Enhance UniProt ID handling (#36)

- adds support for sp/tr annotations
- handle different formats in ID mapping

Author: timholy

src/naming_conventions.jl

@@ -64,6 +64,9 @@ julia> uniprotX("Q8VGW6_MOUSE/31-308")
 ```
 """
 function uniprotX(name::AbstractString)::AbstractString
+    if startswith(name, "tr|") || startswith(name, "sp|")
+        name = name[4:end]
+    end
     m = match(rex_uniprotX_Swiss, name)
     m !== nothing && return m.captures[1]
     m = match(rex_uniprot_accession, name)
@@ -101,7 +104,7 @@ function query_uniprot_accession(id)
 end
 
 """
-    jobID = GPCRAnalysis.map_uniprot_submit(ids, from, to="UniProtKB")
+    jobID = GPCRAnalysis.map_uniprot_submit(ids, from="UniProtKB_AC-ID", to="UniProtKB")
 
 Submit a list of `ids` to the Uniprot ID mapping service, to convert from ID convention `from` to `to`.
 The jobID can be used to check the status (`map_uniprot_status`) and retrieve the results (`map_uniprot_retrieve`).
@@ -111,24 +114,24 @@ The jobID can be used to check the status (`map_uniprot_status`) and retrieve th
 julia> jobID = GPCRAnalysis.map_uniprot_submit(["ENSMUSG00000067064", "ENSMUSG00000057464"], "Ensembl");
 ```
 """
-function map_uniprot_submit(ids::AbstractString, from::AbstractString, to::AbstractString="UniProtKB")
+function map_uniprot_submit(ids::AbstractString, from::AbstractString="UniProtKB_AC-ID", to::AbstractString="UniProtKB")
     resp = HTTP.post("https://rest.uniprot.org/idmapping/run", [],
-                     Dict("from" => from, "to" => "UniProtKB", "ids" => ids))
+                     Dict("from" => from, "to" => to, "ids" => ids))
     if resp.status == 200
         return JSON3.read(String(resp.body))["jobId"]
     end
     return nothing
 end
-map_uniprot_submit(ids::AbstractVector, from::AbstractString) = map_uniprot_submit(join(ids, ','), from)
+map_uniprot_submit(ids::AbstractVector, args...) = map_uniprot_submit(join(ids, ','), args...)
 
 """
-    status = GPCRAnalysis.map_uniprot_status(jobId)
+    status = GPCRAnalysis.map_uniprot_status(jobID)
 
 Check the status of a Uniprot ID mapping job. Returns `true` if the results are
 ready. Otherwise, returns the status object.
 """
-function map_uniprot_status(jobId)
-    resp = HTTP.get("https://rest.uniprot.org/idmapping/status/$jobId", ["Accept" => "application/json"])
+function map_uniprot_status(jobID)
+    resp = HTTP.get("https://rest.uniprot.org/idmapping/status/$jobID", ["Accept" => "application/json"]; decompress = true)
     if resp.status == 200
         status = JSON3.read(String(HTTP.decode(resp)))
         haskey(status, "results") && return true
@@ -138,12 +141,12 @@ function map_uniprot_status(jobId)
 end
 
 """
-    result = GPCRAnalysis.map_uniprot_retrieve(jobId)
+    result = GPCRAnalysis.map_uniprot_retrieve(jobID)
 
 Retrieve the results of a Uniprot ID mapping job.
 """
-function map_uniprot_retrieve(jobId)
-    resp = HTTP.get("https://rest.uniprot.org/idmapping/stream/$jobId", ["Accept" => "application/json"])
+function map_uniprot_retrieve(jobID)
+    resp = HTTP.get("https://rest.uniprot.org/idmapping/stream/$jobID", ["Accept" => "application/json"]; decompress = true)
     if resp.status == 200
         return JSON3.read(String(HTTP.decode(resp)))
     end

test/runtests.jl

@@ -30,6 +30,8 @@ using Test
         @test_throws ErrorException uniprotX("Q8VGW67_MOUSE/31-308")
         @test_throws ErrorException uniprotX("q8vgw6_MOUSE/31-308")
         @test_throws ErrorException uniprotX("QV8GW6_MOUSE/31-308")
+        # FASTA
+        @test @inferred(uniprotX("tr|M3WEA8|M3WEA8_FELCA Olfactory receptor family 51 subfamily S member 1 OS=Felis catus OX=9685 GN=OR51S1 PE=4 SV=2")) == "M3WEA8"
 
         # Versioned
         @test uniprotX("Q8VGW6.37") == "Q8VGW6"
@@ -299,6 +301,18 @@ using Test
         @testset "Uniprot" begin
             @test query_uniprot_accession("T2R38_MOUSE") == "Q7TQA6"
 
+            jobID = GPCRAnalysis.map_uniprot_submit(["T2R38_MOUSE"])
+            tstart = time()
+            sleep(1)
+            status = false
+            while status != true && time() < tstart + 20
+                sleep(1)
+                status = GPCRAnalysis.map_uniprot_status(jobID)
+            end
+            results = GPCRAnalysis.map_uniprot_retrieve(jobID)[:results]
+            resultsdict = Dict(obj["from"] => obj["to"] for obj in results)
+            @test resultsdict["T2R38_MOUSE"] == "Q7TQA6"
+
             jobID = GPCRAnalysis.map_uniprot_submit(["ENSMUSG00000067064", "ENSMUSG00000057464"], "Ensembl")
             tstart = time()
             sleep(1)
@@ -310,6 +324,8 @@ using Test
             results = GPCRAnalysis.map_uniprot_retrieve(jobID)[:results]
             resultsdict = Dict(obj["from"] => obj["to"] for obj in results)
             @test resultsdict["ENSMUSG00000067064"] == "Q8VGU4"
+
+
         end
 
         @testset "EBI and NCBI" begin