Jennifer Wei

Hi @amardeepranu , thanks for your interest in Soloseq. Could you try generating the embeddings first using: `python scripts/precompute_embeddings.py fasta_dir/ embeddings_output_dir/` And then using the same `run_pretrained_openfold.py` command, but with...

There are a separate set of weights used for soloseq, which were defined in your earlier command by this argument: `--openfold_checkpoint_path openfold/openfold/resources/openfold_soloseq_params/seq_model_esm1b_ptm.pt` Judging by the `bash: line 6: --output_dir: command...

You will need to provide a directory for the `--template_mmcif_dir`. Despite the required flag, templates are not necessary for folding predictions. If your precomputed alignments directory does not contain any...

Hi thanks for your interest! We're not going to have bandwidth to support apple silicon any time soon unfortunately. Help would be very appreciated on this front. We do have...

Hi, thanks for your interest in OpenFold. It's hard to be certain without seeing your full environment, but based on the error message by OP, it looks like an older...

Hi @rostro36 , thank you very much for this contribution. This is a really nice option to have for running with templates, and we would like to work with you...

Hi @rostro36 thanks for the fixes. I finally had a chance to take a closer look at this PR and do some more testing. I had a couple more thoughts/requests:...

Leaving my notes here regarding the sequence alignments in case they are helpful later. - A good test would be to compare structure prediction for a query using the default...

Hi all, Thanks for all the interest and for sharing notes! The environments I wanted to support at this time were: - For use with CUDA 11.x: (main branch) pytorch...

Hi thanks for the interest. We're actively working on finalizing the changes in `pl_upgrades` into `main`. I'd expect ~3ish weeks