Year: 2024
Type: conference-paper
Abstract: The amount of genetic data that can be analysed has grown by a factor of ten because genome sequencing methods are improving so quickly. However, it is still hard to find genetic diseases in big amounts of genome data because the data is so complicated and there is so much of it. AI-powered tests, especially those that use machine learning (ML) and deep learning (DL) methods, look like a good way to deal with this problem. AI can successfully look at genome patterns to find genetic changes linked to different genetic diseases by using complex algorithms. Large genome datasets with annotations can be used to teach these models how to find trends and changes in the sequence that could mean a genetic disease, a rare mutation, or a higher risk of getting certain conditions. Using AI in genetic tests has several major benefits: it improves the accuracy of the diagnosis, cuts down on human mistake, speeds up the analysis process, and makes it possible for personalised medicine by adapting treatments to each person's genetic make-up. AI models like convolutional neural networks (decision tree), recurrent neural networks (RNNs), and support vector machines (SVMs) have also shown a lot of promise in finding rare genetic variants that may not be picked up by traditional testing methods. This essay looks at how combining AI technologies with genome sequencing could change the way genetic diseases are found, leading to earlier diagnoses and better treatment plans. The improvement and creation of AI-based diagnostic tools should not only make it easier to find genetic disorders, but it should also help the field of precision medicine by making genetic testing faster, more accurate, and easier for more people to access.
Authors: Shekhar Kumbhar, Monali Gulhane, K. Gavhale, Sushil Bhise, Abhijeet Nashte, Shikha Gautam
Language: English
Topic: Genomics and Rare Diseases
Subfield: Genetics
Domain: Life Sciences
Open Access status: hybrid
OpenAlex ID: W4413915545