semtools 0.1.8 → 0.1.91
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +2 -0
- data/bin/semtools.rb +140 -65
- data/lib/semtools/ontology.rb +1235 -2061
- data/lib/semtools/parsers/file_parser.rb +32 -0
- data/lib/semtools/parsers/json_parser.rb +84 -0
- data/lib/semtools/parsers/oboparser.rb +511 -0
- data/lib/semtools/version.rb +1 -1
- data/lib/semtools.rb +3 -0
- data/semtools.gemspec +1 -1
- metadata +9 -6
- data/lib/semtools/math_methods.rb +0 -148
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: semtools
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.91
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- seoanezonjic
|
|
@@ -9,7 +9,7 @@ authors:
|
|
|
9
9
|
autorequire:
|
|
10
10
|
bindir: bin
|
|
11
11
|
cert_chain: []
|
|
12
|
-
date:
|
|
12
|
+
date: 2025-09-02 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: text
|
|
@@ -95,8 +95,9 @@ dependencies:
|
|
|
95
95
|
- - ">="
|
|
96
96
|
- !ruby/object:Gem::Version
|
|
97
97
|
version: 0.7.3
|
|
98
|
-
description:
|
|
99
|
-
|
|
98
|
+
description: 'DEPRECATED PROJECT. MIGRATED TO PYTHON: https://github.com/seoanezonjic/py_semtools.
|
|
99
|
+
This gem allows to perform ontology based operations and calculation of Semantic
|
|
100
|
+
similarity and information coefficient using different implementations.'
|
|
100
101
|
email:
|
|
101
102
|
- seoanezonjic@hotmail.com
|
|
102
103
|
- fmjabato@gmail.com
|
|
@@ -126,8 +127,10 @@ files:
|
|
|
126
127
|
- lib/data/hp.obo
|
|
127
128
|
- lib/data/phenotype_annotation.tab
|
|
128
129
|
- lib/semtools.rb
|
|
129
|
-
- lib/semtools/math_methods.rb
|
|
130
130
|
- lib/semtools/ontology.rb
|
|
131
|
+
- lib/semtools/parsers/file_parser.rb
|
|
132
|
+
- lib/semtools/parsers/json_parser.rb
|
|
133
|
+
- lib/semtools/parsers/oboparser.rb
|
|
131
134
|
- lib/semtools/sim_handler.rb
|
|
132
135
|
- lib/semtools/version.rb
|
|
133
136
|
- semtools.gemspec
|
|
@@ -150,7 +153,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
150
153
|
- !ruby/object:Gem::Version
|
|
151
154
|
version: '0'
|
|
152
155
|
requirements: []
|
|
153
|
-
rubygems_version: 3.
|
|
156
|
+
rubygems_version: 3.3.7
|
|
154
157
|
signing_key:
|
|
155
158
|
specification_version: 4
|
|
156
159
|
summary: Gem to handle semantic based calculations in text and defined ontologies
|
|
@@ -1,148 +0,0 @@
|
|
|
1
|
-
# # TODO: Make a pull request to https://rubygems.org/gems/ruby-statistics, with all the statistic code implemented here.
|
|
2
|
-
# #to cmpute fisher exact test
|
|
3
|
-
# #Fisher => http://www.biostathandbook.com/fishers.html
|
|
4
|
-
# def get_fisher_exact_test(listA, listB, all_elements_count, tail ='two_sided', weigths=nil, partial_weigths=true)
|
|
5
|
-
# #puts '-', listA.inspect, listB.inspect, '-'
|
|
6
|
-
# listA_listB = listA & listB
|
|
7
|
-
# listA_nolistB = listA - listB
|
|
8
|
-
# nolistA_listB = listB - listA
|
|
9
|
-
# if weigths.nil?
|
|
10
|
-
# listA_listB_count = listA_listB.length
|
|
11
|
-
# listA_nolistB_count = listA_nolistB.length
|
|
12
|
-
# nolistA_listB_count = nolistA_listB.length
|
|
13
|
-
# nolistA_nolistB_count = all_elements_count - (listA | listB).length
|
|
14
|
-
# else
|
|
15
|
-
# # Fisher exact test weigthed as proposed in Improved scoring of functional groups from gene expression data by decorrelating GO graph structure
|
|
16
|
-
# # https://academic.oup.com/bioinformatics/article/22/13/1600/193669
|
|
17
|
-
# listA_listB_count = listA_listB.map{|i| weigths[i]}.inject(0){|sum, n| sum + n}.ceil
|
|
18
|
-
# listA_nolistB_count = listA_nolistB.map{|i| weigths[i]}.inject(0){|sum, n| sum + n}.ceil
|
|
19
|
-
# nolistA_listB_count = nolistA_listB.map{|i| weigths[i]}.inject(0){|sum, n| sum + n}.ceil
|
|
20
|
-
|
|
21
|
-
# if partial_weigths
|
|
22
|
-
# nolistA_nolistB_count = all_elements_count - (listA | listB).length
|
|
23
|
-
# all_elements_count = nolistA_nolistB_count + listA_listB_count + listA_nolistB_count + nolistA_listB_count
|
|
24
|
-
# else
|
|
25
|
-
# nolistA_nolistB_count = (weigths.keys - (listA | listB)).map{|i| weigths[i]}.inject(0){|sum, n| sum + n}.ceil
|
|
26
|
-
# all_elements_count = weigths.values.inject(0){|sum, n| sum + n}.ceil
|
|
27
|
-
# end
|
|
28
|
-
# end
|
|
29
|
-
# #puts [listA_listB_count, listA_nolistB_count, nolistA_listB_count, nolistA_nolistB_count, all_elements_count].inspect
|
|
30
|
-
# if tail == 'two_sided'
|
|
31
|
-
# accumulated_prob = get_two_tail(listA_listB_count, listA_nolistB_count, nolistA_listB_count, nolistA_nolistB_count, all_elements_count)
|
|
32
|
-
# elsif tail == 'less'
|
|
33
|
-
# accumulated_prob = get_less_tail(listA_listB_count, listA_nolistB_count, nolistA_listB_count, nolistA_nolistB_count, all_elements_count)
|
|
34
|
-
# end
|
|
35
|
-
# return accumulated_prob
|
|
36
|
-
# end
|
|
37
|
-
|
|
38
|
-
# def get_two_tail(listA_listB_count, listA_nolistB_count, nolistA_listB_count, nolistA_nolistB_count, all_elements_count)
|
|
39
|
-
# #https://www.sheffield.ac.uk/polopoly_fs/1.43998!/file/tutorial-9-fishers.pdf
|
|
40
|
-
# accumulated_prob = 0
|
|
41
|
-
# ref_prob = compute_hyper_prob(
|
|
42
|
-
# listA_listB_count,
|
|
43
|
-
# listA_nolistB_count,
|
|
44
|
-
# nolistA_listB_count,
|
|
45
|
-
# nolistA_nolistB_count,
|
|
46
|
-
# all_elements_count
|
|
47
|
-
# )
|
|
48
|
-
# accumulated_prob += ref_prob
|
|
49
|
-
# [listA_listB_count, nolistA_nolistB_count].min.times do |n| #less
|
|
50
|
-
# n += 1
|
|
51
|
-
# prob = compute_hyper_prob(
|
|
52
|
-
# listA_listB_count - n,
|
|
53
|
-
# listA_nolistB_count + n,
|
|
54
|
-
# nolistA_listB_count + n,
|
|
55
|
-
# nolistA_nolistB_count - n,
|
|
56
|
-
# all_elements_count
|
|
57
|
-
# )
|
|
58
|
-
# prob <= ref_prob ? accumulated_prob += prob : break
|
|
59
|
-
# end
|
|
60
|
-
|
|
61
|
-
# [listA_nolistB_count, nolistA_listB_count].min.times do |n| #greater
|
|
62
|
-
# n += 1
|
|
63
|
-
# prob = compute_hyper_prob(
|
|
64
|
-
# listA_listB_count + n,
|
|
65
|
-
# listA_nolistB_count - n,
|
|
66
|
-
# nolistA_listB_count - n,
|
|
67
|
-
# nolistA_nolistB_count + n,
|
|
68
|
-
# all_elements_count
|
|
69
|
-
# )
|
|
70
|
-
# accumulated_prob += prob if prob <= ref_prob
|
|
71
|
-
# end
|
|
72
|
-
|
|
73
|
-
# return accumulated_prob
|
|
74
|
-
# end
|
|
75
|
-
|
|
76
|
-
# def get_less_tail(listA_listB_count, listA_nolistB_count, nolistA_listB_count, nolistA_nolistB_count, all_elements_count)
|
|
77
|
-
# accumulated_prob = 0
|
|
78
|
-
# [listA_listB_count, nolistA_nolistB_count].min.times do |n|
|
|
79
|
-
# accumulated_prob += compute_hyper_prob(
|
|
80
|
-
# listA_listB_count - n,
|
|
81
|
-
# listA_nolistB_count + n,
|
|
82
|
-
# nolistA_listB_count + n,
|
|
83
|
-
# nolistA_nolistB_count - n,
|
|
84
|
-
# all_elements_count
|
|
85
|
-
# )
|
|
86
|
-
# end
|
|
87
|
-
# return accumulated_prob
|
|
88
|
-
# end
|
|
89
|
-
|
|
90
|
-
# def compute_hyper_prob(a, b, c, d, n)
|
|
91
|
-
# # https://en.wikipedia.org/wiki/Fisher%27s_exact_test
|
|
92
|
-
# binomA = binom(a + b, a)
|
|
93
|
-
# binomC = binom(c + d, c)
|
|
94
|
-
# divisor = binom(n, a + c)
|
|
95
|
-
# return (binomA * binomC).fdiv(divisor)
|
|
96
|
-
# end
|
|
97
|
-
|
|
98
|
-
# def binom(n,k)
|
|
99
|
-
# if k > 0 && k < n
|
|
100
|
-
# res = (1+n-k..n).inject(:*)/(1..k).inject(:*)
|
|
101
|
-
# else
|
|
102
|
-
# res = 1
|
|
103
|
-
# end
|
|
104
|
-
# end
|
|
105
|
-
|
|
106
|
-
# #to cmpute adjusted pvalues
|
|
107
|
-
# #https://rosettacode.org/wiki/P-value_correction#Ruby
|
|
108
|
-
# def get_benjaminiHochberg_pvalues(arr_pvalues)
|
|
109
|
-
# n = arr_pvalues.length
|
|
110
|
-
# arr_o = order(arr_pvalues, true)
|
|
111
|
-
# arr_cummin_input = []
|
|
112
|
-
# (0..(n - 1)).each do |i|
|
|
113
|
-
# arr_cummin_input[i] = (n / (n - i).to_f) * arr_pvalues[arr_o[i]]
|
|
114
|
-
# end
|
|
115
|
-
# arr_ro = order(arr_o)
|
|
116
|
-
# arr_cummin = cummin(arr_cummin_input)
|
|
117
|
-
# arr_pmin = pmin(arr_cummin)
|
|
118
|
-
# return arr_pmin.values_at(*arr_ro)
|
|
119
|
-
# end
|
|
120
|
-
|
|
121
|
-
# def order(array, decreasing = false)
|
|
122
|
-
# if decreasing == false
|
|
123
|
-
# array.sort.map { |n| array.index(n) }
|
|
124
|
-
# else
|
|
125
|
-
# array.sort.map { |n| array.index(n) }.reverse
|
|
126
|
-
# end
|
|
127
|
-
# end
|
|
128
|
-
|
|
129
|
-
# def cummin(array)
|
|
130
|
-
# cumulative_min = array.first
|
|
131
|
-
# arr_cummin = []
|
|
132
|
-
# array.each do |p|
|
|
133
|
-
# cumulative_min = [p, cumulative_min].min
|
|
134
|
-
# arr_cummin << cumulative_min
|
|
135
|
-
# end
|
|
136
|
-
# return arr_cummin
|
|
137
|
-
# end
|
|
138
|
-
|
|
139
|
-
# def pmin(array)
|
|
140
|
-
# x = 1
|
|
141
|
-
# pmin_array = []
|
|
142
|
-
# array.each_index do |i|
|
|
143
|
-
# pmin_array[i] = [array[i], x].min
|
|
144
|
-
# abort if pmin_array[i] > 1
|
|
145
|
-
# end
|
|
146
|
-
# return pmin_array
|
|
147
|
-
# end
|
|
148
|
-
|