Neuropeptides are a diverse and complex class of signaling molecules that regulate a variety of biological processes. Neuropeptides provide many opportunities for the discovery of new drugs and targets for the treatment of a wide range of diseases, and thus, computational tools for the rapid and accurate large-scale identification of neuropeptides are of great significance for peptide research and drug development. Although several machine learning-based prediction tools have been developed, there is room for improvement in the performance and interpretability of the proposed methods. In this work, we developed an interpretable and robust neuropeptide prediction model, named NeuroPred-PLM. First, we employed a language model (ESM) of proteins to obtain semantic representations of neuropeptides, which could reduce the complexity of feature engineering. Next, we adopted a multi-scale convolutional neural network to enhance the local feature representation of neuropeptide embeddings. To make the model interpretable, we proposed a global multi-head attention network that could be used to capture the position-wise contribution to neuropeptide prediction via the attention scores. In addition, NeuroPred-PLM was developed based on our newly constructed NeuroPep 2.0 database. Benchmarks based on the independent test set show that NeuroPred-PLM achieves superior predictive performance compared with other state-of-the-art predictors. For the convenience of researchers, we provide an easy-to-install PyPi package (https://pypi.org/project/NeuroPredPLM/) and a web server (https://huggingface.co/spaces/isyslab/NeuroPred-PLM).

Motivation: Protein domains are the basic units of proteins that can fold, function and evolve independently. Protein domain boundary partition plays an important role in protein structure prediction, understanding their biological functions, annotating their evolutionary mechanisms and protein design. Although there are many methods that have been developed to predict domain boundaries from protein sequence over the past two decades, there is still much room for improvement.Results: In this article, a novel domain boundary prediction tool called Res-Dom was developed, which is based on a deep residual network, bidirectional long short-term memory (Bi-LSTM) and transfer learning. We used deep residual neural networks to extract higher-order residue-related information. In addition, we also used a pre-trained protein language model called ESM to extract sequence embedded features, which can summarize sequence context information more abundantly. To improve the global representation of these deep residual networks, a Bi-LSTM network was also designed to consider long-range interactions between residues. Res-Dom was then tested on an independent test set including 342 proteins and generated correct single-domain and multi-domain classifications with a Matthew’s correlation coefficient of 0.668, which was 17.6% higher than the second-best compared method. For domain boundaries, the normalized domain overlapping score of Res-Dom was 0.849, which was 5% higher than the second-best compared method. Furthermore, Res-Dom required significantly less time than most of the recently developed state-of-the-art domain prediction methods.Availability and implementation: All source code, datasets and model are available at http://isyslab.info/Res-Dom/.

The advent of highly accurate structure prediction techniques such as AlphaFold3 is driving an unprecedented expansion of protein structure databases. This rapid growth creates an urgent demand for novel search tools, as even the current fastest available methods like Foldseek face significant limitations in sensitivity and scalability when confronted with these massive repositories. To meet this challenge, we have developed SSAlign, a protein structure retrieval tool that leverages protein language models to jointly encode sequence and structural information and adopts a two-stage alignment strategy. On large-scale datasets such as AFDB50, SSAlign achieves a two-orders-of-magnitude speedup over Foldseek in search, substantially improving scalability for high-throughput structural analysis. Compared to Foldseek, SSAlign retrieves substantially more high-quality matches on Swiss-Prot and achieves marked performance improvements on SCOPe40, with relative AUC increases of +20.2% at the family level and +33.3% at the superfamily level, demonstrating significantly enhanced sensitivity and recall. In sum, SSAlign achieves TM-align–comparable accuracy with Foldseek-surpassing speed and coverage, offering an efficient, sensitive, and scalable solution for large-scale structural biology and structure-based drug discovery.

Proteins are essential to life's processes, underpinning evolution and diversity. Advances in sequencing technology have revealed millions of proteins, underscoring the need for sophisticated pre-trained protein models for biological analysis and AI development. Facebook's ESM2, the most advanced protein language model to date, leverages a masked prediction task for unsupervised learning, crafting amino acid representations with notable biochemical accuracy. Yet, it lacks in delivering functional protein insights, signaling an opportunity for enhancing representation quality.Our study addresses this gap by incorporating protein family classification into ESM2's training.This approach, augmented with Community Propagation-Based Clustering Algorithm, improves global protein representations, while a contextual prediction task fine-tunes local amino acid accuracy. Significantly, our model achieved state-of-the-art results in several downstream experiments, demonstrating the power of combining global and local methodologies to substantially boost protein representation quality.