Polymer-Unit Fingerprint (PUFp): An Accessible Expression of Polymer Organic Semiconductors for Machine Learning

High-performance organic semiconductors (OSCs) can be designed based on the identification of functional units and their role in the material properties. Herein, we present a polymer unit fingerprint (PUFp) generation framework, Python-based polymer-unit-recognition script (PURS), to identify the subunits polymer unit in the polymer and generate polymer-unit fingerprint (PUFp). Using 678 collected OSC data, machine learning (ML) models can be used to determine structure-mobility relationships by using PUFp as a structural input, and the classification accuracy reaches 85.2%. A polymer-unit library consisting of 445 units is constructed, and the key polymer units affecting the mobility of OSCs are identified. By investigating the combinations of polymer units with mobility performance, a scheme for designing OSCs by combining ML approaches and PUFp information is proposed. This scheme not only passively predicts OSC mobility but also actively provides structural guidance for high-mobility OSC material design. The proposed scheme demonstrates the ability to screen materials through pre-evaluation and classification ML steps and is an alternative methodology for applying ML in high-mobility OSC discovery.

Automated summary

High-performance organic semiconductors (OSCs) can be designed by identifying functional units and their role in material properties. A Python-based polymer-unit recognition script (PURS) is proposed to generate polymer-unit fingerprints (PUFp) and classify OSCs based on structure-mobility relationships. The scheme combines machine learning approaches and PUFp information to actively guide the design of high-mobility OSC materials.