multi-roi-analysis-with-deeplabcut-csv-outputs
https://github.com/farhanaugustine/multi-roi-analysis-with-deeplabcut-csv-outputs
Science Score: 67.0%
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
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (11.4%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: farhanaugustine
- License: gpl-3.0
- Language: Jupyter Notebook
- Default Branch: main
- Size: 1.77 MB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 2
Metadata Files
README.md
Update:
Bug Fixes:
"Data becoming inverted when plotted using Matplotlib." - Fixed
Multiple ROI Analysis with DeepLabCut CSV Files
Overview
This project involves analyzing multiple Regions of Interest (ROIs) using CSV files generated by DeepLabCut, a machine-learning tool for animal pose estimation.
Video Tutorial and Walkthrough: Link
Features
- Import Libraries: Utilizes essential Python libraries for data manipulation and visualization.
- Data Import: Loads CSV data for analysis, focusing on body part coordinates and likelihoods.
- Body Part Data: Creates a dictionary mapping body parts to their respective coordinates and likelihood values.
- ROI Drawing: Allows users to draw ROIs and calculates the time spent by subjects within these regions.
- Temporal Analysis: Analyzes the number of entries and exits from ROIs, including the first entry and the sequence of visits.
- Velocity Calculation: Computes velocities for each body part and graphs them per ROI.
- Graphing: Visualizes data such as the number of entries and exits per ROI and the average velocities.
Usage
To use this project, follow the steps outlined in the code cells, from importing libraries to graphing the results. Customize the ROI names, colors, and body parts as per your experimental setup.
Data Structure
The data is structured with body part coordinates and likelihoods, which are used to calculate distances, velocities, and time spent in ROIs. In addition, the code allows for the tracking of sequences and frequency of ROI visits.
Visualization
The project comprises features that allow the plotting of data and ROIs, thus providing valuable insights into the animal's movements and behavior patterns over time. Please note that certain blocks of code use a paired-body part system and have constraints on the minimum number of frames that the animal must be present inside/outside the ROI before entry/exit can be counted.
Customization
Users can modify the body parts, ROIs, and other parameters (e.g., debounce_frames and body_part_pairs) to fit their research needs.
Owner
- Name: Farhan
- Login: farhanaugustine
- Kind: user
- Location: Maryland
- Company: University of Maryland Baltimore County
- Website: https://www.farhanaugustine.com/
- Repositories: 1
- Profile: https://github.com/farhanaugustine
Citation (CITATION.CFF)
cff-version: 1.0.0 message: "If you use this software, please cite it as below." authors: - family-names: "Augustine" given-names: "Farhan" orcid: "https://orcid.org/0000-0002-8348-6039" title: "Kinetic Analysis System for DeepLabCut (KAS-DLC)" version: 0.1.0 doi: 10.5281/zenodo.10867106 date-released: 2024-03-24 url: "https://github.com/farhanaugustine/Multi-ROI-Analysis-with-DeepLabCut-CSV-Outputs"