> ## Documentation Index > Fetch the complete documentation index at: https://proto.evodesign.org/docs/llms.txt > Use this file to discover all available pages before exploring further. # Random Protein Mutation > Random amino acid mutations using codon scheme-biased sampling

**License:** Random Protein Sampling is open source and free for academic and commercial use under an MIT license. Please refer to [the license](https://github.com/evo-design/proto-tools) for full terms.

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.

Tools Used Tools Used Source Source

Go to Tool Page

evo-design/proto-language/proto\_language/generator/random\_protein\_generator.py

View source

Generator contributors

Protein sequence generator that introduces random amino acid mutations. This generator creates sequence diversity by randomly mutating masked positions in protein sequences. Amino acid selection is biased by the configured codon scheme, allowing simulation of library diversity achievable through degenerate codon synthesis. Optional amino-acid exclusions remove unwanted residues from the sampled mutation alphabet. The generator category is `"mutation"`. When the assigned segment has a starting sequence (or an upstream optimizer stage has populated proposals), `masking_strategy` controls which positions are mutated on each call. When the segment has no starting sequence, the first `sample()` call fills each proposal with a fully random sequence of the segment's length using the configured `codon_scheme`; subsequent calls then apply `masking_strategy` normally. ## API Reference

ConfigRandomProteinGeneratorConfig Source

Configuration object for RandomProteinGenerator. This class defines configuration parameters for the random protein generator, which introduces random amino acid mutations at masked positions using codon scheme-biased sampling. Controls which positions to mask for sampling. Default: random 30%. Codon scheme for amino acid sampling probabilities. Options: `UNIFORM`, `NNN`, `NNK`, `NNS`, `NDT`, `DBK`, `NRT` Residues to remove after codon-scheme handling (e.g. \['C'] to forbid cysteine).

## Usage ```python python icon="python" theme={null} >>> from proto_language.generator import RandomProteinGenerator, RandomProteinGeneratorConfig >>> from proto_language.core import Segment >>> from proto_tools.transforms.masking import MaskingStrategy >>> config = RandomProteinGeneratorConfig( ... masking_strategy=MaskingStrategy(num_mutations=2), ... excluded_amino_acids=["C"], ... ) >>> gen = RandomProteinGenerator(config) >>> segment = Segment(length=100, sequence_type="protein") >>> gen.assign(segment) >>> gen.sample() # First call: random init (no starting sequence) >>> gen.sample() # Second call onward: 2 non-cysteine mutations ``` ## Metadata | Property | Value | | ------------------------ | ------------------------ | | Key | `random-protein` | | Class | `RandomProteinGenerator` | | Category | `mutation` | | Input Type | `starting_sequence` | | Uses GPU | `False` | | Supported Sequence Types | `protein` | | Allows Empty Start | `True` |