library(InterMineR)

listMines()

humanMine <- listMines()["HumanMine"] #select humanmine
humanMine #print out the value to see what's inside

im <- initInterMine(mine=humanMine, "YOUR TOKEN HERE")

query1Diabetes <- setQuery( 
  # here we're choosing which columns of data we'd like to see
  select = c("Gene.primaryIdentifier", "Gene.symbol"),
    # set the logic for constraints. The first constraint is the first path+operator+value, 
    # e.g. Gene.organism.name = Homo sapiens, and the second constraint is the combination 
    # of the second path+operator+value, e.g. Gene.diseases.name CONTAINS diabetes
  where = setConstraints(
    paths = c("Gene.organism.name", "Gene.diseases.name"),
    operators = c("=", "CONTAINS"),
    values = list("Homo sapiens","diabetes")
  )
)

query1DiabetesResults <- runQuery(im,query1Diabetes)

# and let's print out the first few results to make sure it looks like we'd expect:
head(query1DiabetesResults)

# We don't want to see *all* genes and their expression. 
# Let's narrow it down a little by constraining it to genes that are of interest
query2UpInPancreasConstraint = setConstraints(
  paths = c("Gene", 
            "Gene.proteinAtlasExpression.level", 
            "Gene.proteinAtlasExpression.level", 
            "Gene.proteinAtlasExpression.tissue.name"),
  operators = c("IN", rep("=", 3)),
  # each constraint is automatically given a code, allowing us to manipulate the 
  # logic for the constraint. 
  #  So for us, constraints are set to codes A, B, C, D in order, 
  #  e.g. Code A: "Gene" should be "IN" the list named "PL_DiabetesGenes"
  #       Code B: "Gene.proteinAtlasExpression.level" should be equal to "Medium"
  #       Code C: "Gene.proteinAtlasExpression.level" should be equal to "High"
  #       Code D: "Gene.proteinAtlasExpression.tissue.name" should be equal to Pancreas"
  # 
  # Now, you might be thinking "how can the expression level be equal to both Medium
  # AND High?" The answer is - it can't, but take a quick look at the constraintLogic
  # we will set in the next code cell for an explanation
  values = list("PL_Pax6_Targets", "Medium", "High", "Pancreas")
)

# Create a new query
query2UpInPancreas = newQuery(
  # Choose which columns of data we'd like to see
  view = c("Gene.primaryIdentifier",
             "Gene.symbol",
             "Gene.proteinAtlasExpression.cellType",
             "Gene.proteinAtlasExpression.level",
             "Gene.proteinAtlasExpression.tissue.name"
  ),
  # set the logic for constraints. This means our pancreas expression level 
  # is EITHER Medium (B) or High (C), but not both.
  # --
  # Note: Constraint logic only needs to be set if you wish to use OR. All other
  # constraints have AND logic applied by default. 
  constraintLogic = "A and (B or C) and D"
)

# Add the constraint to our expressed pancreas query (previously we just _defined_ the constraint)
query2UpInPancreas$where <- query2UpInPancreasConstraint

# Now we have the query set up the way we want, let's actually *run* the query! 
query2UpInPancreasResults <-  runQuery(im = im, qry = query2UpInPancreas)

# Show me the first few results please! 
head(query2UpInPancreasResults) 

# Extract the primaryIdentifier columns from query1 (diabetes genes) and query 2 (upexpressed in pancreas)
primaryIdentifiers.diabetes <- query1DiabetesResults[["Gene.primaryIdentifier"]]
primaryIdentifiers.pancreas <- query2UpInPancreasResults[["Gene.primaryIdentifier"]]

# Find the intersection of the two lists of primary identifiers
diabetesAndPancreasGenes <- intersect(primaryIdentifiers.diabetes,primaryIdentifiers.pancreas)

# Show the results
print(diabetesAndPancreasGenes)

# First, we set up the constraints. The last three constraints are the 
# diabetesAndPancreas result genes from our last query.
query3GWASConstraints <- setConstraints(
    paths = c("GWAS.results.pValue", 
              "GWAS.results.phenotype",
              # using rep so we don't have to type this three times... 
              rep("GWAS.results.associatedGenes.primaryIdentifier",3)
             ),
    operators = c("<=", 
                  "CONTAINS",
                  rep("=",3)),
    values = list("1e-04",   #A
                  "diabetes",#B 
                  "3172",    #C
                  "6928",    #D
                  "6934")    #E
  )

query3GWAS <- newQuery( 
  # Quite a few columns this time!
  view = c("GWAS.results.associatedGenes.primaryIdentifier",
    "GWAS.results.associatedGenes.symbol", "GWAS.results.associatedGenes.name",
    "GWAS.results.SNP.primaryIdentifier", "GWAS.results.pValue", "GWAS.results.phenotype",
    "GWAS.firstAuthor", "GWAS.name", "GWAS.publication.pubMedId",
    "GWAS.results.associatedGenes.organism.shortName"),
    # set the logic for constraints. Remember that we want our results
    # to include any one of the three genes we found in the list of diabetes+pancreas genes
    # so we need to use some OR logic.
  constraintLogic = "A and B and (C or D or E)"
)

#add constraint
query3GWAS$where <- query3GWASConstraints
#run query
query3GWASResults <- runQuery(im, query3GWAS)

query3GWASResults

GWASIds <- query3GWASResults["GWAS.results.associatedGenes.symbol"]
unique(GWASIds)