https://github.com/armbrustlab/trophic-mode-ml
Accompanying code for 'The dynamic trophic architecture of open-ocean protist communities revealed through machine-guided metatranscriptomics.'
Science Score: 10.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.6%) to scientific vocabulary
Last synced: 10 months ago
·
JSON representation
Repository
Accompanying code for 'The dynamic trophic architecture of open-ocean protist communities revealed through machine-guided metatranscriptomics.'
Basic Info
- Host: GitHub
- Owner: armbrustlab
- License: mit
- Language: HTML
- Default Branch: main
- Size: 1.12 MB
Statistics
- Stars: 2
- Watchers: 5
- Forks: 0
- Open Issues: 0
- Releases: 0
Created over 5 years ago
· Last pushed over 4 years ago
https://github.com/armbrustlab/trophic-mode-ml/blob/main/
# Trophic mode ml Scripts for feature extraction, training, and model application. ## Contents - param_feature_selection: - Hyperparameter selection via gridsearch for the 3 classifiers compared in the manuscript. - Feature selection using Mean Decrease in Accuracy. - training_evaluation: - Script to perform cross-validation on resulting models. - model - CLI to make predictions using either XGBoost or Random Forest. ## Dependencies - Pandas - NumPy - Scikit-learn - XGBoost - Keras==2.3.1 - Tensorflow==2.0.0 Zenodo data repository for this work: https://zenodo.org/record/4425690 Link to paper: https://www.pnas.org/content/119/7/e2100916119
Owner
- Name: Armbrust Lab
- Login: armbrustlab
- Kind: organization
- Location: Seattle, WA
- Website: http://armbrustlab.ocean.washington.edu
- Repositories: 23
- Profile: https://github.com/armbrustlab
Biological Oceanography Lab at the University of Washington