In current times people think that machine learning is the panacea, a belief that is far from the truth. At panacea lab we aim to build machine learning, computer vision, and NLP methods that help to generate insights from multi-modal large-scale data sources. With applications to precision medicine, medical informatics, astroinformatics and other domains, our work addresses domain-specific problems with data science methods and practices. Additionally, we are fully invested in helping science reproducibility by releasing (when possible) open-source and publicly available datasets and tools to aid reproducibility efforts.
With the new challenges brought by the data deluge in all fields, we are open to collaborations. Contact us here.
Our lab at Georgia State University department of Computer Science is supported by: Department of Veterans Affairs (Grant 1 I01 HX002487-01), National Institute of Aging through Stanford Universitiy's Stanford Aging & Ethnogeriatrics Transdisciplinary Collaborative Center (SAGE) center (Grant 3P30AG059307-02S1), and an internal GSU Research Initiation grant
COVID-19 Twitter dataset with over 730 Million tweets for scientific research. Downloaded over 30K Times and over 220 stars on GitHub
Social Media Mining Toolkit (SMMT) a set of tool to facilitate the gathering and mining of social media data
R package for Automated PHenotype Routine for Observational Definition, Identification, Training and Evaluation (APHRODITE). Built the OHDSI collaborative.
R package for Mapping Between OHDSI Concept Identifiers to Unified Medical Language System (UMLS). Built for the OHDSI collaborative.
Provenance-centered dataset of drug-drug interactions.
A large-scale solar dynamics observatory image dataset for computer vision applications.
Introducing a Data Mining Framework for the Creation of Large-scale Content-based Image Retrieval Systems
For a other code and datasets visit the lab's github page.
For a full list of publications go here.
25 Park Place - Suite 752,
Atlanta, GA 30303