Structure-Based Classification of CRISPR/Cas9 Proteins: A Machine Learning Approach to Elucidating Cas9 Allostery

Area of Science:

• Biochemistry
• Structural Biology
• Computational Biology

Background:

• The CRISPR/Cas9 system's efficacy depends on allosteric regulation for specificity and stability.
• Understanding these mechanisms is vital for developing high-fidelity Cas9 variants with fewer off-target effects.

Purpose of the Study:

• To systematically identify long-range allosteric networks in Cas9 using a novel structure-based machine learning approach.
• To refine these networks and pinpoint critical residues mediating interdomain communication, stability, and specificity in Streptococcus pyogenes Cas9 (SpCas9).

Main Methods:

• Trained a machine learning model on all available Cas9 structures.
• Applied a SHAP feature selection strategy using Cα-Cα inter-residue distances to identify key Lysine-Arginine (Lys-Arg) residue pairs.
• Utilized molecular dynamics simulations and mutational analysis to investigate the identified allosteric networks and the
• Main_Results
• Identified 28 critical Lys-Arg residue pairs involved in SpCas9 allosteric regulation.
• Discovered an
• Conclusions
• Developed a novel machine learning framework for analyzing protein allostery, applicable beyond Cas9.
• Provided a rational strategy for engineering high-fidelity Cas9 variants by understanding allosteric networks and the electrostatic valley concept.

Main Results:

• Identified 28 critical Lysine-Arginine (Lys-Arg) residue pairs mediating SpCas9 interdomain communication, stability, and specificity.
• Uncovered an
• Conclusions
• Developed a novel machine learning framework for analyzing protein allostery, applicable beyond Cas9.
• Provided a rational strategy for engineering high-fidelity Cas9 variants by understanding allosteric networks and the electrostatic valley concept.

Conclusions:

• Developed a novel machine learning framework for analyzing protein allostery, applicable beyond Cas9.
• Provided a rational strategy for engineering high-fidelity Cas9 variants by understanding allosteric networks and the electrostatic valley concept.