slee-ai

Generate paired MSAs directly from locally generated unpaired MSAs (taxonomy-based pairing)

2

I am running large-scale protein–protein interaction (PPI) predictions using Boltz-2. Because of the scale, I am not using the ColabFold server to generate MSAs. Instead, I am running the ColabFold...

MSA pairing algorithm without using the ColabFold server

3

I would like to provide the model with pre computed MSAs for individual protein chains. I want to figure out (1) whether Boltz-2 provides support to pair the precomputed unpaired...

Clarification on GPU thread-group sizing, GPU utilization, and runtime estimation in MMseqs2-GPU

1

I am using MMseqs2-GPU for large-scale MSA generation (millions of queries) and would like to better understand GPU behavior so I can estimate runtime and GPU-hours accurately. 1. CPU --threads...

I’m trying to get MSAs for ~3,500 human proteins (given as UniProt accessions) and I’d like to reuse precomputed MSAs wherever possible and had following questions about using ColabFold server...