Polymer design via SHAP and Bayesian machine learning optimizes pDNA and CRISPR ribonucleoprotein delivery

Keyphrases

• Plasmid DNA (pDNA) 100%
• Bayesian Machine Learning 100%
• Polymer Design 100%
• CRISPR Ribonucleoproteins 100%
• Ribonucleoprotein Delivery 100%
• Closed-loop 33%
• Machine Learning 33%
• Design Space 33%
• Nucleic Acid Carrier 33%
• Facile Synthesis 33%
• Explainable Machine Learning 33%
• Design Parameters 33%
• Combinatorial Design 33%
• Quantitative Structure-property Relationship 33%
• Ethanethiol 33%
• Click-iT 33%
• Hydrophobicity 33%
• Nucleic Acid Therapeutics 33%
• Analysis-by-synthesis 33%
• Character Analysis 33%
• Performance Parameters 33%
• Benzimidazole 33%
• Physicochemical Characterization 33%
• Systematic Variation 33%
• ClogP 33%
• In Vitro Performance 33%
• Polymer Yield 33%
• Stable Transgene Expression 33%
• Binary Compositions 33%
• Polymer Library 33%
• Bayesian Optimization 33%
• Cas9 Ribonucleoprotein 33%
• Next-generation Vehicle 33%
• Machine Analysis 33%
• High Signal 33%
• High-Stable 33%
• Polymer Length 33%

Material Science

• Nucleic Acid 100%
• Hydrophobicity 50%

Chemical Engineering

• Learning System 100%