Introduction to AI in Biotechnology and Biomedical Engineering

1. Introduction

Artificial Intelligence (AI) is a field of computer science that works towards using machines/computer programs to perform tasks that would normally require human intelligence, some of these tasks may include prediction, problem-solving, reasoning, and inferring (Google Cloud, 2023). The field of AI can be divided into two subfields, Machine Learning (something that learns to predict outcomes based on the data provided, more data provided usually equates to more accurate predictions or outputs, does not need to explicitly coded) and Deep Learning (a subset of machine learning that does not require much human intervention in feature extraction*). Since 2019, various studies have been published on the implementation/use of AI in the fields of biomedicine and biotechnology.

Some the most notable uses are protein structure prediction (AlphaFold2) and the prediction of disease-causing genetic mutations in primates (PrimateAI-3D). AlphaFold2 is a machine learning model developed by Google DeepMind to predict highly accurate protein structures based on a given amino acid sequence. PrimateAI-3D was developed by Illumina and was trained on genetic data from 703 individuals across 211 species, the model was then used to identify correlation between PrimateAI-3D scores and real-world data. PrimateAI-3D was used to score LDLR gene variants, the scores were then compared to individuals with low LDL cholesterol levels, lower the score equated with low LDL cholesterol levels. Machine Learning models have also found use in diagnosis, the study showed that it is possible to get accurate diagnosis from limited amounts of data, if the data is handled and processed properly. The model trained on the data obtained from patients who had already been diagnosed with the Sars-CoV-2 virus had a maximum accuracy of 96.99%. Deep learning models have been trained on CT scans to detect tumors in liver the liver and predicting the origin of liver metastasis. A study has also been published on detecting and distinguishing focal liver lesions. Overall, AI can be applied in predicting many things, given that accurate and sufficient data is provided, and these are what is known, there are many more applications that might come up over time.