# sandromikautadze/neural-response-identification architecture

> Architecture diagram of the GitHub repository sandromikautadze/neural-response-identification, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sandromikautadze/neural-response-identification
- Repository: https://github.com/sandromikautadze/neural-response-identification

## Overview

##### Project type and purpose
- This is a data‐analysis and modeling project (not a web or full-stack app). Its goal is to build and compare mathematical models (linear, quadratic, MLP) that predict mouse VISam neuron spike counts from static grating features.

##### File structure
- data/
- CSV files (static_gratings_VISam_*.csv) – the raw/cleaned datasets of stimuli and spike counts.
- utils/
- regression.py – utility functions for building and evaluating regression models.
- Jupyter notebooks at root
- data_analysis.ipynb – exploratory analysis and visualization.
- neurons_range_selection.ipynb / neurons_variance_selection.ipynb – separate modeling pipelines based on different neuron selection criteria.
- report.pdf – compiled write-up of methods, results, and conclusions.
- Configuration files
- .gitignore – standard ignore rules.

##### README insights
- Research question: predict spike counts given orientation, spatial frequency, phase.
- Workflow: select responsive neurons → featurize inputs (linear, quadratic, sinusoidal) → fit models (MLP, linear) → evaluate → report.
- No external services; everything is local files and Python notebooks.

##### Main components
a. Data Layer
– Raw/cleaned CSV files in data/
b. Preprocessing & Feature Engineering
– Python functions in utils/regression.py
– Notebooks call these to build feature matrices (linear, quadratic, sinusoidal)
c. Modeling
– MLP and linear regression routines in utils and notebooks
d. Evaluation & Selection
– Range-based and variance-based neuron filters (notebooks)
– Performance metrics calculation
e. Reporting
– Figures and tables embedded in notebooks → final report.pdf

##### Relationships and data flow
– The notebooks orchestrate calls to utils/regression.py.

##### Architectural patterns & design principles
- Modular separation of concerns:
- Data storage (data/)
- Reusable code (utils/)
- Notebook workflows (analysis & modeling)
- Documentation output (report.pdf)
- Reproducibility via notebooks and version control.

- Labels: describe what each component does (e.g., “compute quadratic features”).

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Layer
    subgraph "Data Layer"
        D1["static_gratings_VISam_range_80_5neurons.csv"]:::data
        D2["static_gratings_VISam_var_80_6neurons.csv"]:::data
    end

    %% Preprocessing & Feature Engineering
    subgraph "Preprocessing & Feature Engineering"
        REG["utils/regression.py: feature & model functions"]:::code
    end

    %% Notebook Workflows
    subgraph "Notebook Workflows"
        DA["data_analysis.ipynb: exploratory analysis"]:::notebook
        NR["neurons_range_selection.ipynb: range‐based pipeline"]:::notebook
        NV["neurons_variance_selection.ipynb: variance‐based pipeline"]:::notebook
    end

    %% Reporting Output
    REPORT["report.pdf: compiled methods & results"]:::output

    %% Data Ingestion
    D1 -->|"ingest raw/cleaned data"| DA
    D2 -->|"ingest raw/cleaned data"| DA
    D1 -->|"ingest raw/cleaned data"| NR
    D2 -->|"ingest raw/cleaned data"| NR
    D1 -->|"ingest raw/cleaned data"| NV
    D2 -->|"ingest raw/cleaned data"| NV

    %% Feature Engineering & Modeling Calls
    DA -->|"calls feature & model functions"| REG
    NR -->|"calls feature & model functions"| REG
    NV -->|"calls feature & model functions"| REG

    %% Reporting
    DA -.->|"generate figures & tables"| REPORT
    NR -.->|"generate figures & tables"| REPORT
    NV -.->|"generate figures & tables"| REPORT

    %% Click Events
    click D1 "https://github.com/sandromikautadze/neural-response-identification/blob/main/data/static_gratings_VISam_range_80_5neurons.csv"
    click D2 "https://github.com/sandromikautadze/neural-response-identification/blob/main/data/static_gratings_VISam_var_80_6neurons.csv"
    click REG "https://github.com/sandromikautadze/neural-response-identification/blob/main/utils/regression.py"
    click DA "https://github.com/sandromikautadze/neural-response-identification/blob/main/data_analysis.ipynb"
    click NR "https://github.com/sandromikautadze/neural-response-identification/blob/main/neurons_range_selection.ipynb"
    click NV "https://github.com/sandromikautadze/neural-response-identification/blob/main/neurons_variance_selection.ipynb"
    click REPORT "https://github.com/sandromikautadze/neural-response-identification/blob/main/report.pdf"

    %% Styles
    classDef data fill:#a8ddb5,stroke:#2b7a0b,color:#000;
    classDef code fill:#9ecae1,stroke:#2171b5,color:#000;
    classDef notebook fill:#fdae6b,stroke:#e6550d,color:#000;
    classDef output fill:#d9d9d9,stroke:#636363,color:#000;
```
