Intrinsically Disordered Regions (IDRs) play essential roles in cellular processes through interactions with proteins, nucleic acids, lipids, and metal ions, yet predicting their binding partners remains challenging for understanding protein function and drug discovery. However, current computational methods including protein language models face performance plateaus where traditional approaches to improve accuracy have become ineffective. Here, we present a hybrid quantum-classical machine learning approach that combines variational quantum circuits with the ESM2 protein language model for multi-class IDR binding partner prediction using a prototypical network. Through systematic evaluation of quantum circuit architectures across factorial experiments, we demonstrate that the hybrid model achieves statistically significant performance improvements over classical baselines, with entanglement topology governing model stability and encoding methods determining performance gains. These findings establish that quantum advantage in computational biology emerges from architectural design principles rather than computational scale, providing a framework for overcoming performance limitations in bioinformatics applications where dataset expansion is constrained.
Seok-Jin Kang, Hongchul Shin· IEEE transactions on computa...· 0 citations
Several viral vectors have been developed for gene therapy due to their high transduction efficiency, but some integrate into the host genome, raising safety concerns. Recent studies have identified recombinant adeno-associated virus serotype 6 (rAAV6) as a promising vector for hematopoietic stem and progenitor cell-targeted gene therapy because of its non-pathogenic nature, low integration frequency, and capacity for sustained episomal transgene expression. Nevertheless, its chromosomal integration profile remains incompletely defined, warranting a comprehensive evaluation to assess long-term safety. In this study, human CD34＋ cells were transduced with rAAV6 under varying vector doses and transgene contexts, and integration-site mapping was performed using the integration-site enriched library sequencing approach. Consistent with the largely episomal nature of AAV, high vector sequence alignment rates were observed across all groups. rAAV6 integrations occurred randomly throughout the genome, showing a broad pan-chromosomal distribution without evidence of sequence-specific targeting or clustering. Although integrations were more frequent in CpG islands, commonly located within open chromatin, this pattern likely reflects chromatin accessibility rather than targeting bias. Functional enrichment analysis indicated associations with general cellular and structural processes, without enrichment in oncogenic pathways. Distance-based analysis confirmed that integration sites were mapped at a distance from oncogenes and tumor suppressor genes, even under high-dose conditions. The data support the genomic safety of rAAV6 and its applicability to hematological gene therapy.
H. Lee, Nayoung Park, In-Byung Park et al.· International Journal of Ste...· 0 citations