Dr. Argenis A. Arriojas Maldonado
Position: Postdoctoral Fellow, Center for Personalized Cancer Therapy
Role: Computational Biologist
Education:
- Ph.D. in Computational Sciences, University of Massachusetts Boston, 2022
- M.S. in Physics, Simón Bolívar University, 2014
- B.S. in Physics, Simón Bolívar University, 2010
Research Interests:
- Bioinformatics and computational biology
- Bayesian inference and statistical modeling
- Gene regulatory networks
- Machine learning and computer vision
- Semantic image segmentation and analysis
- Reinforcement learning
- Stochastic models of gene expression
Email: [email protected]
Links: LinkedIn | ORCID | GitHub | Google Scholar
Biography
Dr. Argenis Arriojas Maldonado is a Postdoctoral Fellow at the Center for Personalized Cancer Therapy, University of Massachusetts Boston. With a background in physics and computational sciences, his research focuses on developing computational methods and tools for analyzing complex biological data, particularly in the fields of gene regulation, single-cell genomics, and parasitology. His interdisciplinary expertise spans machine learning, Bayesian inference, and mathematical modeling of biological systems.
Research Focus
Dr. Arriojas Maldonado develops innovative computational approaches to analyze multi-omics data and model biological systems. His current research areas include:
- Time course analysis in single-cell RNA and ATAC-seq datasets
- Visualization tools for parasite atlases
- Automated data analysis pipelines for cut-and-run, scRNA, scATAC, and single-cell multi-omics
- Deep learning models for image segmentation of cellular structures
- Bayesian inference models for transcription factor activity
- Stochastic modeling of gene expression regulation
Current Projects
Cell Flow: Interactive Analysis of Single-Cell Omics Data
Developing interactive tools for cell density and trajectory analysis of single-cell omics data, with applications in parasite biology research.
Computational Analysis of Transcriptional Regulation
Working on integrated analysis of CUT&RUN and single-cell knockdown data to reveal hierarchical gene regulation in Toxoplasma gondii.
AI-Enabled Analysis of Mitochondrial Morphology
Developing automated analysis pipelines to assess the impact of chemotherapy on mitochondrial morphology in triple negative breast cancer using transmission electron micrographs.
Selected Publications
-
Lou J, Rezvani Y, Arriojas A, Wu Y, Shankar N, Degras D, et al. (2024). "Single cell expression and chromatin accessibility of the Toxoplasma gondii lytic cycle identifies AP2XII-8 as an essential ribosome regulon driver." Nature Communications, 15(1):7419.
-
Arriojas A, Patalano S, Macoska J, Zarringhalam K (2023). "A Bayesian noisy logic model for inference of transcription factor activity from single cell and bulk transcriptomic data." NAR Genomics and Bioinformatics, 5(4):lqad106.
-
Arriojas A, Adamczyk J, Tiomkin S, Kulkarni RV (2023). "Bayesian inference approach for entropy regularized reinforcement learning with stochastic dynamics." In: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR, 99-109.
-
Arriojas A, Adamczyk J, Tiomkin S, Kulkarni RV (2023). "Entropy regularized reinforcement learning using large deviation theory." Physical Review Research, 5(2):023085.
-
Rezvani Y, Keroack CD, Elsworth B, Arriojas A, Gubbels MJ, Duraisingh MT, et al. (2022). "Comparative single-cell transcriptional atlases of Babesia species reveal conserved and species-specific expression profiles." PLOS Biology, 20(9):e3001816.
Software and Resources
- T. gondii Single Cell Atlas Web App
- Babesia Single Cell Atlas WebApp
- NLBayes WebApp
- NLBayes R Package
- NLBayes Python Package
Honors and Awards
- Oracle Doctoral Research Fellowship, College of Science and Mathematics, UMass Boston (Fall 2019, Fall 2020, Fall 2021)
- U54 Program Trainee, UMass Boston Dana-Farber/Harvard Cancer Center U54 Partnership Graduate Research Education Program (2018)