Functional annotation of enzyme-encoding genes using deep learning with transformer layers

GB Kim, JY Kim, JA Lee, CJ Norsigian… - Nature …, 2023 - nature.com
Functional annotation of open reading frames in microbial genomes remains substantially
incomplete. Enzymes constitute the most prevalent functional gene class in microbial …

A transformer-based ensemble framework for the prediction of protein–protein interaction sites

M Mou, Z Pan, Z Zhou, L Zheng, H Zhang, S Shi, F Li… - Research, 2023 - spj.science.org
The identification of protein–protein interaction (PPI) sites is essential in the research of
protein function and the discovery of new drugs. So far, a variety of computational tools …

Precision enzyme discovery through targeted mining of metagenomic data

S Ariaeenejad, J Gharechahi… - Natural Products and …, 2024 - Springer
Metagenomics has opened new avenues for exploring the genetic potential of uncultured
microorganisms, which may serve as promising sources of enzymes and natural products for …

Machine learning for predicting protein properties: A comprehensive review

Y Wang, Y Zhang, X Zhan, Y He, Y Yang, L Cheng… - Neurocomputing, 2024 - Elsevier
In the field of protein engineering, the function and structure of proteins are key to
understanding cellular mechanisms, biological evolution, and biodiversity. With the …

Evidential deep learning for trustworthy prediction of enzyme commission number

SR Han, M Park, S Kosaraju, JM Lee… - Briefings in …, 2024 - academic.oup.com
The rapid growth of uncharacterized enzymes and their functional diversity urge accurate
and trustworthy computational functional annotation tools. However, current state-of-the-art …

FM-FCN: a neural network with filtering modules for accurate vital signs extraction

F Zhu, Q Niu, X Li, Q Zhao, H Su, J Shuai - Research, 2024 - spj.science.org
Neural networks excel at capturing local spatial patterns through convolutional modules, but
they may struggle to identify and effectively utilize the morphological and amplitude periodic …

[HTML][HTML] Reconstruction and metabolic profiling of the genome-scale metabolic network model of pseudomonas stutzeri a1501

Q Yuan, F Wei, X Deng, A Li, Z Shi, Z Mao, F Li… - Synthetic and Systems …, 2023 - Elsevier
Pseudomonas stutzeri A1501 is a non-fluorescent denitrifying bacteria that belongs to the
gram-negative bacterial group. As a prominent strain in the fields of agriculture and …

From unsuccessful to successful learning: profiling behavior patterns and student clusters in Massive Open Online Courses

H Shi, Y Zhou, VP Dennen, J Hur - Education and Information …, 2024 - Springer
The imbalance in student-teacher ratio and the diversity of student population pose
challenges to MOOC's quality of instructor support. An understanding of student profiles …

基因组深度挖掘驱动微生物萜类化合物高效发现

雷茹, 陶慧, 刘天罡 - 合成生物学, 2024 - synbioj.cip.com.cn
萜类天然产物广泛分布于动物, 植物, 微生物, 海洋无脊椎动物中, 具有复杂的化学结构和丰富的
生物活性. 人们通过从植物和微生物中直接分离提取的方式获得了大量萜类天然产物 …

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning

R Han, W Huang, L Luo, X Han, J Shen… - arXiv preprint arXiv …, 2024 - arxiv.org
Understanding and leveraging the 3D structures of proteins is central to a variety of
biological and drug discovery tasks. While deep learning has been applied successfully for …