In massive multiple-input multiple-output (MIMO) systems, the frequency division duplex (FDD) mode significantly enhances data transmission capabilities. However, it requires user equipment (UE) to feedback the channel state information (CSI) to the base station (BS) for efficient precoding. As the number of BS antennas increases, the complexity of CSI feedback grows, making CSI compression techniques essential. Deep learning (DL)-based approaches have shown great potential in addressing this challenge. Given the storage and computational limitations at the UE, it is critical to design networks that deliver high reconstruction performance with minimal floating-point operations per second (FLOPS). We propose a novel method that leverages dilated convolutional attention and multi-head attention mechanism to improve CSI feedback quality without increasing system complexity. To enhance its practical application, we introduce a denoise block based on multi-head attention to correct errors that occur during transmission. Simulation results show that our method achieves lower FLOPS compared to existing models, while maintaining comparable or even better performance. Additionally, the attention-based denoising block exhibits strong error-correction capabilities, further improving system robustness.

MOTIVATION: Gene deletion and overexpression are critical technologies for designing or improving the metabolic flux distribution of microbes. Some algorithms including flux balance analysis (FBA) and minimization of metabolic adjustment (MOMA) predict a flux distribution from a stoichiometric matrix in the mutants in which some metabolic genes are deleted or non-functional, but there are few algorithms that predict how a broad range of genetic modifications, such as over- and underexpression of metabolic genes, alters the phenotypes of the mutants at the metabolic flux level. RESULTS: To overcome such existing limitations, we develop a novel algorithm that predicts the flux distribution of the mutants with a broad range of genetic modification, based on elementary mode analysis. It is denoted as genetic modification of flux (GMF), which couples two algorithms that we have developed: modified control effective flux (mCEF) and enzyme control flux (ECF). mCEF is proposed based on CEF to estimate the gene expression patterns in genetically modified mutants in terms of specific biological functions. GMF is demonstrated to predict the flux distribution of not only gene deletion mutants, but also the mutants with underexpressed and overexpressed genes in Escherichia coli and Corynebacterium glutamicum. This achieves breakthrough in the a priori flux prediction of a broad range of genetically modified mutants. SUPPLEMENTARY INFORMATION: Supplementary file and programs are available at Bioinformatics online or http://www.cadlive.jp.