- Spearheaded the launch of Nucleate Arizona, a pivotal non-profit initiative designed to catalyze biotech entrepreneurship among students and professionals.- Build and maintain strong relationships with key stakeholders, including investors, industry experts, and academic institutions, to support Nucleate's mission and its members' ventures.- Orchestrate high-impact events that bring together industry leaders, investors, and academic pioneers to stimulate collaboration and innovation in the biotech sector.- Champion fundraising efforts, successfully securing essential funding to sustain and grow the organization's reach and impact.

- Pioneered a novel biomarker discovery approach using unsupervised feature learning from scRNA-seq data, streamlining the identification of key indicators for neuroimmune states.- Led a multidisciplinary team in a groundbreaking project mapping neuroimmune responses post-brain injury, employing spatial transcriptomics and high-resolution MERFISH microscopy.- Synthesized and communicated complex research findings to the scientific community through presentations at conferences and publications in top-tier journals.

- Led a team of 2 undergraduate students in analyzing the Allen Brain Atlas (ABA) data and collaborated on GitHub- Organized, imputed, and feature engineered 20,000 gene expression images of ABA data using Pandas library in CSV format- Reduced dimensionality of the data using these Unsupervised Feature Learning methods: o PCA, KernelPCA (with polynomial, RBF, and sigmoid kernels), SparsePCA, and ICA o Dictionary Learning, NMF (including Graph-Regularized non-Negative matrix factorization), and Sparse Filtering o Implemented L1 and L2 sparsity objectives in Neural Nets in PyTorch- Identified Neuroanatomical regions in dimension-reduced data using such clustering techniques: o K-means, Agglomerative, DBSCAN, and OPTICS- Achieved 15% improvement in clustering accuracy (Mutual Information score) of the dimension reduced ABA data compared to the historical average

- Designed and developed a comprehensive pipeline for integrating, batch-correcting, and analyzing multiple transcriptomic datasets to identify novel biomarkers of infectious diseases and predict disease states.- Utilized advanced bioinformatics and machine learning tools and libraries, including Scanpy, Seurat, and SciKit-Learn, in Python and R programming languages, computed using AWS S3, EC2, and RSWB.- Collaborated with a multidisciplinary team to understand project requirements, tailor the pipeline to specific research objectives, document the pipeline development process, and ensure seamless adoption.

- Aggregated and prepared Radiomics data from brain MRI images, enabling machine learning analysis.- Developed and tuned Convolutional Neural Network models to segment Vestibular Schwannoma tumors in brain scans, achieving 5% higher accuracy than published models.

- Closely collaborated with 3 graduate students in Italy to compute Wall Shear Stress (WSS) from 4D-Flow MRI images of 100+ patients- Generated a mathematical model to combine 4D-Flow MRI data with Computational Fluid Dynamics (CFD)- Attained 10% furtherance in WSS accuracy and identified regions of high risk in the patients