OncoMark is a deep learning tool designed to systematically quantify hallmark activity using transcriptomics data from routine tumor biopsies. Ideal for applications in oncology research, personalized medicine, and biomarker discovery.
Comprehensive documentation is available at:
OncoMark Documentation
Install OncoMark using pip:
pip install OncoMarkimport pandas as pd
from OncoMark import predict_hallmark_scores
# Load input data as a pandas DataFrame. Genes must be in column.
input_data = pd.read_csv('input_data.csv', index_col=0)
# Predict hallmark scores
predictions = predict_hallmark_scores(input_data)
# Display the predictions
predictionsOncoMark also provides a web server for easy interaction.
You can use the hosted web server directly:
We welcome suggestions! If you have any ideas or feedback to improve OncoMark, please reach out to Shreyansh Priyadarshi.
@article {Priyadarshi2025.02.03.636380,
author = {Priyadarshi, Shreyansh and Mazumder, Camellia and Neekhra, Bhavesh and Biswas, Sayan and Chowdhury, Debojyoti and Gupta, Debayan and Haldar, Shubhasis},
title = {Robust Prediction of Patient-Specific Cancer Hallmarks Using Neural Multi-Task Learning: a model development and validation study},
elocation-id = {2025.02.03.636380},
year = {2025},
doi = {10.1101/2025.02.03.636380},
publisher = {Cold Spring Harbor Laboratory},
URL = {https://www.biorxiv.org/content/early/2025/02/08/2025.02.03.636380},
eprint = {https://www.biorxiv.org/content/early/2025/02/08/2025.02.03.636380.full.pdf},
journal = {bioRxiv}
}