It seems the environment file is broken when following the code at the top of the environment.yml file:

$ conda create --name fold2seq --file environment.yml
Collecting package metadata (current_repodata.json): done
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed

PackagesNotFoundError: The following packages are not available from current channels:

  - rdflib==5.0.0=pypi_0
  - decorator==4.4.2=pypi_0
  - pandas==1.2.3=pypi_0
  - libidn2==2.3.0=h516909a_0
  - mmseqs2==13.45111=h95f258a_1
  - jinja2==2.11.3=pypi_0
  - libgcc-ng==9.3.0=h2828fa1_18
  - pytorch==1.7.1=py3.8_cuda10.2.89_cudnn7.6.5_0
  - torchaudio==0.7.2=py38
  - llvmlite==0.35.0=pypi_0
  - torch-sparse==0.6.9=pypi_0
  - idna==2.10=pypi_0
  - esm==0.2.0=pypi_0
  - tokenizers==0.8.0rc4=pypi_0
  - scipy==1.5.4=pypi_0
  - networkx==2.5=pypi_0
  - sacremoses==0.0.43=pypi_0
  - markupsafe==1.1.1=pypi_0
  - packaging==20.9=pypi_0
  - torch-geometric==1.6.3=pypi_0
  - biopython==1.77=pypi_0
  - h5py==3.2.0=pypi_0
  - matplotlib==3.3.1=pypi_0
  - cycler==0.10.0=pypi_0
  - isodate==0.6.0=pypi_0
  - regex==2020.11.13=pypi_0
  - pyparsing==2.4.7=pypi_0
  - torchvision==0.8.2=py38_cu102
  - kiwisolver==1.2.0=pypi_0
  - bzip2==1.0.8=h7f98852_4
  - tqdm==4.58.0=pypi_0
  - pytz==2021.1=pypi_0
  - libstdcxx-ng==9.3.0=h6de172a_18
  - googledrivedownloader==0.4=pypi_0
  - transformers==3.0.0=pypi_0
  - torch-scatter==2.0.6=pypi_0
  - python-dateutil==2.8.1=pypi_0
  - sentencepiece==0.1.95=pypi_0
  - gawk==5.1.0=h7f98852_0
  - requests==2.25.1=pypi_0
  - torch-cluster==1.5.9=pypi_0
  - filelock==3.0.12=pypi_0
  - torch-spline-conv==1.2.1=pypi_0
  - libunistring==0.9.10=h14c3975_0
  - scikit-learn==0.24.0=pypi_0
  - sklearn==0.0=pypi_0
  - numba==0.52.0=pypi_0
  - gettext==0.19.8.1=hf34092f_1004
  - python-louvain==0.15=pypi_0
  - chardet==4.0.0=pypi_0
  - libgomp==9.3.0=h2828fa1_18
  - openssl==1.1.1k=h7f98852_0
  - ase==3.21.1=pypi_0
  - joblib==1.0.0=pypi_0
  - threadpoolctl==2.1.0=pypi_0
  - certifi==2020.6.20=pypi_0
  - ca-certificates==2020.12.5=ha878542_0
  - urllib3==1.26.3=pypi_0
  - _libgcc_mutex==0.1=conda_forge
  - python_abi==3.8=1_cp38
  - click==7.1.2=pypi_0
  - wget==1.20.1=h22169c7_0

Current channels:

  - https://repo.anaconda.com/pkgs/main/linux-64
  - https://repo.anaconda.com/pkgs/main/noarch
  - https://repo.anaconda.com/pkgs/r/linux-64
  - https://repo.anaconda.com/pkgs/r/noarch

To search for alternate channels that may provide the conda package you're
looking for, navigate to

    https://anaconda.org

and use the search bar at the top of the page.

The =pypi_0 looks suspicious and the channel information was not included. So I tried removing the =pypi_0 and adding the channel information:

$ conda create --name fold2seq --file new-environment.yml -c pytorch -c huggingface -c conda-forge
Collecting package metadata (current_repodata.json): done
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed

PackagesNotFoundError: The following packages are not available from current channels:

  - mmseqs2==13.45111=h95f258a_1
  - torch-sparse==0.6.9
  - sklearn==0.0
  - esm==0.2.0
  - torch-geometric==1.6.3
  - scipy==1.5.4
  - torch-cluster==1.5.9
  - torch-spline-conv==1.2.1
  - transformers==3.0.0
  - torch-scatter==2.0.6
  - tokenizers==0.8.0rc4
  - h5py==3.2.0

Current channels:

  - https://conda.anaconda.org/pytorch/linux-64
  - https://conda.anaconda.org/pytorch/noarch
  - https://conda.anaconda.org/anaconda/linux-64
  - https://conda.anaconda.org/anaconda/noarch
  - https://conda.anaconda.org/huggingface/linux-64
  - https://conda.anaconda.org/huggingface/noarch
  - https://conda.anaconda.org/conda-forge/linux-64
  - https://conda.anaconda.org/conda-forge/noarch
  - https://repo.anaconda.com/pkgs/main/linux-64
  - https://repo.anaconda.com/pkgs/main/noarch
  - https://repo.anaconda.com/pkgs/r/linux-64
  - https://repo.anaconda.com/pkgs/r/noarch

Help would be appreciated

I'm getting errors running the preprocessing script:

total number of seqs: 470679
removed # seqs in ss.txt: 9337
Traceback (most recent call last):
  File "fold_feat_gen.py", line 154, in <module>
    x1,x2 = selection(line[0] ,  line[2], int(line[3]), int(line[4]), seq_ss)  
  File "fold_feat_gen.py", line 44, in selection
    start = start.replace(')','')
AttributeError: 'int' object has no attribute 'replace'

start and end are integers when I print them, so doesn't make sense that a string replace is applied to them... Any idea what's going on here?

Hi, I am facing a data source problem. I would like to apply my own data to your amazing model, but I cannot try to make the wrong data structure that fits your model' expected input.

Can I be provided the right data structure or just be shown the file "../data/domain_dict_full.pkl" to figure this problem out?

By the way, there is a bug on the file fold_feat_gen.py lines 42 and 48: variables 'start' and 'end' should be strings so as to fit function 'replace'. Similarly, the same file lines 83, 87, 89, and 91: information extraction of nested dictionary cannot be simply implemented by indexing as ss['seq'].

Looking forward to your precious reply. Many thanks!!

Hi, I am facing a data source problem. I would like to apply my own data to your amazing model, but I cannot try to make the wrong data structure that fits your model' expected input.

Can I be provided the right data structure or just be shown the file "../data/domain_dict_full.pkl" to figure this problem out?

By the way, there is a bug on the file fold_feat_gen.py lines 42 and 48: variables 'start' and 'end' should be strings so as to fit function 'replace'. Similarly, the same file lines 83, 87, 89, and 91: information extraction of nested dictionary cannot be simply implemented by indexing as ss['seq'].

Looking forward to your precious reply. Many thanks!!

I can get a domain_seq.pkl containing coords and seq info from the code, but the dataset requires emb, padding and foldclass which the code can't generate. So how can I generate them , write my own code or is there some details that I miss ?