Article
Multidisciplinary Sciences
Zander Harteveld, Jaume Bonet, Stephene Rosset, Che Yang, Fabian Sesterhenn, Bruno E. Correia
Summary: De novo protein design is a powerful tool to explore new sequences and structures not found in nature. By using the TopoBuilder method, we were able to design sequences that adopt predicted folds and demonstrated their stability through experimental characterization.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2022)
Article
Biochemistry & Molecular Biology
Francois Bucchini, Andrea Del Cortona, Lukasz Kreft, Alexander Botzki, Michiel Van Bel, Klaas Vandepoele
Summary: Advances in high-throughput sequencing have led to a massive increase in RNA-Seq transcriptome data, with de novo assembled (meta)transcriptomes becoming popular tools for investigating gene repertoires. However, these datasets often contain fragmented or contaminant sequences, making analysis difficult. To address these challenges, TRAPID 2.0 was developed as a web application for efficient processing of assembled transcriptome data, offering global characterization, functional analysis, and interactive data visualizations for extracting biological insights.
NUCLEIC ACIDS RESEARCH
(2021)
Article
Biochemistry & Molecular Biology
Francois Bucchini, Andrea Del Cortona, Lukasz Kreft, Alexander Botzki, Michiel Van Bel, Klaas Vandepoele
Summary: Advances in high-throughput sequencing have led to a massive increase in RNA-Seq transcriptome data, but also present new computational challenges. TRAPID 2.0 is a web application designed for fast and efficient processing of assembled transcriptome data, providing global characterization and multi-layer annotation for downstream analysis.
NUCLEIC ACIDS RESEARCH
(2021)
Article
Biochemical Research Methods
Minghua Hou, Chunxiang Peng, Xiaogen Zhou, Biao Zhang, Guijun Zhang
Summary: In this work, a multi-contact-based folding method called MultiCFold is introduced. It utilizes the detailed information from different contact maps to guide protein structure folding, and incorporates non-contact information as a supplement. Experimental results show that MultiCFold performs well in protein structure prediction.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Multidisciplinary Sciences
Daniel K. K. Hartline, Matthew C. C. Cieslak, Ann M. M. Castelfranco, Brandon Lieberman, Vittoria Roncalli, Petra H. H. Lenz
Summary: This study presents eight new high-quality de novo transcriptomes for six co-occurring species of calanoid copepods, including the first published ones for Neocalanus plumchrus, N. cristatus, Eucalanus bungii, and Metridia pacifica, as well as additional ones for N. flemingeri and Calanus marshallae. These species are ecologically important members of the sub-arctic North Pacific marine zooplankton communities. The study provides a resource for gene expression studies and enables quantitative inter- and intra-species comparisons of gene expression patterns across biological processes. It also demonstrates the potential use of the integrated database for discovering novel and evolutionarily-significant proteins in the Calanoida.
Article
Biotechnology & Applied Microbiology
Alex Di Genova, Elena Buena-Atienza, Stephan Ossowski, Marie-France Sagot
Summary: WENGAN is a genome assembler tool that produces high-quality human genome sequences at low computational cost. It achieves de novo assembly of four human genomes by combining sequencing data from multiple technologies, improving assembly contiguity and consensus quality.
NATURE BIOTECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Twinkle Tiwari, Mukesh Saraswat
Summary: This paper presents a firefly algorithm-based superpixel clustering method for vehicle segmentation in crowded and unstructured road traffic images. The proposed method incorporates the best solution to enhance the firefly algorithm and achieves good segmentation results on a traffic dataset.
Article
Multidisciplinary Sciences
Ivan Anishchenko, Samuel J. Pellock, Tamuka M. Chidyausiku, Theresa A. Ramelot, Sergey Ovchinnikov, Jingzhou Hao, Khushboo Bafna, Christoffer Norn, Alex Kang, Asim K. Bera, Frank DiMaio, Lauren Carter, Cameron M. Chow, Gaetano T. Montelione, David Baker
Summary: Recent progress in protein structure prediction using deep neural networks has shown that these networks can be used to design new proteins with novel functions, by generating new folded proteins with sequences unrelated to those of naturally occurring proteins.
Article
Computer Science, Artificial Intelligence
Himanshu Mittal, Avinash Chandra Pandey, Raju Pal, Ashish Tripathi
Summary: A novel clustering method using a variant of gravitational search algorithm is proposed in this study, with comparative analysis conducted among recent metaheuristic algorithms to validate its performance. Experimental results demonstrate that the proposed method outperforms in terms of accuracy and performance when dealing with different types of COVID-19 medical images.
APPLIED INTELLIGENCE
(2021)
Article
Biochemical Research Methods
Tim Kucera, Matteo Togninalli, Laetitia Meng-Papaxanthos
Summary: Motivation: Protein design is crucial for medical and biotechnological applications. However, creating novel proteins is laborious and time-consuming due to the complex mechanisms involved. Machine learning has shown promise in solving complex problems, particularly in generative modeling. In this study, the authors address the problem of general protein design by developing a conditional generative adversarial network called ProteoGAN. They evaluate the model using biologically and statistically inspired metrics and demonstrate its superiority over other deep-learning baselines.
Article
Computer Science, Artificial Intelligence
Alican Dogan, Derya Birant
Summary: This article introduces a new hierarchical clustering linkage method, the k-centroid link, and demonstrates through experiments its superior performance compared to traditional linkage methods.
APPLIED INTELLIGENCE
(2022)
Article
Engineering, Marine
Yuyao Liu, Wei Chen, Yu Chen, Wen Chen, Lina Ma, Zhou Meng
Summary: This study proposed a method for ocean front reconstruction based on sound speed profiles, which was applied to reconstruct the Gulf Stream front in a related sea area. The method utilizes iterative hierarchical clustering of sound speed profiles for judging frontal zones in different depth ranges.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Microbiology
Cong-Cong Liu, Shan-Shan Dong, Jia-Bin Chen, Chen Wang, Pan Ning, Yan Guo, Tie-Lin Yang
Summary: In this study, a novel clustering algorithm called MetaDecoder was introduced, which can classify metagenomic contigs based on the frequencies of k-mers and coverages. Benchmark tests on simulated and real-world datasets demonstrated that MetaDecoder can effectively cluster metagenomic contigs and has the potential to be a promising approach.
Article
Chemistry, Medicinal
Xiaochu Tong, Xiaohong Liu, Xiaoqin Tan, Xutong Li, Jiaxin Jiang, Zhaoping Xiong, Tingyang Xu, Hualiang Jiang, Nan Qiao, Mingyue Zheng
Summary: Generative models in the field of artificial intelligence have made remarkable achievements in drug design, covering various models and applications. Through generative models, compounds can be generated to expand the compound library, design compounds with specific properties, and use some publicly available tools to directly generate molecules.
JOURNAL OF MEDICINAL CHEMISTRY
(2021)
Article
Chemistry, Multidisciplinary
Martins Balodis, Manuel Cordova, Albert Hofstetter, Graeme M. Day, Lyndon Emsley
Summary: The determination of the three-dimensional atomic-level structure of powdered solids is an important goal in current chemistry. This study successfully determined the crystal structures of ampicillin, piroxicam, cocaine, and two polymorphs of the drug molecule AZD8329 using machine-learned isotropic chemical shifts generated on-the-fly to guide a Monte Carlo-based structure determination process.
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY
(2022)