where is .cif

[yuzimu1]

I want to run the example FASTA sequence in the examples directory, using the precomputed MSA provided there and the template_free model. However, it seems that OpenFold doesn't provide the corresponding .cif files, and I have to manually create empty .cif files one by one in order to proceed.

Does anyone else have the same issue?

this is the order i used
`#!/bin/bash
export LD_LIBRARY_PATH=$CONDA_PREFIX/lib:$LD_LIBRARY_PATH
export LIBRARY_PATH=$CONDA_PREFIX/lib:$LIBRARY_PATH

export FASTA_DIR=/home/rotation14/export/openfold/examples/monomer/fasta_dir
export OUTPUT_DIR=/home/rotation14/export/openfold/examples/monomer/output_dir
export PRECOMPUTED_ALIGNMENT_DIR=/home/rotation14/export/openfold/examples/monomer/alignments
export MMCIF_DIR=/home/rotation14/export/openfold/examples/template_free_empty4 # UPDATE with path to your mmcifs directory

python3 run_pretrained_openfold.py
$FASTA_DIR
$MMCIF_DIR
--output_dir $OUTPUT_DIR
--use_precomputed_alignments $PRECOMPUTED_ALIGNMENT_DIR
--config_preset model_3_ptm
--openfold_checkpoint_path /home/rotation14/export/openfold/openfold/resources/params/finetuning_no_templ_ptm_1.pt
--model_device "cuda:0" `

and it says
(openfold_env) rotation14@GPU-210:~/export/openfold$ bash inference.sh [2025-08-03 12:25:11,290] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect) [WARNING] async_io requires the dev libaio .so object and headers but these were not found. [WARNING] async_io: please install the libaio-dev package with apt [WARNING] If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found. /export/disk2/rotation14/conda_envs/210/envs/openfold_env/lib/python3.10/site-packages/deepspeed/runtime/zero/linear.py:49: FutureWarning: torch.cuda.amp.custom_fwd(args...)is deprecated. Please usetorch.amp.custom_fwd(args..., device_type='cuda')instead. def forward(ctx, input, weight, bias=None): /export/disk2/rotation14/conda_envs/210/envs/openfold_env/lib/python3.10/site-packages/deepspeed/runtime/zero/linear.py:67: FutureWarning:torch.cuda.amp.custom_bwd(args...)is deprecated. Please usetorch.amp.custom_bwd(args..., device_type='cuda')instead. def backward(ctx, grad_output): /export/disk2/rotation14/openfold/openfold/utils/script_utils.py:97: FutureWarning: You are usingtorch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. d = torch.load(ckpt_path) INFO:/export/disk2/rotation14/openfold/openfold/utils/script_utils.py:Loaded OpenFold parameters at /home/rotation14/export/openfold/openfold/resources/params/finetuning_no_templ_ptm_1.pt... INFO:/export/disk2/rotation14/openfold/run_pretrained_openfold.py:Using precomputed alignments for 6KWC_1 at /home/rotation14/export/openfold/examples/monomer/alignments... Traceback (most recent call last): File "/export/disk2/rotation14/openfold/run_pretrained_openfold.py", line 499, in <module> main(args) File "/export/disk2/rotation14/openfold/run_pretrained_openfold.py", line 299, in main feature_dict = generate_feature_dict( File "/export/disk2/rotation14/openfold/run_pretrained_openfold.py", line 151, in generate_feature_dict feature_dict = data_processor.process_fasta( File "/export/disk2/rotation14/openfold/openfold/data/data_pipeline.py", line 889, in process_fasta template_features = make_template_features( File "/export/disk2/rotation14/openfold/openfold/data/data_pipeline.py", line 57, in make_template_features templates_result = template_featurizer.get_templates( File "/export/disk2/rotation14/openfold/openfold/data/templates.py", line 1158, in get_templates result = _process_single_hit( File "/export/disk2/rotation14/openfold/openfold/data/templates.py", line 866, in _process_single_hit cif_string = _read_file(cif_path) File "/export/disk2/rotation14/openfold/openfold/data/templates.py", line 820, in _read_file with open(path, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: '/home/rotation14/export/openfold/examples/template_free_empty4/1f5j.cif'

[IngridPuppet]

Getting started with the project, I also ran into this issue. In the meantime it is properly addressed, one may find the following command useful for constituting the mmcifs folder enabling to run the example provided:

mkdir -p examples/monomer/mmcifs
wget -P examples/monomer/mmcifs https://files.rcsb.org/download/{2dfb,3akq,1te1,1h1a,5hxv,1xnk,1pvx,3wp3,1yna,3mf9,3mf6,2vgd,2vuj,1f5j,1h4g,1qh7,2f6b,4ixl,5ej3,2dcz,5vqj,5tvy,1t6g,1xyn,2qz2,6qe8,6kka,3m4f,2dcj,2dck,2vg9,2c1f,1axk,3wp5,3wp4,3wp6,5gyc,5gyf,5gv1,3lb9,1h8v,1oa4,1oa3,1ks5,1ks4,5gm5,1olr,1uu5,1oa2,5m2d,2nlr,2jen,5gm4,5gm3,2bw8,4g6t,3vlb,3b7m,1h0b}.cif

Besides, this ticket appears to be a duplicate of:

• $TEMPLATE_MMCIF_DIR #545
• missing .cif files. #546