ColabFold
ColabFold copied to clipboard
sokrypton
Making Protein folding accessible to all!
We are running the following protein sequence with AlphaFold2-ptm, using the AlphaFold2_mmseqs2 notebook. It is approximately 629 AA long. I have a Colab Pro account, so RAM should not be...
## Expected Behavior Colabfold returns a structure ## Current Behavior `TypeError: 'NoneType' object is not subscriptable` ## Steps to Reproduce (for bugs) Seq: ENQALEQKNAQLKQEIAALEQEIAQLEY:KNAQLKEENAALEEKIQQLKEKIQALKY:ENQALEQEIAQLEQEIAALEQKNAQLKY:KNAQLKEKIAALKEKIQQLKEENQALEY Name: P9P10P11P12_unpaired MSA_Mode: single pair_mode: unpaired...
Hi Everyone. Whenever I try to save embeddings for my protein sequence I get an error suggesting nothing is returned from running the model. Running the multimer model on a...
## Expected Behavior I have successfully mounted my google drive and the batch ColaFold states using the Alphafold2 batch notebook at https://colab.research.google.com/github/sokrypton/ColabFold/blob/main/batch/AlphaFold2_batch.ipynb #@title Mount google drive from google.colab import drive...
Hi, While running ColabFold locally, I get warnings like the following every time the model is (re)compiled, which is slow. ``` 2022-02-15 16:22:05.982180: E external/org_tensorflow/tensorflow/compiler/xla/service/slow_operation_alarm.cc:55] ******************************** Very slow compile? If...
Hi! I am currently exploring the behaviour of ColabFold with different custom MSAs and was hoping to explore which sequences are ending up in the MMSeqs MSAs a little more...
Is there a way to get MSA for multimers (homo/hetro) with the local MMSEQ similar to what the API outputs? I am running the version compiled from git, downloaded about...
WARNING: found GPU Tesla K80: limited to total length < 1000 Downloading alphafold2 weights to .: 100%|██████████| 3.47G/3.47G [00:39 52 prediction_callback=prediction_callback, 53 ) 10 frames [/usr/local/lib/python3.7/dist-packages/jax/interpreters/xla.py](https://localhost:8080/#) in _execute_compiled(name, compiled, output_buffer_counts,...
## Expected Behavior In the Run Prediction step, model 1 is created without issue within approximately 450 seconds. I would expect models 2 and 3 to also be accomplished within...
## Expected Behavior If a long-running job times out before finishing all five models, it should still be possible to download those models (and associated metadata) that it did produce....
