Hugging Face's logo

RomanCohort
/
RNAQwen

Transformers
English
biology
RNA
multimodal
llm
foundation-models
quantization
fsq
Model card Files
xet
 Community
RomanCohort commited on
Commit
ab2b085
·
verified ·
1 Parent(s): c854070

add reports/_leak_diag_400.json

Browse files
Files changed (1) hide show
  1. reports/_leak_diag_400.json +159 -0
reports/_leak_diag_400.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "records": 400,
3
+ "split_counts": {
4
+ "train": 321,
5
+ "test": 39,
6
+ "val": 40
7
+ },
8
+ "k": 12,
9
+ "leaking_kmers_true": 2121,
10
+ "leaking_record_pairs": 1458,
11
+ "records_involved": 322,
12
+ "note": "14_build_evalset.py 打印的数字被 `len(leaks) < 20` 截断，只是上限",
13
+ "top_pairs": [
14
+ {
15
+ "shared_kmers": 83,
16
+ "jaccard_12mer": 0.062,
17
+ "a": {
18
+ "uid": "urs:URS00001B3B08|taxid:9606",
19
+ "ent_id": "LUADT1",
20
+ "type": "lncRNA",
21
+ "split": "train",
22
+ "n_nt": 453
23
+ },
24
+ "b": {
25
+ "uid": "urs:URS000052446E|taxid:9606",
26
+ "ent_id": "PINK1-AS",
27
+ "type": "lncRNA",
28
+ "split": "test",
29
+ "n_nt": 1022
30
+ }
31
+ },
32
+ {
33
+ "shared_kmers": 64,
34
+ "jaccard_12mer": 0.046,
35
+ "a": {
36
+ "uid": "urs:URS00001B3B08|taxid:9606",
37
+ "ent_id": "LUADT1",
38
+ "type": "lncRNA",
39
+ "split": "train",
40
+ "n_nt": 453
41
+ },
42
+ "b": {
43
+ "uid": "urs:URS000075BAC1|taxid:9606",
44
+ "ent_id": "LOH12CR2",
45
+ "type": "lncRNA",
46
+ "split": "test",
47
+ "n_nt": 1022
48
+ }
49
+ },
50
+ {
51
+ "shared_kmers": 45,
52
+ "jaccard_12mer": 0.027,
53
+ "a": {
54
+ "uid": "urs:URS0000052DF4|taxid:9606",
55
+ "ent_id": "P3H2-AS1",
56
+ "type": "lncRNA",
57
+ "split": "train",
58
+ "n_nt": 730
59
+ },
60
+ "b": {
61
+ "uid": "urs:URS000075BAC1|taxid:9606",
62
+ "ent_id": "LOH12CR2",
63
+ "type": "lncRNA",
64
+ "split": "test",
65
+ "n_nt": 1022
66
+ }
67
+ },
68
+ {
69
+ "shared_kmers": 45,
70
+ "jaccard_12mer": 0.027,
71
+ "a": {
72
+ "uid": "urs:URS000052446E|taxid:9606",
73
+ "ent_id": "PINK1-AS",
74
+ "type": "lncRNA",
75
+ "split": "test",
76
+ "n_nt": 1022
77
+ },
78
+ "b": {
79
+ "uid": "urs:URS0000052DF4|taxid:9606",
80
+ "ent_id": "P3H2-AS1",
81
+ "type": "lncRNA",
82
+ "split": "train",
83
+ "n_nt": 730
84
+ }
85
+ },
86
+ {
87
+ "shared_kmers": 44,
88
+ "jaccard_12mer": 0.4,
89
+ "a": {
90
+ "uid": "urs:URS00003FA6CD|taxid:9606",
91
+ "ent_id": "MIR9-2",
92
+ "type": "ncRNA",
93
+ "split": "test",
94
+ "n_nt": 87
95
+ },
96
+ "b": {
97
+ "uid": "urs:URS000075C54E|taxid:9606",
98
+ "ent_id": "MIR9-1",
99
+ "type": "ncRNA",
100
+ "split": "train",
101
+ "n_nt": 89
102
+ }
103
+ },
104
+ {
105
+ "shared_kmers": 38,
106
+ "jaccard_12mer": 0.02,
107
+ "a": {
108
+ "uid": "urs:URS000075DC05|taxid:9606",
109
+ "ent_id": "LINC00836",
110
+ "type": "lncRNA",
111
+ "split": "test",
112
+ "n_nt": 1022
113
+ },
114
+ "b": {
115
+ "uid": "urs:URS00007E3A2E|taxid:9606",
116
+ "ent_id": "CCR5AS",
117
+ "type": "lncRNA",
118
+ "split": "train",
119
+ "n_nt": 951
120
+ }
121
+ },
122
+ {
123
+ "shared_kmers": 35,
124
+ "jaccard_12mer": 0.018,
125
+ "a": {
126
+ "uid": "urs:URS00022AE7E2|taxid:9606",
127
+ "ent_id": "MRPL20-DT",
128
+ "type": "lncRNA",
129
+ "split": "train",
130
+ "n_nt": 1022
131
+ },
132
+ "b": {
133
+ "uid": "urs:URS00007DCF59|taxid:9606",
134
+ "ent_id": "RPP38-DT",
135
+ "type": "lncRNA",
136
+ "split": "test",
137
+ "n_nt": 1022
138
+ }
139
+ },
140
+ {
141
+ "shared_kmers": 34,
142
+ "jaccard_12mer": 0.017,
143
+ "a": {
144
+ "uid": "urs:URS000052446E|taxid:9606",
145
+ "ent_id": "PINK1-AS",
146
+ "type": "lncRNA",
147
+ "split": "test",
148
+ "n_nt": 1022
149
+ },
150
+ "b": {
151
+ "uid": "urs:URS0000812110|taxid:9606",
152
+ "ent_id": "BISPR",
153
+ "type": "lncRNA",
154
+ "split": "train",
155
+ "n_nt": 1022
156
+ }
157
+ }
158
+ ]
159
+ }