modify environments.yml

remove redundant LICENSE file
remove outdated download_models.py script

Author: hjgwak

environments.yml

@@ -1,169 +1,18 @@
 name: deepcoi
 channels:
-  - pytorch
-  - huggingface
   - conda-forge
   - bioconda
-  - defaults
+  - pytorch
+  - huggingface
 dependencies:
-  - _libgcc_mutex=0.1=main
-  - _openmp_mutex=5.1=1_gnu
-  - abseil-cpp=20211102.0=hd4dd3e8_0
-  - absl-py=1.3.0=py37h06a4308_0
-  - aiohttp=3.8.3=py37h5eee18b_0
-  - aiosignal=1.2.0=pyhd3eb1b0_0
-  - arrow-cpp=8.0.0=py37h60b952e_1
-  - async-timeout=4.0.2=py37h06a4308_0
-  - asynctest=0.13.0=py_0
-  - attrs=22.1.0=py37h06a4308_0
-  - aws-c-common=0.4.57=he6710b0_1
-  - aws-c-event-stream=0.1.6=h2531618_5
-  - aws-checksums=0.1.9=he6710b0_0
-  - aws-sdk-cpp=1.8.185=hce553d0_0
-  - beautifulsoup4=4.12.3=pyha770c72_0
-  - biopython=1.79=py37h5e8e339_1
-  - blas=1.0=mkl
-  - blinker=1.4=py37h06a4308_0
-  - boost-cpp=1.73.0=h7f8727e_12
-  - bottleneck=1.3.5=py37h7deecbd_0
-  - brotlipy=0.7.0=py37h27cfd23_1003
-  - bzip2=1.0.8=h7b6447c_0
-  - c-ares=1.18.1=h7f8727e_0
-  - ca-certificates=2025.4.26=hbd8a1cb_0
-  - cachetools=4.2.2=pyhd3eb1b0_0
-  - certifi=2024.2.2=pyhd8ed1ab_0
-  - cffi=1.15.1=py37h5eee18b_3
-  - charset-normalizer=2.0.4=pyhd3eb1b0_0
-  - click=8.0.4=py37h06a4308_0
-  - cryptography=38.0.4=py37h9ce1e76_0
-  - cudatoolkit=11.3.1=h2bc3f7f_2
-  - curl=7.87.0=h5eee18b_0
-  - dataclasses=0.8=pyh6d0b6a4_7
-  - datasets=2.9.0=py_0
-  - dill=0.3.6=py37h06a4308_0
-  - expat=2.4.9=h6a678d5_0
-  - fftw=3.3.9=h27cfd23_1
-  - filelock=3.9.0=py37h06a4308_0
-  - flit-core=3.6.0=pyhd3eb1b0_0
-  - frozenlist=1.3.3=py37h5eee18b_0
-  - fsspec=2022.11.0=py37h06a4308_0
-  - gdbm=1.18=hd4cb3f1_4
-  - gdown=4.5.4=pyhd8ed1ab_0
-  - gettext=0.21.0=hf68c758_0
-  - gflags=2.2.2=he6710b0_0
-  - git=2.34.1=pl5262hc120c5b_0
-  - glog=0.5.0=h2531618_0
-  - google-auth=2.6.0=pyhd3eb1b0_0
-  - google-auth-oauthlib=0.4.4=pyhd3eb1b0_0
-  - grpc-cpp=1.46.1=h33aed49_1
-  - grpcio=1.42.0=py37hce63b2e_0
-  - huggingface_hub=0.10.1=py37h06a4308_0
-  - icu=58.2=he6710b0_3
-  - idna=3.4=py37h06a4308_0
-  - importlib-metadata=4.11.3=py37h06a4308_0
-  - importlib_metadata=4.11.3=hd3eb1b0_0
-  - intel-openmp=2021.4.0=h06a4308_3561
-  - joblib=1.1.1=py37h06a4308_0
-  - krb5=1.19.4=h568e23c_0
-  - ld_impl_linux-64=2.38=h1181459_1
-  - libboost=1.73.0=h28710b8_12
-  - libbrotlicommon=1.0.9=h5eee18b_7
-  - libbrotlidec=1.0.9=h5eee18b_7
-  - libbrotlienc=1.0.9=h5eee18b_7
-  - libcurl=7.87.0=h91b91d3_0
-  - libedit=3.1.20221030=h5eee18b_0
-  - libev=4.33=h7f8727e_1
-  - libevent=2.1.12=h8f2d780_0
-  - libffi=3.4.2=h6a678d5_6
-  - libgcc-ng=11.2.0=h1234567_1
-  - libgfortran-ng=11.2.0=h00389a5_1
-  - libgfortran5=11.2.0=h1234567_1
-  - libgomp=11.2.0=h1234567_1
-  - libnghttp2=1.46.0=hce63b2e_0
-  - libprotobuf=3.20.3=he621ea3_0
-  - libssh2=1.10.0=h8f2d780_0
-  - libstdcxx-ng=11.2.0=h1234567_1
-  - libthrift=0.15.0=hcc01f38_0
-  - libxml2=2.9.14=h74e7548_0
-  - lz4-c=1.9.4=h6a678d5_0
-  - markdown=3.4.1=py37h06a4308_0
-  - markupsafe=2.1.1=py37h7f8727e_0
-  - mkl=2021.4.0=h06a4308_640
-  - mkl-service=2.4.0=py37h7f8727e_0
-  - mkl_fft=1.3.1=py37hd3c417c_0
-  - mkl_random=1.2.2=py37h51133e4_0
-  - multidict=6.0.2=py37h5eee18b_0
-  - multiprocess=0.70.14=py37h06a4308_0
-  - ncurses=6.4=h6a678d5_0
-  - numexpr=2.8.4=py37he184ba9_0
-  - numpy=1.21.5=py37h6c91a56_3
-  - numpy-base=1.21.5=py37ha15fc14_3
-  - oauthlib=3.2.1=py37h06a4308_0
-  - openssl=1.1.1w=h7f8727e_0
-  - orc=1.7.4=hb3bc3d3_1
-  - packaging=22.0=py37h06a4308_0
-  - pandas=1.3.5=py37h8c16a72_0
-  - pcre2=10.37=he7ceb23_1
-  - perl=5.34.0=h5eee18b_2
-  - protobuf=3.20.3=py37h6a678d5_0
-  - pyarrow=8.0.0=py37h992f0b0_0
-  - pyasn1=0.4.8=pyhd3eb1b0_0
-  - pyasn1-modules=0.2.8=py_0
-  - pycparser=2.21=pyhd3eb1b0_0
-  - pydeprecate=0.3.2=pyhd8ed1ab_0
-  - pyjwt=2.4.0=py37h06a4308_0
-  - pyopenssl=22.0.0=pyhd3eb1b0_0
-  - pysocks=1.7.1=py37_1
-  - python=3.7.16=h7a1cb2a_0
-  - python-dateutil=2.8.2=pyhd3eb1b0_0
-  - python-xxhash=2.0.2=py37h5eee18b_1
-  - python_abi=3.7=2_cp37m
-  - pytorch=1.12.0=py3.7_cuda11.3_cudnn8.3.2_0
-  - pytorch-lightning=1.7.7=pyhd8ed1ab_0
-  - pytorch-mutex=1.0=cuda
-  - pytz=2022.7=py37h06a4308_0
-  - pyyaml=6.0=py37h5eee18b_1
-  - re2=2022.04.01=h295c915_0
-  - readline=8.2=h5eee18b_0
-  - regex=2022.7.9=py37h5eee18b_0
-  - requests=2.28.1=py37h06a4308_0
-  - requests-oauthlib=1.3.0=py_0
-  - rsa=4.7.2=pyhd3eb1b0_1
-  - sacremoses=0.0.43=pyhd3eb1b0_0
-  - scikit-learn=1.0.2=py37h51133e4_1
-  - scipy=1.7.3=py37h6c91a56_2
-  - setuptools=65.6.3=py37h06a4308_0
-  - six=1.16.0=pyhd3eb1b0_1
-  - snappy=1.1.9=h295c915_0
-  - soupsieve=2.0.1=py37hc8dfbb8_0
-  - sqlite=3.40.1=h5082296_0
-  - tensorboard=2.10.0=py37h06a4308_0
-  - tensorboard-data-server=0.6.1=py37h52d8a92_0
-  - tensorboard-plugin-wit=1.8.1=py37h06a4308_0
-  - threadpoolctl=2.2.0=pyh0d69192_0
-  - tk=8.6.12=h1ccaba5_0
-  - torchmetrics=0.11.1=pyhd8ed1ab_0
-  - tqdm=4.64.1=py37h06a4308_0
-  - transformers=4.26.1=py_0
-  - typing-extensions=4.4.0=py37h06a4308_0
-  - typing_extensions=4.4.0=py37h06a4308_0
-  - urllib3=1.26.14=py37h06a4308_0
-  - utf8proc=2.6.1=h27cfd23_0
-  - werkzeug=2.2.2=py37h06a4308_0
-  - wheel=0.38.4=py37h06a4308_0
-  - xxhash=0.8.0=h7f8727e_3
-  - xz=5.2.10=h5eee18b_1
-  - yaml=0.2.5=h7b6447c_0
-  - yarl=1.8.1=py37h5eee18b_0
-  - zipp=3.11.0=py37h06a4308_0
-  - zlib=1.2.13=h5eee18b_0
-  - zstd=1.5.2=ha4553b6_0
-  - pip:
-      - fair-esm==2.0.0
-      - markdown-it-py==2.1.0
-      - mdurl==0.1.2
-      - pip==23.0.1
-      - pygments==2.14.0
-      - rich==13.3.1
-      - tokenizers==0.13.2
-      - torchinfo==1.7.2
+  - python=3.8
+  - cudatoolkit=11.3
+  - pytorch=1.12
+  - transformers
+  - datasets
+  - pytorch-lightning
+  - scikit-learn
+  - scipy
+  - biopython
+  - torchinfo
+  - fair-esm==2.0.0

models/README.md

@@ -3,29 +3,8 @@
 This is a directory to save models. You can check that models have been downloaded properly using the give MD5 checksum list.  
 The pre-trained/fine-tuned models could be downloaded through the links as follow:  
 
-**Pre-trained model**
+The pre-trained and fine-tuned models have been uploaded on **Zenodo** since the size of some models is larger than 100MB. PLEASE make sure to download models after cloning this repository.
 
-* [DeepCOI-t6-320](https://drive.google.com/file/d/1nIlli1OLAQUdsO-faK__ou-bmwQZYk8s/view?usp=sharing)
-* [DeepCOI-t12-480](https://drive.google.com/file/d/1yIInuQHOY-eK5mJPsmcnB-h5uDmaulPt/view?usp=sharing)
+Please download the model you need through the link below and save them in the `models` directory.  
 
-**Phylum-level classifier**
-
-* [DeepCOI-phylum](https://drive.google.com/file/d/1OniD3g_mWNeQSsov42cjGMQJS3iGFgYg/view?usp=sharing)
-
-**Class-to-species classifiers**
-
-* [DeepCOI-Annelida](https://drive.google.com/file/d/1wQs2Z9KyL-o7UmcxA51knmES_8WCRXA1/view?usp=sharing)
-* [DeepCOI-Arthropoda](https://drive.google.com/file/d/1v3d790mOrguKumEYOAg4_4TjmBubnbzb/view?usp=sharing)
-* [DeepCOI-Chordata](https://drive.google.com/file/d/1REk2R4cmIZnMsqtykyU0Ej2ws57kpFvz/view?usp=sharing)
-* [DeepCOI-Cnidaria](https://drive.google.com/file/d/1lh_oi99UIqCg6JSMSQw-ED0qTlZvZE5z/view?usp=sharing)
-* [DeepCOI-Echinodermata](https://drive.google.com/file/d/1Rub95cNkoTSx2KfvwpA7btcpVXQ3gnMN/view?usp=sharing)
-* [DeepCOI-Mollusca](https://drive.google.com/file/d/1J37pfJSXrhmP0p1I1s52WvWJRWuyGxVj/view?usp=sharing)
-* [DeepCOI-Nematoda](https://drive.google.com/file/d/1fnNu6wZHaQ78O2PiTQI17KzVOtiBppig/view?usp=sharing)
-* [DeepCOI-Platyhelminthes](https://drive.google.com/file/d/1DKwJidN7NeOOaCunoiScj25KFtZ1tCSh/view?usp=sharing)
-
-or using `download_models.py` script in this directory.
-
-```
-conda install gdown [optional]
-python ./download_models.py -d all -o ./
-```
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.16660862.svg)](https://doi.org/10.5281/zenodo.16660862)