98%
921
2 minutes
20
Drug-target interaction (DTI) prediction is a crucial component of drug discovery. Recent deep learning methods show great potential in this field but also encounter substantial challenges. These include generating reliable confidence estimates for predictions, enhancing robustness when handling novel, unseen DTIs, and mitigating the tendency toward overconfident and incorrect predictions. To solve these problems, we propose EviDTI, a novel approach utilizing evidential deep learning (EDL) for uncertainty quantification in neural network-based DTI prediction. EviDTI integrates multiple data dimensions, including drug 2D topological graphs and 3D spatial structures, and target sequence features. Through EDL, EviDTI provides uncertainty estimates for its predictions. Experimental results on three benchmark datasets demonstrate the competitiveness of EviDTI against 11 baseline models. In addition, our study shows that EviDTI can calibrate prediction errors. More importantly, well-calibrated uncertainty information enhances the efficiency of drug discovery by prioritizing DTIs with higher confident predictions for experimental validation. In a case study focused on tyrosine kinase modulators, uncertainty-guided predictions identify novel potential modulators targeting tyrosine kinase FAK and FLT3. These results underscore the potential of evidential deep learning as a robust tool for uncertainty quantification in DTI prediction and its broader implications for accelerating drug discovery.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12297561 | PMC |
http://dx.doi.org/10.1038/s41467-025-62235-6 | DOI Listing |
Materials (Basel)
August 2025
School of Transportation, Southeast University, Nanjing 210018, China.
Permittivity measurements of concrete materials benefit from the application of high-frequency electromagnetic waves (HF-EMWs), but they still face the problem of being aleatory and exhibit epistemic uncertainty, originating from multi-phase heterogeneous materials and the limited knowledge of HF-EMW propagation. This limitation restricts the precision of non-destructive testing. This study proposes an evidential regression deep network for conducting permittivity measurements with uncertainty quantification.
View Article and Find Full Text PDFInfect Dis Now
August 2025
Groupe Infectiologie Digitale-SPILF, Paris, France; Infectious Disease Department, University Hospital Montpellier, Montpellier France; ERIOS, University Hospital Montpellier, Montpellier, France.
Artificial intelligence (AI) is set to permeate every facet of infectious disease practice-from prevention and public health surveillance to epidemic management and bedside care. Routine care data (laboratory results, medication orders, progress notes) and research-generated datasets now fuel state-of-the-art machine-learning (ML) pipelines that sharpen diagnosis, prognosis, antimicrobial stewardship, and, by combining both sources, accelerate drug discovery. In diagnostics, deep networks that now flag pneumonia or tuberculosis on chest images are increasingly able to identify-and localize-virtually more infectious processes throughout the body, while simultaneously predicting pathogen identity and antimicrobial resistance from routine microbiology.
View Article and Find Full Text PDFKnee Surg Sports Traumatol Arthrosc
September 2025
Hospital for Special Surgery, New York, New York, USA.
Introduction: Deep learning (DL) models have achieved remarkable performance in musculoskeletal (MSK) medical imaging research, yet their clinical integration remains hindered by their black-box nature and the absence of reliable confidence measures. Uncertainty quantification (UQ) seeks to bridge this gap by providing each DL prediction with a calibrated estimate of uncertainty, thereby fostering clinician trust and safer deployment.
Methods: We conducted a targeted narrative review, performing expert-driven searches in PubMed, Scopus, and arXiv and mining references from relevant publications in MSK imaging utilizing UQ, and a thematic synthesis was used to derive a cohesive taxonomy of UQ methodologies.
Nat Commun
July 2025
Academy of Military Medical Sciences, Beijing, China.
Drug-target interaction (DTI) prediction is a crucial component of drug discovery. Recent deep learning methods show great potential in this field but also encounter substantial challenges. These include generating reliable confidence estimates for predictions, enhancing robustness when handling novel, unseen DTIs, and mitigating the tendency toward overconfident and incorrect predictions.
View Article and Find Full Text PDFJ Biomed Inform
September 2025
Department of Biostatistics Data Science, University of Kansas Medical Center and University of Kansas Cancer Center, Kansas City, 66160, KS, USA. Electronic address:
Early diagnosis of breast cancer remains a significant global health challenge, and the potential use of deep learning in Digital Breast Tomosynthesis (DBT) based breast cancer diagnosis is a promising avenue. To address data scarcity and domain shift problems in building a lesion malignancy predictive model, we proposed a domain adaptive automated multiobjective neural network (Adaptive-AutoMO) for reliable lesion malignancy prediction via DBT. Adaptive-AutoMO addresses three key challenges simultaneously, they are: privacy preserving, credibility measurement, and balance, which consists of training, adaptation and testing stages.
View Article and Find Full Text PDF