Data

Tools

Indexes

Applications

Experiments

Open Source Science

sptnano

https://github.com/michael-shannon/sptnano

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: Michael-shannon
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 1.65 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed 7 months ago
Metadata Files
Readme License Citation

README.md

SPTnano

pre-commit Tests status Linting status Documentation status License

Single particle tracking analysis with machine learning. This package combines traditional trajectory analysis with transformer-based deep learning to classify motion patterns.

About

Project Team

Michael Shannon (m.j.shannon@pm.me)

The structure for this repo was made using a cookiecutter from the Centre for Advanced Research Computing, University College London.

Installation

Quick Install (Recommended)

bash pip install git+https://github.com/Michael-shannon/SPTnano.git

For Development

bash git clone https://github.com/Michael-shannon/SPTnano.git cd SPTnano pip install -e .

If you get dependency errors, try installing them first:

bash pip install numpy pandas matplotlib seaborn scikit-learn torch trackpy

Getting Started

```python import SPTnano as spt import pandas as pd

Load your trajectory data

df = pd.readcsv("yourtrajectories.csv")

Calculate motion features

metrics = spt.ParticleMetrics(df, timebetweenframes=0.01) metrics.calculatetimewindowedmetrics(windowsize=60, overlap=30)

Train a transformer model

results = spt.trainmotiontransformer(df, epochs=25, use_tensorboard=True)

Analyze results

windoweddf = metrics.gettimewindoweddf() spt.plottracksbymotionclass(windoweddf, metrics.gettimeaverageddf()) ```

Data Format

Your CSV should have these columns:

  • unique_id - Unique identifier for each track
  • frame - Frame number
  • x, y - Coordinates
  • time_s - Time in seconds
  • condition - Experimental condition (optional)

Configuration

Set your data directory:

```python

Edit this line in src/SPTnano/config.py

MASTER = '/path/to/your/data/' ```

Or change it programmatically:

python import SPTnano as spt spt.config.MASTER = '/path/to/your/data/'

Features

  • Traditional Analysis: MSD, diffusion coefficients, motion classification
  • Transformer Models: Deep learning on trajectory windows
  • Visualization: Track plotting, clustering, UMAP embeddings
  • TensorBoard: Training monitoring and visualization

Examples

Check out the notebooks/ folder for examples:

Troubleshooting

Import errors? Make sure you installed the package: pip install -e .

Missing dependencies? Install them: pip install torch numpy pandas matplotlib

Path issues? Check your config: print(spt.config.MASTER)

Contributing

This is research software - expect rough edges. Pull requests welcome.

License

MIT License

Owner

  • Name: Michael Shannon
  • Login: Michael-shannon
  • Kind: user
  • Location: New York City
  • Company: Columbia University Medical Center

Image analyst, Columbia University

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
type: software
authors:
  - family-names: "Shannon"
    given-names: "Michael"
    email: "m.j.shannon@pm.me"
repository-code: "https://github.com/Michael-shannon/SPTnano"
title: "SPTnano: Pipeline for easy single particle detection, linking/tracking, and analysis"
license: "MIT"

GitHub Events

Total
  • Member event: 2
  • Push event: 59
Last Year
  • Member event: 2
  • Push event: 59

Dependencies

.github/workflows/docs.yml actions
  • actions/cache 0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 composite
  • actions/checkout a5ac7e51b41094c92402da3b24376905380afc29 composite
  • actions/setup-python 82c7e631bb3cdc910f68e0081d67478d79c6982d composite
  • peaceiris/actions-gh-pages 4f9cc6602d3f66b9c108549d475ec49e8ef4d45e composite
.github/workflows/linting.yml actions
  • actions/cache 0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 composite
  • actions/checkout a5ac7e51b41094c92402da3b24376905380afc29 composite
  • actions/setup-python 82c7e631bb3cdc910f68e0081d67478d79c6982d composite
.github/workflows/tests.yml actions
  • actions/cache 0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 composite
  • actions/checkout a5ac7e51b41094c92402da3b24376905380afc29 composite
  • actions/setup-python 82c7e631bb3cdc910f68e0081d67478d79c6982d composite
pyproject.toml pypi