The algorithm to use for MSA. AlphaFold2 was trained on JackHMMer; MMSeqs2 provides faster inference.

Databases used for Multiple Sequence Alignment. By default, uniref90, mgnify, and small_bfd are used.Choice of databases(s) can significantly impact downstream structure prediction, so we recommend modifying carefully.

The e-value used for filtering hits when building the Multiple Sequence Alignment.

The number of MSA iterations to perform.

Run structural relaxation after prediction

The AlphaFold2 structural prediction model to use for inference.

Which structural prediction to relax with AMBER. Default: relax all models

Determines the number of times the trunk of the network is run with different random MSA cluster centers.

Allows selecting the parameters used for protein structure prediction.

The maximum sequences taken from the MSA for model prediction.

Do NOT template search using HHSearch or HMMSearch. [False]

Removes the default limits for maximum MSA sequences cutoff for the Uniref90 (10,000 sequences) and Mgnify databases (501 sequences).

The template searcher to use for templating. hmmsearch should be used for multimer; most other queries should rely on hhsearch.