Preprint
AI Safety & Alignment

Advancing genome editing with artificial intelligence: opportunities, challenges, and future directions

Shriniket Dixit, Anant Kumar, Kathiravan Srinivasan, P. M. Durai Raj Vincent, Nadesh Ramu Krishnan
January 8, 2024Frontiers in Bioengineering and Biotechnology120 citations
DOI

120

Citations

5

Influential Citations

Frontiers in Bioengineering and Biotechnology

Venue

2024

Year

Abstract

Clustered regularly interspaced short palindromic repeat (CRISPR)-based genome editing (GED) technologies have unlocked exciting possibilities for understanding genes and improving medical treatments. On the other hand, Artificial intelligence (AI) helps genome editing achieve more precision, efficiency, and affordability in tackling various diseases, like Sickle cell anemia or Thalassemia. AI models have been in use for designing guide RNAs (gRNAs) for CRISPR-Cas systems. Tools like DeepCRISPR, CRISTA, and DeepHF have the capability to predict optimal guide RNAs (gRNAs) for a specified target sequence. These predictions take into account multiple factors, including genomic context, Cas protein type, desired mutation type, on-target/off-target scores, potential off-target sites, and the potential impacts of genome editing on gene function and cell phenotype. These models aid in optimizing different genome editing technologies, such as base, prime, and epigenome editing, which are advanced techniques to introduce precise and programmable changes to DNA sequences without relying on the homology-directed repair pathway or donor DNA templates. Furthermore, AI, in collaboration with genome editing and precision medicine, enables personalized treatments based on genetic profiles. AI analyzes patients’ genomic data to identify mutations, variations, and biomarkers associated with different diseases like Cancer, Diabetes, Alzheimer’s, etc. However, several challenges persist, including high costs, off-target editing, suitable delivery methods for CRISPR cargoes, improving editing efficiency, and ensuring safety in clinical applications. This review explores AI’s contribution to improving CRISPR-based genome editing technologies and addresses existing challenges. It also discusses potential areas for future research in AI-driven CRISPR-based genome editing technologies. The integration of AI and genome editing opens up new possibilities for genetics, biomedicine, and healthcare, with significant implications for human health.

Analysis

Why This Paper Matters

This review is timely as CRISPR-based genome editing is rapidly advancing, and AI is becoming integral to improving its precision and efficiency. The paper provides a comprehensive overview of how AI models are used in guide RNA design, off-target prediction, and optimization of advanced editing techniques. It bridges the gap between AI practitioners and biologists, offering a consolidated resource for understanding current tools and challenges.

The paper also highlights the potential of AI-driven genome editing in personalized medicine, which is a growing area of interest. By discussing applications in diseases like sickle cell anemia, cancer, and Alzheimer's, it underscores the clinical relevance. This makes it valuable for researchers and practitioners looking to apply AI in genomics and healthcare.

Technical Contributions

The paper systematically categorizes AI applications in genome editing:

  • Guide RNA design: Tools like DeepCRISPR, CRISTA, and DeepHF predict optimal gRNAs by considering genomic context, Cas protein type, and on/off-target scores.
  • Off-target prediction: AI models assess potential off-target sites to minimize unintended edits.
  • Advanced editing optimization: AI aids in base, prime, and epigenome editing, which enable precise DNA changes without donor templates.
  • Precision medicine integration: AI analyzes patient genomic data to identify mutations and biomarkers, enabling personalized treatments.
  • Challenge identification: The paper outlines key hurdles such as cost, delivery methods, editing efficiency, and safety, providing a roadmap for future research.

Results

As a review, the paper does not present new metrics but synthesizes existing evidence. It notes that AI models like DeepCRISPR and CRISTA have demonstrated improved gRNA design accuracy, though specific quantitative comparisons are not provided. The paper emphasizes that AI contributes to making genome editing more precise, efficient, and affordable, but also acknowledges that challenges like off-target effects and delivery remain.

Significance

This review is significant for the AI community as it highlights a high-impact application domain where AI can drive breakthroughs in medicine. It encourages AI researchers to explore challenges like improving model generalizability, handling genomic context, and integrating multi-modal data. The paper also touches on AI safety aspects, such as ensuring safe clinical applications, which aligns with broader AI safety concerns. By outlining future directions, it sets the stage for interdisciplinary collaboration between AI and genomics, potentially accelerating the development of curative therapies for genetic diseases.

crisprgenome-editingdeep-learningguide-rnaprecision-medicineai-safetyreview
Ai Safety

Related Papers