v1.0.0

.github/workflows/ai-review.yaml

@@ -39,8 +39,8 @@ jobs:
           debug: false
           review_simple_changes: false
           review_comment_lgtm: false
-          openai_light_model: gpt-4
-          openai_heavy_model: gpt-4
+          openai_light_model: gpt-4 # changed to gpt-4.1
+          openai_heavy_model: gpt-4 # changed to gpt-4.1
           openai_timeout_ms: 900000 # 15分.
           language: ja-JP
           path_filters: |

README.md

@@ -5,7 +5,7 @@
 
 ## What is RaptGen-UI?
 
-RaptGen-UI is a web-based user-friendly interface for RaptGen, a powerful Latent Space Bayesian Optimization (LSBO) method for identifying and optimizing aptamers from high-throughput SELEX data. For more information about RaptGen, please refer to the [RaptGen paper](https://doi.org/10.1038/s43588-022-00249-6).
+RaptGen-UI is a web-based user-friendly interface for RaptGen, a powerful Latent Space Bayesian Optimization (LSBO) method for identifying and optimizing aptamers from high-throughput SELEX data. For more information about RaptGen-UI, please refer to the [paper](https://doi.org/10.1093/bioadv/vbaf120).
 
 ## Overview
 
@@ -27,7 +27,7 @@ Click on the links to learn more about each module.
 Git clone this repository.
 
 ```shell
-$ git clone https://github.com/Unkosan/RaptGen-UI.git
+$ git clone https://github.com/hmdlab/RaptGen-UI.git
 $ cd RaptGen-UI
 ```
 
@@ -52,17 +52,24 @@ The detailed procedure can be found in the [documentation](https://unkosan.githu
 Contributions are welcome!
 If you find any bugs or have any suggestions, please feel free to open an issue or submit a pull request.
 
-<!-- Just make sure to follow the [Code of Conduct](CODE_OF_CONDUCT.md). -->
-
 ## Citation
 
 If you use RaptGen-UI in your research, please cite the following paper:
 
 ```bibtex
 @article{nakano2025raptgenui,
-   title={RaptGen-UI: Interactive Interface for RNA Aptamer Identification Using Latent Space Bayesian Optimization}
-   author={Nakano, Ryota and Iwano, Natsuki and Ichinose, Akiko and Hamada, Michiaki}
-   year={2025},
+    author = {Nakano, Ryota and Iwano, Natsuki and Ichinose, Akiko and Hamada, Michiaki},
+    title = {RaptGen-UI: an integrated platform for exploring and analyzing the sequence landscape of HT-SELEX experiments},
+    journal = {Bioinformatics Advances},
+    volume = {5},
+    number = {1},
+    pages = {vbaf120},
+    year = {2025},
+    month = {05},
+    issn = {2635-0041},
+    doi = {10.1093/bioadv/vbaf120},
+    url = {https://doi.org/10.1093/bioadv/vbaf120},
+    eprint = {https://academic.oup.com/bioinformaticsadvances/article-pdf/5/1/vbaf120/63309611/vbaf120.pdf},
 }
 ```
 

backend/core/gmmjobs.py

@@ -1,21 +1,13 @@
 import time
+from threading import Semaphore
 from uuid import uuid4
-from celery.contrib.abortable import AbortableTask
 
-from sqlalchemy.orm import Session
-
-from core.db import (
-    GMMJob,
-    OptimalTrial,
-    BIC,
-    ViewerSequenceEmbeddings,
-    get_db_session,
-)
-from tasks import celery
-from threading import Semaphore
 import numpy as np
+from celery.contrib.abortable import AbortableTask
+from core.db import BIC, GMMJob, OptimalTrial, ViewerSequenceEmbeddings, get_db_session
 from sklearn.mixture import GaussianMixture
-
+from sqlalchemy.orm import Session
+from tasks import celery
 
 semaphore = Semaphore(value=2)
 

backend/routers/gmm.py

@@ -1,24 +1,23 @@
-from typing import List, Optional, Literal
-from fastapi import APIRouter, Depends
-from pydantic import BaseModel
-from sqlalchemy.orm import Session
-
-from core.db import GMMJob, OptimalTrial, BIC
 import re
-from fastapi import HTTPException
-from core.gmmjobs import initialize_job_gmm, run_job_gmm
 from time import time
-from celery.contrib.abortable import AbortableAsyncResult
-from tasks import celery
+from typing import List, Literal, Optional
 from uuid import uuid4
 
+from celery.contrib.abortable import AbortableAsyncResult
 from core.db import (
+    BIC,
+    GMMJob,
     JobStatus,
+    OptimalTrial,
     ViewerGMM,
     ViewerSequenceEmbeddings,
     get_db_session,
 )
-
+from core.gmmjobs import initialize_job_gmm, run_job_gmm
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+from sqlalchemy.orm import Session
+from tasks import celery
 
 router = APIRouter()
 

backend/routers/upload.py

@@ -3,17 +3,18 @@
 router = APIRouter()
 
 import os
-from io import BytesIO
 import pickle
-from typing import List, Optional, Tuple, Dict, Any, OrderedDict
-from pydantic import BaseModel
-from core.preprocessing import calc_target_length, estimate_adapters
-from core.algorithms import CNN_PHMM_VAE
 from datetime import datetime
-import torch
-import pandas as pd
-import numpy as np
+from io import BytesIO
+from typing import Any, Dict, List, Optional, OrderedDict, Tuple
 
+import numpy as np
+import pandas as pd
+import torch
+from core.algorithms import CNN_PHMM_VAE
+from core.preprocessing import calc_target_length, estimate_adapters
+from pydantic import BaseModel
+from sklearn.mixture import GaussianMixture
 
 DATA_PATH = "/app/data/"
 
@@ -250,9 +251,6 @@ def _validate_pHMM_model(pickle_state_dict: BytesIO) -> Dict[str, Any]:
     }
 
 
-from sklearn.mixture import GaussianMixture
-
-
 @router.post("/api/upload/validate-GMM-model")
 async def validate_GMM_model(gmm_data: bytes = File(...)):
     result = _validate_GMM_model(BytesIO(gmm_data))
@@ -286,8 +284,8 @@ def _validate_GMM_model(pickle_gmm: BytesIO) -> Dict[str, Any]:
     }
 
 
-from tasks import batch_encode, celery
 from fastapi import Form
+from tasks import batch_encode, celery
 
 
 @router.post("/api/upload/batch-encode")

backend/tests/unit/test_jobs.py

@@ -1,27 +1,25 @@
+import os
+from time import sleep
+
+import numpy as np
+import pandas as pd
 import pytest
 import pytest_postgresql.factories as factories
-
-from sqlalchemy import create_engine
-from sqlalchemy.orm import sessionmaker, scoped_session
 from celery.contrib.abortable import AbortableAsyncResult
-from time import sleep
-import pandas as pd
-import os
-import numpy as np
-
-from core.jobs import run_job_raptgen, ChildJobTask, initialize_job_raptgen
 from core.db import (
     BaseSchema,
-    ParentJob,
     ChildJob,
-    SequenceData,
+    ParentJob,
     PreprocessingParams,
     RaptGenParams,
+    SequenceData,
 )
+from core.jobs import ChildJobTask, initialize_job_raptgen, run_job_raptgen
 from core.schemas import RaptGenTrainingParams
+from sqlalchemy import create_engine
+from sqlalchemy.orm import scoped_session, sessionmaker
 from tasks import celery
 
-
 raptgen_parent_params = {
     "uuid": "8aab26d7-7657-47fa-b624-ed752864ae76",
     "name": "test_raptgen",

docs/about.md

@@ -1,5 +1,9 @@
 # About
 
+## Paper
+
+[RaptGen-UI: an integrated platform for exploring and analyzing the sequence landscape of HT-SELEX experiments](https://doi.org/10.1093/bioadv/vbaf120)
+
 ## Developers
 
 Design and engineering: [Ryota Nakano](https://github.com/unkosan) and [Natsuki Iwano](https://github.com/Xilorole)

docs/index.md

@@ -2,7 +2,7 @@
 
 ## Welcome to RaptGen-UI
 
-RaptGen-UI is a web-based user-friendly interface for RaptGen, a powerful Latent Space Bayesian Optimization (LSBO) method for identifying and optimizing aptamers from high-throughput SELEX data. For more information about RaptGen, please refer to the [RaptGen paper](https://doi.org/10.1038/s43588-022-00249-6).
+RaptGen-UI is a web-based user-friendly interface for RaptGen, a powerful Latent Space Bayesian Optimization (LSBO) method for identifying and optimizing aptamers from high-throughput SELEX data. For more information about RaptGen-UI, please refer to the [paper](https://doi.org/10.1093/bioadv/vbaf120).
 
 ## Overview of Pipeline