Data mining and library generation to search electron-rich and electron-deficient building blocks for the designing of polymers for photoacoustic imaging

Abstract

Photoacoustic imaging is a good method for biological imaging, for this purpose, materials with strong near infrared (NIR) absorbance are required. In the present study, machine learning models are used to predict the light absorption behavior of polymers. Molecular descriptors are utilized to train a variety of machine learning models. Building blocks are searched from chemical databases, as well as new building blocks are designed using chemical library enumeration method. The Breaking Retrosynthetically Interesting Chemical Substructures (BRICS) method is employed for the creation of 10,000 novel polymers. These polymers are designed based on the input of searched and selected building blocks. To enhance the process, the optimal machine learning model is utilized to predict the UV/visible absorption maxima of the newly designed polymers. Concurrently, chemical similarity analysis is also performed on the selected polymers, and synthetic accessibility of selected polymers is calculated. In summary, the polymers are all easy to synthesize, increasing their potential for practical applications.