# csubiogroup/dtiam architecture

> Architecture diagram of the GitHub repository csubiogroup/dtiam, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-21). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/csubiogroup/dtiam
- Repository: https://github.com/csubiogroup/dtiam

## Overview

##### Project type and purpose
- DTIAM is a research‐oriented, full‐stack Python framework for three ML tasks:
- Drug-Target Interaction (DTI) prediction
- Drug-Target Affinity (DTA) prediction
- Mechanism of Action (MoA) classification (activation/inhibition)
- It combines data preparation, self-supervised molecular representation learning (BerMol), and downstream model training/validation.

##### File structure
- Top‐level directories/files:
- code/ — contains all Python modules, scripts, and package code
– BerMol/bermol/ — reusable Python package: data loading, tokenizer/vocab, model, trainer, utils
– scripts/ — standalone helpers, e.g., featurize.py
– data_process/ — dataset splitting and feature extraction pipelines
– training_validation.py — main entrypoint orchestrating experiments
– run.sh, test.sh — convenience wrappers
- data/ — raw benchmark datasets grouped by task and source
- img/ — architecture/flowchart reference
- requirements.txt, README.md, setup files, environment scripts
- Architectural patterns:
- Modular Python package (BerMol) for core representations
- Layered pipeline: Data → Preprocessing → Feature Extraction → Model → Training/Validation
- CLI entry point driving experiments with parameterized tasks/datasets/settings

##### README for additional insights
- High‐level flowchart (img/flowchart.png) outlines:
Raw data → Preprocessing → Self-supervised pretraining (BerMol) → Downstream fine-tuning and evaluation
- Instructions for conda environment and dependencies
- How to invoke training: `python training_validation.py <task> <dataset> <setting>`

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Layer
    subgraph "Data Layer"
        direction TB
        raw_data["data/"]:::data
        dti["dti/"]:::data
        dta["dta/"]:::data
        moa["moa/"]:::data
        docking["docking/"]:::data
    end

    %% Data Preparation Layer
    subgraph "Data Preparation Layer"
        direction TB
        prepare_sh["data_prepare.sh"]:::data
        split_dti["data_split_dti.py"]:::data
        split_dta["data_split_dta.py"]:::data
        split_moa["data_split_moa.py"]:::data
        extract_feat["extract_feature.py"]:::data
    end

    %% Feature Extraction & Representation Learning
    subgraph "Feature Extraction & Representation Learning"
        direction TB
        init_pkg["__init__.py"]:::ml
        tokenizer["tokenizer.py"]:::ml
        vocab["vocab.py"]:::ml
        dataloading["dataloading.py"]:::ml
        model["model.py"]:::ml
        trainer["trainer.py"]:::ml
        utils_pkg["utils.py"]:::ml
        pretrain_shell["run.sh"]:::ml
        featurize_script["featurize.py"]:::ml
    end

    %% Downstream Model Training & Validation
    subgraph "Downstream Model Training & Validation"
        direction TB
        orchestrator["training_validation.py"]:::orch
    end

    %% Utilities & Scripts
    subgraph "Utilities & Scripts"
        direction TB
        gen_utils["utils.py"]:::util
        test_sh["test.sh"]:::util
        run_wrapper["run.sh"]:::util
    end

    %% External Dependencies
    subgraph "External Dependencies"
        direction TB
        pytorch["PyTorch, AutoGluon, fair_esm, RDKit"]:::external
        pretrain_model["BerMolModel_base.pkl"]:::external
    end

    %% Connections
    raw_data -->|"raw data ingestion"| prepare_sh
    prepare_sh --> split_dti
    prepare_sh --> split_dta
    prepare_sh --> split_moa
    split_dti --> extract_feat
    split_dta --> extract_feat
    split_moa --> extract_feat
    extract_feat --> dataloading
    tokenizer --> dataloading
    vocab --> dataloading
    pretrain_shell --> trainer
    trainer --> model
    pretrain_model -.-> model
    model --> trainer
    trainer -->|"embedding vectors"| orchestrator
    featurize_script --> extract_feat
    run_wrapper --> pretrain_shell

    %% Click Events
    click raw_data "https://github.com/csubiogroup/dtiam/tree/main/data/"
    click dti "https://github.com/csubiogroup/dtiam/tree/main/data/dti/"
    click dta "https://github.com/csubiogroup/dtiam/tree/main/data/dta/"
    click moa "https://github.com/csubiogroup/dtiam/tree/main/data/moa/"
    click docking "https://github.com/csubiogroup/dtiam/tree/main/data/docking/"
    click prepare_sh "https://github.com/csubiogroup/dtiam/blob/main/code/data_prepare.sh"
    click split_dti "https://github.com/csubiogroup/dtiam/blob/main/code/data_process/data_split_dti.py"
    click split_dta "https://github.com/csubiogroup/dtiam/blob/main/code/data_process/data_split_dta.py"
    click split_moa "https://github.com/csubiogroup/dtiam/blob/main/code/data_process/data_split_moa.py"
    click extract_feat "https://github.com/csubiogroup/dtiam/blob/main/code/data_process/extract_feature.py"
    click init_pkg "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/__init__.py"
    click tokenizer "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/tokenizer.py"
    click vocab "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/vocab.py"
    click dataloading "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/dataloading.py"
    click model "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/model.py"
    click trainer "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/trainer.py"
    click utils_pkg "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/utils.py"
    click pretrain_shell "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/bermol/run.sh"
    click featurize_script "https://github.com/csubiogroup/dtiam/blob/main/code/BerMol/scripts/featurize.py"
    click orchestrator "https://github.com/csubiogroup/dtiam/blob/main/code/training_validation.py"
    click gen_utils "https://github.com/csubiogroup/dtiam/blob/main/code/utils.py"
    click test_sh "https://github.com/csubiogroup/dtiam/blob/main/code/test.sh"
    click run_wrapper "https://github.com/csubiogroup/dtiam/blob/main/code/code/BerMol/run.sh"

    %% Styles
    classDef data fill:#ccffcc,stroke:#333,stroke-width:1px
    classDef ml fill:#ccccff,stroke:#333,stroke-width:1px
    classDef orch fill:#ffcc99,stroke:#333,stroke-width:1px
    classDef util fill:#eeeeee,stroke:#333,stroke-width:1px
    classDef external fill:#dddddd,stroke:#333,stroke-width:1px
```
