https://github.com/kuleshov-group/genomics-lrb-viztool

Visualization of results on Genomics Long-Range Benchmark by annotations

https://github.com/kuleshov-group/genomics-lrb-viztool

Science Score: 21.0%

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

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
    Organization kuleshov-group has institutional domain (www.cs.cornell.edu)
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.4%) to scientific vocabulary
Last synced: 4 months ago · JSON representation

Repository

Visualization of results on Genomics Long-Range Benchmark by annotations

Basic Info
  • Host: GitHub
  • Owner: kuleshov-group
  • Language: Python
  • Default Branch: main
  • Size: 7.07 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

Analyzing results of Genomics LRB Benchmarking

Use the notebook lrb_results_analysis.ipynb to analyze results of the initial model benchmarking; slice results by distances to transcription start sites (TSS) and different annotations (e.g., promoter, enhancer, intron/exon, etc.).

Getting started

Step 1: Clone this repository: bash git clone git@github.com:kuleshov-group/genomics-lrb-viztool.git cd genomics-lrb-viztool

Step 2: Create conda env and install requirements: bash conda create -n lrb_env python=3.10 conda activate lrb_env pip install -r requirements.txt

Step 3: Download and unzip results files from the HF dataset: bash wget -O results_with_annotations.zip https://huggingface.co/datasets/InstaDeepAI/genomics-long-range-benchmark/resolve/main/results_with_annotations.zip?download=true unzip results_with_annotations.zip

Start the notebook server and use this notebook lrb_results_analysis.ipynb: bash jupyter notebook Run all cells. Use the widgets to analyze different tasks by various splits. notebook-usage

Owner

  • Name: Kuleshov Group @ Cornell Tech
  • Login: kuleshov-group
  • Kind: organization

Research group at Cornell focused on machine learning, generative models, AI for science

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Dependencies

requirements.txt pypi
  • gdown *
  • ipdb *
  • ipython *
  • ipywidgets *
  • matplotlib *
  • notebook *
  • numpy *
  • pandas *
  • scikit-learn *
  • seaborn *
  • tqdm *