_df.shape)
sem_df.drop_duplicates(inplace=True)
logger.info(sem_df.shape)
sem_df.columns = ["source", "predicate", "target", "count"]
logger.info("\n {}", sem_df)
create_import(df=sem_df, meta_id=meta_id)
def process():
# load predicate data
logger.info("loading data...")
df = pd.read_csv(
os.path.join(dataDir, FILE), sep=",", compression="gzip"
)
logger.info(df.shape)
# group
# keep_cols = ["predicate","subject_name","object_name","subject_type","object_type","subject_id","object_id","id"]
keep_cols = ["PMID", "predicate", "subject_id", "object_id", "id"]
# need to split subject and object ids by |
df = (
df.assign(subject_id=df.subject_id.str.split("|"))
.explode("subject_id")
.reset_index(drop=True)
)
logger.info(df.shape)
df = (
df.assign(object_id=df.object_id.str.split("|"))
.explode("object_id")
.reset_index(drop=True)
)
logger.info(df.shape)
logger.info("\n {}", df)
df["id"] = df["subject_id"] + ":" + df["predicate"] + ":" + df["object_id"]
df = df[["PMID", "id"]]
logger.info(df.shape)
df.drop_duplicates(inplace=True)
logger.info(df.shape)
df.columns = ["target", "source"]
logger.info("\n {}", df)
create_import(df=df, meta_id=meta_id)
def process():
# load predicate data
logger.info("loading predication data...")
pred_df = pd.read_csv(os.path.join(dataDir, PREDICATION_FILE),
sep=",",
compression="gzip")
pred_df["PMID"] = pred_df["PMID"].astype(str)
logger.info("loading citation data...")
df = pd.read_csv(os.path.join(dataDir, PUB_FILE),
sep="\t",
compression="gzip")
df.columns = ["id", "issn", "dp", "edat", "year"]
df["id"] = df["id"].str.replace("'", "")
logger.info(df.shape)
# merge with predication data
df_merge = df.merge(pred_df["PMID"], left_on="id", right_on="PMID")
logger.info(df_merge.shape)
# drop PMID column
df_merge.drop("PMID", inplace=True, axis=1)
# make unique
df_merge.drop_duplicates(inplace=True)
logger.info(df_merge.shape)
logger.info(df_merge.shape)
logger.info("\n {}", df_merge.head())
create_import(df=df_merge, meta_id=args.name)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (s:Literature) ASSERT s.id IS UNIQUE;",
]
create_constraints(constraintCommands, meta_id)
def process_data():
logger.info("Processing vep data {}", vep_data)
col_names = [
"source",
"location",
"allele",
"target",
"feature",
"feature_type",
"consequence",
"cdna_position",
"cds_position",
"protein_position",
"amino_acids",
"codons",
"existing_variation",
"extra",
]
# create csv file
df = pd.read_csv(os.path.join(dataDir, vep_data), sep="\t", comment="#")
df.drop_duplicates(inplace=True)
df.columns = col_names
print(df.head())
create_import(df=df, meta_id=meta_id)
def process():
df = pd.read_csv(os.path.join(dataDir, FILE), sep="\t").drop_duplicates()
print(df.head())
print(df.shape)
df.columns = ["source", "target", "gene_relationship_type", "last_updated"]
logger.info(df.shape)
logger.info("\n {}", df.head())
create_import(df=df, meta_id=meta_id)
def gwas():
df = pd.read_csv(os.path.join(dataDir, FILE), low_memory=False)
df = df[["id", "rsid", "beta", "p"]].drop_duplicates()
# edit column names to match schema
df.rename(columns={"id": "source", "rsid": "target", "p": "pval"}, inplace=True)
create_import(df=df, meta_id=meta_id)
def process():
df = pd.read_csv(os.path.join(dataDir, FILE), sep="\t")
print(df.head())
print(df.shape)
df.columns = ["source", "target"]
logger.info(df.shape)
logger.info("\n {}", df.head())
create_import(df=df, meta_id=meta_id)
def process():
merge = merge_data(BIO_DATA, BIO_SEM)
logger.info(merge.shape)
create_import(df=merge, meta_id=args.name)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (s:Literature) ASSERT s.id IS UNIQUE;",
]
create_constraints(constraintCommands, meta_id)
def process():
df = pd.read_csv(os.path.join(dataDir, FILE))
logger.info(df.head())
keep_cols = ["source_id", "reactome_id"]
df = df[keep_cols]
df.rename(columns={"source_id": "source", "reactome_id": "target"}, inplace=True)
df.drop_duplicates(inplace=True)
logger.info(df.head())
create_import(df=df, meta_id=meta_id)
def process():
# load predicate data
logger.info("loading data...")
df = pd.read_csv(os.path.join(dataDir, FILE), sep="\t", compression="gzip")
logger.info(df.shape)
col_names = ["source", "target", "score"]
df.columns = col_names
df.drop_duplicates(inplace=True)
logger.info(df.shape)
logger.info("\n {}", df)
create_import(df=df, meta_id=meta_id)
def protein():
data = os.path.join(dataDir, FILE)
df = pd.read_csv(data, sep="\t")
df.columns = ["uniprot_id"]
df["name"] = df["uniprot_id"]
create_import(df=df, meta_id=meta_id)
constraintCommands = [
"CREATE CONSTRAINT ON (p:Protein) ASSERT p.uniprot_id IS UNIQUE",
"CREATE index on :Protein(name);",
]
create_constraints(constraintCommands, meta_id)
def process():
logger.info("Loading efo...")
data = os.path.join(dataDir, FILE)
df = pd.read_csv(data)
df.drop_duplicates(inplace=True)
df.rename(columns={
'efo.id': "target",
'parent_efo.id': "source"
},
inplace=True)
logger.info("\n{}", df.head())
create_import(df=df, meta_id=meta_id)
def process():
logger.info("Loading efo...{}", FILE)
df = pd.read_csv(
os.path.join(dataDir, FILE),
sep="\t",
names=["target", "efo_value", "score", "gwas_value", "source"],
)
df = df.drop(["efo_value", "gwas_value"], axis=1)
logger.info("\n{}", df.head())
logger.info(df.shape)
df.drop_duplicates(inplace=True)
logger.info(df.shape)
create_import(df=df, meta_id=meta_id)
def process():
FILE = get_source(meta_id, 1)
df = pd.read_csv(os.path.join(dataDir, FILE), low_memory=False)
df = df[["rsid"]].drop_duplicates()
# change column name to match schema
df.rename(columns={"rsid": "name"}, inplace=True)
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (v:Variant) ASSERT v.name IS UNIQUE;",
]
create_constraints(constraintCommands, meta_id)
def process():
data = os.path.join(dataDir, FILE)
# not sure why double quotes weren't being handled properly, added engine param
df = pd.read_csv(data, sep=",", engine="python")
logger.info(df.shape)
logger.info("\n {}", df.head())
keep_cols = ["molecule_name", "target_id", "action_type", "phase"]
df = df[keep_cols]
col_names = ["source", "target", "action_type", "phase"]
df.columns = col_names
df["source"] = df["source"].str.upper()
df.drop_duplicates(inplace=True)
logger.info(df.shape)
logger.info("\n {}", df.head())
create_import(df=df, meta_id=meta_id)
def process():
# load predicate data
logger.info("loading data... {}", FILE)
df = pd.read_csv(os.path.join(dataDir, FILE),
sep="\t",
compression="gzip",
header=None)
logger.info(df.shape)
col_names = [
"query",
"triple",
"subject_name",
"subject_type",
"subject_id",
"predicate",
"object_name",
"object_type",
"object_id",
"localCount",
"localTotal",
"globalCount",
"globalTotal",
"odds",
"pval",
"pmids",
"gwas-id",
]
df.columns = col_names
logger.info(df.shape)
keep_cols = ["pmids", "gwas-id"]
df = df[keep_cols]
# group
# keep_cols = ["predicate","subject_name","object_name","subject_type","object_type","subject_id","object_id","id"]
# need to split pmids
df = (df.assign(
pmids=df.pmids.str.split(" ")).explode("pmids").reset_index(drop=True))
logger.info(df.shape)
logger.info("\n {}", df)
df.drop_duplicates(inplace=True)
df.columns = ["target", "source"]
logger.info(df.shape)
logger.info("\n {}", df)
create_import(df=df, meta_id=meta_id)
def process():
df = pd.read_csv(os.path.join(dataDir, FILE))
logger.info(df.head())
keep_cols = ["source_id"]
df = df[keep_cols]
df.rename(columns={"source_id": "uniprot_id"}, inplace=True)
df["name"] = df["uniprot_id"]
df.drop_duplicates(inplace=True)
logger.info(df.head())
create_import(df=df, meta_id=meta_id)
constraintCommands = [
"CREATE CONSTRAINT ON (p:Protein) ASSERT p.uniprot_id IS UNIQUE",
"CREATE index on :Protein(name);",
]
create_constraints(constraintCommands, meta_id)
def variant():
print("Reading...", FILE)
df = pd.read_csv(os.path.join(dataDir, FILE))
print("Writing...")
# create csv
df.rename(columns={"rsid": "name"}, inplace=True)
df = df[["name"]].drop_duplicates()
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (v:Variant) ASSERT v.name IS UNIQUE;",
"CREATE index on :Variant(chr);",
"CREATE index on :Variant(pos);",
]
create_constraints(constraintCommands, meta_id)
def process():
logger.info("Processing data...")
FILE = "XQTL_SINGLE_SNP_MR_SNP_GENE.csv"
df = pd.read_csv(os.path.join(dataDir, FILE), sep=",")
df.rename(columns={
"Snp.name": "source",
"Gene.ensembl_id": "target",
},
inplace=True)
logger.info(df.shape)
logger.info("\n{}", df.head())
df.drop_duplicates(inplace=True)
logger.info(df.shape)
logger.info("\n{}", df.head())
create_import(df=df, meta_id=meta_id)
def process():
data = os.path.join(dataDir, FILE)
# not sure why double quotes weren't being handled properly, added engine param
df = pd.read_csv(data, sep=",", engine="python")
logger.info(df.shape)
logger.info("\n {}", df.head())
#get disease data
disease_df = get_disease_data()
disease_df['mondo_efo_id'] = 'http://www.ebi.ac.uk/efo/EFO_' + disease_df[
'mondo_efo_id'].astype(str)
logger.info(disease_df)
keep_cols = [
"molecule_name",
"efo_id",
]
df = df[keep_cols]
mondo_match = pd.merge(df,
disease_df,
left_on='efo_id',
right_on='disease_id')[[
'molecule_name', 'disease_id'
]]
#logger.info(mondo_match)
efo_match = pd.merge(df,
disease_df,
left_on='efo_id',
right_on='mondo_efo_id')[[
'molecule_name', 'disease_id'
]]
#logger.info(efo_match)
cat_df = pd.concat([mondo_match, efo_match])
logger.info(cat_df.shape)
cat_df.drop_duplicates(inplace=True)
logger.info(cat_df.shape)
col_names = ["source", "target"]
cat_df.columns = col_names
cat_df["source"] = cat_df["source"].str.upper()
create_import(df=cat_df, meta_id=meta_id)
def process_data():
print("Processing instruments...")
csv_data = []
col_names = [
"target",
"source",
"beta",
"se",
"pval",
"eaf",
"samplesize",
"ncase",
"ncontrol",
]
with gzip.open(os.path.join(dataDir, FILE), "rt") as f:
next(f)
filereader = csv.reader(f, delimiter=",")
for line in filereader:
variant, gwas, beta, se, pval, eaf, samplesize, ncase, ncontrol = line
try:
float(pval)
float(se)
float(eaf)
except ValueError:
continue
if not gwas.startswith("UKB"):
gwas = "IEU-a-" + gwas
gwas = gwas.replace(":", "-")
t = [
variant,
gwas.lower(),
beta,
se,
pval,
eaf,
str(int(float(samplesize))),
ncase,
ncontrol,
]
csv_data.append(t)
# create csv file
df = pd.DataFrame(csv_data)
df.columns = col_names
print(df.head())
create_import(df=df, meta_id=meta_id)
def process():
# load predicate data
logger.info("loading data...")
df = pd.read_csv(os.path.join(dataDir, PREDICATION_FILE),
sep=",",
compression="gzip")
logger.info(df.shape)
# need to split subject and object ids by |
df = (df.assign(subject_id=df.subject_id.str.split("|")).explode(
"subject_id").reset_index(drop=True))
logger.info(df.shape)
df = (df.assign(object_id=df.object_id.str.split("|")).explode(
"object_id").reset_index(drop=True))
logger.info(df.shape)
logger.info("\n {}", df)
df["id"] = df["subject_id"] + ":" + df["predicate"] + ":" + df["object_id"]
df["name"] = df["subject_name"] + " " + df["predicate"] + " " + df[
"object_name"]
# keep_cols = ["predicate","subject_name","object_name","subject_type","object_type","subject_id","object_id","id"]
keep_cols = ["predicate", "subject_id", "object_id", "id", "name"]
#df = pd.DataFrame({"count": df.groupby(keep_cols).size()}).reset_index()
df = df[keep_cols]
df.drop_duplicates(subset=['id'], inplace=True)
logger.info(df.shape)
logger.info("\n {}", df.head())
#drop nas/rows with empty string
df.replace('', np.nan, inplace=True)
df.dropna(inplace=True)
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (s:LiteratureTriple) ASSERT s.id IS UNIQUE",
"CREATE INDEX ON :LiteratureTriple(name);",
"CREATE INDEX ON :LiteratureTriple(subject_id);",
"CREATE INDEX ON :LiteratureTriple(object_id);",
"CREATE INDEX ON :LiteratureTriple(predicate);",
]
create_constraints(constraintCommands, meta_id)
def process():
df = pd.read_csv(os.path.join(dataDir, FILE))
logger.info(df.head())
keep_cols = ["reactome_id", "name"]
df = df[keep_cols]
df["url"] = "https://reactome.org/PathwayBrowser/#/" + df["reactome_id"]
df.rename(columns={"reactome_id": "id"}, inplace=True)
df.drop_duplicates(inplace=True)
logger.info(df["url"].head())
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (p:Pathway) ASSERT p.id IS UNIQUE",
"CREATE index on :Pathway(name);",
]
create_constraints(constraintCommands, meta_id)
def process():
data = os.path.join(dataDir, FILE)
df = pd.read_csv(data, sep=",")
logger.info("\n {}", df.head())
keep_cols = ["molecule_name", "molecule_type", "chembl_uri"]
df = df[keep_cols]
col_names = ["label", "molecule_type", "id"]
df.columns = col_names
df.drop_duplicates(inplace=True)
# set label to uppercase
df["label"] = df["label"].str.upper()
logger.info(df.shape)
logger.info("\n {}", df.head())
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = ["CREATE index on :Drug(label);"]
create_constraints(constraintCommands, meta_id)
def process():
logger.info("loading semrep data...{}",FILE)
sem_df = pd.read_csv(os.path.join(dataDir, FILE), sep=",", compression="gzip")
logger.info(sem_df)
#create new ids
logger.info('Dealing with IDs')
sub_id = sem_df.apply(lambda row : make_id(row,'sub'), axis = 1)
obj_id = sem_df.apply(lambda row : make_id(row,'obj'), axis = 1)
sem_df['sub_id_all']=sub_id
sem_df['obj_id_all']=obj_id
# need to split subject and object ids by ,
logger.info(sem_df.shape)
sem_df = (
sem_df.assign(sub_id_all=sem_df.sub_id_all.str.split(","))
.explode("sub_id_all")
.reset_index(drop=True)
)
logger.info(sem_df.shape)
sem_df = (
sem_df.assign(obj_id_all=sem_df.obj_id_all.str.split(","))
.explode("obj_id_all")
.reset_index(drop=True)
)
logger.info(sem_df.shape)
sem_id = sem_df['sub_id_all']+':'+sem_df['pred']+':'+sem_df['obj_id_all']
logger.debug(sem_id)
sem_df['id']=sem_id
logger.info("\n{}", sem_df)
logger.info(sem_df.shape)
sem_df.rename(columns={'sub_id_all':'subject_id'},inplace=True)
keep_cols = ["subject_id", "id"]
sem_df = sem_df[keep_cols]
logger.info(sem_df.shape)
sem_df.drop_duplicates(inplace=True)
sem_df.columns = ["target", "source"]
logger.info(sem_df.shape)
logger.info("\n {}", sem_df.head())
create_import(df=sem_df, meta_id=meta_id)
def process():
data = os.path.join(dataDir, FILE)
# some bad rows caused by extra commas so need to skip
df = pd.read_csv(data, sep=",", skiprows=1, error_bad_lines=False)
keep_cols = ["Drug"]
df = df[keep_cols]
df.drop_duplicates(inplace=True)
df.columns = ["label"]
# set label to uppercase
df["label"] = df["label"].str.upper()
logger.info(df.shape)
logger.info("\n {}", df.head())
create_import(df=df, meta_id=meta_id)
# create constraints
constraintCommands = [
"CREATE CONSTRAINT ON (s:Drug) ASSERT s.label IS UNIQUE;"
]
create_constraints(constraintCommands, meta_id)
