AI Model TIGER Enables Predictive Control of RNA-Targeting CRISPR Tools
Researchers have developed an artificial intelligence model, TIGER, that predicts the on- and off-target activity of RNA-targeting CRISPR tools. This innovation, detailed in a study published in Nature Biotechnology, can accurately design guide RNAs, modulate gene expression, and is poised to drive advancements in CRISPR-based therapies.
Artificial Intelligence Predicts On- and Off-Target Activity of RNA-Targeting CRISPR Tools
Artificial intelligence can predict on- and off-target activity of CRISPR tools that target RNA instead of DNA, according to new research published in the journal Nature Biotechnology.
Combining Deep Learning and CRISPR Screens to Control Gene Expression
The study by researchers at New York University, Columbia Engineering, and the New York Genome Center combines a deep learning model with CRISPR screens to control the expression of human genes in different ways, such as flicking a light switch to shut them off completely or using a dimmer knob to partially turn down their activity. These precise gene controls could be used to develop new CRISPR-based therapies.
RNA-Targeting CRISPRs and Their Versatile Applications
RNA-targeting CRISPRs can be used in a wide range of applications, including RNA editing, knocking down RNA to block expression of a particular gene, and high-throughput screening to determine promising drug candidates. Researchers at NYU and the New York Genome Center created a platform for RNA-targeting CRISPR screens using Cas13 to better understand RNA regulation and to identify the function of non-coding RNAs.
Maximizing On-Target and Minimizing Off-Target Effects
A key goal of the study is to maximize the activity of RNA-targeting CRISPRs on the intended target RNA and minimize activity on other RNAs, which could have detrimental side effects for the cell. Off-target activity includes both mismatches between the guide and target RNA as well as insertion and deletion mutations.
TIGER Model: Accurate Predictions of On- and Off-Target Activity
The research team engineered the TIGER model, combining deep learning algorithms and laboratory tests, to accurately predict both on-target and off-target activity of RNA-targeting CRISPRs. The model outperforms previous designs and provides a valuable tool for the development of RNA-targeting CRISPR therapies.
Deep Learning in Genomics and Interpretable Machine Learning
Machine learning and deep learning techniques are proving valuable in genomics, leveraging large datasets generated by high-throughput experiments. The researchers used “interpretable machine learning” techniques to understand the reasons behind the TIGER model’s predictions, enhancing its effectiveness.
Precise Modulation of Gene Dosage and Therapeutic Applications
TIGER’s off-target predictions allow for the precise modulation of gene dosage, enabling partial inhibition of gene expression with mismatch guides. This has implications for diseases characterized by abnormal gene expression, such as Down syndrome, certain forms of schizophrenia, and cancer.
The Path to a New Generation of RNA-Targeting Therapies
By combining artificial intelligence with RNA-targeting CRISPR screens, the TIGER model’s predictions help avoid undesired off-target effects, driving the development of a new generation of RNA-targeting therapies. Collaboration between research teams paves the way for innovative cross-disciplinary approaches and opens up exciting opportunities in biomedicine.