Knowledge Graph Question Answering (KGQA) is a crucial task in natural language processing, aiming to answer natural language questions by reasoning over structured knowledge graphs (KGs). Existing approaches using large language models (LLMs) often suffer from imprecise query generation and hallucination, especially in complex multi-hop questions. To address these challenges, we propose the Entity Shuffling-Augmented Generation method for KGQA (ESAG-KGQA), a novel semantic parsing method based on the Extract-Generate-Retrieve (EGR) framework. Unlike traditional methods that rely on retrieving information from KGs or external documents, our approach directly utilizes key entities from the question to minimize noise from early retrieval. ESAG-KGQA first extracts and completes key entities from the question. It then fine-tunes LLMs via entity shuffling, thereby enhancing robustness and enabling dynamic capture of both explicit entity cues and implicit semantic signals. The generation phase produces logical forms with key entity augmentation. These logical forms are further refined using an unsupervised retrieval method to enhance semantic parsing accuracy. This integrated process effectively mitigates hallucination in LLMs and significantly improves both semantic parsing accuracy and the interpretability of logical queries. Experiments demonstrate that ESAG-KGQA outperforms the state-of-the-art on the standard KGQA datasets, WebQSP by 2.8%, 1.3% and 3.2% and ComplexWebQuestions by 1.9%, 1.2% and 2.5% in terms of F1, Hits@1 and Accuracy, respectively. Our code is publicly available at https://github.com/6-git/ESAG-KGQA.git.

Digital informatization in bioinformatics research has developed rapidly, resulting in the emergence of tens of thousands of bioinformatics tools in recent decades. However, few researchers systematically study how to manage and recommend bioinformatics tools. Meanwhile, the existing recommendation methods suffer from the incompatibility with bioinformatics tool recommendations, specifically, i) the inability to mine rich semantic information and potential correlations of bioinformatics tools to make up for the sparse problem of operation-tool history interaction; ii) the inability to accommodate recommendations dominated by tools. To address these problems, we collected quantitative bioinformatics operations, tools, and context from https://bio.tools, constructed a knowledge graph dataset for the bioinformatics tools, and proposed the Bioinformatics Tool Recommendation Method with Multi-view Contrastive Learning (BTR-MCL). The method utilizes BERT to enrich the descriptive information and constructs three fine-grained views for multi-view contrastive learning, namely the tool-tool graph, the operation-tool graph, and the bioinformatics tools knowledge graph. By data augmentation and enhancing the importance of tool embedding in local and global contrastive learning, BTR-MCL achieves significant improvements over the state-of-the-art baselines on the top-K recommendation task, outperforming the best baseline by 82.71% on the Recall@10 metric.

MOTIVATION: The k-mer frequency in whole genome sequences provides researchers with an insightful perspective on genomic complexity, comparative genomics, metagenomics and phylogeny. The current k-mer counting tools are typically slow, and they require large memory and hard disk for assembled genome analysis. RESULTS: We propose a novel and ultra-fast k-mer counting algorithm, KCOSS, to fulfill k-mer counting mainly for assembled genomes with segmented Bloom filter, lock-free queue, lock-free thread pool and cuckoo hash table. We optimize running time and memory consumption by recycling memory blocks, merging multiple consecutive first-occurrence k-mers into C-read, and writing a set of C-reads to disk asynchronously. KCOSS was comparatively tested with Jellyfish2, CHTKC and KMC3 on seven assembled genomes and three sequencing datasets in running time, memory consumption, and hard disk occupation. The experimental results show that KCOSS counts k-mer with less memory and disk while having a shorter running time on assembled genomes. KCOSS can be used to calculate the k-mer frequency not only for assembled genomes but also for sequencing data. AVAILABILITYAND IMPLEMENTATION: The KCOSS software is implemented in C++. It is freely available on GitHub: https://github.com/kcoss-2021/KCOSS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.