98%
921
2 minutes
20
Drug combination therapy with significant advantages is a well-established concept in cancer treatment. Some related efforts have been made with multiple artful deep learning techniques. However, they are usually based on data for drug synergy prediction, ignoring the professional characteristics of data and the systematic knowledge accumulation. Meanwhile, integrating the dispersed professional knowledge and effectively utilizing it in data remains a crucial technical challenge. In this study, we propose KSDDC, a novel model for knowledge-aware synergistic discovery of drug combinations from a large language model (LLM) perspective (i.e., from the continuously learnable and refined large database). Within this framework, three main modules are well-designed, i.e., knowledge-aware drug feature auto-encoding, knowledge-aware cell line feature encoding and drug-drug synergy prediction. Informative embeddings of samples are discovered and combined to make accurate drug synergy prediction. Overall, KSDDC is superior compared with the other shallow machine learning based methods and deep learning based methods on several synergistic prediction benchmarks, where about 19% F1-score improvements over the second best method on DrugComb_1 can be observed. Starting with drug synergy prediction, our studies with knowledge-enabled data mining offer valuable insights and serve as a reference method for future research in this field.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1109/TCBBIO.2025.3592471 | DOI Listing |
Drug Discov Today
September 2025
Department of Pharmaceutical and Artificial-Intelligence Sciences, Shanghai Jiao Tong University School of Medicine, Shanghai 200025, China; Key Laboratory of Protection, Development and Utilization of Medicinal Resources in Liupanshan Area, Ministry of Education, Peptide & Protein Drug Research Cen
The landscape of allosteric drug discovery is undergoing a transformative shift, driven by the integration of three computational approaches: machine learning (ML), molecular dynamics (MD) simulations, and network theory. ML identifies potential allosteric sites from multidimensional biological datasets; MD simulations, empowered by enhanced sampling algorithms, reveal transient conformational states; and network analyses uncover communication pathways, further aiding in site identification. Their synergy enables rational allosteric modulator design.
View Article and Find Full Text PDFSci Total Environ
September 2025
Department of Applied Biosciences, Kyungpook National University, Daegu 41566, Republic of Korea; KNU NGS Core Facility, Kyungpook National University, Daegu 41566, Republic of Korea; Microblance Inc., Daegu 41566, Republic of Korea. Electronic address:
Abandoned mines have created extensive idle areas contaminated with heavy metals (HMs). Conventional remediation methods are often costly, environmentally disruptive, and pose risks to human health. As a sustainable alternative, a biological approach utilizing metal-tolerant plant growth-promoting bacteria (mPGPBs) was employed to remediate HM-contaminated soils and assess their biological safety.
View Article and Find Full Text PDFFront Oncol
August 2025
German Center for Lung Research (Deutsches Zentrum für Lungenforschung (DZL)) (Comprehensive Pneumology Center - Munich (CPC-M)), Munich, Germany.
Background: Predictors for checkpoint inhibitor-related pneumonitis (cinrPneumonitis) are desperately needed. This study aimed to investigate the pretreatment standardized uptake value (SUV) on [F]FDG-PET/CT of non-tumorous lung tissue as a predictive imaging marker for the development of cinrPneumonitis in 239 patients with lung cancer.
Methods: All patients with lung cancer receiving [F]Fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) prior to immune checkpoint inhibitor (ICI) therapy were included and retrospectively analyzed.
Eur J Pharm Biopharm
September 2025
WuXi Biologics, 299 Fute Zhong Road, Waigaoqiao Free Trade Zone, Shanghai 200131, China. Electronic address:
Polysorbate 80 (PS80), a vital stabilizer in biotherapeutic formulations, faces persistent oxidative degradation challenges that threaten drug product stability during storage. While PS80 instability has been studied for decades, the oxidation mechanisms in specific formulation-packaging systems remain poorly understood. This work resolves this knowledge gap by demonstrating that PS80 oxidative degradation occurs exclusively in histidine-buffered formulations stored in glass vials.
View Article and Find Full Text PDFIEEE J Biomed Health Inform
September 2025
The personalization of cancer treatment through drug combinations is critical for improving healthcare outcomes, increasing effectiveness, and reducing side effects. Computational methods have become increasingly important to prioritize synergistic drug pairs because of the vast search space of possible chemicals. However, existing approaches typically rely solely on global molecular structures, neglecting information exchange between different modality representations and interactions between molecular and fine-grained fragments, leading to limited understanding of drug synergy mechanisms for personalized treatment.
View Article and Find Full Text PDF