Nim Api Post Call Protein Structure Alphafold2 Predict Structure From Sequence Post

Body Params

sequences

array of strings

required

length between 1 and 6

An input polypeptide (i.e., amino acid) sequence that must be composed of valid Amino Acid IUPAC symbols.

Input Polypeptide Sequence*

algorithm

string

enum

Defaults to jackhmmer

The algorithm to use for MSA. AlphaFold2 was trained on JackHMMer; MMSeqs2 provides faster inference. (MMSeqs2 will be supported in a future version of AlphaFold2 NIM!)

Allowed:

bit_score

Sequence Bit Score cutoff for filtering sequences used in seeding the Multiple Sequence Alignment. Bit score must be > 0 or NULL. Note: If this value is unset, e-value is ignored.

databases

array of strings

length between 1 and 3

Defaults to uniref90,mgnfiy,small_bfd

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.

MSA Databases

e_value

number

≤ 10

Defaults to 0.0001

The e-value used for filtering hits when building the Multiple Sequence Alignment. Takes values between 0 < x <= 10.

iterations

integer

≥ 1

Defaults to 1

The number of MSA iterations to perform.

relax_prediction

boolean

Defaults to true

Run structural relaxation after prediction

structure_models_to_relax

string

enum

Defaults to all

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

Allowed:

num_predictions_per_model

integer

1 to 8

Defaults to 1

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

max_msa_sequences

1 to 100000

The maximum sequences taken from the MSA for model prediction.

template_searcher

string

enum

Defaults to hhsearch

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

Allowed:

200Successful Response

422Validation Error