Proteins are the foundation of life, and designing functional proteins remains a key challenge in biotechnology. Before the development of AlphaFold2, the focus of design was primarily on structure-centric approaches such as using the well-known open-source software Rosetta3. Following the development of AlphaFold2, deep-learning techniques for protein design gained prominence. This study proposes a new method to generate functional proteins using the diffusion model and ESM2 protein language model. Diffusion models, which are widely used in image and natural language generation, are used here for protein design, facilitating the controlled generation of new sequences. The ESM2 model, trained on the basis of large-scale protein sequence data, provides a deep understanding of the context of the sequence, thus improving the model’s ability to generate biologically relevant proteins. In this study, we used the Protein A-like peptide as a model study object, combined the diffusion model and the ESM2 model to generate new peptide sequences from minimal input data, and verified their biological activities through experiments such as the BLI affinity test. In conclusion, we developed a new method for protein design that provides a novel strategy to meet the challenges of generic protein generation.

Corner points contain important information about the shape of an object. An efficient technique for extracting corners on an image contour is presented. The technique is based on the calculation of contour curvature. The procedure first process the contour through Gaussian multi-scale smoothing, then calculates the curvature of each contour point within the region of local support, and finally determines corners by a process of corner filtering at some criterion. The rationality and feasibility of algorithm is verified mathematically. The contrast experiments show that the curvature calculation approach can represents image contour properly and the corners extraction is robust and accurate.

With the advancement of building energy efficiency simulation technology, sensitivity analysis has become increasingly important in optimizing architectural design. This study examines typical rural dwellings in the Beijing–Tianjin–Hebei region, using Regional Sensitivity Analysis (RSA) to assess how design parameters affect energy consumption, carbon emissions, costs, and thermal comfort. Eleven parameters were analyzed through 1,000 simulations, including insulation type, envelope geometry, and photovoltaic configuration. Eave depth showed the highest sensitivity for all metrics, while roof insulation thickness and PV panel angle strongly influenced thermal performance and cost. The study also applies an RSA workflow to mixed continuous and categorical variables, with binning adjustment improving sensitivity results for discrete parameters. Based on sensitivity findings, differentiated optimization strategies were proposed: prioritizing passive shading and roof insulation for comfort optimization, while focusing on PV system scale for carbon emission and cost control. This study provides quantifiable evidence for low-carbon, efficient, and comfortable design in rural buildings.

Objective. Learning robust representations from scarce labeled bio-electrical time-series data remains a critical challenge in clinical diagnosis. While contrastive learning has shown promise, existing approaches often overlook the intrinsic causal dynamics inherent in physiological signals, leading to over-smoothed representations. This study presents CausalTCC, an end-to-end framework for causal temporal contrastive learning of bio-electrical signals toward Alzheimer’s disease (AD) biomarker discovery. Approach. CausalTCC is developed through three modules: (1) asymmetrical augmentation: distinct weak and strong augmentation strategies generate diverse views while respecting physiological characteristics; (2) causal temporal contrasting: a Transformer-based autoregressive backbone with causal masking integrates intra-view causal loss to capture intrinsic temporal dependencies; and (3) causal contextual contrasting: a symmetric InfoNCE loss leverages instance-level discrimination to learn domain-invariant causal representations, reducing reliance on labeled examples. Main results. Extensive experiments compared CausalTCC to six state-of-the-art counterparts (e.g., EEGNet and EEG-SSL) on four datasets (HAR, AD_A, AD_FTD, and Brain_Lat): (1) CausalTCC achieves the best average F1-scores of 60.1%, 71.0%, and 76.9% under 1%, 5%, and 10% labeled data, outperforming the second-best method by up to 7.2%; (2) under extreme data scarcity (1% labels), it demonstrates substantial improvements on AD_A (Acc: 70.0%, F1: 67.9%); and (3) the causal self-supervision makes CausalTCC far superior to conventional supervised methods. Significance. Overall, CausalTCC presents a physiologically grounded and relatively parameter-efficient framework that maintains competitive inference efficiency while balancing model complexity and predictive performance for EEG-based clinical decision support.