Research Projects

AutoMAxO

Summary:

AutoMAxO is a tool that automates the curation of the Medical Action Ontology (MAxO) database. Using PubMed-BERT and large language models, AutoMAxO extracts disease-treatment relationships from PubMed abstracts and integrates them into the MAxO database. Testing the tool on 21 rare diseases resulted in over 500 novel ontology entries, significantly enhancing the database's scope and usability.

Supervisors:

Prof. Peter N. Robinson, Dr. Justin Reese, Dr. Caufield Harry, Dr. Chriss Mungall

Affiliations:

Trinity College - CT, Jackson Laboratory for Genomic Medicine - CT, Lawrence Berkeley National Lab - CA.

Citation:

Niyonkuru, E., Caufield, J. H., Carmody, L. C., Gargano, M. A., Toro, S., Whetzel, P. L., Blau, H., Soto Gomez, M., Casiraghi, E., Chimirri, L., Reese, J. T., Valentini, G., Haendel, M. A., Mungall, C. J., & Robinson, P. N. (2025). Leveraging generative AI to assist biocuration of medical actions for rare disease. Bioinformatics Advances, 5(1), vbaf141. https://doi.org/10.1093/bioadv/vbaf141

Summary:

WordNet2Vec, a pipeline designed to improve biomedical concept embeddings. Using the WordNet library to standardize terminology, I processed over 30 million PubMed abstracts, achieving an 8% improvement in clustering accuracy for biomedical concepts.

Supervisors:

Prof. Peter N. Robinson, Dr. Hannah Blau

Affiliations:

Trinity College - CT, Jackson Laboratory for Genomic Medicine - CT

Citation:

Niyonkuru, E., Gomez, M. S., Casarighi, E., Antogiovanni, S., Blau, H., Reese, J. T., Valentini, G., & Robinson, P. N. (2025). Replacing non-biomedical concepts improves embedding of biomedical concepts. PloS one, 20(5), e0322498. https://doi.org/10.1371/journal.pone.0322498

WordNet2Vec

Summary:

This research presents a CNN-LSTM model to forecast short-term coronal hole activity using image and tabular data from NASA's Solar Dynamics Observatory. The model outperforms traditional methods (LSTM, GRU, ARIMA), reducing errors by up to 34%. This work addresses gaps in predictive modeling, aiding space weather forecasting and preparedness.

Supervisors:

Dr. Chandranil Chakraborttii

Affiliations:

Trinity College - CT, NASA Solar Dynamics Observatory.

Citation:

Alsolame, T., Aritra, B.D.S., Niyonkuru, E., Antogiovanni, S., Chakraborttii, C. (2025). Predicting Coronal Hole Activity: Key to Mitigating Space Weather Impacts. In: N. Ngatched, T.M., Woungang, I., Tapamo, JR., Viriri, S. (eds) Pan-African Artificial Intelligence and Smart Systems. PAAISS 2024. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 631. Springer, Cham. https://doi.org/10.1007/978-3-031-94442-0_13

Forecasting Coronal Hole Activity with CNN-LSTM Models

Other Research Projects

Chimirri, L., Caufield, J. H., Bridges, Y., Matentzoglu, N., Gargano, M., Cazalla, M., Chen, S., Danis, D., Dingemans, A. J., Gehle, P., Graefe, A. S. L., Gu, W., Ladewig, M. S., Lapunzina, P., Nevado, J., Niyonkuru, E., Ogishima, S., Seelow, D., Castaño, J. A. T., Turnovec, M., … Robinson, P. N. (2025). Consistent Performance of GPT-4o in Rare Disease Diagnosis Across Nine Languages and 4967 Cases. medRxiv : the preprint server for health sciences, 2025.02.26.25322769. https://doi.org/10.1101/2025.02.26.25322769

Education

Trinity College Hartford, CT

• BS in Computer Science Major & Entrepreneurship Minor

• Machine Learning Certificate

• Sept 2020 - May 2024

Bridge2Rwanda Leadership Academy Kigali, Rwanda

• Entrepreneurship, Leadership, Literature, Personal Development, Public Health, Psychopathology

• Nov 2018 - May 2020

College St Andre Kigali, Rwanda

• High school Diploma (Physics, Chemistry, and Biology)

• Jan 2013 - May 2018

University of California San Francisco (UCSF) San Francisco, CA

• Ph.D in Biological and Medical Informatics (Bioinformatics)

• Sept 2025 - June 2030

"Try to be a rainbow in someone's cloud." ~ Maya Angelou