BiodataAnalysisGroup/BioHackathon
Nov 2024 – Nov 2024
1 Month active
Languages Used
Jupyter NotebookPython
Technical Skills
AnndataBioinformaticsComputational biologyData AnalysisData VisualizationData visualization
astaburuaga-garcia
PROFILE
Astaburuaga-garcia
Developed an end-to-end scGen perturbation analysis workflow for LPS-stimulation across cell types in the BiodataAnalysisGroup/BioHackathon repository, focusing on single-cell RNA-seq analysis. The work encompassed data preprocessing, model training, prediction of stimulated cell states, and evaluation using metrics and visualizations. Implemented configurable data processing improvements, including PCA dimension constraints and log1p transformation options, leveraging Python, Jupyter Notebook, and libraries such as Scanpy and Pandas. Enhanced the evaluation framework with additional metrics and plots to assess prediction accuracy. Also addressed repository hygiene by refining ignore rules to prevent accidental artifact tracking, ensuring cleaner version control and project maintenance.
Overall Statistics
Feature vs Bugs
50%Features
Repository Contributions
6Total
Bugs
1
Commits
6
Features
1
Lines of code
4,677
Activity Months1
Your Network
6 peopleSame Organization
@charite.de2
Kyle KruegerMember
Oliver StolpeMember
Shared Repositories
4
Work History
November 2024
6 Commits • 1 Features
Nov 1, 2024Concise monthly summary for 2024-11 focused on delivering an end-to-end scGen perturbation analysis workflow for LPS-stimulation in BioHackathon, plus repository hygiene improvements. Highlights include end-to-end pipeline (preprocessing, model training, predictions of stimulated cell states, evaluation with metrics and visualizations) across existing cell types; targeted improvements for dimensionality handling and data transformation options; and a configuration maintenance effort to tighten ignore rules and prevent accidental artifact tracking.
6 Commits • 1 Features
Nov 1, 2024Concise monthly summary for 2024-11 focused on delivering an end-to-end scGen perturbation analysis workflow for LPS-stimulation in BioHackathon, plus repository hygiene improvements. Highlights include end-to-end pipeline (preprocessing, model training, predictions of stimulated cell states, evaluation with metrics and visualizations) across existing cell types; targeted improvements for dimensionality handling and data transformation options; and a configuration maintenance effort to tighten ignore rules and prevent accidental artifact tracking.
November 2024
Activity
Loading activity data...
Quality Metrics
Correctness78.4%
Maintainability78.4%
Architecture71.6%
Performance63.4%
AI Usage20.0%
Skills & Technologies
Programming Languages
Jupyter NotebookPython
Technical Skills
AnndataBioinformaticsComputational biologyData AnalysisData VisualizationData visualizationJupyter NotebookMachine LearningMachine learningMatplotlibPandasPertpyPerturbation analysisPythonPython programming
Repositories Contributed To
Overview of all repositories you've contributed to across your timeline