d0choa

import pyspark.sql.functions as F
from pyspark import SparkConf
from pyspark.sql import SparkSession


sparkConf = SparkConf()

spark = (
    SparkSession.builder
    .config(conf=sparkConf)

d0choa

from pymol import cmd

cmd.load("/Users/ochoa/Downloads/AF-Q9HC29-F1-model_v1.cif")

cmd.bg_color("grey95")

cmd.set_color("veryHigh", [0, 83, 214])
cmd.set_color("confident", [101, 203, 243])
cmd.set_color("low", [255, 219, 19])
cmd.set_color("veryLow", [255, 125, 69])

d0choa

library("tidyverse")
library("googleAnalyticsR")
library("zoo")
library("lubridate")

date_range <- c("2019-01-01", as.character(Sys.Date() - 1))

# Authorisation
ga_auth()

d0choa

import pyspark.sql.functions as F
from pyspark import SparkConf
from pyspark.sql import SparkSession
from pyspark.sql.window import Window

sparkConf = SparkConf()
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.mode', 'AUTO')
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.project.id',
                          'open-targets-eu-dev')

d0choa

library(tidyverse)
library(cowplot)
library(ggrepel)

df <- bind_rows(
    read_csv("~/Projects/ot-release-metrics/data/21.06.5.csv"),
    read_csv("~/Projects/ot-release-metrics/data/21.09.2.csv")
)

df %>%

d0choa

import pyspark.sql.functions as F
from pyspark import SparkConf
from pyspark.sql import SparkSession

sparkConf = SparkConf()
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.mode', 'AUTO')
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.project.id',
                          'open-targets-eu-dev')

# establish spark connection

d0choa

---
title: "Batch-query all platform evidence associated with a gene/target list (R)"
output:
  md_document:
    variant: markdown_github
---

How to batch-access information related to a list of targets from the Open Targets Platform is a recurrent question. Here, I provide an example on how to access all target-disease evidence for a set of IFN-gamma signalling related proteins. I will further reduce the evidence to focus on all the coding or non-coding variants clinically-associated with the gene list of interest. I used R and sparklyr, but a Python implementation would be very similar. The platform documentation and the community space have very similar examples. 

d0choa

library("tidyverse")
library("sparklyr")
library("sparklyr.nested")
library("cowplot")
library("ggsci")

#Spark config
config <- spark_config()

# Allowing to GCP datasets access

d0choa

import pyspark.sql.functions as F
from pyspark import SparkConf
from pyspark.sql import SparkSession

sparkConf = SparkConf()
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.mode', 'AUTO')
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.project.id',
                          'open-targets-eu-dev')

# establish spark connection

d0choa

from os import sep
import pyspark.sql.functions as F
from pyspark import SparkConf
from pyspark.sql import SparkSession

sparkConf = SparkConf()
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.mode', 'AUTO')
sparkConf = sparkConf.set('spark.hadoop.fs.gs.requester.pays.project.id',
                          'open-targets-eu-dev')