Digitization and artificial intelligence (AI) have profoundly  revolutionized the biotech industry, transporting scientists beyond the  lab into a new era of computationally-driven discovery. By automating  repetitive tasks in drug research and manufacturing, enabling the  analysis of massive datasets, and driving the production of highly  sophistocated technologies, AI has become the cornerstone of modern  biotechnology. The convergence of biology with computational science is  not simply a technical implementation- it is a catalyst for monumental  advancement: streamlined drug manufacturing, accelerated scientific  breakthroughs, and a healthcare system capable of delivering earlier,  more accurate diagnoses alongside more effective treatments. By  embracing an interdisciplinary approach early on in my studies at  Northeastern, I positioned myself to contribute meaningfully to the next  generation of biotech innovations, where the synergy of biology, programming, and AI/ML is not optional, but essential.

As the biotech program does not traditionally offer courses on  programming, machine learning, artificial intelligence, or  bioinformatics, I chose to design my own genomic-bioinformatics  specialization as a supplement to my master's. However, since I was  required to complete my core curriculum prior to taking courses  towards my  specialization, I could not enroll in computer science  courses at Northeastern until Spring 2025. Therefore, I took the  initiative to engage in independent learning courses and seminars  from  LinkedIn, Coursera, Simplilearn, Rosalind Franklin, Oxford  Academic,  etc, to enhance my statistical analysis skills, learn to program, and develop an algorithmic mindset for approaching  biological challenges. I also had the opportunity to learn  about AI and  ML through a three-seminar series offered by Northeastern's Koury  College of Computer Sciences, for which you can view my badges of  accomplishment. 

 Some of the skills and concepts I have learned include: using a high  performance computing (HPC) cluster (Explorer) and Slurm to run  quality control steps such as trimming (Trimmomatic), deduping  (BBMap toolkit-dedupe), decontamination (BBMap Toolkit-bbduk)  FastQC, and MultiQC analysis on large genomic datasets, proficiency in  Python, R, Bash, and PHP, designing multi-module applications, building, training, and testing statistical and algorithmic models such as HMM, phylogenetic trees, KNN & clustering, dynamic  programming, neighbor joining & UPGMA, Bayesian Networks, Needleman-Wunsch & Smith-Waterman, Multiple Sequence Alignment, Position Weight Matrices, maximum likelihoods, De Bruijn graphs, Viterbi, classification models & gene prediction, forecasting, linear regression & OLS, random forests, gradient boosting models,  

In this section, you will find a collection of programs, statistical  investigations, and and algorithmic modeling reports from assignments  and projects I have completed. Important to note is that while not all  this work was completed at  Northeastern University, I did complete it  all while in pursuit of my master's. This collection demonstrates my  proficiency in and successful integration of computational methods and  developing an algorithmic mindset.