Open James-lin9 opened 4 days ago
Hello, thank you for reporting. Do you have any pTMs in your sequence? If so, this is a duplicate of https://github.com/google-deepmind/alphafold3/issues/54 and we are working on a fix.
Hello, thank you for reporting. Do you have any pTMs in your sequence? If so, this is a duplicate of #54 and we are working on a fix.
No. The modification is empty in the input json. I found that somehow U is mutated to X in the run_inference step while the data_pipeline output looks fine. It seems a bug in the run inference step even without modifications. In addition, I found 2 more proteins: O60613 and P07203 got the same error. Not sure if the error can be reproduced or not.
Hi, I ran default MSA search by jackhammer for P26341 (uniprot ID) and then when I did the inference, I got an error: 'First MSA sequence is not the {query_sequence=}'. How do I fix this? Shall I rerun the jackhammer? I check the run_alphafold.py this could be caused by mutation from jackhammer? "# Check if the 1st MSA sequence matches the query sequence. Since it may be mutated by the search tool (jackhmmer) check using the featurized version."