MOTIVATION: Due to the varying delivery methods of mRNA vaccines, codon optimization plays a critical role in vaccine design to improve the stability and expression of proteins in specific tissues. Considering the many-to-one relationship between synonymous codons and amino acids, the number of mRNA sequences encoding the same amino acid sequence could be enormous. Finding stable and highly expressed mRNA sequences from the vast sequence space using in silico methods can generally be viewed as a path-search problem or a machine translation problem. However, current deep learning-based methods inspired by machine translation may have some limitations, such as recurrent neural networks, which have a weak ability to capture the long-term dependencies of codon preferences. RESULTS: We develop a BERT-based architecture that uses the cross-attention mechanism for codon optimization. In CodonBERT, the codon sequence is randomly masked with each codon serving as a key and a value. In the meantime, the amino acid sequence is used as the query. CodonBERT was trained on high-expression transcripts from Human Protein Atlas mixed with different proportions of high codon adaptation index codon sequences. The result showed that CodonBERT can effectively capture the long-term dependencies between codons and amino acids, suggesting that it can be used as a customized training framework for specific optimization targets. AVAILABILITY AND IMPLEMENTATION: CodonBERT is freely available on https://github.com/FPPGroup/CodonBERT.

The Internet has led to the development of online markets, and computer scientists have designed various auction algorithms, as well as automated exchanges for standardized commodities; however, they have done little work on exchanges for complex non-standard goods. We present an exchange system for trading complex goods, such as used cars or non-standard financial securities. The system allows traders to represent their buy and sell orders by multiple attributes; for example, a car buyer can specify a model, options, colour, and other desirable features. Traders can also provide complex price constraints, along with preferences among acceptable trades; for instance, a car buyer can specify dependency of an acceptable price on the model, year of production, and mileage. We describe the representation and indexing of orders, and give algorithms for fast identification of matches between buy and sell orders. The system identifies the most preferable matches, which maximize trader satisfaction, and it allows control over the trade-off between speed and optimality of matching. It supports markets with up to 300 000 orders, and processes hundreds of new orders per second.