A faster computational frame work for dye design and screening: A goal to achieve higher ionization energy

This study introduces an advanced framework that use machine learning (ML) for dye design. ML models are trained to predict the ionization energy of dyes. Using the Breaking Retrosynthetically Interesting Chemical Substructures (BRICS) technique, 10 k new dyes are generated. The pre-trained ML model then forecasts the ionization energy values of these dyes. The selection process prioritizes dyes with higher ionization energy. The chosen dyes are evaluated for synthetic accessibility and structural similarity, revealing significant diversity among them. This approach efficiently identifies and optimizes new dyes, greatly enhancing the potential for finding superior materials for various applications.