Pinned Loading

1. im_not_a_rapper im_not_a_rapper Public

   2025: Helper code for working with the UK Biobank RAP's DNAnexus cloud platform, performing genetic analyses, efficiently setting up an environment, and other miscellaneous code

   Python 2

2. Know2BIO Know2BIO Public

   Forked from Yijia-Xiao/Know2BIO

   2022-2024: A comprehensive multi-view and multi-modal biomedical knowledge graph for benchmarking graph learning. Includes ontology and instance views, sequences (natural language, molecules), and …

   Python

3. nl_to_sql_to_figure nl_to_sql_to_figure Public

   2025 - 2026: A pipeline that processes a natural language query, curates from an SQL database (In Progress), and should analyze the data per the user's request. Runs on transformer language models.

   Jupyter Notebook 1

4. caseolap_lift caseolap_lift Public

   Forked from CaseOLAP/caseolap_lift

   2022-2023: A multi-omics biomedical text-mining pipeline for extracting protein-disease associations + a knowledge graph prediciton pipeline to predict protein-disease associations. Leverages biolo…

   Python

5. knowledge_graph_of_text_mined_pubmed knowledge_graph_of_text_mined_pubmed Public

   2023: Creating knowledge graph embeddings on text-mined data to support exploratory characterization of proteins, oxidative stress, and cardiovascular disease.

   Python 1

6. classifying_pubmed_documents classifying_pubmed_documents Public

   2023: Pipeline to categorize PubMed articles via a multi-stage machine learning classifier (naive Bayes + fine-tuned language models); tied "SOTA" for cardiovascular disease use case compared to th…

   Python