Identification of Dementia & Mild Cognitive Impairment in Chinese Elderly Using Machine Learning.

OBJECTIVE: To assess the role of Machine Learning (ML) in identification critical factors of dementia and mild cognitive impairment. METHODS: 371 elderly individuals were ultimately included in the ML analysis. Demographic information (including gender, age, parity, visual acuity, auditory function, mobility, and medication history) and 35 features from 10 assessment scales were used for modeling. Five machine learning classifiers were used for evaluation, employing a procedure involving feature extraction, selection, model training, and performance assessment to identify key indicative factors. RESULTS: The Random Forest model, after data preprocessing, Information Gain, and Meta-analysis, utilized three training features and four meta-features, achieving an area under the curve of 0.961 and a accuracy of 0.894, showcasing exceptional accuracy for the identification of dementia and mild cognitive impairment. CONCLUSIONS: ML serves as a identification tool for dementia and mild cognitive impairment. Using Information Gain and Meta-feature analysis, Clinical Dementia Rating (CDR) and Neuropsychiatric Inventory (NPI) scale information emerged as crucial for training the Random Forest model.

Simultaneously degradation of various phthalate esters by Rhodococcus sp. AH-ZY2: Strain, omics and enzymatic study.

Phthalate esters (PAEs) are widely used as plasticizers and cause serious complex pollution problem in environment. Thus, strains with efficient ability to simultaneously degrade various PAEs are required. In this study, a newly isolated strain Rhodococcus sp. AH-ZY2 can degrade 500 mg/L Di-n-octyl phthalate completely within 16 h and other 500 mg/L PAEs almost completely within 48 h at 37 °C, 180 rpm, and 2 % (v/v) inoculum size of cultures with a OD600 of 0.8. OD600 = 0.8, 2 % (v/v). Twenty genes in its genome were annotated as potential esterase and four of them (3963, 4547, 5294 and 5359) were heterogeneously expressed and characterized. Esterase 3963 and 4547 is a type I PAEs esterase that hydrolyzes PAEs to phthalate monoesters. Esterase 5294 is a type II PAEs esterase that hydrolyzes phthalate monoesters to phthalate acid (PA). Esterase 5359 is a type III PAEs esterase that simultaneously degrades various PAEs to PA. Molecular docking results of 5359 suggested that the size and indiscriminate binding feature of spacious substrate binding pocket may contribute to its substrate versatility. AH-ZY2 is a potential strain for efficient remediation of PAEs complex pollution in environment. It is first to report an esterase that can efficiently degrade mixed various PAEs.

Assimilation of phthalate esters in bacteria.

The massive usage of phthalate esters (PAEs) has caused serious pollution. Bacterial degradation is a potential strategy to remove PAE contamination. So far, an increasing number of PAE-degrading strains have been isolated, and the catabolism of PAEs has been extensively studied and reviewed. However, the investigation into the bacterial PAE uptake process has received limited attention and remains preliminary. PAEs can interact spontaneously with compounds like peptidoglycan, lipopolysaccharides, and lipids on the bacterial cell envelope to migrate inside. However, this process compromises the structural integrity of the cells and causes disruptions. Thus, membrane protein-facilitated transport seems to be the main assimilation strategy in bacteria. So far, only an ATP-binding-cassette transporter PatDABC was proven to transport PAEs across the cytomembrane in a Gram-positive bacterium Rhodococcus jostii RHA1. Other cytomembrane proteins like major facilitator superfamily (MFS) proteins and outer membrane proteins in cell walls like FadL family channels, TonB-dependent transporters, and OmpW family proteins were only reported to facilitate the transport of PAEs analogs such as monoaromatic and polyaromatic hydrocarbons. The functions of these proteins in the intracellular transport of PAEs in bacteria await characterization and it is a promising avenue for future research on enhancing bacterial degradation of PAEs. KEY POINTS: • Membrane proteins on the bacterial cell envelope may be PAE transporters. • Most potential transporters need experimental validation.