Artificial Intelligence, Machine Learning, and Genomics PDF

Artificial Intelligence, Machine Learning and Genomics The Big Picture The genomics field continues to expand the use of computational methods such as artificial intelligence and machine learning to improve our understanding of hidden patterns in large and compl...

Artificial Intelligence, Machine Learning and Genomics The Big Picture The genomics field continues to expand the use of computational methods such as artificial intelligence and machine learning to improve our understanding of hidden patterns in large and complex genomics data sets from basic and clinical research. What are machine learning and deep learning? ▪ Machine learning (ML) and deep learning are fields of study frequently mentioned in the context of AI. Both kinds of learning are subfields of AI. ▪ Machine learning is a process by which machines can be given the capability to learn about a given dataset without being explicitly programmed on what to learn. ▪ Machines can usually learn in either a supervised or unsupervised manner. ▪ Under supervised learning, scientists provide machines with separate training and test data sets. ▪ The training data has defined categories (e.g., people with coronary heart disease and those without) that the machine can use to infer hidden qualities of the data and distinguish the categories from each other. ▪ It is then able to use this knowledge to work on the test data and make informed predictions (e.g., which people in a population are likely to develop coronary heart disease). ▪ In an unsupervised learning setting, machines can recognize patterns in large datasets and make predictions about the real world without requiring any additional help from humans. ▪ When machines can learn in an unsupervised manner, they are considered to be learning “deeply.” Deep learning is a relatively modern technique used to implement machine learning. 1 ▪ A deep learning algorithm takes a dataset and finds patterns and critical information by imitating how a human brain’s neurons interact with each other. The algorithms are artificial neural networks — a computing system that simulates the brain’s ability to weigh the importance of some data versus others, and handle bias. 2 Human Genome ▪ The human genome is the complete set of DNA in a human, containing all the genetic information necessary for growth, development, and functioning. ▪ The genome includes over 20,000 genes and around 3 billion base pairs of DNA. ▪ Each human cell (except red blood cells) has a copy of this entire genome, which acts as a biological blueprint. Structure of the Genome ▪ The human genome is organized into 23 pairs of chromosomes, which carry our DNA. ▪ DNA itself is a double-helix structure composed of four nitrogenous bases: adenine (A), thymine (T), cytosine (C), and guanine (G). ▪ These bases pair specifically (A with T, and C with G), creating the genetic code, or sequence, that makes up our genes. Function and Importance of Genes in the Genome ▪ Genes are sections of DNA that provide instructions for producing proteins, which are essential molecules for most body functions. ▪ Each gene has a specific location on a chromosome and plays a particular role in determining traits, such as eye color, height, and susceptibility to diseases. ▪ The majority of the human genome is non-coding, meaning it does not code for proteins. ▪ However, these regions still play essential roles in gene regulation and chromosome structure. 3  Functions of the Genome and Its Role in Heredity 1. Storage and Transmission of Information: The genome holds genetic information and passes it from generation to generation. 2. Guiding Growth and Development: Genes in the genome direct the synthesis of proteins and enzymes that regulate all cellular functions. 3. Adapting to the Environment: Some genes evolve over time, allowing organisms to adapt to their environments—a process known as evolution. The Human Genome Project (HGP) ▪ The Human Genome Project was an international effort completed in 2003 to map the entire human genome. ▪ It has had a profound impact on medical and biological research by providing insights into the genetic basis of diseases, human evolution, and individual genetic variation. Key Outcomes of the HGP: ▪ Understanding genetic diseases: Scientists have identified many genes linked to disorders such as cystic fibrosis and certain cancers. ▪ Personalized medicine: Genomic data from the HGP has helped shape treatments tailored to an individual’s genetic makeup. Significance of Studying the Human Genome ▪ Medical Research: Genomic research has advanced our understanding of genetic diseases, helping in diagnosis and treatment. ▪ Evolutionary Biology: Studying the genome provides insights into human evolution and our relationship with other species. 4  ▪ Personalized Medicine: With knowledge of a patient’s genome, doctors can create customized treatment plans that are more effective and have fewer side effects. Modern Genomic Technologies ▪ Gene Sequencing: Advanced sequencing technologies now allow scientists to decode DNA quickly and accurately, opening doors for new genetic discoveries. ▪ Gene Editing (CRISPR): This tool allows scientists to modify specific genes precisely, showing promise in treating genetic disorders. Challenges and Future of Genomic Research ▪ Ethical and Privacy Concerns: Genomic data is highly personal and sensitive, raising issues about its use and storage. 5 Artificial Intelligence (AI) and genomics are closely related today, with AI accelerating our ability to analyze and understand the genome in ways previously unimaginable. How Does AI Contribute to Genome Research? 1- Big Data Analysis ▪ The human genome contains approximately 3 billion base pairs, which represents a vast amount of data. ▪ AI, especially machine learning and deep learning techniques, is used to process this complex data. ▪ For instance, machine learning algorithms can identify patterns within genomic data, helping to pinpoint genes associated with specific diseases. 2- Personalized Diagnosis and Treatment ▪ AI aids in analyzing individual genomes, contributing to the early diagnosis of genetic or cancer-related diseases. ▪ Precision medicine, a field advancing through AI, relies on genomic data to create personalized treatment plans based on a patient’s genetic makeup. 3- Drug Discovery ▪ AI techniques model target proteins and predict drug effects based on genomic data. ▪ This reduces the time and cost of drug development and increases the success rate of new drugs, as they are tested against genes relevant to specific cells and diseases. 6 Why is there a need for AI/ML in genomics? As of 2021, 20 years have passed since the landmark completion of the draft human genome sequence. This milestone has led to the generation of an extraordinary amount of genomic data. Estimates predict that genomics research will generate between 2 and 40 exabytes of data within the next decade. DNA sequencing and other biological techniques will continue to increase the number and complexity of such data sets. This is why genomics researchers need AI/ML-based computational tools that can handle, extract and interpret the valuable information hidden within this large trove of data. 7  What are some ways in which AI/ML are being used in genomics? Although the use of AI/ML tools in genomics is still at an early stage, researchers have already benefited from developing programs that assist in specific ways. Some examples include: Examining people’s faces with facial analysis AI programs to accurately identify genetic disorders. Using machine learning techniques to identify the primary kind of cancer from a liquid biopsy. Predicting how a certain kind of cancer will progress in a patient. Identifying disease-causing genomic variants compared to benign variants using machine learning. Using deep learning to improve the function of gene editing tools such as CRISPR. These are just a few ways by which AI/ML methods are helping predict and identify hidden patterns in genomic data. Scientists are also using AI/ML to predict future variations in the genomes of the influenza and SARS-CoV-2 viruses to assist public health efforts. 8