Article
Biotechnology & Applied Microbiology
Yang Fang, Menglong Li, Xufeng Li, Yi Yang
Summary: GFICLEE is a new tree-based phylogenetic profiling algorithm that infers common loss events in evolutionary patterns, showing better predictive performance and high computational efficiency for exploring gene functions at the genome-wide level.
Review
Biochemistry & Molecular Biology
Gaurav D. Diwan, Juan Carlos Gonzalez-Sanchez, Gordana Apic, Robert B. Russell
Summary: The necessity to interpret genetic variants in terms of pathology or biological mechanism is urgent, with many insights into protein function impacted by genetic changes obtainable from three-dimensional structures. The development of precise methods, like Alphafold2, to predict structures from amino acid sequences may greatly benefit those seeking to understand genetic changes. This paper examines the current state of protein structures known for human and other proteomes, as well as the potential impact of Alphafold2 on variant interpretation efforts, suggesting that the available structural data for the human proteome may have a smaller impact on interpretation than anticipated. Additional efforts in structure prediction are also discussed for aiding the understanding of genetic variants.
JOURNAL OF MOLECULAR BIOLOGY
(2021)
Article
Biochemistry & Molecular Biology
Luciana Esposito, Nicole Balasco, Luigi Vitagliano
Summary: Oligomerization plays an important role in conferring certain properties to proteins. This study utilized the machine-learning algorithms implemented in AlphaFold to predict the structural states of functional oligomers in the KCTD protein family. The findings identified reliable three-dimensional models for several pentameric states that were previously uncharacterized from a structural point of view. The study provides a comprehensive view of KCTD protein oligomerization and offers insights into key biological processes.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Plant Sciences
Lirong Cai, Holger Kreft, Amanda Taylor, Pierre Denelle, Julian Schrader, Franz Essl, Mark van Kleunen, Jan Pergl, Petr Pysek, Anke Stein, Marten Winter, Julie F. Barcelona, Nicol Fuentes, Inderjit, Dirk Nikolaus Karger, John Kartesz, Andreij Kuprijanov, Misako Nishino, Daniel Nickrent, Arkadiusz Nowak, Annette Patzelt, Pieter B. Pelser, Paramjit Singh, Jan J. Wieringa, Patrick Weigelt
Summary: This study used machine learning and conventional statistical methods to investigate and predict global plant diversity, revealing complex interactions between environmental factors and plant diversity. Current climate and environmental heterogeneity were found to be the primary drivers, while past environmental conditions had smaller but detectable impacts on plant diversity. The results provide accurate estimates of global plant diversity at resolutions relevant for conservation and macroecology.
Article
Biochemistry & Molecular Biology
Tobias Olenyi, Celine Marquet, Michael Heinzinger, Benjamin Kroeger, Tiha Nikolova, Michael Bernhofer, Philip Saendig, Konstantin Schuetze, Maria Littmann, Milot Mirdita, Martin Steinegger, Christian Dallago, Burkhard Rost
Summary: The availability of accurate and fast AI solutions for predicting protein aspects is revolutionizing molecular biology. LambdaPP is a webserver aiming to replace the first internet server PredictProtein from 1992, providing AI protein predictions. LambdaPP offers accessible visualizations of protein 3D structure and predictions at both the protein level and residue level, including various phenotypes, within seconds.
Article
Genetics & Heredity
Cole A. Deisseroth, Won-Seok Lee, Jiyoen Kim, Hyun-Hwan Jeong, Ryan S. Dhindsa, Julia Wang, Huda Y. Zoghbi, Zhandong Liu
Summary: Correcting the underlying molecular imbalance may be more effective than symptomatic treatment for Mendelian disorders. PARMESAN is a computational tool that searches PubMed and PubMed Central to assemble drug-gene and gene-gene relationships into a central knowledge base. It predicts novel drug-gene relationships and assigns evidence-based scores to each prediction.
AMERICAN JOURNAL OF HUMAN GENETICS
(2023)
Article
Physics, Fluids & Plasmas
A. Banon Navarro, A. Di Siena, J. L. Velasco, F. Wilms, G. Merlo, T. Windisch, L. L. LoDestro, J. B. Parker, F. Jenko
Summary: In this article, a new computer simulation method is proposed to predict plasma profiles in modern optimized stellarators. The researchers identified the cause of energy confinement degradation in electron-heated plasmas and provided a solution to this issue.
Article
Engineering, Marine
Wen Chen, Kaijun Ren, Yongchui Zhang, Yuyao Liu, Yu Chen, Lina Ma, Silin Chen
Summary: The study uses the Single Empirical Orthogonal Function Regression (sEOF-R) method to establish the regression relationship between surface parameters and sound speed anomaly profiles (SSAP) in three typical sea areas. Based on this relationship and the surface parameters, the underwater sound speed profile (SSP) is reconstructed. The results show that the reconstruction effects are best in the Northeast Pacific, followed by the equator and then the Kuroshio Extension (KE). The study also analyzes the factors influencing the reconstruction effect and concludes that local sea level anomaly (SLA) and sea surface temperature anomaly (SSTA) play important roles.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Fang Xu, Ganggang Guo, Feida Zhu, Xiaojun Tan, Liqing Fan
Summary: This study introduces the DPPCG framework to identify causal genes for specific disease phenotypes using deep learning computational modeling. By integrating heterogeneous biomedical big data, it creatively utilizes protein deep profiles and deep CNN models to predict causal genes of male infertility and associated pathological processes.
INFORMATION FUSION
(2021)
Article
Genetics & Heredity
Xiaoting Wang, Nan Zhang, Yulan Zhao, Juan Wang
Summary: The study introduced the TSSN method for constructing PPI networks and proposed the NNP algorithm for identifying protein complexes, which can accurately filter PPI data noise and identify more protein complexes.
FRONTIERS IN GENETICS
(2021)
Article
Environmental Sciences
Yonglan Miao, Xuefeng Zhang, Yunbo Li, Lianxin Zhang, Dianjun Zhang
Summary: A hybrid model combining convolutional neural network (CNN) and transfer learning (TL) was established to predict sea surface temperature anomalies (SSTAs) and sea surface height anomalies (SSHAs) at monthly scales. The model effectively captures the evolving spatial characteristics of SSTAs and SSHAs with low prediction errors over a 30-day range.
FRONTIERS IN MARINE SCIENCE
(2023)
Article
Forestry
Rong Zhao, Shicheng Cao, Jianjun Zhu, Longchong Fu, Yanzhou Xie, Tao Zhang, Haiqiang Fu
Summary: Forest height and vertical structure can be estimated using PolInSAR data based on RVoG model and PCT theory. A forest height inversion algorithm based on PCT technology was developed using dual-baseline PolInSAR data. The accuracy of the proposed method was validated using LiDAR and PolInSAR data.
Article
Chemistry, Multidisciplinary
Shailesh Kumar Panday, Emil Alexov
Summary: A Gaussian-based method called f5-MM/PBSA/E is proposed for estimating protein-protein binding entropy to predict binding free energy. This method is computationally efficient and achieves similar or better performance compared to other computationally demanding approaches when tested on a dataset of 46 protein-protein binding cases.
Article
Computer Science, Interdisciplinary Applications
Yazhen Sun, Rui Guo, Lin Gao, Changyu Wu, Huaizhi Zhang
Summary: The study found that using a third power function design for the transition zone profile of ski jumping inrun is more beneficial for athletes' skiing, improving competition levels and optimizing the system. By considering air resistance and skiing friction, dynamic differential equations were used to investigate skiing velocity and force exertion of athletes under different profiles.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Biology
Xiao-Yao Qiu, Hao Wu, Jiangyi Shao
Summary: In this study, the integration of sequence embeddings, contact map embeddings, and GO label embeddings based on the TALE architecture was employed to improve the accuracy of protein function prediction, outperforming other existing methods.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)