PaddlePaddle / PaddleHelix

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集
Other
1.02k stars 225 forks source link

ssDNA won't work #339

Closed jkosinski closed 2 months ago

jkosinski commented 2 months ago

This input:

{
    "entities": [
        {
            "type": "dna",
            "ccd": "TGTCTTTCC",
            "count": 1
        }
    ]
}

gives

Traceback (most recent call last):
  File "/g/kosinski/kosinski/software/PaddleHelix/apps/protein_folding/helixfold3/inference.py", line 637, in <module>
    main(args)
  File "/g/kosinski/kosinski/software/PaddleHelix/apps/protein_folding/helixfold3/inference.py", line 442, in main
    all_entitys = preprocess_json_entity(args.input_json, args.output_dir)
  File "/g/kosinski/kosinski/software/PaddleHelix/apps/protein_folding/helixfold3/inference.py", line 87, in preprocess_json_entity
    all_entitys = preprocess.online_json_to_entity(json_path, out_dir)
  File "/g/kosinski/kosinski/software/PaddleHelix/apps/protein_folding/helixfold3/infer_scripts/preprocess.py", line 290, in online_json_to_entity
    raise RuntimeError(f'[Error] Failed to convert {len(error_ids)}/{len(entities)} entities')
RuntimeError: [Error] Failed to convert 1/1 entities
leaves520 commented 2 months ago

Hi, @jkosinski , for the polymer(include DNA, RNA, Protein) input, we only support sequence rather than ccd. Best practices are as follows:

{
    "entities": [
        {
            "type": "dna",
            "sequence": "TGTCTTTCC",
            "count": 1
        }
    ]
}
jkosinski commented 2 months ago

Ah I made a typo from copy and paste 🫢 thanks!