update
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitignore +2 -0
- .idea/OmniGenomeLeaderboard.iml +7 -0
- .idea/inspectionProfiles/Project_Default.xml +88 -0
- .idea/inspectionProfiles/profiles_settings.xml +6 -0
- .idea/misc.xml +6 -0
- .idea/vcs.xml +6 -0
- .idea/workspace.xml +56 -5
- app.py +24 -25
- eval-queue/GB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/GB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/GUE/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/GUE/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/PGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/PGB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json +1 -0
- eval-queue/RGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json +1 -0
- eval-results/GB/3UTRBERT.json +48 -0
- eval-results/GB/Caduceus.json +48 -0
- eval-results/GB/DNABERT-2-117M.json +48 -0
- eval-results/GB/HyenaDNA.json +48 -0
- eval-results/GB/NT-V2-100M.json +48 -0
- eval-results/GB/OmniGenome186M.json +48 -0
- eval-results/GB/SpliceBERT.json +48 -0
- eval-results/GUE/3UTRBERT.json +42 -0
- eval-results/GUE/Caduceus.json +42 -0
- eval-results/GUE/DNABERT-2-117M.json +42 -0
- eval-results/GUE/HyenaDNA.json +42 -0
- eval-results/GUE/NT-V2-100M.json +42 -0
- eval-results/GUE/OmniGenome186M.json +42 -0
- eval-results/GUE/SpliceBERT.json +42 -0
- eval-results/PGB/3UTRBERT.json +45 -0
- eval-results/PGB/Agro-NT.json +45 -0
- eval-results/PGB/CDSBERT.json +45 -0
- eval-results/PGB/Caduceus.json +45 -0
- eval-results/PGB/DNABERT-2-117M.json +45 -0
- eval-results/PGB/HyenaDNA.json +45 -0
- eval-results/PGB/NT-V2-100M.json +45 -0
- eval-results/PGB/OmniGenome186M.json +45 -0
- eval-results/PGB/RNA-BERT.json +46 -0
- eval-results/PGB/RNA-FM.json +45 -0
- eval-results/PGB/RNA-MSM.json +45 -0
- eval-results/PGB/SpliceBERT.json +45 -0
- eval-results/RGB/yangheng/3UTRBERT.json +39 -0
- eval-results/RGB/yangheng/Agro-NT.json +39 -0
- eval-results/RGB/yangheng/CDSBERT.json +39 -0
- eval-results/RGB/yangheng/DNABERT-2-117M.json +39 -0
- eval-results/RGB/yangheng/HyenaDNA.json +39 -0
- eval-results/RGB/yangheng/NT-V2-100M.json +39 -0
- eval-results/RGB/yangheng/OmniGenome186M.json +39 -0
- eval-results/RGB/yangheng/SpliceBERT.json +39 -0
- eval-results/RGB/yangheng/results_OmniGenome-52M.json +39 -0
.gitignore
CHANGED
@@ -11,3 +11,5 @@ __pycache__/
|
|
11 |
#eval-queue-bk/
|
12 |
#eval-results-bk/
|
13 |
logs/
|
|
|
|
|
|
11 |
#eval-queue-bk/
|
12 |
#eval-results-bk/
|
13 |
logs/
|
14 |
+
.idea/
|
15 |
+
|
.idea/OmniGenomeLeaderboard.iml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<module version="4">
|
3 |
+
<component name="PyDocumentationSettings">
|
4 |
+
<option name="format" value="PLAIN" />
|
5 |
+
<option name="myDocStringFormat" value="Plain" />
|
6 |
+
</component>
|
7 |
+
</module>
|
.idea/inspectionProfiles/Project_Default.xml
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<component name="InspectionProjectProfileManager">
|
2 |
+
<profile version="1.0">
|
3 |
+
<option name="myName" value="Project Default" />
|
4 |
+
<inspection_tool class="DuplicatedCode" enabled="true" level="WEAK WARNING" enabled_by_default="true">
|
5 |
+
<Languages>
|
6 |
+
<language minSize="54" name="Python" />
|
7 |
+
</Languages>
|
8 |
+
</inspection_tool>
|
9 |
+
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
|
10 |
+
<option name="ignoredPackages">
|
11 |
+
<value>
|
12 |
+
<list size="70">
|
13 |
+
<item index="0" class="java.lang.String" itemvalue="ftfy" />
|
14 |
+
<item index="1" class="java.lang.String" itemvalue="gensim" />
|
15 |
+
<item index="2" class="java.lang.String" itemvalue="diffusers" />
|
16 |
+
<item index="3" class="java.lang.String" itemvalue="tensorflow_text" />
|
17 |
+
<item index="4" class="java.lang.String" itemvalue="tensorflow" />
|
18 |
+
<item index="5" class="java.lang.String" itemvalue="TextAttack" />
|
19 |
+
<item index="6" class="java.lang.String" itemvalue="tensorflow_hub" />
|
20 |
+
<item index="7" class="java.lang.String" itemvalue="pyabsa" />
|
21 |
+
<item index="8" class="java.lang.String" itemvalue="protobuf" />
|
22 |
+
<item index="9" class="java.lang.String" itemvalue="networkx" />
|
23 |
+
<item index="10" class="java.lang.String" itemvalue="update-checker" />
|
24 |
+
<item index="11" class="java.lang.String" itemvalue="boostaug" />
|
25 |
+
<item index="12" class="java.lang.String" itemvalue="pandas" />
|
26 |
+
<item index="13" class="java.lang.String" itemvalue="termcolor" />
|
27 |
+
<item index="14" class="java.lang.String" itemvalue="metric-visualizer" />
|
28 |
+
<item index="15" class="java.lang.String" itemvalue="spacy" />
|
29 |
+
<item index="16" class="java.lang.String" itemvalue="seqeval" />
|
30 |
+
<item index="17" class="java.lang.String" itemvalue="autocuda" />
|
31 |
+
<item index="18" class="java.lang.String" itemvalue="sentencepiece" />
|
32 |
+
<item index="19" class="java.lang.String" itemvalue="findfile" />
|
33 |
+
<item index="20" class="java.lang.String" itemvalue="gitpython" />
|
34 |
+
<item index="21" class="java.lang.String" itemvalue="pytorch_warmup" />
|
35 |
+
<item index="22" class="java.lang.String" itemvalue="torchtext" />
|
36 |
+
<item index="23" class="java.lang.String" itemvalue="googledrivedownloader" />
|
37 |
+
<item index="24" class="java.lang.String" itemvalue="opennmt-py" />
|
38 |
+
<item index="25" class="java.lang.String" itemvalue="opencv-contrib-python" />
|
39 |
+
<item index="26" class="java.lang.String" itemvalue="timm" />
|
40 |
+
<item index="27" class="java.lang.String" itemvalue="pytorch_lightning" />
|
41 |
+
<item index="28" class="java.lang.String" itemvalue="invisible-watermark" />
|
42 |
+
<item index="29" class="java.lang.String" itemvalue="tqdm" />
|
43 |
+
<item index="30" class="java.lang.String" itemvalue="tokenizers" />
|
44 |
+
<item index="31" class="java.lang.String" itemvalue="gradio" />
|
45 |
+
<item index="32" class="java.lang.String" itemvalue="scikit-learn" />
|
46 |
+
<item index="33" class="java.lang.String" itemvalue="nltk" />
|
47 |
+
<item index="34" class="java.lang.String" itemvalue="arxiv" />
|
48 |
+
<item index="35" class="java.lang.String" itemvalue="imblearn" />
|
49 |
+
<item index="36" class="java.lang.String" itemvalue="packaging" />
|
50 |
+
<item index="37" class="java.lang.String" itemvalue="setuptools" />
|
51 |
+
<item index="38" class="java.lang.String" itemvalue="numpy" />
|
52 |
+
<item index="39" class="java.lang.String" itemvalue="requests" />
|
53 |
+
<item index="40" class="java.lang.String" itemvalue="nlpaug" />
|
54 |
+
<item index="41" class="java.lang.String" itemvalue="yacs" />
|
55 |
+
<item index="42" class="java.lang.String" itemvalue="tensorboardX" />
|
56 |
+
<item index="43" class="java.lang.String" itemvalue="rouge" />
|
57 |
+
<item index="44" class="java.lang.String" itemvalue="datasets" />
|
58 |
+
<item index="45" class="java.lang.String" itemvalue="transformers" />
|
59 |
+
<item index="46" class="java.lang.String" itemvalue="typing_extensions" />
|
60 |
+
<item index="47" class="java.lang.String" itemvalue="torch" />
|
61 |
+
<item index="48" class="java.lang.String" itemvalue="cmudict" />
|
62 |
+
<item index="49" class="java.lang.String" itemvalue="pykakasi" />
|
63 |
+
<item index="50" class="java.lang.String" itemvalue="fastapi" />
|
64 |
+
<item index="51" class="java.lang.String" itemvalue="rouge-chinese" />
|
65 |
+
<item index="52" class="java.lang.String" itemvalue="peft" />
|
66 |
+
<item index="53" class="java.lang.String" itemvalue="uvicorn" />
|
67 |
+
<item index="54" class="java.lang.String" itemvalue="sse-starlette" />
|
68 |
+
<item index="55" class="java.lang.String" itemvalue="trl" />
|
69 |
+
<item index="56" class="java.lang.String" itemvalue="tiktoken" />
|
70 |
+
<item index="57" class="java.lang.String" itemvalue="scipy" />
|
71 |
+
<item index="58" class="java.lang.String" itemvalue="pydantic" />
|
72 |
+
<item index="59" class="java.lang.String" itemvalue="jieba" />
|
73 |
+
<item index="60" class="java.lang.String" itemvalue="matplotlib" />
|
74 |
+
<item index="61" class="java.lang.String" itemvalue="transformers_stream_generator" />
|
75 |
+
<item index="62" class="java.lang.String" itemvalue="accelerate" />
|
76 |
+
<item index="63" class="java.lang.String" itemvalue="optimum" />
|
77 |
+
<item index="64" class="java.lang.String" itemvalue="auto-gptq" />
|
78 |
+
<item index="65" class="java.lang.String" itemvalue="bitsandbytes" />
|
79 |
+
<item index="66" class="java.lang.String" itemvalue="deepspeed" />
|
80 |
+
<item index="67" class="java.lang.String" itemvalue="evaluate" />
|
81 |
+
<item index="68" class="java.lang.String" itemvalue="tensorboardx" />
|
82 |
+
<item index="69" class="java.lang.String" itemvalue="sklearn" />
|
83 |
+
</list>
|
84 |
+
</value>
|
85 |
+
</option>
|
86 |
+
</inspection_tool>
|
87 |
+
</profile>
|
88 |
+
</component>
|
.idea/inspectionProfiles/profiles_settings.xml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<component name="InspectionProjectProfileManager">
|
2 |
+
<settings>
|
3 |
+
<option name="USE_PROJECT_PROFILE" value="false" />
|
4 |
+
<version value="1.0" />
|
5 |
+
</settings>
|
6 |
+
</component>
|
.idea/misc.xml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<project version="4">
|
3 |
+
<component name="Black">
|
4 |
+
<option name="sdkName" value="C:\Users\chuan\miniconda3" />
|
5 |
+
</component>
|
6 |
+
</project>
|
.idea/vcs.xml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<?xml version="1.0" encoding="UTF-8"?>
|
2 |
+
<project version="4">
|
3 |
+
<component name="VcsDirectoryMappings">
|
4 |
+
<mapping directory="" vcs="Git" />
|
5 |
+
</component>
|
6 |
+
</project>
|
.idea/workspace.xml
CHANGED
@@ -5,8 +5,57 @@
|
|
5 |
</component>
|
6 |
<component name="ChangeListManager">
|
7 |
<list default="true" id="4dc9d937-d789-48c5-9ba5-fe08d01bc11f" name="Changes" comment="">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
<change beforePath="$PROJECT_DIR$/.gitignore" beforeDir="false" afterPath="$PROJECT_DIR$/.gitignore" afterDir="false" />
|
|
|
9 |
<change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
|
|
|
10 |
</list>
|
11 |
<option name="SHOW_DIALOG" value="false" />
|
12 |
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
@@ -26,10 +75,10 @@
|
|
26 |
</component>
|
27 |
<component name="PropertiesComponent"><![CDATA[{
|
28 |
"keyToString": {
|
29 |
-
"Python.app.executor": "
|
30 |
"RunOnceActivity.ShowReadmeOnStart": "true",
|
31 |
"git-widget-placeholder": "main",
|
32 |
-
"last_opened_file_path": "C:/Users/chuan/OneDrive - University of Exeter/AIProjects/OmniGenomeLeaderboard
|
33 |
"node.js.detected.package.eslint": "true",
|
34 |
"node.js.detected.package.tslint": "true",
|
35 |
"node.js.selected.package.eslint": "(autodetect)",
|
@@ -40,9 +89,9 @@
|
|
40 |
}]]></component>
|
41 |
<component name="RecentsManager">
|
42 |
<key name="CopyFile.RECENT_KEYS">
|
|
|
43 |
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard\eval-queue" />
|
44 |
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard\eval-queue\.cache\huggingface\download\GB\InstaDeepAI" />
|
45 |
-
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard" />
|
46 |
</key>
|
47 |
</component>
|
48 |
<component name="RunManager">
|
@@ -94,7 +143,9 @@
|
|
94 |
<workItem from="1726143220520" duration="3239000" />
|
95 |
<workItem from="1726146471494" duration="2362000" />
|
96 |
<workItem from="1726223901200" duration="2056000" />
|
97 |
-
<workItem from="1726434553745" duration="
|
|
|
|
|
98 |
</task>
|
99 |
<servers />
|
100 |
</component>
|
@@ -134,6 +185,6 @@
|
|
134 |
</breakpoint-manager>
|
135 |
</component>
|
136 |
<component name="com.intellij.coverage.CoverageDataManagerImpl">
|
137 |
-
<SUITE FILE_PATH="coverage/OmniGenomeLeaderboard$app.coverage" NAME="app Coverage Results" MODIFIED="
|
138 |
</component>
|
139 |
</project>
|
|
|
5 |
</component>
|
6 |
<component name="ChangeListManager">
|
7 |
<list default="true" id="4dc9d937-d789-48c5-9ba5-fe08d01bc11f" name="Changes" comment="">
|
8 |
+
<change afterPath="$PROJECT_DIR$/.idea/OmniGenomeLeaderboard.iml" afterDir="false" />
|
9 |
+
<change afterPath="$PROJECT_DIR$/.idea/inspectionProfiles/Project_Default.xml" afterDir="false" />
|
10 |
+
<change afterPath="$PROJECT_DIR$/.idea/inspectionProfiles/profiles_settings.xml" afterDir="false" />
|
11 |
+
<change afterPath="$PROJECT_DIR$/.idea/misc.xml" afterDir="false" />
|
12 |
+
<change afterPath="$PROJECT_DIR$/.idea/vcs.xml" afterDir="false" />
|
13 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/GB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
14 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/GB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
15 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/GUE/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
16 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/GUE/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
17 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/PGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
18 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/PGB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
19 |
+
<change afterPath="$PROJECT_DIR$/eval-queue/RGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json" afterDir="false" />
|
20 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/3UTRBERT.json" afterDir="false" />
|
21 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/Caduceus.json" afterDir="false" />
|
22 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/DNABERT-2-117M.json" afterDir="false" />
|
23 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/HyenaDNA.json" afterDir="false" />
|
24 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/NT-V2-100M.json" afterDir="false" />
|
25 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/OmniGenome186M.json" afterDir="false" />
|
26 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GB/SpliceBERT.json" afterDir="false" />
|
27 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/3UTRBERT.json" afterDir="false" />
|
28 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/Caduceus.json" afterDir="false" />
|
29 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/DNABERT-2-117M.json" afterDir="false" />
|
30 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/HyenaDNA.json" afterDir="false" />
|
31 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/NT-V2-100M.json" afterDir="false" />
|
32 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/OmniGenome186M.json" afterDir="false" />
|
33 |
+
<change afterPath="$PROJECT_DIR$/eval-results/GUE/SpliceBERT.json" afterDir="false" />
|
34 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/3UTRBERT.json" afterDir="false" />
|
35 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/Agro-NT.json" afterDir="false" />
|
36 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/CDSBERT.json" afterDir="false" />
|
37 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/Caduceus.json" afterDir="false" />
|
38 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/DNABERT-2-117M.json" afterDir="false" />
|
39 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/HyenaDNA.json" afterDir="false" />
|
40 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/NT-V2-100M.json" afterDir="false" />
|
41 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/OmniGenome186M.json" afterDir="false" />
|
42 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/RNA-BERT.json" afterDir="false" />
|
43 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/RNA-FM.json" afterDir="false" />
|
44 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/RNA-MSM.json" afterDir="false" />
|
45 |
+
<change afterPath="$PROJECT_DIR$/eval-results/PGB/SpliceBERT.json" afterDir="false" />
|
46 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/3UTRBERT.json" afterDir="false" />
|
47 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/Agro-NT.json" afterDir="false" />
|
48 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/CDSBERT.json" afterDir="false" />
|
49 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/DNABERT-2-117M.json" afterDir="false" />
|
50 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/HyenaDNA.json" afterDir="false" />
|
51 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/NT-V2-100M.json" afterDir="false" />
|
52 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/OmniGenome186M.json" afterDir="false" />
|
53 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/SpliceBERT.json" afterDir="false" />
|
54 |
+
<change afterPath="$PROJECT_DIR$/eval-results/RGB/yangheng/results_OmniGenome-52M.json" afterDir="false" />
|
55 |
<change beforePath="$PROJECT_DIR$/.gitignore" beforeDir="false" afterPath="$PROJECT_DIR$/.gitignore" afterDir="false" />
|
56 |
+
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
57 |
<change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
|
58 |
+
<change beforePath="$PROJECT_DIR$/src/about.py" beforeDir="false" afterPath="$PROJECT_DIR$/src/about.py" afterDir="false" />
|
59 |
</list>
|
60 |
<option name="SHOW_DIALOG" value="false" />
|
61 |
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
|
|
75 |
</component>
|
76 |
<component name="PropertiesComponent"><![CDATA[{
|
77 |
"keyToString": {
|
78 |
+
"Python.app.executor": "Run",
|
79 |
"RunOnceActivity.ShowReadmeOnStart": "true",
|
80 |
"git-widget-placeholder": "main",
|
81 |
+
"last_opened_file_path": "C:/Users/chuan/OneDrive - University of Exeter/AIProjects/OmniGenomeLeaderboard",
|
82 |
"node.js.detected.package.eslint": "true",
|
83 |
"node.js.detected.package.tslint": "true",
|
84 |
"node.js.selected.package.eslint": "(autodetect)",
|
|
|
89 |
}]]></component>
|
90 |
<component name="RecentsManager">
|
91 |
<key name="CopyFile.RECENT_KEYS">
|
92 |
+
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard" />
|
93 |
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard\eval-queue" />
|
94 |
<recent name="C:\Users\chuan\OneDrive - University of Exeter\AIProjects\OmniGenomeLeaderboard\eval-queue\.cache\huggingface\download\GB\InstaDeepAI" />
|
|
|
95 |
</key>
|
96 |
</component>
|
97 |
<component name="RunManager">
|
|
|
143 |
<workItem from="1726143220520" duration="3239000" />
|
144 |
<workItem from="1726146471494" duration="2362000" />
|
145 |
<workItem from="1726223901200" duration="2056000" />
|
146 |
+
<workItem from="1726434553745" duration="6270000" />
|
147 |
+
<workItem from="1726515056209" duration="632000" />
|
148 |
+
<workItem from="1726687104634" duration="322000" />
|
149 |
</task>
|
150 |
<servers />
|
151 |
</component>
|
|
|
185 |
</breakpoint-manager>
|
186 |
</component>
|
187 |
<component name="com.intellij.coverage.CoverageDataManagerImpl">
|
188 |
+
<SUITE FILE_PATH="coverage/OmniGenomeLeaderboard$app.coverage" NAME="app Coverage Results" MODIFIED="1726687258224" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
|
189 |
</component>
|
190 |
</project>
|
app.py
CHANGED
@@ -35,31 +35,30 @@ def restart_space():
|
|
35 |
|
36 |
|
37 |
### Space initialisation
|
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 |
-
restart_space()
|
63 |
|
64 |
RGB_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH+"/RGB/", EVAL_REQUESTS_PATH+"/RGB/", RGB_COLS, RGB_BENCHMARK_COLS)
|
65 |
PGB_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH+"/PGB/", EVAL_REQUESTS_PATH+"/PGB/", PGB_COLS, PGB_BENCHMARK_COLS)
|
|
|
35 |
|
36 |
|
37 |
### Space initialisation
|
38 |
+
# try:
|
39 |
+
# print(EVAL_REQUESTS_PATH)
|
40 |
+
# snapshot_download(
|
41 |
+
# repo_id=QUEUE_REPO,
|
42 |
+
# local_dir=EVAL_REQUESTS_PATH,
|
43 |
+
# repo_type="dataset",
|
44 |
+
# tqdm_class=None,
|
45 |
+
# etag_timeout=30,
|
46 |
+
# token=TOKEN,
|
47 |
+
# )
|
48 |
+
# except Exception:
|
49 |
+
# restart_space()
|
50 |
+
# try:
|
51 |
+
# print(EVAL_RESULTS_PATH)
|
52 |
+
# snapshot_download(
|
53 |
+
# repo_id=RESULTS_REPO,
|
54 |
+
# local_dir=EVAL_RESULTS_PATH,
|
55 |
+
# repo_type="dataset",
|
56 |
+
# tqdm_class=None,
|
57 |
+
# etag_timeout=30,
|
58 |
+
# token=TOKEN,
|
59 |
+
# )
|
60 |
+
# except Exception:
|
61 |
+
# restart_space()
|
|
|
62 |
|
63 |
RGB_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH+"/RGB/", EVAL_REQUESTS_PATH+"/RGB/", RGB_COLS, RGB_BENCHMARK_COLS)
|
64 |
PGB_LEADERBOARD_DF = get_leaderboard_df(EVAL_RESULTS_PATH+"/PGB/", EVAL_REQUESTS_PATH+"/PGB/", PGB_COLS, PGB_BENCHMARK_COLS)
|
eval-queue/GB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 96, "license": "custom"}
|
eval-queue/GB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 7.73, "license": "custom"}
|
eval-queue/GUE/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 96, "license": "custom"}
|
eval-queue/GUE/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 7.73, "license": "custom"}
|
eval-queue/PGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 96, "license": "custom"}
|
eval-queue/PGB/kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 7.73, "license": "custom"}
|
eval-queue/RGB/InstaDeepAI/nucleotide-transformer-v2-100m-multi-species_eval_request_False_bfloat16_Original.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "InstaDeepAI/nucleotide-transformer-v2-100m-multi-species", "base_model": "", "revision": "main", "private": false, "precision": "bfloat16", "weight_type": "Original", "status": "FINISHED", "submitted_time": "2023-11-21T18:10:08Z", "model_type": "\ud83d\udfe2 : pretrained", "likes": 0, "params": 100, "license": "custom"}
|
eval-results/GB/3UTRBERT.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/utrbert-4mer",
|
4 |
+
"model_args":"pretrained=multimolecule/utrbert-4mer,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"86M", "Pretraining Data":"20,362 Sequences", "Species":"Multi-Species", "Nucleic Acid":"mRNA 3'UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/utrbert-4mer",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.8950
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9022
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7435
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.8014
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7023
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.7633
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.9847
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8249
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6678
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/Caduceus.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
4 |
+
"model_args":"pretrained= kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"7.73M", "Pretraining Data":"35 billion nucleotide base pairs", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.9213
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9474
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7203
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.7561
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7020
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.7647
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.7916
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8436
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6317
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/DNABERT-2-117M.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"zhihan1996/DNABERT-2-117M",
|
4 |
+
"model_args":"pretrained=zhihan1996/DNABERT-2-117M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"BPE", "# of Params":"117M", "Pretraining Data":"32.49B Tokens", "Species":"Human + 135 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"zhihan1996/DNABERT-2-117M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.9267
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9517
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.4377
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.7721
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7558
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.8066
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.7814
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8580
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6803
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/HyenaDNA.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
4 |
+
"model_args":"pretrained=LongSafari/hyenadna-large-1m-seqlen-hf,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"47M", "Pretraining Data":"~3.2B Tokens", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.8821
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9413
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7011
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.7644
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7038
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.7958
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.9633
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8599
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6703
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/NT-V2-100M.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/nucleotide-transformer-v2-100m-multi-species,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"96M", "Pretraining Data":"300B Tokens", "Species":"Human + 850 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.9166
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9432
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7820
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.8172
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7198
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.7985
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.9330
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8530
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6853
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/OmniGenome186M.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"yangheng/omnigenome-186M",
|
4 |
+
"model_args":"pretrained=yangheng/omnigenome-186M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"186M", "Pretraining Data":"54.2B Tokens", "Species":"1124 Plant Species", "Nucleic Acid":"mRNA, CDS, UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"yangheng/omnigenome-186M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.9416
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9349
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7717
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.8034
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7351
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.8223
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.9566
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8787
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6897
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GB/SpliceBERT.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/splicebert",
|
4 |
+
"model_args":"pretrained=multimolecule/splicebert,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"19.7M", "Pretraining Data":"65 billion nucleotides", "Species":"Multi-Species", "Nucleic Acid":"mRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/splicebert",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"DEM":{
|
21 |
+
"F1":0.9472
|
22 |
+
},
|
23 |
+
"DOW":{
|
24 |
+
"F1":0.9642
|
25 |
+
},
|
26 |
+
"DRE":{
|
27 |
+
"F1":0.7229
|
28 |
+
},
|
29 |
+
"DME":{
|
30 |
+
"F1":0.7470
|
31 |
+
},
|
32 |
+
"HCE":{
|
33 |
+
"F1":0.7350
|
34 |
+
},
|
35 |
+
"HEE":{
|
36 |
+
"F1":0.7960
|
37 |
+
},
|
38 |
+
"HRE":{
|
39 |
+
"F1":0.9523
|
40 |
+
},
|
41 |
+
"HNP":{
|
42 |
+
"F1":0.8957
|
43 |
+
},
|
44 |
+
"HOR":{
|
45 |
+
"F1":0.6889
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
eval-results/GUE/3UTRBERT.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/utrbert-4mer",
|
4 |
+
"model_args":"pretrained=multimolecule/utrbert-4mer,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"86M", "Pretraining Data":"20,362 Sequences", "Species":"Multi-Species", "Nucleic Acid":"mRNA 3'UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/utrbert-4mer",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7189
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.7146
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.6871
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.7485
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.8237
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.9051
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.8195
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/Caduceus.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
4 |
+
"model_args":"pretrained= kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"7.73M", "Pretraining Data":"35 billion nucleotide base pairs", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7349
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.7818
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.4909
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.7956
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.8913
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8509
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.8182
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/DNABERT-2-117M.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"zhihan1996/DNABERT-2-117M",
|
4 |
+
"model_args":"pretrained=zhihan1996/DNABERT-2-117M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"BPE", "# of Params":"117M", "Pretraining Data":"32.49B Tokens", "Species":"Human + 135 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"zhihan1996/DNABERT-2-117M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7585
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.8623
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.6890
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.8180
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.9017
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8257
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.8521
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/HyenaDNA.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
4 |
+
"model_args":"pretrained=LongSafari/hyenadna-large-1m-seqlen-hf,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"47M", "Pretraining Data":"~3.2B Tokens", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7308
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.7344
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.6637
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.7762
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.9119
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8431
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.8334
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/NT-V2-100M.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/nucleotide-transformer-v2-100m-multi-species,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"96M", "Pretraining Data":"300B Tokens", "Species":"Human + 850 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7493
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.7810
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.5923
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.7912
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.9087
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8470
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.8413
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/OmniGenome186M.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"yangheng/omnigenome-186M",
|
4 |
+
"model_args":"pretrained=yangheng/omnigenome-186M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"186M", "Pretraining Data":"54.2B Tokens", "Species":"1124 Plant Species", "Nucleic Acid":"mRNA, CDS, UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"yangheng/omnigenome-186M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7851
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.8472
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.7472
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.8173
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.9004
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8522
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.9039
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/GUE/SpliceBERT.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/splicebert",
|
4 |
+
"model_args":"pretrained=multimolecule/splicebert,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"19.7M", "Pretraining Data":"65 billion nucleotides", "Species":"Multi-Species", "Nucleic Acid":"mRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/splicebert",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"Yeast EMP":{
|
21 |
+
"F1":0.7766
|
22 |
+
},
|
23 |
+
"Mouse TF-M":{
|
24 |
+
"F1":0.8497
|
25 |
+
},
|
26 |
+
"Virus CVC":{
|
27 |
+
"F1":0.5624
|
28 |
+
},
|
29 |
+
"Human TF-H":{
|
30 |
+
"F1":0.8277
|
31 |
+
},
|
32 |
+
"Human PD":{
|
33 |
+
"F1":0.9224
|
34 |
+
},
|
35 |
+
"Human CPD":{
|
36 |
+
"F1":0.8396
|
37 |
+
},
|
38 |
+
"Human SSP":{
|
39 |
+
"F1":0.9381
|
40 |
+
}
|
41 |
+
}
|
42 |
+
}
|
eval-results/PGB/3UTRBERT.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/utrbert-4mer",
|
4 |
+
"model_args":"pretrained=multimolecule/utrbert-4mer,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"86M", "Pretraining Data":"20,362 Sequences", "Species":"Multi-Species", "Nucleic Acid":"mRNA 3'UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/utrbert-4mer",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.7648
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.7075
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6371
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":1.04
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.36
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9444
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.87
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.7167
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/Agro-NT.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/agro-nucleotide-transformer-1b",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/agro-nucleotide-transformer-1b,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"985M", "Pretraining Data":"472.5B Tokens", "Species":"48 Edible Plants", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/agro-nucleotide-transformer-1b",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.7889
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.6724
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6327
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.94
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.78
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.8845
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":15.56
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.6283
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/CDSBERT.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"GleghornLab/cdsBERT",
|
4 |
+
"model_args":"pretrained=GleghornLab/cdsBERT,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"420M", "Pretraining Data":"4M Sequences", "Species":"4,069 RNA families", "Nucleic Acid":"CDS"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"GleghornLab/cdsBERT",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.3972
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.3306
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.4895
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":2.19
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.59
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.5220
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.77
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.3393
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/Caduceus.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
4 |
+
"model_args":"pretrained= kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"7.73M", "Pretraining Data":"35 billion nucleotide base pairs", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"kuleshov-group/caduceus-ps_seqlen-131k_d_model-256_n_layer-16",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.7089
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.6840
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6453
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.91
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.26
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.7951
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.72
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.6083
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/DNABERT-2-117M.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"zhihan1996/DNABERT-2-117M",
|
4 |
+
"model_args":"pretrained=zhihan1996/DNABERT-2-117M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"BPE", "# of Params":"117M", "Pretraining Data":"32.49B Tokens", "Species":"Human + 135 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"zhihan1996/DNABERT-2-117M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.4135
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.7255
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6149
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.99
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.24
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.4534
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.78
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.3640
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/HyenaDNA.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
4 |
+
"model_args":"pretrained=LongSafari/hyenadna-large-1m-seqlen-hf,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"47M", "Pretraining Data":"~3.2B Tokens", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.8311
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.5821
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.5220
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.88
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.26
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9028
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.76
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.6617
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/NT-V2-100M.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/nucleotide-transformer-v2-100m-multi-species,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"96M", "Pretraining Data":"300B Tokens", "Species":"Human + 850 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.7126
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.7308
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6571
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.81
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.27
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9505
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.69
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.7389
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/OmniGenome186M.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"yangheng/omnigenome-186M",
|
4 |
+
"model_args":"pretrained=yangheng/omnigenome-186M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"186M", "Pretraining Data":"54.2B Tokens", "Species":"1124 Plant Species", "Nucleic Acid":"mRNA, CDS, UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"yangheng/omnigenome-186M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.8755
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.7796
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6769
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.59
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.18
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9841
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.71
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.7977
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/RNA-BERT.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/rnabert",
|
4 |
+
"model_args":"pretrained=multimolecule/rnabert,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"0.48M", "Pretraining Data":"76,237 human ncRNA sequences", "Species":"Human", "Nucleic Acid":"ncRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/rnabert",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.7854
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.6199
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.4894
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":1.81
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.38
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9445
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.89
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.5761
|
43 |
+
}
|
44 |
+
|
45 |
+
}
|
46 |
+
}
|
eval-results/PGB/RNA-FM.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/rnafm",
|
4 |
+
"model_args":"pretrained=multimolecule/rnafm,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"99.52M", "Pretraining Data":"23.7 million non-redundant RNA sequences", "Species":"Multi-Species", "Nucleic Acid":"ncRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/rnafm",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.8494
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.6875
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.5492
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.95
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.27
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9595
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.83
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.5714
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/RNA-MSM.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/rnamsm",
|
4 |
+
"model_args":"pretrained=multimolecule/rnamsm,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"96.5M", "Pretraining Data":"3,932 RNA families", "Species":"Multi-Species", "Nucleic Acid":"RNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/rnamsm",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.8425
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.6749
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.5352
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":1.28
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.28
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9549
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.87
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.6145
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/PGB/SpliceBERT.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/splicebert",
|
4 |
+
"model_args":"pretrained=multimolecule/splicebert,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"19.7M", "Pretraining Data":"65 billion nucleotides", "Species":"Multi-Species", "Nucleic Acid":"mRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/splicebert",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"PolyA":{
|
21 |
+
"F1":0.6523
|
22 |
+
},
|
23 |
+
"LncRNA":{
|
24 |
+
"F1":0.7188
|
25 |
+
},
|
26 |
+
"Chrom Acc":{
|
27 |
+
"F1":0.6362
|
28 |
+
},
|
29 |
+
"Prom Str":{
|
30 |
+
"RMSE":0.75
|
31 |
+
},
|
32 |
+
"Term Str":{
|
33 |
+
"RMSE":0.22
|
34 |
+
},
|
35 |
+
"Splice":{
|
36 |
+
"F1":0.9645
|
37 |
+
},
|
38 |
+
"Gene Exp":{
|
39 |
+
"RMSE":14.70
|
40 |
+
},
|
41 |
+
"Enhancer":{
|
42 |
+
"F1":0.6971
|
43 |
+
}
|
44 |
+
}
|
45 |
+
}
|
eval-results/RGB/yangheng/3UTRBERT.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/utrbert-4mer",
|
4 |
+
"model_args":"pretrained=multimolecule/utrbert-4mer,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"86M", "Pretraining Data":"20,362 Sequences", "Species":"Multi-Species", "Nucleic Acid":"mRNA 3'UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/utrbert-4mer",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7772
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.5002
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.2401
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.7898
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.5693
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9203
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/Agro-NT.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/agro-nucleotide-transformer-1b",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/agro-nucleotide-transformer-1b,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"985M", "Pretraining Data":"472.5B Tokens", "Species":"48 Edible Plants", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/agro-nucleotide-transformer-1b",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7830
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.4999
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.2638
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.7013
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.4871
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.7521
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/CDSBERT.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"GleghornLab/cdsBERT",
|
4 |
+
"model_args":"pretrained=GleghornLab/cdsBERT,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"420M", "Pretraining Data":"4M Sequences", "Species":"4,069 RNA families", "Nucleic Acid":"CDS"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"GleghornLab/cdsBERT",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7468
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.5503
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.3616
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.8934
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.7001
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9715
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/DNABERT-2-117M.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"zhihan1996/DNABERT-2-117M",
|
4 |
+
"model_args":"pretrained=zhihan1996/DNABERT-2-117M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"BPE", "# of Params":"117M", "Pretraining Data":"32.49B Tokens", "Species":"Human + 135 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"zhihan1996/DNABERT-2-117M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.8158
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.4994
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.1586
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.5982
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.4340
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.6549
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/HyenaDNA.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
4 |
+
"model_args":"pretrained=LongSafari/hyenadna-large-1m-seqlen-hf,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"47M", "Pretraining Data":"~3.2B Tokens", "Species":"Human", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"LongSafari/hyenadna-large-1m-seqlen-hf",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.8056
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.5332
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.3980
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.8423
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.5662
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9542
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/NT-V2-100M.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
4 |
+
"model_args":"pretrained=InstaDeepAI/nucleotide-transformer-v2-100m-multi-species,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"k-mers", "# of Params":"96M", "Pretraining Data":"300B Tokens", "Species":"Human + 850 Species", "Nucleic Acid":"DNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"InstaDeepAI/nucleotide-transformer-v2-100m-multi-species",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7826
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.5049
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.2601
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.7990
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.5660
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9084
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/OmniGenome186M.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"yangheng/omnigenome-186M",
|
4 |
+
"model_args":"pretrained=yangheng/omnigenome-186M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"186M", "Pretraining Data":"54.2B Tokens", "Species":"1124 Plant Species", "Nucleic Acid":"mRNA, CDS, UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"yangheng/omnigenome-186M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7164
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.6381
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.4980
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.9520
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.8248
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9912
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/SpliceBERT.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"multimolecule/splicebert",
|
4 |
+
"model_args":"pretrained=multimolecule/splicebert,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"19.7M", "Pretraining Data":"65 billion nucleotides", "Species":"Multi-Species", "Nucleic Acid":"mRNA"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"multimolecule/splicebert",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7340
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.5811
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.4644
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.8905
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.6910
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9697
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|
eval-results/RGB/yangheng/results_OmniGenome-52M.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config":{
|
3 |
+
"model":"yangheng/omnigenome-52M",
|
4 |
+
"model_args":"pretrained=yangheng/omnigenome-52M,revision=main,dtype=bfloat16",
|
5 |
+
"num_fewshot":0,
|
6 |
+
"batch_size":1,
|
7 |
+
"batch_sizes":[
|
8 |
+
|
9 |
+
],
|
10 |
+
"device":"cpu",
|
11 |
+
"no_cache":true,
|
12 |
+
"limit":20,
|
13 |
+
"bootstrap_iters":100000,
|
14 |
+
"description_dict":{"Tokenization":"SNT", "# of Params":"52M", "Pretraining Data":"54.2B Tokens", "Species":"1124 Plant Species", "Nucleic Acid":"mRNA, CDS, UTR"},
|
15 |
+
"model_dtype":"bfloat16",
|
16 |
+
"model_name":"yangheng/omnigenome-52M",
|
17 |
+
"model_sha":"main"
|
18 |
+
},
|
19 |
+
"results":{
|
20 |
+
"mRNA":{
|
21 |
+
"RMSE":0.7191
|
22 |
+
},
|
23 |
+
"SNMD":{
|
24 |
+
"AUC":0.6244
|
25 |
+
},
|
26 |
+
"SNMR":{
|
27 |
+
"F1":0.4891
|
28 |
+
},
|
29 |
+
"ArchiveII":{
|
30 |
+
"F1":0.9498
|
31 |
+
},
|
32 |
+
"bpRNA":{
|
33 |
+
"F1":0.8234
|
34 |
+
},
|
35 |
+
"RNAStralign":{
|
36 |
+
"F1":0.9901
|
37 |
+
}
|
38 |
+
}
|
39 |
+
}
|