MSA Generator

Sample mutations from MSA position-specific distributions

This generator is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.

---

Source

proto-bio/proto-language/proto_language/generator/msa_generator.py

View source

Generator that samples mutations from MSA position-specific distributions.

This generator computes empirical probability distributions for each position in a multiple sequence alignment, then mutates proposal sequences by sampling from these distributions.

API Reference

ConfigMSAGeneratorConfig Source

Configuration object for MSAGenerator.

This class defines configuration parameters for the MSA generator, which samples mutations from position-specific probability distributions derived from a multiple sequence alignment.

msa · MSA · required

Multiple sequence alignment (list of aligned sequences).

num_mutations · integer · default: "1"

Number of positions to mutate per sample

include_gaps · boolean · default: "False"

Whether to include gaps when calculating position probabilities

Usage

python

>>> from proto_language.generator import MSAGenerator, MSAGeneratorConfig
>>> from proto_language.core import Segment
>>> from proto_tools.entities.msa import MSA
>>> config = MSAGeneratorConfig(
...     msa=MSA(aligned_sequences=["MVLS", "AVLS", "MVLS"]),
...     num_mutations=1,
... )
>>> gen = MSAGenerator(config)
>>> segment = Segment(sequence="MVLS", sequence_type="protein")
>>> gen.assign(segment)
>>> gen.sample()  # Position 0 has 2/3 chance of M, 1/3 chance of A

Metadata

Property	Value
Key	msa
Class	MSAGenerator
Category	mutation
Input Type	starting_sequence
Uses GPU	False
Supported Sequence Types	All
Allows Empty Start	False