Module: Exodb::Utils

Defined in:
lib/exodb/utils.rb,
lib/exodb/rositza.rb,
lib/exodb/rositza/load.rb,
lib/exodb/utils/upload_var.rb,
lib/exodb/extra/upload_generef.rb more...

Class Method Summary collapse

Class Method Details

.guess_miriam(str) ⇒ String

Guess the type of id

Parameters:

Returns:

  • (String) —

    a miriam registry or the string itself incase cannot guess

[View source]

29
30
31
32
33
34
35
36
37
38
39
40
41
42
 
# File 'lib/exodb/utils.rb', line 29

def guess_miriam(str)
	case str
	when /\A((AC|AP|NC|NG|NM|NP|NR|NT|NW|XM|XP|XR|YP|ZP)_\d+|(NZ\_[A-Z]{4}\d+))(\.\d+)?\z/
		return "urn:miriam:refseq:#{str}"
	when /\A((ENS[A-Z]*[FPTG]\d{11}(\.\d+)?)|(FB\w{2}\d{7})|(Y[A-Z]{2}\d{3}[a-zA-Z](\-[A-Z])?)|([A-Z_a-z0-9]+(\.)?(t)?(\d+)?([a-z])?))\z/
		return "urn:miriam:ensembl:#{str}"
	when /\A((HGNC|hgnc):)?\d{1,5}\z/
		return "urn:miriam:hgnc:#{str}"
	when /\ACCDS\d+\.\d+\z/
		return "urn:miriam:ccds:#{str}"
	else
		return str
	end
end

.load_indel_from_csv(csvfile) ⇒ Object

[View source]

59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/exodb/rositza/load.rb', line 59

def load_indel_from_csv(csvfile)
	
	CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
		
		var = Exodb::Variant.new()
		var.location=("#{record["chr"]}:#{record["pos"]}")
		#var.reference = record["Reference Genotype"]
		var.alternatet = ['-2N']
		var.somstatus = record["Somatic Status"].downcase
		var.passfilter = true
		#var.pileupt = record["Reads"]
		var.predicted_damage = true
		var.temp = {} if var.temp.blank?
		var.temp['aachange'] = "#{record["symbol"]}:InDel"
		var.add_to_sample(record["cell lines"])
		p var.save!
	end
end

.load_sample_from_csv(csvfile) ⇒ Object

[View source]

78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
 
# File 'lib/exodb/rositza/load.rb', line 78

def load_sample_from_csv(csvfile)
	CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
		
		sample = Cell.new({oid: record["SampleFinal"],
						type: record["Type"].downcase,
						typeid: "urn:miriam:bioportal.meddra:#{record["Type"] =~ /^spitz /i ? '10041632' : record["Type"] =~ /^spitzoid /i ? '10072450' : '10028679'}",
						patient: record["SampleFinal"].split('T')[0],
						preferred: record["Preferred"] == 'Y' ? true : false,
						paired: record["merge41final"] =~ /\Apaired\z/i ? true : false},
						labels: {})
		
		sample.add_to_dataset('internal.ds:000001')
		
		p sample.save!
		
	end
end

.load_snv_from_csv(csvfile) ⇒ Object

[View source]

20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/exodb/rositza/load.rb', line 20

def load_snv_from_csv(csvfile)
	
	CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
		
		var = Exodb::Variant.new()
		var.location=("chr#{record["chromosome"]}:#{record["start position"]}")
		var.reference = record["ref nucleotide"].split('/')[0]
		var.alternatet = record["var nucleotide"].split('/').uniq
		var.somstatus = record["Somatic Status"].downcase
		var.passfilter = true
		var.pileupt = record["Reads"]
		var.predicted_damage = record["PolyPhen"] =~ /probably_damaging/ || record["SIFT"] =~ /deleterious/i || record["PROVEAN"] =~ /deleterious/i ? true : false
		var.temp = {} if var.temp.blank?
		var.temp['aachange'] = "#{record["symbol"]}:#{record["AA Change"]}"
		var.add_to_sample(record["cell"])
		
		p var.save!
	end
end

.load_splice_from_csv(csvfile) ⇒ Object

[View source]

40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
 
# File 'lib/exodb/rositza/load.rb', line 40

def load_splice_from_csv(csvfile)
	
	CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
		
		var = Exodb::Variant.new()
		var.location=("chr#{record["chr"]}:#{record["Position"]}")
		var.reference = record["Reference Genotype"]
		var.alternatet = ['N']
		var.somstatus = 'somatic'
		var.passfilter = true
		#var.pileupt = record["Reads"]
		var.predicted_damage = true
		var.temp = {} if var.temp.blank?
		var.temp['aachange'] = "#{record["Gene Symbol"]}:SpV"
		var.add_to_sample(record["Sample"])
		p var.save!
	end
end

.load_variant_from_merge(mergefile, normal = false, assembly = Exodb::DEFAULTASSEMBLY) ⇒ Object

[View source]

96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
 
# File 'lib/exodb/rositza/load.rb', line 96

def load_variant_from_merge(mergefile, normal = false, assembly = Exodb::DEFAULTASSEMBLY)
	
	File.open(mergefile).each do |line|
		record = line.chomp.split("\t")
		
		header = record[0..15]
		
		list = record[16..-1]
		
		until list.empty?
			if normal
				snv = Exodb::Variant.where(oid: "#{header[2]}:#{header[3]}:#{assembly}:#{sampledata[0]}").first
				snv.pileupn = sampledata[6] if snv != nil
			else
				sampledata = list.shift(7)
				snv = Exodb::Variant.new()
				snv.location=("#{header[2]}:#{header[3]}:#{assembly}")
				snv.reference = header[10]
				snv.pileupt = sampledata[6]
				snv.temp = {} if snv.temp.blank?
				snv.add_to_sample(sampledata[0])
				p snv.save!
			end
		end
	end
	
end

.upload_generef_from_gff3(filename, assembly = Exodb::DEFAULTASSEMBLY) ⇒ Object

Upload gene information to database using gff3 and genome sequence fasta file Exodb::Utils.upload_generef_from_gff3(‘ref_GRCh37.p5_top_level.gff3’)

Parameters:

  • gff3 (String) —

    file

  • assembly (String) (defaults to: Exodb::DEFAULTASSEMBLY) —

    name [default: gff file name]

[View source]

24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
 
# File 'lib/exodb/extra/upload_generef.rb', line 24

def upload_generef_from_gff3(filename, assembly = Exodb::DEFAULTASSEMBLY)
	
	gff = Bio::GFF::GFF3.new(File.open(filename).read)
	
	processDbxref = lambda do |str|
		case str
		when /^GeneID/
			return "urn:miriam:ncbigene:#{str.split(/:/)[1]}"
		when /^HGNC/
			return "urn:miriam:hgnc:#{str}"
		when /^HPRD/
			return "urn:miriam:hprd:#{str.split(/:/)[1]}"
		when /^miRBase/
			return "urn:miriam:mirbase:#{str.split(/:/)[1]}"
		when /^Genbank/
			return "urn:miriam:refseq:#{str.split(/:/)[1]}"
		when /^CCDS/
			return "urn:miriam:ccds:#{str.split(/:/)[1]}"
		when /^MIM/
			return "urn:miriam:omim:#{str.split(/:/)[1]}"
		else
			return str
		end
	end
	
	assembly = assembly.blank? ? Exodb::DEFAULTASSEMBLY : Exodb::ASSEMBLY[assembly.downcase]
	
	regions = {}
	genes = {}
	seq = {}
	regions.default='chr0'
	
	gff.records.each do |e|
		
		case e.feature
		when 'region'
			e.attributes.each do |attr|
				case attr[0]
				when 'chromosome'
					regions[e.seqname] = e.seqname =~ /\ANC_/ ? "chr#{attr[1]}" : e.seqname
				end
			end
			
			chr = Exodb::Chrref.new()
			chr.location=("#{regions.has_key?(e.seqname) ? regions[e.seqname] : e.seqname}:#{e.start}..#{e.end}:#{assembly}")
			chr.oid = "#{chr.chr}:#{assembly}"
			chr.add_to_set(:xrefs, guess_miriam(e.seqname))
			chr.save!
			
			if File.exist?("./genome/#{e.seqname}.fa")
				seq = {}
				Bio::FlatFile.open(Bio::FastaFormat, "./genome/#{e.seqname}.fa").each {|fasta| seq[fasta.acc_version] = fasta.to_seq}
			end
			
		when 'gene', 'tRNA'
			
			gene = {type: 'gene', xrefs: [], strand: e.strand, chrrefseq: "#{guess_miriam(e.seqname)}", location: "#{regions[e.seqname]}:#{e.start}..#{e.end}:#{assembly}", childs: [], exon: [], cds: []}
			
			e.attributes.each do |attr|
				case attr[0]
				when 'Dbxref'
					gene[:xrefs].push(processDbxref.call(attr[1]))
				when 'Name'
					gene[:xrefs].push("urn:miriam:hgnc.symbol:#{attr[1]}") if attr[1] !~ /^LOC\d+$/
				when 'pseudo'
					gene[:psuedo] = attr[1] == 'true' ? true : false
				when 'ID'
					gene[:id] = attr[1]
				end
			end
			
			gene[:sequence] = seq[e.seqname].subseq(e.start.to_i - Exodb::Generef.expanding, e.end.to_i + Exodb::Generef.expanding).to_s if seq.has_key?(e.seqname)
			gene[:seqstart] = e.start.to_i - Exodb::Generef.expanding
			gene[:seqstop] = e.end.to_i + Exodb::Generef.expanding
			gene[:oid] = "#{gene[:location]}:#{assembly}"
			genes[gene[:id]] = gene
			
		when /\A(transcript|[^t]*RNA)/
			rna = {type: 'rna', xrefs: [], strand: e.strand, chr: regions[e.seqname], location: "#{regions[e.seqname]}:#{e.start}..#{e.end}:#{assembly}", exon: [], cds: []}
			
			e.attributes.each do |attr|
				case attr[0]
				when 'Dbxref'
					rna[:xrefs].push(processDbxref.call(attr[1]))
				when 'pseudo'
					rna[:psuedo] = attr[1] == 'true' ? true : false
				when 'ID'
					rna[:id] = attr[1]
				when 'Parent'
					rna[:parent] = attr[1]
				end
			end
			
			genes[rna[:id]] = rna
			genes[rna[:parent]][:childs].push(rna[:id]) if rna[:parent]
			
		when 'exon'
			e.attributes.each do |attr|
				case attr[0]
				when 'Parent'
					genes[attr[1]][:exon].push([e.start, e.end].sort)
				end
			end
		when 'CDS'
			e.attributes.each do |attr|
				case attr[0]
				when 'Parent'
					genes[attr[1]][:cds].push([e.start, e.end].sort)
				end
			end
		end
	end
	
	count = {succ: 0, fail: 0}
	
	genes.each_pair do |id, entry|
		if entry[:type] == 'gene'
			
			gene = Exodb::Generef.new()
			
			entry.each_pair do |k, v|
				gene.method(:"#{k}=").call(v) if ![:type, :childs, :exon, :cds].include?(k)
			end
			
			entry[:childs].each do |child|
				
				rna = Isoform.new()
				data = genes[child]
				rna.xrefs = data[:xrefs]
				rna.exon = data[:exon].sort
				rna.cds = data[:cds].sort
				
				gene.isoforms.push(rna)
				
			end
			
			if gene.save!
				count[:succ] += 1
				Exodb::putstv "Deposit Gene reference #{gene.xrefs[0]}"
			else
				count[:fail] += 1
				Exodb::putstv "Deposit Gene reference #{gene.xrefs[0]}"
			end
			
		end
		
	end
	
	Exodb::putst "SUCCESS: #{count[:succ]} , FAIL: #{count[:fail]}"
	
end