# manoj-devvvvv/drug-food-ai-upgraded architecture

> Architecture diagram of the GitHub repository manoj-devvvvv/drug-food-ai-upgraded, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/manoj-devvvvv/drug-food-ai-upgraded
- Repository: https://github.com/manoj-devvvvv/drug-food-ai-upgraded

## Overview

This repository builds and serves a drug–food interaction recommender. Its user workflow is a drug/food request to the FastAPI service, recommendation and risk result; the serving engine combines model-based prediction with curated rules and supporting resolution, applicability-domain, calibration, and explanation capabilities. The broader research workflow covers cleaning and labeling data, generating pair features, selecting and training models, then evaluating them. Evidence is limited to the supplied source excerpts and SOURCE INDEX; several preparation-stage connections are represented as components without guessed links.

Main entry points: [`src/recommend.py`](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/recommend.py) (Recommendation engine), [`src/common.py`](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/common.py) (Shared config and utilities), [`src/brick8_models.py`](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick8_models.py) (Model training), [`src/features.py`](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/features.py) (Molecular pair features)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_serve["Serving and recommendations"]
  node_api["FastAPI service<br/>[app.py]"]
  node_engine["Recommendation engine<br/>[recommend.py]"]
  node_resolution["Name resolution<br/>[resolve.py]"]
  node_rules["Curated interaction rules<br/>[rules.py]"]
  node_domain["Applicability domain<br/>[domain.py]"]
  node_calibration["Probability calibration<br/>[calibration.py]"]
  node_explain["Prediction explanation<br/>[explain.py]"]
end

subgraph group_science["Data and features"]
  node_clean_drugs["Drug cleaning"]
  node_clean_foods["Food cleaning"]
  node_labels["Pair labeling<br/>[brick4_labels.py]"]
  node_features["Molecular pair features<br/>[features.py]"]
end

subgraph group_model["Model development"]
  node_selection["Feature selection"]
  node_training["Model training<br/>[brick8_models.py]"]
  node_single_model["Deployed model selection"]
end

subgraph group_quality["Validation and evidence"]
  node_splits["Data splits<br/>[splits_extra.py]"]
  node_evaluation["Model evaluation<br/>[brick9_evaluate.py]"]
  node_domain_cal["Domain calibration analysis"]
  node_generalization["Generalization analysis"]
  node_shared["Shared config and utilities<br/>[common.py]"]
end

node_user(("Drug/food user"))

node_user -->|"submits request"| node_api
node_api -->|"requests recommendation"| node_engine
node_api -->|"reports rule version"| node_rules
node_engine -->|"resolves names"| node_resolution
node_engine -->|"checks rules"| node_rules
node_engine -->|"checks applicability"| node_domain
node_engine -->|"calibrates probabilities"| node_calibration
node_engine -->|"generates explanation"| node_explain
node_engine -->|"builds pair features"| node_features
node_engine -->|"loads model"| node_training
node_clean_drugs -->|"uses utilities"| node_shared
node_clean_foods -->|"uses utilities"| node_shared
node_labels -->|"uses utilities"| node_shared
node_selection -->|"builds features"| node_features
node_selection -->|"uses utilities"| node_shared
node_training -->|"builds features"| node_features
node_training -->|"uses utilities"| node_shared
node_single_model -->|"reuses model methods"| node_training
node_single_model -->|"uses utilities"| node_shared
node_evaluation -->|"builds features"| node_features
node_evaluation -->|"uses estimators"| node_training
node_evaluation -->|"uses utilities"| node_shared
node_domain_cal -->|"uses model artifacts"| node_training
node_domain_cal -->|"fits domain thresholds"| node_domain
node_domain_cal -->|"uses split helpers"| node_splits
node_domain_cal -->|"uses utilities"| node_shared
node_generalization -->|"reuses model setup"| node_single_model
node_generalization -->|"builds features"| node_features
node_generalization -->|"uses split helpers"| node_splits
node_generalization -->|"uses utilities"| node_shared

click node_api "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/web/app.py"
click node_engine "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/recommend.py"
click node_resolution "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/resolve.py"
click node_rules "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/rules.py"
click node_domain "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/domain.py"
click node_calibration "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/calibration.py"
click node_explain "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/explain.py"
click node_clean_drugs "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick2_clean_drugs.py"
click node_clean_foods "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick3_clean_foods.py"
click node_labels "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick4_labels.py"
click node_features "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/features.py"
click node_selection "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick7_selection.py"
click node_training "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick8_models.py"
click node_single_model "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick17_single_model.py"
click node_splits "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/splits_extra.py"
click node_evaluation "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick9_evaluate.py"
click node_domain_cal "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick14_domain_calibration.py"
click node_generalization "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick15_generalization.py"
click node_shared "https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/common.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_api,node_engine,node_resolution,node_rules,node_domain,node_calibration,node_explain,node_user toneBlue
class node_clean_drugs,node_clean_foods,node_labels,node_features toneAmber
class node_selection,node_training,node_single_model toneMint
class node_splits,node_evaluation,node_domain_cal,node_generalization,node_shared toneRose
```

## Components

### Serving and recommendations

- [FastAPI service](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/web/app.py): `web/app.py`
- [Recommendation engine](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/recommend.py): `src/recommend.py`
- [Name resolution](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/resolve.py): `src/resolve.py`
- [Curated interaction rules](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/rules.py): `src/rules.py`
- [Applicability domain](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/domain.py): `src/domain.py`
- [Probability calibration](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/calibration.py): `src/calibration.py`
- [Prediction explanation](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/explain.py): `src/explain.py`

### Data and features

- [Drug cleaning](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick2_clean_drugs.py): `src/brick2_clean_drugs.py`
- [Food cleaning](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick3_clean_foods.py): `src/brick3_clean_foods.py`
- [Pair labeling](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick4_labels.py): `src/brick4_labels.py`
- [Molecular pair features](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/features.py): `src/features.py`

### Model development

- [Feature selection](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick7_selection.py): `src/brick7_selection.py`
- [Model training](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick8_models.py): `src/brick8_models.py`
- [Deployed model selection](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick17_single_model.py): `src/brick17_single_model.py`

### Validation and evidence

- [Data splits](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/splits_extra.py): `src/splits_extra.py`
- [Model evaluation](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick9_evaluate.py): `src/brick9_evaluate.py`
- [Domain calibration analysis](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick14_domain_calibration.py): `src/brick14_domain_calibration.py`
- [Generalization analysis](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/brick15_generalization.py): `src/brick15_generalization.py`
- [Shared config and utilities](https://github.com/manoj-devvvvv/drug-food-ai-upgraded/blob/main/src/common.py): `src/common.py`

### Other components

- **Drug/food user**

## Connections

- Drug/food user → FastAPI service: submits request (evidence: `web/app.py`)
- FastAPI service → Recommendation engine: requests recommendation (evidence: `web/app.py`)
- FastAPI service → Curated interaction rules: reports rule version (evidence: `web/app.py`)
- Recommendation engine → Name resolution: resolves names (evidence: `src/recommend.py`)
- Recommendation engine → Curated interaction rules: checks rules (evidence: `src/recommend.py`)
- Recommendation engine → Applicability domain: checks applicability (evidence: `src/recommend.py`)
- Recommendation engine → Probability calibration: calibrates probabilities (evidence: `src/recommend.py`)
- Recommendation engine → Prediction explanation: generates explanation (evidence: `src/recommend.py`)
- Recommendation engine → Molecular pair features: builds pair features (evidence: `src/recommend.py`)
- Recommendation engine → Model training: loads model (evidence: `src/recommend.py`)
- Drug cleaning → Shared config and utilities: uses utilities (evidence: `src/brick2_clean_drugs.py`)
- Food cleaning → Shared config and utilities: uses utilities (evidence: `src/brick3_clean_foods.py`)
- Pair labeling → Shared config and utilities: uses utilities (evidence: `src/brick4_labels.py`)
- Feature selection → Molecular pair features: builds features (evidence: `src/brick7_selection.py`)
- Feature selection → Shared config and utilities: uses utilities (evidence: `src/brick7_selection.py`)
- Model training → Molecular pair features: builds features (evidence: `src/brick8_models.py`)
- Model training → Shared config and utilities: uses utilities (evidence: `src/brick8_models.py`)
- Deployed model selection → Model training: reuses model methods (evidence: `src/brick17_single_model.py`)
- Deployed model selection → Shared config and utilities: uses utilities (evidence: `src/brick17_single_model.py`)
- Model evaluation → Molecular pair features: builds features (evidence: `src/brick9_evaluate.py`)
- Model evaluation → Model training: uses estimators (evidence: `src/brick9_evaluate.py`)
- Model evaluation → Shared config and utilities: uses utilities (evidence: `src/brick9_evaluate.py`)
- Domain calibration analysis → Model training: uses model artifacts (evidence: `src/brick14_domain_calibration.py`)
- Domain calibration analysis → Applicability domain: fits domain thresholds (evidence: `src/brick14_domain_calibration.py`)
- Domain calibration analysis → Data splits: uses split helpers (evidence: `src/brick14_domain_calibration.py`)
- Domain calibration analysis → Shared config and utilities: uses utilities (evidence: `src/brick14_domain_calibration.py`)
- Generalization analysis → Deployed model selection: reuses model setup (evidence: `src/brick15_generalization.py`)
- Generalization analysis → Molecular pair features: builds features (evidence: `src/brick15_generalization.py`)
- Generalization analysis → Data splits: uses split helpers (evidence: `src/brick15_generalization.py`)
- Generalization analysis → Shared config and utilities: uses utilities (evidence: `src/brick15_generalization.py`)
