Machine learning assisted designing of Indacenodithiophene (IDT)-based polymers for future application of photoacoustic imaging

Non-invasive imaging tools are essential for diagnosis of complex disease. Photoacoustic (PA) imaging is a multiscale noninvasive imaging modality with high resolution and sensitivity for deep-seated pathologies. However, microenvironment of some pathologies produce PA signals compromising the optical resolution of PA imaging. This demands the construction of PA imaging agents to avoid the low signal to noise ratio with improved resolution and sensitivity. In this study, we use machine learning to design the IDT-based polymers with their absorption coefficient in NIR-I region. We used the database of polymer structures and properties to identify promising candidates for PAI. The models were then used to predict the properties of new IDT-based polymers with optimized absorption, biocompatibility and acoustic performance. Several promising candidates were identified and their in silico synthesis potential and PA imaging performance was predicted. The results demonstrates the potential of machine learning-guided polymers design for PA imaging agents and suggest that IDT-based polymers could be a valuable addition to the toolkit of PA imaging contrast agents.