Protein fold recognition refers to predicting the most likely fold type of the query protein and is a critical step of protein structure and function prediction. With the popularity of deep learning in bioinformatics, protein fold recognition has obtained impressive progress. In this study, to extract the fold-specific feature to improve protein fold recognition, we proposed a unified deep metric learning framework based on a joint loss function, termed NPCFold. In addition, we also proposed an integrated machine learning model based on the similarity of proteins in various properties, termed NPCFoldpro. Benchmark experiments show both NPCFold and NPCFoldpro outperform existing protein fold recognition methods at the fold level, indicating that our proposed strategies of fusing loss functions and fusing features could improve the fold recognition level.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1021/acs.jcim.2c00959 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Molecular Basis for Short-Chain Thioester Hydrolysis by Acyl Hydrolases in -Acyltransferase Polyketide Synthases.
JACS Au
January 2025
Department of Chemistry, University of Warwick, Coventry CV4 7AL, U.K.
Polyketide synthases (PKSs) are multidomain enzymatic assembly lines that biosynthesize a wide selection of bioactive natural products from simple building blocks. In contrast to their -acyltransferase (AT) counterparts, -AT PKSs rely on stand-alone ATs to load extender units onto acyl carrier protein (ACP) domains embedded in the core PKS machinery. -AT PKS gene clusters also encode stand-alone acyl hydrolases (AHs), which are predicted to share the overall fold of ATs but function like type II thioesterases (TEs), hydrolyzing aberrant acyl chains from ACP domains to promote biosynthetic efficiency.
View Article and Find Full Text PDFAI-based analysis of fetal growth restriction in a prospective obstetric cohort quantifies compound risks for perinatal morbidity and mortality and identifies previously unrecognized high risk clinical scenarios.
BMC Pregnancy Childbirth
January 2025
Department of Obstetrics and Gynecology, Division of Maternal-Fetal Medicine, University of Utah Health, 30 N. Mario Capecchi Dr., Level 5 South, Salt Lake City, UT, 84132, USA.
Background: Fetal growth restriction (FGR) is a leading risk factor for stillbirth, yet the diagnosis of FGR confers considerable prognostic uncertainty, as most infants with FGR do not experience any morbidity. Our objective was to use data from a large, deeply phenotyped observational obstetric cohort to develop a probabilistic graphical model (PGM), a type of "explainable artificial intelligence (AI)", as a potential framework to better understand how interrelated variables contribute to perinatal morbidity risk in FGR.
Methods: Using data from 9,558 pregnancies delivered at ≥ 20 weeks with available outcome data, we derived and validated a PGM using randomly selected sub-cohorts of 80% (n = 7645) and 20% (n = 1,912), respectively, to discriminate cases of FGR resulting in composite perinatal morbidity from those that did not.
Aptamer-Antibody Birecognized Sandwich SERRS Biosensor in Accurate and Rapid Identification of Intraoperative Parathyroid Hormone.
Anal Chem
January 2025
State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, College of Energy, Discipline of Intelligent Instrument and Equipment, Cancer Center and Department of Breast and Thyroid Surgery, Department of Ultrasound, Xiang'an Hospital of Xiamen University, School of Medicine, Laboratory Animal Center Xiamen University, Xiamen University, Xiamen 361005, China.
With the increasing incidence of thyroid cancer worldwide and the increasing demand for surgery, the risk of parathyroid injury is also increasing, which will lead to postoperative hypoparathyroidism (HP) and hypocalcemia. In order to improve the quality of life of patients after surgery, there is an urgent need to develop a novel platform that can identify the parathyroid gland immediately during surgery. The parathyroid gland promotes the increase of blood calcium concentration by secreting parathyroid hormone (PTH).
View Article and Find Full Text PDFCoding Variants of the Genitourinary Development Gene Carry High Risk for Prostate Cancer.
JCO Precis Oncol
January 2025
Medical Research Service, Department of Veterans Affairs, Tennessee Valley Healthcare System, Nashville, TN.
Purpose: Considerable genetic heterogeneity is currently thought to underlie hereditary prostate cancer (HPC). Most families meeting criteria for HPC cannot be attributed to currently known pathogenic variants.
Methods: To discover pathogenic variants predisposing to prostate cancer, we conducted a familial case-control association study using both genome-wide single-allele and identity-by-descent analytic approaches.
InterDIA: Interpretable Prediction of Drug-induced Autoimmunity through Ensemble Machine Learning Approaches.
Toxicology
January 2025
Deparment of clinical pharmacy, Jieyang People's Hospital, 522000, China. Electronic address:
Drug-induced autoimmunity (DIA) is a non-IgE immune-related adverse drug reaction that poses substantial challenges in predictive toxicology due to its idiosyncratic nature, complex pathogenesis, and diverse clinical manifestations. To address these challenges, we developed InterDIA, an interpretable machine learning framework for predicting DIA toxicity based on molecular physicochemical properties. Multi-strategy feature selection and advanced ensemble resampling approaches were integrated to enhance prediction accuracy and overcome data imbalance.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!