AI Article Synopsis
- The study focuses on using supervised learning with recurrent neural networks (RNNs) to predict protein secondary structures based on amino acid sequences.
- It proposes a combination of modular reciprocal recurrent neural networks (MRR-NN) for adjacent structure correlations and multilayer bidirectional recurrent neural networks (MBR-NN) for capturing long-range interactions.
- The integrated system achieved an accuracy of 79.36% and a segment overlap score of 70.09% on the PSIPRED dataset during three-fold cross-validation.
Article Abstract
The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q₃) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.cmpb.2010.04.005 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Endophytic Microbial Community Structure and Dynamics Influence Agarwood Formation in Aquilaria malaccensis Lam.
Curr Microbiol
January 2025
DBT-North East Centre for Agricultural Biotechnology, Assam Agricultural University, Jorhat, Assam, 785013, India.
Aquilaria malaccensis Lam., an Agarwood-producing tree native to Southeast Asia, secretes oleoresin, a resin with diverse applications, in response to injuries. To explore the role of endosphere microbial communities during Agarwood development, we utilized a metagenomics approach across three stages: non-symptomatic (NC), symptomatic early (IN), and symptomatic mature (IN1).
View Article and Find Full Text PDFAn active protein from Dendrobium officinale residue: Protects the gastric mucosa and stabilized in the gastrointestinal tract.
Int J Biol Macromol
January 2025
Changchun University of Chinese Medicine, Key Laboratory of Ginseng Efficacy Substance Base and Biological Mechanism Research, Ministry of Education, Changchun 130117, China; Northeast Asia Research Institute of Traditional Chinese Medicine, Changchun University of Chinese Medicine, Changchun 130117, China. Electronic address:
A large number of by-products generated in the food industry is discarded as waste, especially the residue left after extracting plant resources, which is typically repurposed as fertilizer. In this study, we extracted and purified a new protein, DOP1, from the residue of Dendrobium officinale Kimura & Migo (D. officinale), and explored the protective effect of DOP1 on alcohol-induced gastric mucosal injury.
View Article and Find Full Text PDFDecellularized cartilage tissue bioink formulation for osteochondral graft development.
Biomed Mater
January 2025
Department of Orthopaedic Surgery, University of Connecticut, Chemical, Materials & Biomolecular Engineering MC-3711, ARB7-E7018, 263 Farmington Avenue, Farmington, CT 06032, USA, Storrs, Connecticut, 06269, UNITED STATES.
Articular cartilage and osteochondral defect repair and regeneration presents significant challenges to the field of tissue engineering (TE). TE and regenerative medicine strategies utilizing natural and synthetic-based engineered scaffolds have shown potential for repair, however, they face limitations in replicating the intricate native microenvironment and structure to achieve optimal regenerative capacity and functional recovery. Herein, we report the development of a cartilage extracellular matrix (ECM) as a printable biomaterial for tissue regeneration.
View Article and Find Full Text PDFStructures and properties of α-amylase and glucoamylase immobilized by ZIF-8 via one-pot preparation.
Enzyme Microb Technol
December 2024
Guangxi Key Laboratory of Natural Polymer Chemistry and Physics, College of Chemistry and Materials, Nanning Normal University, Nanning 530001, PR China.
The immobilization of α-amylase and glucoamylase using a metal-organic framework (enzyme@ZIF-8) was prepared in situ through a one-pot method. The morphology, crystal structure, and molecular characteristics of the free enzyme and enzyme@ZIF-8 were characterized. The enzyme@ZIF-8 exhibited the rhombic dodecahedron morphology, with a decrease in particle size.
View Article and Find Full Text PDFA workflow to assess the recoverability of secondary raw materials via physical separation.
Waste Manag
January 2025
Helmholtz-Zentrum Dresden-Rossendorf, Helmholtz-Institute Freiberg for Resource-Technology, Freiberg, Germany.
Printed circuit boards represent an extraordinarily challenging fraction for the recycling of waste electric and electronic equipment. Due to the closely interlinked structure of the composing materials, the selective recycling of copper and closely associated precious metals from this composite material is compromised by losses during mechanical pre-processing. This problem could partially be overcome by a better understanding of the influence of particle size and shape on the recovery of finely comminuted and well-liberated metal particles during mechanical separation.
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!