p2smi 1.0.0

A package for converting peptide FASTA to SMILES strings and calculating molecular properties.

p2smi: Peptide FASTA-to-SMILES Conversion and Molecular Property Tools

p2smi is a Python package for generating and modifying peptide SMILES strings from FASTA input and computing molecular properties. It supports cyclic and linear peptides, noncanonical amino acids, and common chemical modifications (e.g., N-methylation, PEGylation).

This package was released in its current form to support work on the PeptideCLM model, described in our Publication.

If you use this tool, please cite the PeptideCLM paper. A JOSS publication is forthcoming.

Manuscript

• View PDF
• View markdown source

Directory

• Features
• Installation
• Command-Line Tools
• Example Usage
• Future Work
• Contributing
• License
• Citation

Features

• Convert peptide FASTA files into valid SMILES strings
• Automatically handle peptide cyclizations (disulfide, head-to-tail, side-chain to N-term, side-chain to C-term, side-chain to side-chain)
• Modify peptide SMILES with customizable N-methylation and PEGylation
• Evaluate synthesis feasibility with defined synthesis rules
• Compute molecular properties: logP, TPSA, molecular formula, and Lipinski rule evaluation

Installation

pip install p2smi

For development:

git clone https://github.com/AaronFeller/p2smi.git
cd p2smi
pip install -e .[dev]

Command-Line Tools

Command	Description
generate-peptides	Generate random peptide sequences based on user-defined constraints and modifications
fasta2smi	Convert a FASTA file of peptide sequences into SMILES format
modify-smiles	Apply modifications (N-methylation, PEGylation) to existing SMILES strings
smiles-props	Compute molecular properties (logP, TPSA, formula, Lipinski rules) from SMILES
synthesis-check	Check synthesis constraints for peptides (currently only functional for natural amino acids)

Run each command with --help to view usage and options:

generate-peptides --help
fasta2smi --help
modify-smiles --help
smiles-props --help
synthesis-check --help

Example Usage

Generate a random peptide:

generate-peptides \
    --max_seq_len 20 \
    --min_seq_len 10 \
    --noncanonical_percent 0.1 \
    --lowercase_percent 0.1 \
    --num_sequences 10 \
    --constraints all \
    --outfile outputfile.smi

Convert a FASTA file to SMILES:

fasta2smi -i peptides.fasta -o output.smi

Modify existing SMILES strings (N-methylation/PEGylation):

modify-smiles -i input.smi -o modified.smi --peg_rate 0.3 --nmeth_rate 0.2 --nmeth_residues 0.25

Compute properties of a SMILES string:

smiles-props "C1CC(NC(=O)C2CC2)C1"

Check synthetic feasability

synthesis-check output.smi  # only works for natural amino acids

Future Work

• Expand support for additional post-translational modifications (build importer)
• Enhance synthesis-check with rules for noncanonical amino acid and modified peptides
• Expand usage of mol files (applying RDKit's Chem.MolFromSmiles() function)
• Include alternative encodings (HELM, SELFIES, etc.)
• Enable batch processing/threading for high-throughput analysis
• Incorporate predictive models for synthesis of unnatural amino acids

For Contributors

There are several ways you can contribute to this project:

• Reporting Bugs: If you encounter any issues or unexpected behavior, please let us know by opening an issue.
• Suggesting Enhancements: Have ideas to improve the project? We’d love to hear them! Share your suggestions by opening an issue.
• Submitting Pull Requests: If you’d like to fix a bug or implement a new feature, you can submit a pull request.
• Improving Documentation: Clear and comprehensive documentation helps everyone.

License

MIT License

Citation

If you use this tool, please cite:

• Peptide-Aware Chemical Language Model Successfully Predicts Membrane Diffusion of Cyclic Peptides (JCIM)
  A JOSS paper will follow.