# sacdallago/biotrainer architecture

> Architecture diagram of the GitHub repository sacdallago/biotrainer, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-01-11). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sacdallago/biotrainer
- Repository: https://github.com/sacdallago/biotrainer

## Overview

##### Main Components

a. Core Components:
- Input Processing Layer
- Embedding Layer
- Model Layer
- Training Layer
- Inference Layer
- Configuration Management
- Protocol Handler

b. Supporting Components:
- Data Validation
- Utilities
- CLI Interface
- Docker Support

##### Component Relationships and Architecture

**[Input Layer]**
- ↓
**[Embedding Layer]**
- ↓
**[Model Layer]**
- ↓
**[Training/Inference Layer]**

##### Detailed Component Breakdown

a. Input Layer:
- FASTA file processing
- Data validation
- To configuration management system

b. Embedding Layer:
- Multiple embedder options (Hugging Face, One-Hot, Custom)
- Embedding preprocessing
- Embedding storage/caching

c. Model Layer:
- Available model architectures:
- CNN
- FNN
- Light Attention
- LogReg
- Model parameter management

d. Training/Inference Layer:
- Split into two parallel paths:
- Training pipeline with cross-validation, HP management
- Inference pipeline with model loading and prediction

##### Key Interactions to Highlight

- Data flow from input through embedding to model
- Protocol selection affecting the entire pipeline
- How the solver interfaces with models and training

##### Implementation Details

**biotrainer/**
- config/         (Configuration Management)
- datasets/       (Data Processing)
- embedders/      (Embedding Layer)
- models/         (Model Architectures)
- trainers/       (Training Pipeline)
- inference/      (Inference Pipeline)
- solvers/        (Problem Solvers)

##### Additional Elements

- Version information
- External dependencies (PyTorch, HuggingFace, etc.)
- Configuration file interaction points

Remember to include notes about the system's extensibility, particularly regarding custom embedders and model architectures, as this appears to be a key feature of the system based on the examples provided.

## Diagram (Mermaid)

```mermaid
graph TB
    subgraph Legend
        L1[Core Processing]:::core
        L2[Data I/O]:::data
        L3[Configuration]:::config
        L4[Model Components]:::model
        L5[Training/Inference]:::training
    end

    subgraph "Input Processing Layer"
        InputProcessor["Input Processor"]:::core
        FastaProcessor["FASTA Processor"]:::data
        LabelProcessor["Label Processor"]:::data
        DataValidator["Data Validator"]:::core
    end

    subgraph "Embedding Layer"
        EmbeddingService["Embedding Service"]:::core
        HuggingFace["HuggingFace Embedder"]:::core
        OneHot["One-Hot Encoder"]:::core
        CustomEmbed["Custom Embedder"]:::core
    end

    subgraph "Model Layer"
        ModelArch["Model Architecture"]:::model
        CNN["CNN"]:::model
        FNN["FNN"]:::model
        LightAttention["Light Attention"]:::model
        LogReg["LogReg"]:::model
    end

    subgraph "Training and Inference"
        TrainingPipeline["Training Pipeline"]:::training
        InferencePipeline["Inference Pipeline"]:::training
        HPManager["HP Manager"]:::training
        CVSplitter["CV Splitter"]:::training
    end

    subgraph "Configuration and Management"
        ConfigManager["Configuration Manager"]:::config
        ProtocolHandler["Protocol Handler"]:::config
        SolverSystem["Solver System"]:::config
    end

    %% Connections
    InputProcessor --> FastaProcessor
    InputProcessor --> LabelProcessor
    InputProcessor --> DataValidator
    
    FastaProcessor --> EmbeddingService
    LabelProcessor --> EmbeddingService
    
    EmbeddingService --> HuggingFace
    EmbeddingService --> OneHot
    EmbeddingService --> CustomEmbed
    
    HuggingFace --> ModelArch
    OneHot --> ModelArch
    CustomEmbed --> ModelArch
    
    ModelArch --> CNN
    ModelArch --> FNN
    ModelArch --> LightAttention
    ModelArch --> LogReg
    
    CNN --> TrainingPipeline
    FNN --> TrainingPipeline
    LightAttention --> TrainingPipeline
    LogReg --> TrainingPipeline
    
    TrainingPipeline --> HPManager
    TrainingPipeline --> CVSplitter
    
    ModelArch --> InferencePipeline
    
    ConfigManager --> InputProcessor
    ConfigManager --> EmbeddingService
    ConfigManager --> ModelArch
    ConfigManager --> TrainingPipeline
    ConfigManager --> InferencePipeline
    
    ProtocolHandler --> SolverSystem
    SolverSystem --> TrainingPipeline
    SolverSystem --> InferencePipeline

    %% Click Events
    click InputProcessor "https://github.com/sacdallago/biotrainer/tree/main/biotrainer/datasets/"
    click FastaProcessor "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/utilities/fasta.py"
    click EmbeddingService "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/embedders/embedding_service.py"
    click HuggingFace "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/embedders/huggingface_transformer_embedder.py"
    click OneHot "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/embedders/one_hot_encoding_embedder.py"
    click CNN "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/models/cnn.py"
    click FNN "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/models/fnn.py"
    click LightAttention "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/models/light_attention.py"
    click LogReg "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/models/log_reg.py"
    click TrainingPipeline "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/trainers/trainer.py"
    click HPManager "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/trainers/hp_manager.py"
    click CVSplitter "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/trainers/cv_splitter.py"
    click InferencePipeline "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/inference/inferencer.py"
    click ConfigManager "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/config/configurator.py"
    click ProtocolHandler "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/protocols/protocol.py"
    click DataValidator "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/validations/sanity_checker.py"
    click SolverSystem "https://github.com/sacdallago/biotrainer/blob/main/biotrainer/solvers/solver.py"

    %% Styles
    classDef core fill:#3498db,stroke:#2980b9,color:white
    classDef data fill:#2ecc71,stroke:#27ae60,color:white
    classDef config fill:#f1c40f,stroke:#f39c12,color:black
    classDef model fill:#9b59b6,stroke:#8e44ad,color:white
    classDef training fill:#e67e22,stroke:#d35400,color:white
```
