Article
Biochemical Research Methods
Ruheng Wang, Junru Jin, Quan Zou, Kenta Nakai, Leyi Wei
Summary: In this study, we propose a BERT-based contrastive learning framework called PepBCL for predicting protein-peptide binding residues. This method eliminates the need for complex feature engineering by utilizing a well-pretrained protein language model to automatically extract and learn feature representations. Additionally, a contrastive learning module is used to optimize the feature representations of binding residues within the imbalanced dataset, resulting in improved performance. Experimental results demonstrate that our method outperforms existing techniques, and the integration of traditional features and learned features further enhances performance.
Article
Chemistry, Physical
Brian Andrews, Jose Guerra, Reinhard Schweitzer-Stenner, Brigita Urbanc
Summary: Molecular dynamics is a powerful tool for studying intrinsically disordered proteins, but its reliability depends on the accuracy of the force field. This study evaluates the performance of several force fields in capturing conformational dynamics of guest residues in peptides and finds that the Gaussian model outperforms all MD force fields. The weaknesses of MD force fields include insufficient variability of certain residue populations, oversampling of certain secondary structures, inadequate sampling of certain conformations, and lack of residue-specificity in the Ramachandran distributions.
PHYSICAL CHEMISTRY CHEMICAL PHYSICS
(2022)
Article
Chemistry, Physical
Zhili Lu, Qiaoxian Zhong, Jingxian Li, Bingjie Zhou, Yan-Ni Xing, Kaien Liu, Kexin Cao, Dongming Lan, Teng Zhou, Yonghua Wang, Jiaqi Wang
Summary: This study used computational approaches and mutagenesis strategies to enhance the stability of a diacylglycerol-specific lipase. Several mutations were found to significantly improve the thermostability and enzymatic activity of the enzyme. Structural analysis revealed how these mutations can release steric strain and increase stability. This suggests that substitution with glycine could be a promising strategy for improving protein thermostability.
Article
Automation & Control Systems
Wen Yu, Erick de la Rosa
Summary: The article proposes a neural model that combines RBM and feedforward NN for learning system dynamics and input-output probability distributions. By comparing two nonlinear systems, the results show that this novel model performs better in handling complex system dynamics and large noises.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2021)
Article
Psychology, Multidisciplinary
Marcus Lindskog, Par Nystrom, Gustaf Gredeback
Summary: Research indicates that the adult human brain has the ability to build a representation of the complex, global pattern of a probability distribution, providing a novel tool for a deeper understanding of related neural mechanics.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Biochemical Research Methods
Jun Zhang, Qingcai Chen, Bin Liu
Summary: The study introduces a new computational method called NCBRPred to predict nucleic acid binding residues in proteins using multilabel sequence labeling model, achieving higher predictive results with lower cross-prediction than existing predictors.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Construction & Building Technology
Fizza Hussain, Yasir Ali, Muhammad Irfan
Summary: This study proposed an alternative approach for modeling the phase angle characteristics of asphalt concrete mixtures based on a recurrent neural network, which effectively captures the effects of covariates and is suitable for sequential data recorded in laboratory testing. By comparing with other competing models, the results demonstrate the superior performance of the proposed approach.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2021)
Article
Multidisciplinary Sciences
Tika Ram Lamichhane, Madhav Prasad Ghimire
Summary: This study evaluated the interactions between a potential drug candidate and the substrate binding site residues of SARS-CoV-2 main protease using molecular docking and dynamics simulations. It found strong interactions between the inhibitor and M-pro, demonstrated by physical parameters, dihedral angle distributions, and radial distribution function peaks. The MM/PBSA free energy of binding between M-pro and the inhibitor was calculated to be -19.45 +/- 3.6 kcal/mol, indicating the binding nature of the inhibitor in the ligand binding domain of M-pro.
Article
Mathematics, Applied
Yizhi Sun, Zhilin Sun
Summary: This work establishes a bridge between probability methods and finite element methods, introducing a spherical probability model and providing sufficient conditions for generating density functions through discrete polynomial spectrum. Computer-based numerical simulations show that the theoretically verified criteria for probability distribution are almost optimal in testing examples.
COMPUTERS & MATHEMATICS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Eng-Jon Ong, Sameed Husain, Miroslaw Bober
Summary: Aggregation is a common process in deep neural network models, which consolidates deep features into a more compact representation, increasing robustness and spatial invariance. Information theoretic methods help to understand the relationship between aggregated features and network performance. We propose a mathematical model to analyze the probability distributions of output values in aggregation layers, and experimentally verify our predictions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Environmental Sciences
Emily V. Upcott, Peter A. Henrys, John W. Redhead, Susan G. Jarvis, Richard F. Pywell
Summary: Cropping decisions have significant impacts on agricultural management strategies and environmental outcomes. Mapping and predicting crop rotations enable targeted mitigation measures and risk forecasting. The study demonstrates the complexity of crop rotations and suggests their importance across disciplines beyond agronomy and ecology.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Mathematics, Applied
Yizhi Sun, Zhilin Sun
Summary: This work investigates the convexity of a specific class of positive definite probability measures and demonstrates the preservation of convexity under multiplication and intertwining product. The study reveals that any integrable function on an interval with a polynomial expansion of fast absolute convergence can be decomposed into a pair of positive convex interval probabilities, simplifying the study of interval distributions and discontinuous probabilistic Galerkin schemes.
COMPUTERS & MATHEMATICS WITH APPLICATIONS
(2024)
Article
Mathematical & Computational Biology
Lingsong Yao, Huadong Wang, Yannan Bin
Summary: Researchers proposed a method named SPDH to predict hot spot residues at protein-DNA binding interfaces solely based on protein sequences, which outperformed other methods on an independent test set.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2021)
Article
Biochemistry & Molecular Biology
Wei Wang, Xili Su, Dong Liu, Hongjun Zhang, Xianfang Wang, Yun Zhou
Summary: This paper introduces a method to improve the accuracy of protein flexibility prediction and applies it to DNA-binding proteins and Coronavirus proteins. The results of the study indicate that protein dihedral angle information, evolution information, and physicochemical properties of amino acids play an important role in protein flexibility.
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
(2023)
Article
Green & Sustainable Science & Technology
Theodoros Konstantinou, Nikos Hatziargyriou
Summary: This article investigates parametric probabilistic forecasting for solar and wind power generation and proposes an ensemble artificial neural network model with a Meta-Learner and sub-models component. The results show that the proposed model outperforms state of the art parametric and non-parametric probabilistic techniques.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Chemistry, Physical
Dimitar V. Pachov, Rasmus Fonseca, Damien Arnol, Julie Bernauer, Henry van den Bedem
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2016)
Article
Biochemical Research Methods
Rasmus Fonseca, Henry van den Bedem, Julie Bernauer
JOURNAL OF COMPUTATIONAL BIOLOGY
(2016)
Article
Chemistry, Physical
Anil Kurut, Rasmus Fonseca, Wouter Boomsma
JOURNAL OF PHYSICAL CHEMISTRY B
(2018)
Article
Biochemistry & Molecular Biology
Dominik Budday, Rasmus Fonseca, Sigrid Leyendecker, Henry van den Bedem
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
(2017)
Article
Chemistry, Multidisciplinary
Rasmus Fonseca, Dominik Budday, Henry van den Bedem
JOURNAL OF COMPUTATIONAL CHEMISTRY
(2018)
Article
Biochemical Research Methods
Pawel Winter, Rasmus Fonseca
JOURNAL OF COMPUTATIONAL BIOLOGY
(2012)
Article
Biochemical Research Methods
Rasmus Fonseca, Pawel Winter
JOURNAL OF COMPUTATIONAL BIOLOGY
(2012)
Article
Biochemistry & Molecular Biology
Rasmus Fonseca, Dimitar V. Pachov, Julie Bernauer, Henry van den Bedem
NUCLEIC ACIDS RESEARCH
(2014)
Article
Chemistry, Medicinal
Gydo C. P. van Zundert, Brandi M. Hudson, Saulo H. P. de Oliveira, Daniel A. Keedy, Rasmus Fonseca, Amelie Heliou, Pooja Suresh, Kenneth Borrelli, Tyler Day, James S. Fraser, Henry van den Bedem
JOURNAL OF MEDICINAL CHEMISTRY
(2018)
Article
Multidisciplinary Sciences
Antoine Koehl, Hongli Hu, Dan Feng, Bingfa Sun, Yan Zhang, Michael J. Robertson, Matthew Chu, Tong Sun Kobilka, Toon Laermans, Jan Steyaert, Jeffrey Tarrasch, Somnath Dutta, Rasmus Fonseca, William I. Weis, Jesper M. Mathiesen, Georgios Skiniotis, Brian K. Kobilka
Article
Multidisciplinary Sciences
A. J. Venkatakrishnan, Anthony K. Ma, Rasmus Fonseca, Naomi R. Latorraca, Brendan Kelly, Robin M. Betz, Chaitanya Asawa, Brian K. Kobilka, Ron O. Dror
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2019)
Article
Multidisciplinary Sciences
Hideaki E. Kato, Yan Zhang, Hongli Hu, Carl-Mikael Suomivuori, Francois Marie Ngako Kadji, Junken Aoki, Kaavya Krishna Kumar, Rasmus Fonseca, Daniel Hilger, Weijiao Huang, Naomi R. Latorraca, Asuka Inoue, Ron O. Dror, Brian K. Kobilka, Georgios Skiniotis
Proceedings Paper
Mathematical & Computational Biology
A. Heliou, Dominik Budday, Rasmus Fonseca, Henry van den Bedem
ACM-BCB' 2017: PROCEEDINGS OF THE 8TH ACM INTERNATIONAL CONFERENCE ON BIOINFORMATICS, COMPUTATIONAL BIOLOGY,AND HEALTH INFORMATICS
(2017)
Article
Biochemical Research Methods
Amelie Heliou, Dominik Budday, Rasmus Fonseca, Henry van den Bedem
Proceedings Paper
Biochemical Research Methods
Rasmus Fonseca, Henry van den Bedem, Julie Bernauer
RESEARCH IN COMPUTATIONAL MOLECULAR BIOLOGY (RECOMB 2015)
(2015)