# mozaffarilegha/drugcombinationprediction_drs architecture

> Architecture diagram of the GitHub repository mozaffarilegha/drugcombinationprediction_drs, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mozaffarilegha/drugcombinationprediction_drs
- Repository: https://github.com/mozaffarilegha/drugcombinationprediction_drs

## Overview

DrugCombinationPrediction_DRS predicts oncology drug-combination synergy using resistance-signature and other biological features, with conventional ML workflows and the SynergyX deep-learning model. The principal SynergyX path loads fold data, constructs cell/drug examples, trains and evaluates the model, and reports synergy scores. The README also describes benchmark evaluation and cross-dataset validation. Some ML model implementations and SynergyX internals are indexed but not excerpted, so their details and unshown connections are kept broad.

Main entry points: [`models/SynergyX/dataset/My_inMemory_dataset.py`](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/dataset/My_inMemory_dataset.py) (Synergy Dataset), [`models/SynergyX/main.py`](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/main.py) (Training Runner), [`models/SynergyX/utlis.py`](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/utlis.py) (Training Utilities), [`models/SynergyX/models/model.py`](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/model.py) (SynergyX Network)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_features["Biological Features"]
  node_prep_deg["DEG Features<br/>[prepareLINCS.py]"]
  node_prep_sen["Sensitivity DEG"]
  node_prep_sub["Substructure Features<br/>[prepareLINCSsub.py]"]
  node_prep_drug["Drug Embeddings"]
end

subgraph group_ml["Classical ML"]
  node_estimators["ML Estimators"]
end

subgraph group_synergyx["SynergyX"]
  node_synergy_main["Training Runner<br/>[main.py]"]
  node_loader["Training Utilities<br/>[utlis.py]"]
  node_dataset["Synergy Dataset"]
  node_dataset_base["Dataset Base"]
  node_network["SynergyX Network<br/>[model.py]"]
  node_attention["Attention Encoders<br/>[model_utlis.py]"]
  node_fusion["Fusion Head<br/>[head.py]"]
  node_metrics["Regression Metrics<br/>[metrics.py]"]
end

subgraph group_data["Datasets"]
  node_expression_data["Cell Expression Data"]
  node_deg_data["DEG Signature Data<br/>[DEGWithMASK.npy]"]
  node_sensitive_data["Sensitivity Signatures<br/>[DEGsenWithMASK.npy]"]
  node_drug_data["Drug Feature Data"]
  node_benchmarks["Synergy Benchmarks"]
end

node_researcher(("Researcher"))

node_researcher -->|"runs"| node_synergy_main
node_synergy_main -->|"loads folds"| node_loader
node_loader -->|"constructs datasets"| node_dataset
node_dataset -->|"inherits"| node_dataset_base
node_dataset -->|"loads features"| node_expression_data
node_dataset -->|"loads features"| node_drug_data
node_synergy_main -->|"uses model"| node_network
node_network -->|"uses encoders"| node_attention
node_network -->|"uses head"| node_fusion
node_loader -->|"evaluates predictions"| node_metrics
node_prep_deg -.->|"uses signatures"| node_deg_data
node_prep_sen -.->|"uses signatures"| node_sensitive_data
node_prep_sub -->|"uses cell features"| node_expression_data
node_prep_drug -->|"loads embeddings"| node_drug_data
node_researcher -.->|"runs predictions"| node_estimators
node_benchmarks -.->|"benchmark data"| node_estimators
node_benchmarks -.->|"validation data"| node_synergy_main

click node_prep_deg "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCS.py"
click node_prep_sen "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCSsenDEG.py"
click node_prep_sub "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCSsub.py"
click node_prep_drug "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareSubstructure.py"
click node_estimators "https://github.com/mozaffarilegha/drugcombinationprediction_drs/tree/main/models/ML%20models"
click node_synergy_main "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/main.py"
click node_loader "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/utlis.py"
click node_dataset "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/dataset/My_inMemory_dataset.py"
click node_dataset_base "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/dataset/base_InMemory_dataset.py"
click node_network "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/model.py"
click node_attention "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/model_utlis.py"
click node_fusion "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/head.py"
click node_metrics "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/metrics.py"
click node_expression_data "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/985_cellGraphs_exp_mut_cn_eff_dep_met_4079_genes_norm.npy"
click node_deg_data "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/DEGWithMASK.npy"
click node_sensitive_data "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/DEGsenWithMASK.npy"
click node_drug_data "https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/drugSmile_drugSubEmbed_2644.npy"
click node_benchmarks "https://github.com/mozaffarilegha/drugcombinationprediction_drs/tree/main/dbs"

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_prep_deg,node_prep_sen,node_prep_sub,node_prep_drug toneBlue
class node_estimators toneAmber
class node_synergy_main,node_loader,node_dataset,node_dataset_base,node_network,node_attention,node_fusion,node_metrics toneMint
class node_expression_data,node_deg_data,node_sensitive_data,node_drug_data,node_benchmarks toneRose
class node_researcher toneIndigo
```

## Components

### Biological Features

- [DEG Features](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCS.py): `models/ML models/prepareLINCS.py`
- [Sensitivity DEG](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCSsenDEG.py): `models/ML models/prepareLINCSsenDEG.py`
- [Substructure Features](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareLINCSsub.py): `models/ML models/prepareLINCSsub.py`
- [Drug Embeddings](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/ML%20models/prepareSubstructure.py): `models/ML models/prepareSubstructure.py`

### Classical ML

- [ML Estimators](https://github.com/mozaffarilegha/drugcombinationprediction_drs/tree/main/models/ML%20models): `models/ML models`

### SynergyX

- [Training Runner](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/main.py): `models/SynergyX/main.py`
- [Training Utilities](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/utlis.py): `models/SynergyX/utlis.py`
- [Synergy Dataset](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/dataset/My_inMemory_dataset.py): `models/SynergyX/dataset/My_inMemory_dataset.py`
- [Dataset Base](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/dataset/base_InMemory_dataset.py): `models/SynergyX/dataset/base_InMemory_dataset.py`
- [SynergyX Network](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/model.py): `models/SynergyX/models/model.py`
- [Attention Encoders](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/model_utlis.py): `models/SynergyX/models/model_utlis.py`
- [Fusion Head](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/models/head.py): `models/SynergyX/models/head.py`
- [Regression Metrics](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/models/SynergyX/metrics.py): `models/SynergyX/metrics.py`

### Datasets

- [Cell Expression Data](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/985_cellGraphs_exp_mut_cn_eff_dep_met_4079_genes_norm.npy): `data/985_cellGraphs_exp_mut_cn_eff_dep_met_4079_genes_norm.npy`
- [DEG Signature Data](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/DEGWithMASK.npy): `data/DEGWithMASK.npy`
- [Sensitivity Signatures](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/DEGsenWithMASK.npy): `data/DEGsenWithMASK.npy`
- [Drug Feature Data](https://github.com/mozaffarilegha/drugcombinationprediction_drs/blob/main/data/drugSmile_drugSubEmbed_2644.npy): `data/drugSmile_drugSubEmbed_2644.npy`
- [Synergy Benchmarks](https://github.com/mozaffarilegha/drugcombinationprediction_drs/tree/main/dbs): `dbs`

### Other components

- **Researcher**

## Connections

- Researcher → Training Runner: runs (evidence: `models/SynergyX/main.py`)
- Training Runner → Training Utilities: loads folds (evidence: `models/SynergyX/main.py`)
- Training Utilities → Synergy Dataset: constructs datasets (evidence: `models/SynergyX/utlis.py`)
- Synergy Dataset → Dataset Base: inherits (evidence: `models/SynergyX/dataset/My_inMemory_dataset.py`)
- Synergy Dataset → Cell Expression Data: loads features (evidence: `models/SynergyX/dataset/My_inMemory_dataset.py`)
- Synergy Dataset → Drug Feature Data: loads features (evidence: `models/SynergyX/dataset/My_inMemory_dataset.py`)
- Training Runner → SynergyX Network: uses model (evidence: `models/SynergyX/main.py`)
- SynergyX Network → Attention Encoders: uses encoders (evidence: `models/SynergyX/models/model.py`)
- SynergyX Network → Fusion Head: uses head (evidence: `models/SynergyX/models/model.py`)
- Training Utilities → Regression Metrics: evaluates predictions (evidence: `models/SynergyX/utlis.py`)
- DEG Features → DEG Signature Data: uses signatures
- Sensitivity DEG → Sensitivity Signatures: uses signatures
- Substructure Features → Cell Expression Data: uses cell features (evidence: `models/ML models/prepareLINCSsub.py`)
- Drug Embeddings → Drug Feature Data: loads embeddings (evidence: `models/ML models/prepareSubstructure.py`)
- Researcher → ML Estimators: runs predictions
- Synergy Benchmarks → ML Estimators: benchmark data
- Synergy Benchmarks → Training Runner: validation data
