Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "Samaneh Jozashoori",
2
  "author": "Samaneh Jozashoori",
            
3
  "author_email": "iglesias@l3s.de",
3
  "author_email": "iglesias@l3s.de",
            
4
  "citations": [
4
  "citations": [
            
5
    {
5
    {
            
6
      "cited_in": ""
6
      "cited_in": ""
            
7
    }
7
    }
            
8
  ],
8
  ],
            
9
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
9
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
10
  "doi": "10.57702/4c9ivpgs",
10
  "doi": "10.57702/4c9ivpgs",
            
11
  "doi_date_published": "2023-10-17",
11
  "doi_date_published": "2023-10-17",
            
12
  "doi_publisher": "TIB",
12
  "doi_publisher": "TIB",
            
13
  "doi_status": true,
13
  "doi_status": true,
            
14
  "domain": "https://service.tib.eu/ldmservice",
14
  "domain": "https://service.tib.eu/ldmservice",
            
15
  "extra_authors": [
15
  "extra_authors": [
            
16
    {
16
    {
            
17
      "extra_author": "Enrique Iglesias",
17
      "extra_author": "Enrique Iglesias",
            
18
      "orcid": "0000-0002-8734-3123"
18
      "orcid": "0000-0002-8734-3123"
            
19
    },
19
    },
            
20
    {
20
    {
            
21
      "extra_author": "Maria-Esther Vidal",
21
      "extra_author": "Maria-Esther Vidal",
            
22
      "orcid": "0000-0003-1160-8727"
22
      "orcid": "0000-0003-1160-8727"
            
23
    }
23
    }
            
24
  ],
24
  ],
            
25
  "extras": [
25
  "extras": [
            
26
    {
26
    {
            
27
      "__extras": {
27
      "__extras": {
            
28
        "id": "24ed91ac-12e1-41ba-9f6b-c10eddce6b5e",
28
        "id": "24ed91ac-12e1-41ba-9f6b-c10eddce6b5e",
            
29
        "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
29
        "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
            
30
        "state": "active"
30
        "state": "active"
            
31
      },
31
      },
            
32
      "key": "",
32
      "key": "",
            
33
      "value": ""
33
      "value": ""
            
34
    }
34
    }
            
35
  ],
35
  ],
            
36
  "groups": [],
36
  "groups": [],
            
37
  "id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
37
  "id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
            
38
  "isopen": false,
38
  "isopen": false,
            
39
  "license_id": "notspecified",
39
  "license_id": "notspecified",
            
40
  "license_title": "License not specified",
40
  "license_title": "License not specified",
            
41
  "maintainer": "Enrique Iglesias",
41
  "maintainer": "Enrique Iglesias",
            
42
  "maintainer_email": "iglesias@l3s.de",
42
  "maintainer_email": "iglesias@l3s.de",
            
43
  "metadata_created": "2023-10-17T09:28:29.260955",
43
  "metadata_created": "2023-10-17T09:28:29.260955",
            
n
44
  "metadata_modified": "2023-10-17T10:49:37.508429",
n
44
  "metadata_modified": "2023-10-17T10:50:05.422930",
            
45
  "name": "sdm-genomic-dataset",
45
  "name": "sdm-genomic-dataset",
            
46
  "notes": "This benchmark is created by randomly sampling data 
46
  "notes": "This benchmark is created by randomly sampling data 
            
47
records from somatic mutation data collected in  COSMIC 
47
records from somatic mutation data collected in  COSMIC 
            
48
(https://cancer.sanger.ac.uk/cosmic). SDM-Genomic-Datasets include 
48
(https://cancer.sanger.ac.uk/cosmic). SDM-Genomic-Datasets include 
            
49
eight different logical sources of various sizes, including 10k, 100k, 
49
eight different logical sources of various sizes, including 10k, 100k, 
            
50
1M, and 5M rows. For every pair of sources of the same size, they 
50
1M, and 5M rows. For every pair of sources of the same size, they 
            
51
differ in the percentage of the data duplicate rate, which can be 
51
differ in the percentage of the data duplicate rate, which can be 
            
52
either 25% or 75%, where each duplicate value is repeated 20 times. 
52
either 25% or 75%, where each duplicate value is repeated 20 times. 
            
53
For example, a 10k logical source with 25% data duplicate rate has 75% 
53
For example, a 10k logical source with 25% data duplicate rate has 75% 
            
54
duplicate-free records (i.e., 7500 rows), and the rest of the 25% 
54
duplicate-free records (i.e., 7500 rows), and the rest of the 25% 
            
55
records (i.e., 2500 rows) correspond to 125 different records which 
55
records (i.e., 2500 rows) correspond to 125 different records which 
            
56
are duplicated 20 times; in total there are 7625 unique values. ",
56
are duplicated 20 times; in total there are 7625 unique values. ",
            
n
57
  "num_resources": 2,
n
57
  "num_resources": 3,
            
58
  "num_tags": 2,
58
  "num_tags": 2,
            
59
  "orcid": "0000-0003-1702-8707",
59
  "orcid": "0000-0003-1702-8707",
            
60
  "organization": {
60
  "organization": {
            
61
    "approval_status": "approved",
61
    "approval_status": "approved",
            
62
    "created": "2021-10-14T10:15:56.594472",
62
    "created": "2021-10-14T10:15:56.594472",
            
63
    "description": "# Forschungszentrum 
63
    "description": "# Forschungszentrum 
            
64
L3S\r\n\r\nhttps://www.l3s.de/",
64
L3S\r\n\r\nhttps://www.l3s.de/",
            
65
    "id": "00c8f767-81fd-41ae-9235-dd4d1d43221c",
65
    "id": "00c8f767-81fd-41ae-9235-dd4d1d43221c",
            
66
    "image_url": 
66
    "image_url": 
            
67
"https://www.l3s.de/sites/default/files/L3S_Logo_NEU_small.jpg",
67
"https://www.l3s.de/sites/default/files/L3S_Logo_NEU_small.jpg",
            
68
    "is_organization": true,
68
    "is_organization": true,
            
69
    "name": "l3s",
69
    "name": "l3s",
            
70
    "state": "active",
70
    "state": "active",
            
71
    "title": "L3S",
71
    "title": "L3S",
            
72
    "type": "organization"
72
    "type": "organization"
            
73
  },
73
  },
            
74
  "owner_org": "00c8f767-81fd-41ae-9235-dd4d1d43221c",
74
  "owner_org": "00c8f767-81fd-41ae-9235-dd4d1d43221c",
            
75
  "private": false,
75
  "private": false,
            
76
  "publications": [
76
  "publications": [
            
77
    {
77
    {
            
78
      "published_in": ""
78
      "published_in": ""
            
79
    }
79
    }
            
80
  ],
80
  ],
            
81
  "relationships_as_object": [],
81
  "relationships_as_object": [],
            
82
  "relationships_as_subject": [],
82
  "relationships_as_subject": [],
            
83
  "resources": [
83
  "resources": [
            
84
    {
84
    {
            
85
      "auto_update": "No",
85
      "auto_update": "No",
            
86
      "auto_update_last_update": "",
86
      "auto_update_last_update": "",
            
87
      "auto_update_url": "",
87
      "auto_update_url": "",
            
88
      "cache_last_updated": null,
88
      "cache_last_updated": null,
            
89
      "cache_url": null,
89
      "cache_url": null,
            
90
      "created": "2023-10-17T09:37:06.230719",
90
      "created": "2023-10-17T09:37:06.230719",
            
91
      "description": "",
91
      "description": "",
            
92
      "format": ".zip",
92
      "format": ".zip",
            
93
      "hash": "",
93
      "hash": "",
            
94
      "id": "d65a3ddc-ff78-4a5e-8863-cbecdc76d803",
94
      "id": "d65a3ddc-ff78-4a5e-8863-cbecdc76d803",
            
95
      "last_modified": "2023-10-17T09:37:06.200438",
95
      "last_modified": "2023-10-17T09:37:06.200438",
            
96
      "metadata_modified": "2023-10-17T09:37:06.220368",
96
      "metadata_modified": "2023-10-17T09:37:06.220368",
            
97
      "mimetype": "application/zip",
97
      "mimetype": "application/zip",
            
98
      "mimetype_inner": null,
98
      "mimetype_inner": null,
            
99
      "name": "SDM-Genomic-Dataset 10k and 100k rows Testbeds",
99
      "name": "SDM-Genomic-Dataset 10k and 100k rows Testbeds",
            
100
      "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
100
      "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
            
101
      "position": 0,
101
      "position": 0,
            
102
      "resource_type": null,
102
      "resource_type": null,
            
103
      "size": 160589043,
103
      "size": 160589043,
            
104
      "state": "active",
104
      "state": "active",
            
105
      "url": 
105
      "url": 
            
106
65a3ddc-ff78-4a5e-8863-cbecdc76d803/download/sdm-genomic-dataset.zip",
106
65a3ddc-ff78-4a5e-8863-cbecdc76d803/download/sdm-genomic-dataset.zip",
            
107
      "url_type": "upload"
107
      "url_type": "upload"
            
108
    },
108
    },
            
109
    {
109
    {
            
110
      "auto_update": "No",
110
      "auto_update": "No",
            
111
      "auto_update_last_update": "",
111
      "auto_update_last_update": "",
            
112
      "auto_update_url": "",
112
      "auto_update_url": "",
            
113
      "cache_last_updated": null,
113
      "cache_last_updated": null,
            
114
      "cache_url": null,
114
      "cache_url": null,
            
115
      "created": "2023-10-17T10:49:37.520638",
115
      "created": "2023-10-17T10:49:37.520638",
            
116
      "description": "",
116
      "description": "",
            
117
      "format": "CSV",
117
      "format": "CSV",
            
118
      "hash": "",
118
      "hash": "",
            
119
      "id": "e6aeaf20-e3ab-446c-af56-8a1d17578a75",
119
      "id": "e6aeaf20-e3ab-446c-af56-8a1d17578a75",
            
120
      "last_modified": "2023-10-17T10:49:37.499916",
120
      "last_modified": "2023-10-17T10:49:37.499916",
            
121
      "metadata_modified": "2023-10-17T10:49:37.512453",
121
      "metadata_modified": "2023-10-17T10:49:37.512453",
            
122
      "mimetype": "text/csv",
122
      "mimetype": "text/csv",
            
123
      "mimetype_inner": null,
123
      "mimetype_inner": null,
            
124
      "name": "10k rows source with 25% duplicate rate",
124
      "name": "10k rows source with 25% duplicate rate",
            
125
      "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
125
      "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
            
126
      "position": 1,
126
      "position": 1,
            
127
      "resource_type": null,
127
      "resource_type": null,
            
128
      "size": 1788734,
128
      "size": 1788734,
            
129
      "state": "active",
129
      "state": "active",
            
130
      "url": 
130
      "url": 
            
131
records_with_duplicate_and_each_duplicate_being_repeated_20times.csv",
131
records_with_duplicate_and_each_duplicate_being_repeated_20times.csv",
            
132
      "url_type": "upload"
132
      "url_type": "upload"
            
t
t
133
    },
            
134
    {
            
135
      "auto_update": "No",
            
136
      "auto_update_last_update": "",
            
137
      "auto_update_url": "",
            
138
      "cache_last_updated": null,
            
139
      "cache_url": null,
            
140
      "created": "2023-10-17T10:50:05.433365",
            
141
      "description": "",
            
142
      "format": "CSV",
            
143
      "hash": "",
            
144
      "id": "845052d6-27f5-47b7-a012-2df643bb5bc7",
            
145
      "last_modified": "2023-10-17T10:50:05.414532",
            
146
      "metadata_modified": "2023-10-17T10:50:05.426325",
            
147
      "mimetype": "text/csv",
            
148
      "mimetype_inner": null,
            
149
      "name": "10k rows source with 75% duplicate rate",
            
150
      "package_id": "5f2180c2-be1d-45c3-a3c3-831f400b2f81",
            
151
      "position": 2,
            
152
      "resource_type": null,
            
153
      "size": 1801842,
            
154
      "state": "active",
            
155
      "url": 
            
156
records_with_duplicate_and_each_duplicate_being_repeated_20times.csv",
            
157
      "url_type": "upload"
            
133
    }
158
    }
            
134
  ],
159
  ],
            
135
  "services_used_list": "",
160
  "services_used_list": "",
            
136
  "state": "active",
161
  "state": "active",
            
137
  "tags": [
162
  "tags": [
            
138
    {
163
    {
            
139
      "display_name": "Benchmark",
164
      "display_name": "Benchmark",
            
140
      "id": "70474eb4-f8bf-42f1-bf26-7511d4f3356c",
165
      "id": "70474eb4-f8bf-42f1-bf26-7511d4f3356c",
            
141
      "name": "Benchmark",
166
      "name": "Benchmark",
            
142
      "state": "active",
167
      "state": "active",
            
143
      "vocabulary_id": null
168
      "vocabulary_id": null
            
144
    },
169
    },
            
145
    {
170
    {
            
146
      "display_name": "health",
171
      "display_name": "health",
            
147
      "id": "4ad8e4c3-0431-4ed0-8d43-25db6f543a69",
172
      "id": "4ad8e4c3-0431-4ed0-8d43-25db6f543a69",
            
148
      "name": "health",
173
      "name": "health",
            
149
      "state": "active",
174
      "state": "active",
            
150
      "vocabulary_id": null
175
      "vocabulary_id": null
            
151
    }
176
    }
            
152
  ],
177
  ],
            
153
  "title": "SDM-Genomic-Dataset",
178
  "title": "SDM-Genomic-Dataset",
            
154
  "type": "dataset",
179
  "type": "dataset",
            
155
  "url": 
180
  "url": 
            
156
"https://figshare.com/articles/dataset/SDM-Genomic-Datasets/14838342",
181
"https://figshare.com/articles/dataset/SDM-Genomic-Datasets/14838342",
            
157
  "version": ""
182
  "version": ""
            
158
}
183
}