Search

Cancer is one of the deadliest diseases in the world.Using machine learning to process microarray data plays an important role in assisting the early diagnosis of cancer,but the numbers of genetic features are much more than samples,leading to an imbalance in the sample,and the efficiency and accuracy of classification are affected,so it is important to select the feature of gene array data.Most of the existing feature selection algorithms are single condition feature selection,which seldom consider feature extraction.Most of them use the long-existing neural network and have low classification accuracy.So,a two-stage deep feature selection(TSDFS) algorithm is proposed.The first stage aggregates three feature selection algorithms for comprehensive feature selection,and feature subsets are obtained.In the second stage,unsupervised neural network is used to obtain the best representation of feature subset and improve the final classification accuracy.This paper analyzes the effectiveness of TSDFS by comparing the classification effect before and after feature selection and different feature selection algorithms.Experimental results show that TSDFS algorithm can reduce the number of features while maintaining or improving the accuracy of classification.

Calcium is a vital trace element for the human body, and its deficiency can result in a range of pathological conditions, including rickets and osteoporosis. Despite the numerous types of calcium supplements currently available on the market, these products are afflicted with a number of inherent deficiencies, such as low calcium content, poor aqueous solubility, and low human absorption rate. Many microorganisms, particularly beneficial microorganisms, including edible fungi, lactic acid bacteria, and yeast, are capable of absorbing and enriching calcium, a phenomenon that has been widely documented. This opens the door to the potential utilization of microorganisms as novel calcium enrichment carriers. However, the investigation of calcium-rich foods from microorganisms still faces many obstacles, including a poor understanding of calcium metabolic pathways in microorganisms, a relatively low calcium enrichment rate, and the slow growth of strains. Therefore, in order to promote the development of calcium-rich products from microorganisms, this paper provides an overview of the impacts of calcium addition on strain growth, calcium enrichment rate, antioxidant system, and secondary metabolite production. Additionally, it highlights calcium transport and enrichment mechanisms in microorganism cells and offers a detailed account of the progress made on calcium-binding proteins, calcium transport pathways, and calcium storage and release. This paper offers insights for further research on the relevant calcium enrichment in microorganism cells. [ABSTRACT FROM AUTHOR]

Calcium (Ca) and phosphorus (P) are essential nutrients for plant growth, with consequences on ruminant diet and health. Their balance in forage, as indicated by Ca:P ratio, is important for the absorption and utilisation of both elements by livestock. While nitrogen (N) deposition has been globally observed, it is declining or is projected to decline due to controls on N emissions in many countries. It is an open question whether N inputs would have legacy effects on forage Ca and P nutrition in grasslands. Here, we examine the changes of Ca and P concentrations and Ca:P ratio in plants and soils in a temperate steppe for three continuous years (2016 ~ 2018) following historically 6 years N inputs (2008 ~ 2013) with a gradient ranging from 0 to 20 g N m−2 year−1. Soil extractable Ca concentrations significantly decreased with increasing N addition rates in all the 3 years, but soil available P concentrations increased and Ca:P ratio decreased only in 2016. Ca and P nutrition varied greatly amongst the four plant functional types, but they were generally conservative across the historical N addition rates, due to the high stoichiometric homeostasis. Furthermore, plant Ca and P concentrations and Ca:P ratios at the community level showed no significant variation along the N addition gradient. Our results highlighted the role of plant Ca and P homeostasis in ensuring stable Ca and P nutrition in forage following historical N inputs in temperate grasslands. [ABSTRACT FROM AUTHOR]

Potassium (K) is the second most abundant nutrient in plant leaves after nitrogen (N) and the most abundant cation in plant cells. It plays an important role in plant growth regulation, homeostasis maintenance, and stress response. Previous studies on the effects of N input on plant nutrient status mainly focus on N and phosphorus (P), but less on K and its stoichiometry. We examined the effects of N input and mowing on K content and N:K at both plant functional group and community levels. We analyzed the relative contribution of changes in functional groups and community composition to changes of community level nutrition status. The results showed that N input increased N content of each plant functional group and increased K content of rhizomatous grasses and legumes. Mowing reduced N content of rhizomatous grasses and bunchgrass, but did not affect K content and N:K of all functional groups. Nitrogen input significantly increased plant N and K contents at the community level, while mowing significantly increased plant N content. Both N input and mowing did not affect plant N:K at functional group and community levels. The contribution of nutritional changes in plant functional groups to the variation at the community level was greater than that of changes in community composition. For all the three examined nutritional traits, the contribution of nutrients at functional group level and that of community composition showed negative covariation. Our results indicated that plant N:K had high homeostasis in meadow steppe and that plants could regulate N and K balance, which was of great significance for maintaining N:K stoichiometry under the background of increasing N deposition. [ABSTRACT FROM AUTHOR]

Summary: The continuing nitrogen (N) deposition observed worldwide alters ecosystem nutrient cycling and ecosystem functioning. Litter decomposition is a key process contributing to these changes, but the numerous mechanisms for altered decomposition remain poorly identified.We assessed these different mechanisms with a decomposition experiment using litter from four abundant species (Achnatherum sibiricum, Agropyron cristatum, Leymus chinensis and Stipa grandis) and litter mixtures representing treatment‐specific community composition in a semi‐arid grassland under long‐term simulation of six different rates of N deposition.Decomposition increased consistently with increasing rates of N addition in all litter types. Higher soil manganese (Mn) availability, which apparently was a consequence of N addition‐induced lower soil pH, was the most important factor for faster decomposition. Soil C : N ratios were lower with N addition that subsequently led to markedly higher bacterial to fungal ratios, which also stimulated litter decomposition.Several factors contributed jointly to higher rates of litter decomposition in response to N deposition. Shifts in plant species composition and litter quality played a minor role compared to N‐driven reductions in soil pH and C : N, which increased soil Mn availability and altered microbial community structure. The soil‐driven effect on decomposition reported here may have long‐lasting impacts on nutrient cycling, soil organic matter dynamics and ecosystem functioning. [ABSTRACT FROM AUTHOR]

Aims: Nitrogen (N) deposition has negative consequences for plant communities and ecosystem functioning. Nitrogen deposition is declining or is projected to decline in many regions due to the reduction of N-compound emissions. It remains unknown whether the cessation of N deposition will have legacy effects on plant nutrient stoichiometry. If there are stoichiometric legacy effects at the community-level from prior N enrichment, the contribution of changes in community composition relative to the stoichiometric responses of individual functional groups in driving these changes is unknown. Methods: We measured plant N:P ratio at both functional group level and community level in a temperate steppe in three consecutive years following cessation of a 7-year N addition experiment with a wide-range of total amount added N in which the total amount of N added ranged from 0 to 350 g m−2. Results: The total amount of N addition was positively correlated with tall rhizomatous grass productivity and negatively correlated with tall bunchgrass productivity. Plant N:P ratios at both functional group and community levels did not change across N addition gradient. Community composition shifts contributed less than intra-group variation to the total variation of community level nutrient status in response to historic N addition. Conclusions: Our results indicated that biological N:P imbalance in response to N deposition can be rapidly ameliorated after the cessation of N deposition. Such legacy effects of N deposition on plant nutrient status are largely driven by the changes of nutrient status of individual plants instead of N-induced shifts in community composition. [ABSTRACT FROM AUTHOR]