Results 61 to 70 of about 539,097 (330)

Structural insights into an engineered feruloyl esterase with improved MHET degrading properties

FEBS Letters, EarlyView.
A feruloyl esterase was engineered to mimic key features of MHETase, enhancing the degradation of PET oligomers. Structural and computational analysis reveal how a point mutation stabilizes the active site and reshapes the binding cleft, expading substrate scope.
Panagiota Karampa, Konstantinos Makryniotis, Theofani‐Iosifina Sousani, Evangelos Topakas, Vangelis Daskalakis, Maria Dimarogona   +5 more
wiley   +1 more source

LPI-EnEDT: an ensemble framework with extra tree and decision tree classifiers for imbalanced lncRNA-protein interaction data classification

BioData Mining, 2021
Background Long noncoding RNAs (lncRNAs) have dense linkages with various biological processes. Identifying interacting lncRNA-protein pairs contributes to understand the functions and mechanisms of lncRNAs. Wet experiments are costly and time-consuming.
Lihong Peng, Ruya Yuan, Ling Shen, Pengfei Gao, Liqian Zhou   +4 more
doaj   +1 more source

IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance [PDF]

, 2021
Grace Deng, Cuize Han, Tommaso Dreossi, Clarence Lee, David S. Matteson   +4 more
openalex   +1 more source

Gut microbiome and aging—A dynamic interplay of microbes, metabolites, and the immune system

FEBS Letters, EarlyView.
Age‐dependent shifts in microbial communities engender shifts in microbial metabolite profiles. These in turn drive shifts in barrier surface permeability of the gut and brain and induce immune activation. When paired with preexisting age‐related chronic inflammation this increases the risk of neuroinflammation and neurodegenerative diseases.
Aaron Mehl, Eran Blacher
wiley   +1 more source

Low-shot learning and class imbalance: a survey

Journal of Big Data
The tasks of few-shot, one-shot, and zero-shot learning—or collectively “low-shot learning” (LSL)—at first glance are quite similar to the long-standing task of class imbalanced learning; specifically, they aim to learn classes for which there is little ...
Preston Billion Polak, Joseph D. Prusa, Taghi M. Khoshgoftaar   +2 more
doaj   +1 more source

EVALUATION OF MULTIVARIATE ADAPTIVE REGRESSION SPLINES ON IMBALANCED DATASET FOR POVERTY CLASSIFICATION IN BENGKULU PROVINCE

Barekeng
Classification is a statistical method that aims to predict the class of an object whose class label is unknown. The Multivariate Adaptive Regression Splines (MARS) classification method is a classification model that involves several basis functions ...
Idhia Sriliana, Sigit Nugroho, Winalia Agwil, Esther Damayanti Sihombing   +3 more
doaj   +1 more source

Linking neurogenesis, oligodendrogenesis, and myelination defects to neurodevelopmental disruption in primary mitochondrial disorders

FEBS Letters, EarlyView.
Mitochondrial remodeling shapes neural and glial lineage progression by matching metabolic supply with demand. Elevated OXPHOS supports differentiation and myelin formation, while myelin compaction lowers mitochondrial dependence, revealing mitochondria as key drivers of developmental energy adaptation.
Sahitya Ranjan Biswas, Porter L. Tomsick, Alicia M. Pickrell, Paul D. Morton   +3 more
wiley   +1 more source

Organizing the interface—Plasma membrane architecture and receptor dynamics in virus‐cell interactions

FEBS Letters, EarlyView.
Plasma membranes contain dynamic nanoscale domains that organize lipids and receptors. Because viruses operate at similar scales, this architecture shapes early infection steps, including attachment, receptor engagement, and entry. Using influenza A virus and HIV‐1 as examples, we highlight how receptor nanoclusters, multivalent glycan interactions ...
Jan Schlegel, Christian Sieben
wiley   +1 more source

Assessing feature selection method performance with class imbalance data

Machine Learning with Applications, 2021
Identifying the most informative features is a crucial step in feature selection. This paper focuses primarily on wrapper feature selection methods designed to detect important features with F1-score as the target metric. As an initial step, most wrapper
Surani Matharaarachchi, Mike Domaratzki, Saman Muthukumarana   +2 more
doaj   +1 more source

AAA+ protein unfoldases—the Moirai of the proteome

FEBS Letters, EarlyView.
AAA+ unfoldases are essential molecular motors that power protein degradation and disaggregation. This review integrates recent cryo‐electron microscopy (cryo‐EM) structures and single‐molecule biophysical data to reconcile competing models of substrate translocation.
Stavros Azinas, Marta Carroni
wiley   +1 more source