Machine learning (ML) is becoming an attractive tool in mutagenesis-based protein engineering because of its ability to design a variant library containing proteins with a desired function. However, it remains unclear how ML guides directed evolution in sequence space depending on the composition of training data. Here, we present a ML-guided directed evolution study of an enzyme to investigate the effects of a known “highly positive” variant (i.e., variant known to have high enzyme activity) in training data. We performed two separate series of ML-guided directed evolution of Sortase A with and without a known highly positive variant called 5M in training data. In each series, two rounds of ML were conducted: variants predicted by the initial round were experimentally evaluated and used as additional training data for the second-round of prediction. The improvements in enzyme activity were comparable between the two series, both achieving enzyme activity 2.2–2.5 times higher than 5M. Intriguingly, the sequences of the improved variants were largely different between the two series, indicating that ML guided the directed evolution to the distinct regions of sequence space depending on the presence/absence of the highly positive variant in the training data. This suggests that the sequence diversity of improved variants can be expanded not only by conventional ML using the whole training data but also by ML using a subset of the training data even when it lacks highly positive variants. In summary, this study demonstrates the importance of regulating the composition of training data in ML-guided directed evolution.

Aromatic carbon nanomaterials, such as carbon nanotubes and graphene, undergo protein adsorption in the early stages of their uptake into biological systems, which determines their bioavailability and cytotoxicity. Although a mechanistic understanding of protein–nanomaterial interactions is essential for realizing safe and controlled in vivo applications of nanomaterials, it remains challenging to predict arbitrary protein–nanomaterial interactions. This study introduces an index, “aromaphilicity (aromatic-loving nature) index”, for 20 proteinogenic amino acids. This index reflects the affinity of the amino acid side chains for the aromatic carbon surfaces, which was quantified by molecular dynamics simulations. This index is significantly correlated with the experimental data (R² = 0.789) and successfully utilized as a versatile tool for predicting the affinity hot spots of the proteins for the aromatic carbon nanomaterials. This approach advances the understanding of the mechanism of protein–nanomaterial interactions and improves prediction of the biological impacts of nanomaterials.