Browse Articles
Discover research articles across all indexed journals
MAGC-DTI: modality-shared space and adaptive gated interactive cross-attention for drug–target interaction prediction
Abstract Accurate drug–target interaction (DTI) prediction is crucial for drug repurposing and accelerating drug development. Although deep learning has advanced DTI prediction, existing methods struggle with two key challenges: (i) capturing complex hierarchical patterns in protein sequences, and (ii) enabling effective bidirectional information exchange between drug and protein modalities. We propose MAGC-DTI, an end-to-end cross-modal framework that integrates bidirectional information exchange into both feature extraction and fusion stages through three key innovations: (i) multi-scale attention aggregation (MSAA) for hierarchical protein pattern capture, (ii) adaptive gated interactive cross attention (AGICA) for context-aware cross-modal interaction, and (iii) multi-path residual classifier (MPRC) for modality-preserving fusion. Comprehensive evaluations on six benchmark datasets show that MAGC-DTI generally achieves favorable performance relative to seven state-of-the-art baselines, with competitive results in cold-start and cross-domain scenarios. The model also provides interpretable insights through attention visualization and case studies confirm the biological relevance of learned representations.
Multi-scale computational analysis of monoacylglycerol lipase inhibition as a new therapeutic strategy for hepatocellular carcinoma
Correction: P2X7 Receptor Suppression Preserves Blood-Brain Barrier through Inhibiting RhoA Activation after Experimental Intracerebral Hemorrhage in Rats
Assessment of pedestrian safety margins at unsignalized mid block crossings in Patna
Optimized multi-tier task offloading strategy for sustainable IoV systems in 6G networks
Integrating digital twin technology with deep reinforcement learning for sustainable marine fishery resource management
MRI assessment of muscle damage after posterolateral versus SuperPATH approach for total hip arthroplasty
Clinician decision-making for polymyxin dosing in critically ill patients with renal impairment: a qualitative study
Abstract Polymyxin remain essential last-line agents for the treatment of multidrug-resistant gram-negative infections in critically ill patients. However, dosing polymyxin B and colistin in patients with renal impairment is clinically challenging due to complex pharmacokinetics, fluctuating renal function, toxicity concerns and limited implementation of therapeutic drug monitoring. While pharmacokinetic and guideline-based recommendations exist, little is known about how clinicians navigate these complexities in real-world practice. We conducted an inductive qualitative study using semi-structured interviews with physicians involved in the management of critically ill patients with severe gram-negative infections. Participants were purposively sampled from critical care, nephrology, infectious diseases and general medicine. Interviews explored experiences and decision-making related to polymyxin selection, dosing adjustments, renal dysfunction, renal replacement therapy, safety monitoring and institutional influences. Transcripts were analysed using a constructivist grounded theory approach, following iterative coding, constant comparison and theme development. Coding and analysis were performed using ATLAS.ti software. Reporting adhered to the COREQ checklist. Seventeen physicians were interviewed. Analysis yielded six interrelated themes: 1. Clinical determinants of polymyxin selection, 2. Individualized and adaptive dosing practices, 3. Renal dysfunction and renal replacement therapy-related uncertainty, 4. Safety-driven decision-making, 5. Monitoring, diagnostic, and evidence limitations, and vi. Institutional and system-level influences. Clinicians described polymyxin dosing as a dynamic experience-driven process requiring continuous reassessment and risk–benefit negotiation. Renal function variability, lack of therapeutic drug monitoring, and absence of standardized institutional protocols contributed to cautious and heterogenous dosing practices, particularly in patients receiving dialysis. Polymyxin dosing in critically ill patients with renal impairment is shaped by complex clinical judgement, safety concerns and systemic constraints rather than rigid adherence to dosing algorithms. These findings highlight a gap between pharmacokinetic evidence and bedside practice and underscore the need for pragmatic, context-appropriate dosing guidance, multidisciplinary stewardship support and decision-support tools to optimize polymyxin use in high-risk populations.