top of page

The Promise of Artificial Intelligence for Genomic Medicine

By Arushi Neravetla



The path of exploration for researching artificial intelligence with genomics has an extensive data field that compromises computational approaches of generated gene data, coupling it with biological and clinical testings. From analyzing these datasets, it brings an opportunity to study the machinery that generates people’s understanding of genetics in relation to certain disease-causing variants. Scientists carefully study every stage of genomic data by testing artificial intelligence, thereby facilitating discoveries such as cancer evolvement, examining microbiomes, and collective genetic material consisting of bacteria, fungi, protozoa, and viruses residing in the human body.


Furthermore, relying on artificial intelligence in genomic medicine follows the disciplines of molecular biology, biochemistry, and applied mathematics with concepts of computer science. For example, researchers are venturing into solutions for neurodegenerative and rare diseases, among a vast range of pathologies that have no cure. Around the world, the crucial necessity of artificial intelligence is being adapted in hospitals, tailoring fresh therapeutics for a patient’s prognosis [1]. Predominantly, genomic medicine also studies a new paradigm in precision medicine, selected by doctors based on the patient’s genetic understanding of the disease. Finally, proteomics, the study of protein networks, is a domain that benefits various genome projects conducted by researchers in studying unknown diseases [2].


To elaborate, scientists also use a method called phenotype prediction, which prospectively aids in analyzing the observable individual traits, becoming an important discipline in drug discovery and precision medicine. Using phenotype distinction, doctors are able to find a set of genes that apply to a particular phenotype disease. As research on artificial intelligence began to grow, the US National Research Council in 2021 developed a comprehensive plan for a new taxonomy for human diseases, integrating molecular, environmental, and phenotype data [4].


Thanks to the advances in mathematical computation, many researchers are developing robust data analysis for approaching difficult pathological issues. For example, a renal biopsy, which is a medical procedure, removes a small piece of the kidney and can provide a significant advantage in understanding the specific tissues or substructures located in the biopsy samples, like glomeruli, a cluster of nerve endings and blood vessels where waste products are filtered [4]. Another example is resistance arterioles, which are important determinants of cardiovascular physiology and obtained through biopsy. Resistance arterioles enable physicians and scientists to collect and process the tissues for intended analysis.


As further investigation with artificial intelligence for genomic medicine develops, researchers are learning to recognize the locations of genetic strands in the DNA and RNA sequences [2]. In general, if a machine can be trained to recognize the compilation of algorithms, it can train to split genes and enhance or position the nucleosomes, which is a structural unit of DNA packaging in eukaryotes. Today, researchers are focusing on the subset of heterogeneous data and statistical concepts, such as the calibration of likelihood estimates for demographic analysis [3]. The rise of artificial intelligence will bring in more demand and change the future of the medical field, advancing into the world of genomics.


References:

  1. “Genomics and Artificial Intelligence – a Good Match?” PHG Foundation, www.phgfoundation.org/blog/genomics-and-artificial-intelligence.

  2. Eguchi, Akiko, et al. “Identification of Actin Network Proteins, Talin-1 and Filamin-A, in Circulating Extracellular Vesicles as Blood Biomarkers for Human Myalgic Encephalomyelitis/Chronic Fatigue Syndrome.” Brain, Behavior, and Immunity, U.S. National Library of Medicine, Feb. 2020, www.ncbi.nlm.nih.gov/pmc/articles/PMC7010541.

  3. Noble, William. “Machine Technology in Genomics.” Https://Alkesgroup.broadinstitute.org/HEATHER/Libbrecht.pdf.

  4. Williams, Anna Marie, et al. “Artificial Intelligence, Physiological Genomics, and Precision Medicine.” Physiological Genomics, 5 Apr. 2018, journals.physiology.org/doi/full/10.1152/physiolgenomics.00119.2017.

Recent Posts

See All

Comments


Commenting has been turned off.
bottom of page