-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path.Rhistory
191 lines (191 loc) · 9.34 KB
/
.Rhistory
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "/2_Derived/Total_DIID_count.csv"
# Read the CSV file
data <- read.table(file_path, sep = ';', header = TRUE)
file_path
getwd()
file_path <- "../2_Derived/Total_DIID_count.csv"
# Read the CSV file
data <- read.table(file_path, sep = ';', header = TRUE)
file_path <- "/2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
getwd()
file_path <- "/2_Derived/Total_DIID_count.csv"
# Read the CSV file
data <- read.table(file_path, sep = ';', header = TRUE)
getwd()
file_path <- "/2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
getwd()
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
getwd()
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Set the file path
getwd()
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
data <- read.table(../2_Derived/Total_DIID_count.csv, sep = ';', header = TRUE)
data <- read.table("../2_Derived/Total_DIID_count.csv", sep = ';', header = TRUE)
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
file.exists("../2_Derived/Total_DIID_count.csv")
getwd()
getwd()
file.exists("../2_Derived/Total_DIID_count.csv")
file_path <- "../2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
list.files("../")
list.files("2_Derived/")
getwd()
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
head(data)
str(data)
head(data)
names(data)
summary(data$DirectRepeatLength)
summary(data$InvertedRepeatLength)
cor.test(data$Ratio,data$DirectRepeatLength, method = 'spearman') # negative == fragile/alternative is decreasing with repeat length
cor.test(data$DIIDFragilityScore,data$DirectRepeatLength, method = 'spearman') # negative == fragile/alternative is decreasing with repeat length
plot(data$DIIDFragilityScore,data$DirectRepeatLength)
cor.test(data$DIIDFragilityScore,data$InvertedRepeatLength, method = 'spearman') # negative == fragile/alternative is decreasing with repeat length
plot(data$DIIDFragilityScore,data$InvertedRepeatLength)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval1, method = 'spearman') # weak positive == the longer the first interval the less fragile combination
plot(data$DIIDFragilityScore,data$LengthOfInterval1)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval2, method = 'spearman') # no effect
plot(data$DIIDFragilityScore,data$LengthOfInterval2)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval3, method = 'spearman') # a bit positive
plot(data$DIIDFragilityScore,data$LengthOfInterval3)
summary(lm(data$DIIDFragilityScore ~ data$DirectRepeatLength + data$InvertedRepeatLength + data$LengthOfInterval1 + data$LengthOfInterval2 + data$LengthOfInterval3))
summary(lm(data$DIIDFragilityScore ~ data$DirectRepeatLength + data$InvertedRepeatLength + data$LengthOfInterval1 + data$LengthOfInterval3))
summary(lm(data$DIIDFragilityScore ~ data$DirectRepeatLength + data$InvertedRepeatLength + data$LengthOfInterval1 + data$LengthOfInterval3))
summary(lm(data$DIIDFragilityScore ~ scale(data$DirectRepeatLength) + scale(data$InvertedRepeatLength) + scale(data$LengthOfInterval1) + scale(data$LengthOfInterval2) + scale(data$LengthOfInterval3)))
data$DIIDFragilityScore = 1/data$DIIDFragilityScore # the higher the score the higher the fragilty
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
summary(data$DIIDFragilityScore)
data$DIIDFragilityScore = 1/data$DIIDFragilityScore # the higher the score the higher the fragilty
summary(data$DirectRepeatLength)
summary(data$InvertedRepeatLength)
cor.test(data$DIIDFragilityScore,data$DirectRepeatLength, method = 'spearman')
plot(data$DIIDFragilityScore,data$DirectRepeatLength)
summary(lm(data$DIIDFragilityScore ~ scale(data$DirectRepeatLength) + scale(data$InvertedRepeatLength) + scale(data$LengthOfInterval1) + scale(data$LengthOfInterval2) + scale(data$LengthOfInterval3)))
summary(data$DIIDFragilityScore)
data = data[data$DIIDFragilityScore < Inf,]
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
summary(data$DIIDFragilityScore)
data$DIIDFragilityScore = 1/data$DIIDFragilityScore # the higher the score (ALT STRUCTURE/ FRAGILE STRUCTURE) the higher the fragility and the higher the deficit of such fragile elements
summary(data$DIIDFragilityScore)
nrow(data)
data = data[data$DIIDFragilityScore < Inf,]
nrow(data)
summary(lm(data$DIIDFragilityScore ~ scale(data$DirectRepeatLength) + scale(data$InvertedRepeatLength) + scale(data$LengthOfInterval1) + scale(data$LengthOfInterval2) + scale(data$LengthOfInterval3)))
names(data)
data$DIIDFragilityScore = data$DI..I.Dcount/data$D.I..IDcount
summary(data$DIIDFragilityScore)
data$DIIDFragilityScore = data$D.I..IDcount/data$DI..I.Dcount # ALTER / FRAGILE
summary(data$DIIDFragilityScore)
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
data$DIIDFragilityScore = data$D.I..IDcount/data$DI..I.Dcount # ALTER / FRAGILE
summary(data$DIIDFragilityScore)
#data$DIIDFragilityScore = 1/data$DIIDFragilityScore # the higher the score (ALT STRUCTURE/ FRAGILE STRUCTURE) the higher the fragility and the higher the deficit of such fragile elements
#summary(data$DIIDFragilityScore)
#nrow(data)
#data = data[data$DIIDFragilityScore < Inf,]
#nrow(data)
summary(data$DIIDFragilityScore)
knitr::opts_chunk$set(echo = TRUE)
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
data$DIIDFragilityScore = data$D.I..IDcount/data$DI..I.Dcount # ALTER / FRAGILE
summary(data$DIIDFragilityScore)
#data$DIIDFragilityScore = 1/data$DIIDFragilityScore # the higher the score (ALT STRUCTURE/ FRAGILE STRUCTURE) the higher the fragility and the higher the deficit of such fragile elements
#summary(data$DIIDFragilityScore)
#nrow(data)
#data = data[data$DIIDFragilityScore < Inf,]
#nrow(data)
summary(lm(data$DIIDFragilityScore ~ scale(data$DirectRepeatLength) + scale(data$InvertedRepeatLength) + scale(data$LengthOfInterval1) + scale(data$LengthOfInterval2) + scale(data$LengthOfInterval3)))
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
data$DIIDFragilityScore = data$D.I..IDcount/data$DI..I.Dcount # ALTER / FRAGILE
# the higher the score (ALT STRUCTURE/ FRAGILE STRUCTURE) the higher the deficit of fragile elements the higher selection
summary(data$DIIDFragilityScore)
#data$DIIDFragilityScore = 1/data$DIIDFragilityScore
#summary(data$DIIDFragilityScore)
#nrow(data)
#data = data[data$DIIDFragilityScore < Inf,]
#nrow(data)
summary(data$DIIDFragilityScore)
nrow(data)
data = data[data$DIIDFragilityScore < Inf,]
nrow(data)
summary(data$DIIDFragilityScore)
data$DIIDFragilityScore = data$D.I..IDcount - data$DI..I.Dcount # ALTER / FRAGILE
knitr::opts_chunk$set(echo = TRUE)
# Set the file path
file_path <- "2_Derived/Total_DIID_count.csv"
data <- read.table(file_path, sep = ';', header = TRUE)
# Display the first few rows of the data
names(data)
head(data)
# str(data)
data$DIIDFragilityScore = data$D.I..IDcount - data$DI..I.Dcount # ALTER / FRAGILE
# the higher the score (ALT STRUCTURE/ FRAGILE STRUCTURE) the higher the deficit of fragile elements the higher selection
summary(data$DIIDFragilityScore)
#data$DIIDFragilityScore = 1/data$DIIDFragilityScore
#summary(data$DIIDFragilityScore)
#nrow(data)
#data = data[data$DIIDFragilityScore < Inf,]
#nrow(data)
summary(data$DIIDFragilityScore)
cor.test(data$DIIDFragilityScore,data$DirectRepeatLength, method = 'spearman')
plot(data$DIIDFragilityScore,data$DirectRepeatLength)
cor.test(data$DIIDFragilityScore,data$InvertedRepeatLength, method = 'spearman')
plot(data$DIIDFragilityScore,data$InvertedRepeatLength)
cor.test(data$DIIDFragilityScore,data$DirectRepeatLength, method = 'spearman')
plot(data$DIIDFragilityScore,data$DirectRepeatLength)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval1, method = 'spearman')
plot(data$DIIDFragilityScore,data$LengthOfInterval1)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval2, method = 'spearman')
plot(data$DIIDFragilityScore,data$LengthOfInterval2)
cor.test(data$DIIDFragilityScore,data$LengthOfInterval3, method = 'spearman')
plot(data$DIIDFragilityScore,data$LengthOfInterval3)
summary(lm(data$DIIDFragilityScore ~ scale(data$DirectRepeatLength) + scale(data$InvertedRepeatLength) + scale(data$LengthOfInterval1) + scale(data$LengthOfInterval2) + scale(data$LengthOfInterval3)))