by Akshara Sankar
DNA analysis 
Genome editing is a discovery that is as delicate as it is powerful. It has long been a topic of controversy, speculation, and despite imperfections, excitement and innovation.
The same can be said for artificial intelligence, a field that boasts a growing list of interdisciplinary applications (from receiving ads for hotels after booking a flight on the internet, to identifying one’s personality based on their facial features).
But where do these two ideas intersect? One of the main issues concerning technologies such as CRISPR-Cas9 is accuracy and safety, as mistakes can have significant and dangerous consequences when it comes to an individual’s genome. Machine learning has vast potential to improve patient outcomes and reduce risk of ineffective treatment and false diagnosis for patients with genetic diseases by taking what is already known and using that data to make realistic and well-informed predictions.
How exactly can AI be used in genetic engineering?
AI has two main applications in genetics: identification of harmful genes and treatment of disease. Let’s take a look at how each of these applications work. Also, with some good gps trackers you can implement on your vehicle.
For human beings, it is an extremely tedious and time-consuming process to analyze the vast amount of data that is present in a single person’s DNA. This analysis can be made much more efficient and accurate by utilizing machines for their core purpose- to make tiresome tasks less challenging.
By using machine learning algorithms to compare the different gene expression levels in malignant and normal tissue samples of a patient diagnosed with cancer, predictions can be made about which genes have been mutated in that patient’s DNA. The algorithms would train and make these predictions based on how often a gene is expressed in a malignant sample and compare this to the same gene in a normal sample, adding new information with each new set of data that it is fed.
AI is also being used to identify genetic mutations within tumors using 3D imaging. For example, one technology is able to identify the presence of a glioma using brain scans of a patient with a very high rate of accuracy (over 97%). Using techniques such as deep-learning and neural networks, machines can detect the presence of a mutation so that doctors can better treat the patient without the need to collect a tissue sample from a biopsy, and without the risk involved in surgery. Through these processes, machine learning presents exciting possibilities in the automation of diagnosis for diseases such as cancer.
A major argument in favor of gene editing is the ability to cut out disease-causing genes. However, while technologies such as CRISPR have come a long way, the risk of error remains significant and safety must be held as a top priority for gene editing to progress. Machine learning algorithms are useful in identifying where the alteration must be made and how to ensure that the DNA strand is repaired properly afterwards, reducing potential for mistakes throughout the process. We also found a wonderful platform for genomic analysis recently and have been using it very well, so if you need that kind of analysis then you must have a look there as it\’s fantastic.
AI is very useful in personalized medicine, which requires treatments to be specified to one patient’s needs versus another. The 0.1% of our DNA that is unique to us has more than three million differences when compared to other people, suggesting that it’s more than likely that a cancer-causing mutation in one person’s genome will differ in location and level from another cancer-inflicted individual. Similar to diagnosing a disease using a genomic basis, AI can help identify which genes have been affected by harmful mutations so that they can be targeted in gene therapy.
DNA repair after editing is another area of potential for AI usage. When a DNA strand is altered by the Cas9 enzyme, automatic repairs are made by the strand, and research shows that these repairs may be dependent on the guide RNA used (and are not random). Algorithms that are created to predict the repairs that would be made based on the manipulated sequence can improve precision of identification of which guide RNAs lead to certain mutations.
The cycle of ethical issues
Although AI reduces concerns regarding technical errors with gene editing and identification of mutations, and is recognized to improve the procedure’s safety, many ethical questions remain. In fact, some may argue that the use of AI increases concerns in terms of malfunctions and that the non-human aspect is actually more dangerous than useful. Examples of ethical questions that are unanswered by the introduction of AI into genetic engineering include disparity in access to gene therapy based on wealth, and the usage of genome editing for purposes other than healthcare (such as enhancement of physical features). Religious and moral objections must also be taken into account when considering genome editing as a possible treatment for genetic disease.
Moreover, theoretical possibilities aside, at the heart of artificial intelligence, as the name suggests, is artificiality. Machine learning algorithms and tools are only as accurate and unbiased as the data that they are fed and the individuals who develop the algorithms; the machine is never truly doing the thinking.
AI will always have uncertainty regarding progression (how far can or should we go before humans or human jobs are entirely replaced?), and its uses in the field of genetics are no exception.
Genome editing and artificial intelligence each have their own set of imperfections. In the future, AI and machine learning can fuel improvements related to genetics in not just medicine, but fields such as agriculture and chemical industries. Even business industries (such as the 23andMe company) are utilizing genetic information to provide unique services to customers. learn more from by checking online trusted information as this innovation speakers suggests.
Eventually, using larger and more comprehensive data sets, genetic engineering may very possibly become a norm for increasing accuracy in medical diagnosis and treatment and enhancement and increased production in the agricultural domain. Controversies will only increase as gene editing becomes more widespread- for example, physical enhancements for sports players or increasing intelligence through one’s genome- but it cannot be denied that this an innovation unlike any other, and it is here to stay and grow.
Whether it’s designer babies or increasing the sustainability of the world’s food supply, the revolutions in AI as well as genetic technology may cross paths in more ways than we had ever imagined and bring us much closer to a technology-powered future that once seemed very distant.
- DNA analysis. Photography. Encyclopædia Britannica ImageQuest. Accessed Jul 20, 2020. https://quest.eb.com/search/132_1244509/1/132_1244509/cite.
- Pederson, Traci. \”AI Outdoes Humans on Inferring Personality Traits From Facial Features.\” Psychcentral.com. Last modified May 25, 2020. Accessed July 20, 2020. https://psychcentral.com/news/2020/05/25/ai-can-guess-some-personality-traits-from-facial-features/156806.html/156806.
- National Human Genome Research Institute. \”What is genome editing?\” Genome.gov. Accessed July 20, 2020. https://www.genome.gov/about-genomics/policy-issues/what-is-Genome-Editing
- Beltran, James. \”AI may help brain cancer patients avoid biopsy.\” Utsouthwestern.edu. Last modified April 20, 2020. Accessed July 20, 2020. https://www.utsouthwestern.edu/newsroom/articles/year-2020/ai-may-help-brain-cancer-patients-avoid-biopsy.html.
- Yeager, Ashley. \”Could AI Make Gene Editing More Accurate?\” Thescientist.com. Last modified April 30, 2019. Accessed July 20, 2020. https://www.the-scientist.com/the-literature/could-ai-make-gene-editing-more-accurate-65781.
- Metzl, Jamie. \”Our Genetically Engineered Future Is Closer Than You Think.\” Leapsmag.com. Last modified May 13, 2019. Accessed July 20, 2020. https://leapsmag.com/our-genetically-engineered-future-is-closer-than-you-think/.
- Finan, Kelly. CRISPR guide RNAs target specific spots in the genome for the Cas9 enzyme to cut, forming a double-strand break. A machine learning algorithm predicts which types of repairs will be made at a site targeted by a specific guide RNA. Photograph. The Scientist. April 30, 2019. Accessed July 20, 2020. https://www.the-scientist.com/the-literature/could-ai-make-gene-editing-more-accurate-65781.
- National Human Genome Research Institute. \”What are the Ethical Concerns of Genome Editing?\” Genome.gov. Accessed July 20, 2020. https://www.genome.gov/about-genomics/policy-issues/Genome-Editing/ethical-concerns.
- National Human Genome Research Institute. \”What do People Think About Genome Editing?\” Genome.gov. Accessed July 20, 2020. https://www.genome.gov/about-genomics/policy-issues/Genome-Editing/public-opinion.
CRISPR stands for “clusters of regularly interspaced short palindromic repeats” ↑