DNA mimic proteins are relatively obscure control factors that resemble DNA by mimicking its negatively charged distribution. They achieve this using negatively charged amino acids like aspartic acid (ASP/D) and glutamic acid (GLU/E). Known DNA mimic proteins control various cellular mechanisms, such as transcription, DNA repair, and gene regulation, by intervening in the binding of DNA to effector proteins. In addition to their biological functions, DNA mimic proteins may also be applicable in biotechnology, for example, by regulating CRISPR Cas9 activity to enhance gene editing precision. Therefore, DNA mimic proteins warrant further research. However, most DNA mimic proteins cannot be identified using traditional bioinformatics methods owing to their unique amino acid sequences and structural features. We developed a new protein fingerprint, called relative distance protein fingerprint (RD-PFP), that can be used to analyze the distribution of amino acids on a protein surface. We optimized our RD-PFP by using machine learning and the characteristic feature of DNA mimic proteins (namely, their DNA-like negatively charged distribution) to more accurately predict DNA mimicry from protein structures. Our pioneering study contributes to the development of machine learning-based bioinformatics methods for screening DNA mimic proteins.
Chien et al. (Thu,) studied this question.