Heterologous expression is the main approach for recombinant protein production ingenetic synthesis, for which codon optimization is necessary. The existing optimization methods are based on biological indexes. In this paper, we propose a novel codon optimization method based on deep learning. First, we introduce the concept of codon boxes, via which DNA sequences can be recoded into codon box sequences while ignoring the order of bases. Then, the problem of codon optimization can be converted to sequence annotation of corresponding amino acids with codon boxes. The codon optimization models for Escherichia Coli were trained by the Bidirectional Long-Short-Term Memory Conditional Random Field. Theoretically, deep learning is a good method to obtain the distribution characteristics of DNA. In addition to the comparison of the codon adaptation index, protein expression experiments for plasmodium falciparum candidate vaccine and polymerase acidic protein were implemented for comparison with the original sequences and the optimized sequences from Genewiz and ThermoFisher. The results show that our method for enhancing protein expression is efficient and competitive.

No abstract

Tropomyosin receptor kinases (TrkA, TrkB, and TrkC) are attractive therapeutic targets for multiple cancers. Two first-generation small-molecule Trks inhibitors, larotrectinib and entrectinib, have just been approved to use clinically. However, the drug-resistance mutations of Trks have already emerged, which calls for new-generation Trks inhibitors. Herein, we report the structural optimization and structure–activity relationship studies of 6,6-dimethyl-4-(phenylamino)-6H-pyrimido­[5,4-b]­[1,4]­oxazin-7­(8H)-one derivatives as a new class of pan-Trk inhibitors. The prioritized compound 11g exhibited low nanomolar IC50 values against TrkA, TrkB, and TrkC and various drug-resistant mutants. It also showed good kinase selectivity. 11g displayed excellent in vitro antitumor activity and strongly suppressed Trk-mediated signaling pathways in intact cells. In in vivo studies, compound 11g exhibited good antitumor activity in BaF3-TEL-TrkA and BaF3-TEL-TrkCG623R allograft mouse models without exhibiting apparent toxicity. Collectively, 11g could be a promising lead compound for drug discovery targeting Trks and deserves further investigation.

No abstract

No abstract