Computational Biology: An Introduction

In recent years, Artificial Intelligence (AI) has been all the craze. (Check out my blog post summarizing AI here: https://www.lavinthelab.com/post/what-is-ai) Though AI has long been used by companies as ubiquitous as YouTube, Amazon, and Facebook, many people would agree OpenAI’s LLM architectures are what made AI a household term, and popularized AI to every generation.

What a lot of people don’t see, however, is the application of AI and ML beyond a chatbot. To help bring to light the ways AI can positively revolutionize day-to-day life, I’m starting the AOAI series on my blog, also known as the applications of artificial intelligence series. In particular, I’ll focus on my two fields of interest: bioengineering and biomaterials engineering. This article dives deeper into the former.

Bioengineering is a field in which engineering techniques are combined with biological principles to create new advancements in biology and medicine. Bioengineering is often used as a synonym for genetic engineering and experimental biology lab work, but it encompasses many subfields, my favorite of which (and most would argue -- the quickest growing of which) is computational biology.

Computational biology is a domain of study in which mathematical models and computational methods are applied to learn more about biology. Comp-bio algorithms have a diverse range: they can be as simple as my first ML algorithm (a neural network that diagnoses an eye illness) to more complex projects, like sequencing the entirety of the human genome or using genomic and proteomic databases to identify novel biomarkers for complex illnesses.

Author’s note: While my first project of diagnosing an illness is a lot simpler than more comp-bio algorithms used in the real world, it paved the way for me to understand many essential components of computational biology and engineering. (I advise everyone to create, or at least study a computational algorithm, like CNNs or GANs, as they truly are the gateway to computational biology! They may seem low-level to study if you want to go directly into computational biology, but the logic and math used in these ML algorithms paves the way for many essential comp-bio topics).

Computational biology has had greatly accelerated medicinal research in the past. Computer-aided drug design (CADD) has led to the discovery of more than 70 approved drugs, ML has been used for retracing the “tree of life” with computational phylogenetics, and generative AI/ML techniques are being extensively researched in a collaborative space to create artifical organs -- such as an artificial pancreas that will automatically control glucose levels of diabetes patients. 

Of course, all of these medicinal revolutions are only possible if society integrates biology with AI & ML. I hope this article gave some insight into why studying CS & ML is essential -- not just for computational advancements -- but for the health of our entire world. 

In my next blog post, I’ll talk about why AI and ML are not going to eliminate jobs or replace humans (at least for a long while). Thank you for reading, and I hope you learned something new about computational biology.