Search

Abstract Deep learning-based inpainting models have achieved success in restoring natural images, yet their application to ancient paintings encounters challenges due to the loss of texture, lines, and color. To address these issues, we introduce an ancient painting inpainting model based on dual encoders and contextual information to overcome the lack of feature extraction and detail texture recovery when restoring ancient paintings. Specifically, the proposed model employs a gated encoding branch that aims to minimize information loss and effectively capture semantic information from ancient paintings. A dense multi-scale feature fusion module is designed to extract texture and detail information at various scales, while dilated depthwise separable convolutions are utilized to reduce parameters and enhance computational efficiency. Furthermore, a contextual feature aggregation module is incorporated to extract contextual features, enhancing the overall consistency of the inpainting results. Finally, a color loss function is introduced to ensure color consistency in the restored area, harmonizing it with the surrounding region. The experimental results indicate that the proposed model effectively restores the texture details of ancient paintings, outperforming other methods both qualitatively and quantitatively. Additionally, the model is tested on real damaged ancient paintings to validate its practicality and efficacy.

Abstract Background Polyketide synthases (PKSs) are classified into three types based on their enzyme structures. Among them, type III PKSs, catalyzing the iterative condensation of malonyl-coenzyme A (CoA) with a CoA-linked starter molecule, are important synthases of valuable natural products. However, low efficiency and byproducts formation often limit their applications in recombinant overproduction. Results Herein, a rapid growth selection system is designed based on the accumulation and derepression of toxic acyl-CoA starter molecule intermediate products, which could be potentially applicable to most type III polyketides biosynthesis. This approach is validated by engineering both chalcone synthases (CHS) and host cell genome, to improve naringenin productions in Escherichia coli. From directed evolution of key enzyme CHS, beneficial mutant with ~ threefold improvement in capability of naringenin biosynthesis was selected and characterized. From directed genome evolution, effect of thioesterases on CHS catalysis is first discovered, expanding our understanding of byproduct formation mechanism in type III PKSs. Taken together, a whole-cell catalyst producing 1082 mg L−1 naringenin in flask with E value (evaluating product specificity) improved from 50.1% to 96.7% is obtained. Conclusions The growth selection system has greatly contributed to both enhanced activity and discovery of byproduct formation mechanism in CHS. This research provides new insights in the catalytic mechanisms of CHS and sheds light on engineering highly efficient heterologous bio-factories to produce naringenin, and potentially more high-value type III polyketides, with minimized byproducts formation.