Aliro is an easy-to-use data science assistant. It allows researchers without machine learning or coding expertise to run supervised machine learning analysis through a clean web interface. It provides results visualization and reproducible scripts so that the analysis can be taken anywhere. And, it has an AI assistant that can choose the analysis to run for you. Dataset profiles are generated and added to a knowledgebase as experiments are run, and the AI assistant learns from this to give more informed recommendations as it is used. Aliro comes with an initial knowledgebase generated from the PMLB benchmark suite.
Browse the repo:
Aliro is actively developed by the Center for AI Research and Education (CAIRE) in the Department of Computational Biomedicine at Cedars-Sinai Medical Center in Los Angeles, California, USA.
Contributors include Hyunjun Choi, Miguel Hernandez, Nick Matsumoto, Jay Moran, Paul Wang, and Jason Moore (PI).
An up-to-date paper describing AI methodology is available in Bioinformatics and arxiv. Here's the biblatex:
@article{pennai_2020,
title = {Evaluating recommender systems for {AI}-driven biomedical informatics},
url = {https://doi.org/10.1093/bioinformatics/btaa698},
journaltitle = {Bioinformatics},
doi = {10.1093/bioinformatics/btaa698},
year = {2020},
author = {La Cava, William and Williams, Heather and Fu, Weixuan and Vitale, Steve and Srivatsan, Durga and Moore, Jason H.},
eprinttype = {arxiv},
eprint = {1905.09205},
keywords = {Computer Science - Machine Learning, Computer Science - Information Retrieval},
}
You can also find our original position paper on arxiv.