# salesforce/progen architecture

> Architecture diagram of the GitHub repository salesforce/progen, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-06-11). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/salesforce/progen
- Repository: https://github.com/salesforce/progen

## Overview

##### Project type and purpose
- ProGen is an open-source Python toolkit for protein engineering that provides:
- Pretrained language models under `progen2/models/progen`
- Tokenization via `progen2/tokenizer.json`
- Two “use-case” scripts: `sample.py` (sequence generation) and `likelihood.py` (fitness or log-likelihood scoring)
- It is not a web app or microservices architecture but rather a stand-alone library/tool intended to be embedded in research or automation pipelines.

##### File structure
Top-level:
- Configuration and policy files (`LICENSE.txt`, `CODE_OF_CONDUCT.md`, `SECURITY.md`, etc.)
- A root `README.md` describing the overall project
`progen2/` directory:
- `requirements.txt` – lists Python dependencies (e.g., PyTorch, HuggingFace Transformers)
- `tokenizer.json` – Byte-pair encoding or tokenizer vocabulary for protein sequences
- `models/progen/` – two core modules:
– `configuration_progen.py` (model hyperparameters, architecture definitions)
– `modeling_progen.py` (PyTorch model classes, forward pass, generation/ scoring API)
- `sample.py` – CLI or script entrypoint for sequence sampling
- `likelihood.py` – CLI or script entrypoint for scoring sequences

##### README for additional insights
- Implied workflow: load a model → tokenize input or generate new sequences → score or output them.

##### Elements
[sample.py] [likelihood.py] → [Tokenizer] → [Model Config] → [Model Class] → [Output]
(PyTorch), (HuggingFace Transformers)
e.g., “sequence string” → Tokenizer → “token IDs” → Model → “scores/sequences”
- Blue for user-facing scripts
- Green for core library modules
- Orange for external dependencies

## Diagram (Mermaid)

```mermaid
graph TB
    subgraph "Client / User Script Layer"
        Sample["sample.py"]:::scripts
        Likelihood["likelihood.py"]:::scripts
    end

    subgraph "Core Library Modules"
        Tokenizer["Tokenizer\nloads tokenizer.json"]:::core
        ModelConfig["configuration_progen.py\nModel Config"]:::core
        ModelClass["modeling_progen.py\nCore Model\n(generate/score)"]:::core
        Output["Sequences / Scores"]:::core
    end

    subgraph "External Dependencies"
        PyTorch["PyTorch"]:::external
        HF["HuggingFace Transformers"]:::external
        Requirements["requirements.txt"]:::external
    end

    Docs["README.md"]:::docs

    %% Data flow
    Sample -->|"sequence string"| Tokenizer
    Likelihood -->|"sequence input"| Tokenizer
    Tokenizer -->|"token IDs"| ModelClass
    ModelClass -->|"uses hyperparameters"| ModelConfig
    ModelClass -->|"outputs sequences/scores"| Output

    %% Dependencies
    Tokenizer -->|uses| HF
    ModelClass -->|runs on| PyTorch
    ModelClass -->|uses| HF
    Requirements -->|specifies| PyTorch
    Requirements -->|specifies| HF

    %% Documentation link
    Sample -->|see docs| Docs

    %% Click events
    click Sample "https://github.com/salesforce/progen/blob/main/progen2/sample.py"
    click Likelihood "https://github.com/salesforce/progen/blob/main/progen2/likelihood.py"
    click Tokenizer "https://github.com/salesforce/progen/blob/main/progen2/tokenizer.json"
    click ModelConfig "https://github.com/salesforce/progen/blob/main/progen2/models/progen/configuration_progen.py"
    click ModelClass "https://github.com/salesforce/progen/blob/main/progen2/models/progen/modeling_progen.py"
    click Requirements "https://github.com/salesforce/progen/blob/main/progen2/requirements.txt"
    click Docs "https://github.com/salesforce/progen/blob/main/README.md"

    %% Styles
    classDef scripts fill:#ddeeff,stroke:#333,stroke-width:1px
    classDef core fill:#ccffcc,stroke:#333,stroke-width:1px
    classDef external fill:#ffdd99,stroke:#333,stroke-width:1px
    classDef docs fill:#eeeeee,stroke:#333,stroke-width:1px
```
