Prediction of protein solvent accessibility using support vector machines

A Support Vector Machine learning system has been trained to predict protein solvent accessibility from the primary structure. Different kernel functions and sliding window sizes have been explored to find how they affect the prediction performance. Using a cut-off threshold of 15% that splits the dataset evenly (an equal number of exposed and buried residues), this method was able to achieve a prediction accuracy of 70.1% for single sequence input and 73.9% for multiple alignment sequence input, respectively. The prediction of three and more states of solvent accessibility was also studied and compared with other methods. The prediction accuracies are better than, or comparable to, those obtained by other methods such as neural networks, Bayesian classification, multiple linear regression, and information theory. In addition, our results further suggest that this system may be combined with other prediction methods to achieve more reliable results, and that the Support Vector Machine method is a very useful tool for biological sequence analysis.     

一种自优化RBF神经网络的叶绿素a浓度时序预测模型

藻类水华发生过程具有复杂性、非线性、时变性等特点,其准确预测一直是一个国际性难题.以天津市于桥水库为研究对象,根据2000年1月至2003年12月常规监测的水生生态数据(采样周期为10 d),提出了一种结合时序方法的可自优化RBF神经网络智能预测模型,对判断藻类水华的重要指标叶绿素a浓度进行预测.研究了训练样本量及RBF神经网络扩展速度SPREAD值的可自优化性能,以及该模型用于于桥水库叶绿素a浓度的短期变化趋势预测的可行性.结果表明,预测性能指标随SPREAD值及样本量不同发生变化,该预测模型能自动寻到最优SPREAD值,并发现至少需要约两年的训练样本量才能达到较好预测效果.当样本量为105,SPREAD值为10时,预测效果最好,精度较高,预测值与实测值的相关系数R达到0.982.该方法对水库的藻类水华预警有一定的参考价值.     

用离散增量结合支持向量机方法预测蛋白质亚细胞定位

对未知蛋白的功能注释是蛋白质组学的主要目标。一个关键的注释是蛋白质亚细胞定位的预测。本文应用离散增量结合支持向量机(ID_SVM)的方法,对阳性革兰氏细菌蛋白的5类亚细胞定位点进行预测。在独立检验下,其总体预测成功率为89.66%。结果发现ID_SVM算法对预测的成功率有很大改进。     

Artificial neural network approaches to one-step weekly prediction of Dinophysis acuminata blooms in Huelva (Western Andalucía, Spain)

On the Atlantic coasts of Andalucía, chronic spring–summer (March–June) diarrhetic shellfish poisoning (DSP) outbreaks are associated with blooms of Dinophysis acuminata, Claparède and Lachmann. Artificial neural networks (ANNs) have been successfully used to model primary production and have recently been tested for the prediction of harmful algae blooms. In this study, we evaluated the performance of feed forward ANN models trained to predict D. acuminata blooms. ANN models were trained and tested using weekly data (5 previous weeks) of D. acuminata cell counts from eight stations of the Andalucía HAB monitoring programme in the coasts of Huelva between 1998 and 2004. Principal component analysis (PCA) were previously carried out to find out possible similarities within time series from each zone with the aim of reducing the number of areas to model. Our results show that ANN models with a low number of input variables are able to reproduce trends in D. acuminata population dynamics.     

Influence of outbreak of macroalgal blooms on phosphorus release from the sediments in Swan Lake Wetland,China

Macroalgal blooms have occurred worldwide frequently in coastal areas in recent decades, which dramatically modify phosphorus (P) cycle in water column and the sediments. Rongcheng Swan Lake Wetland, a coastal wetland in China, is suffering from extensive macroalgal blooms. In order to verify the influence of macroalgal growth on sediment P release, the sediments and filamentous Chaetomorpha spp. were incubated in the laboratory to investigate the changes of water quality parameters, P levels in overlying water, and sediments during the growth period. In addition, algal biomass and tissue P concentration were determined. In general, Chaetomorpha biomasses were much higher in high P treatments than in low P treatments. Compared with algae+low P water treatment, the addition of sediments increased the algal growth rate and P accumulation amount. During the algal growth, water pH increased greatly, which showed significant correlation with algal biomass in treatments with high P (P < 0.05). P fractions in the sediments showed that Fe/Al–P and organic P concentrations declined during the algal growth, and great changes were observed in algae+low P water+sediment treatment for both. As a whole, the sediments can supply P for Chaetomorpha growth when water P level was low, and the probable mechanism was the release of Fe/Al–P at high pH condition induced by intensive Chaetomorpha blooms.     

Responses of spring phytoplankton communities to their habitats in the Xiangxi Bay of Three Gorges Reservoir,China

Since the water storage was initiated in 2003, the environment of Three Gorges Reservoir (TGR) has changed significantly. Algal blooms and eutrophication have been a frequent occurrence, with serious eutrophication in the tributary bays. To provide some theoretical evidence for the prevention and control of algal blooms, the goal of this study is to elucidate factors that influence algal blooms at different sections of the Xiangxi Bay (XXB). Using field data from the XXB, the responses of phytoplankton communities to their habitats were investigated from March to May, 2010. The results indicated a significant spatial and temporal heterogeneity in phytoplankton composition, cellular abundance, and habitats in the spring. Fifty-four genera representing 6 phyla were monitored. Redundancy analysis indicated that the variation in water temperature and relative water column stability (RWCS) contributed greatly to the succession of spring phytoplankton. Due to different physiological adaptabilities and mechanisms of competition among the algae species, significant succession of the community structure had been observed. The predominant species appears to have changed from those adapted to low temperatures and strong mixing (dinoflagellates and diatoms) to those adapted to high temperatures and weak mixing (green algae and cyanobacteria). The lack of silicate resulted in the succession from diatoms to green algae. Due to the influence of the Yangtze River, there is a low potential for algal blooms at lower reaches of the bay because of frequent water exchange. In contrast, the potential is high at middle and upper reaches where the water temperature increases gradually. The hierarchical status of the two sections is significantly different. Precipitation would inhibit algal blooms somewhat, and heavy rainfall would eliminate algal blooms throughout the bay. Phytoplankton are sensitive to their changing habitat in XXB. For a bloom to occur, sufficient nutrients, a lower flow velocity, and appropriate temperature and light conditions are necessary. As an artificial regulating reservoir, proper ecological regulation could not only significantly affect the dynamic conditions of the water body tributaries, but it could also change the transfer characteristics of light and heat, abolishing the algae habitats and thereby inhibiting the water bloom.     

HPLC Retention time prediction for metabolome analysi

Liquid Chromatography Time-of-Flight Mass Spectrometry (LC-TOF-MS) is widely used for profiling metabolite compounds. LC-TOF-MS is a chemical analysis technique that combines the physical separation capabilities of high-pressure liquid chromatography (HPLC) with the mass analysis capabilities of Time-of-Flight Mass Spectrometry (TOF-MS) which utilizes the difference in the flight time of ions due to difference in the mass-to-charge ratio. Since metabolite compounds have various chemical characteristics, their precise identification is a crucial problem of metabolomics research. Contemporaneously analyzed reference standards are commonly required for mass spectral matching and retention time matching, but there are far fewer reference standards than there are compounds in the organism. We therefore developed a retention time prediction method for HPLC to improve the accuracy of identification of metabolite compounds. This method uses a combination of Support Vector Regression and Multiple Linear Regression adaptively to the measured retention time. We achieved a strong correlation (correlation coefficient = 0.974) between measured and predicted retention times for our experimental data. We also demonstrated a successful identification of an E. coli metabolite compound that cannot be identified by precise mass alone.     

赤潮过程中“藻-菌”关系研究进展

微生物对促进海洋物质循环,维持水生环境的生态平衡具有重要作用。在赤潮事件中,基于微生物(尤其是细菌)的多样性和重要性,它们与藻类之间的相互关系成为了研究的热点。过去20年里,人们从不同角度对"藻-菌"间的关系进行了探索,包括物理学过程、生物学过程、环境过程以及化学过程。就化学过程而言,它作为一种较早出现的技术,在以往的研究中带给人们许多认识藻菌关系的方法。随着学科的渗透,化学法有了拓展与延伸,为人们认识藻菌关系带来了新的契机。从化学生态学领域来梳理"藻-菌"关系中涉及的现象和行为,包括菌对藻的有益面、菌对藻的有害面、以及藻类应答细菌行为的化学途径;并从信号语言(群体感应、化感作用)的角度来阐释两者之间的互生或克生关系。通过文献综述的方式来解读藻菌关系的互作过程和机理,为认识赤潮的发生和防控方法提供借鉴。     

A Computationally Efficient Correlational Neural Network for Automated Prediction of Chronic Kidney Disease

ObjectivesIn this paper, we propose a computationally efficient Correlational Neural Network (CorrNN) learning model and an automated diagnosis system for detecting Chronic Kidney Disease (CKD). A Support Vector Machine (SVM) classifier is integrated with the CorrNN model for improving the prediction accuracy.Material and methodsThe proposed hybrid model is trained and tested with a novel sensing module. We have monitored the concentration of urea in the saliva sample to detect the disease. Experiments are carried out to test the model with real-time samples and to compare its performance with conventional Convolutional Neural Network (CNN) and other traditional data classification methods.ResultsThe proposed method outperforms the conventional methods in terms of computational speed and prediction accuracy. The CorrNN-SVM combined network achieved a prediction accuracy of 98.67%. The experimental evaluations show a reduction in overall computation time of about 9.85% compared to the conventional CNN algorithm.ConclusionThe use of the SVM classifier has improved the capability of the network to make predictions more accurately. The proposed framework substantially advances the current methodology, and it provides more precise results compared to other data classification methods.     

伊乐藻生物碱的GC-MS分析及其对铜绿微囊藻的化感作用

藻类暴发性生长是水体富营养化带来的环境问题之一,利用植物化感作用抑制藻类生长作为一种新型的生物抑藻技术在近年来开始受到研究者的重视,并取得了一定的研究成果。文章采用GC-MS联用技术鉴定出伊乐藻中的9种生物碱成分,还研究了其总生物碱对铜绿微囊藻的化感作用。结果发现添加总生物碱的处理组中铜绿微囊藻生物量均受到了抑制,在总生物碱的浓度为62.0mg/L时,3d后铜绿微囊藻的抑制率为44.0%,表明伊乐藻总生物碱对铜绿微囊藻的生物量增长具有明显的抑制作用。该结论为通过沉水植物恢复富营养化水体提供了重要依据。       

Factors in the Testing and Application of Algicides

A review is presented of some of the factors affecting the laboratory testing and practical applications of chemicals toxic to algae. The basic factor demonstrated is that the amount of chemical required to inhibit the growth of algae is dependent on the amount of algae present and not on the volume of water in which the algae are dispersed. It is shown how a chemical can be tested for algistatic or algicidal properties, thus enabling one to decide how best to apply a particular chemical. The selectivity of chemicals and the development of resistance in algae towards certain chemicals is demonstrated. Also, it is shown how certain algae can appear to be resistant to chemical treatments because of their growth habit or their production of extracellular products which affect the toxicity of added chemicals. With a better understanding of how various factors can influence the effectiveness of toxic chemicals, it is hoped that the selection of a chemical and method of application to a particular problem will be more successful.     

Growth and mortality rates of phytoplankton in the northwestern North Pacific estimated by the dilution method and HPLC pigment analysis

Pigment-based growth rates of phytoplankton and mortality rates due to microzooplankton grazing were estimated using a dilution method combined with high-performance liquid chromatography (HPLC) pigment analysis in the northwestern North Pacific in autumn 1998. The dilution experiments were conducted at different hydrographic stations in both colder and warmer water masses. No significant difference was found between the growth rate of the phytoplankton community (0.38–0.70 day⁻¹; estimated by chlorophyll a) at the colder and warmer water stations, while the mortality rate (0.15–0.88 day⁻¹; estimated by chlorophyll a) tended to be higher at warmer water stations. The combination of estimates of daily chlorophyll a production and particulate organic carbon (POC) production enabled us to assess the carbon to chlorophyll a ratio (C/chl a) of “new” organic matter produced by living phytoplankton. The method provided an implicit value of the C/chl a of in situ living phytoplankton. The rate estimates from taxon-specific pigments suggested a possibility that chlorophyll b-containing green algae were grazed preferentially by microzooplankton during their active growth, and the standing stock of green algae was more strictly controlled by micrograzer than other algal groups such as diatoms. This result is one possible explanation for the fact that blooms of green algae have not been reported in the open ocean, in contrast with diatoms.     

A Four-Stage Hybrid Model for Hydrological Time Series Forecasting

Hydrological time series forecasting remains a difficult task due to its complicated nonlinear, non-stationary and multi-scale characteristics. To solve this difficulty and improve the prediction accuracy, a novel four-stage hybrid model is proposed for hydrological time series forecasting based on the principle of ‘denoising, decomposition and ensemble’. The proposed model has four stages, i.e., denoising, decomposition, components prediction and ensemble. In the denoising stage, the empirical mode decomposition (EMD) method is utilized to reduce the noises in the hydrological time series. Then, an improved method of EMD, the ensemble empirical mode decomposition (EEMD), is applied to decompose the denoised series into a number of intrinsic mode function (IMF) components and one residual component. Next, the radial basis function neural network (RBFNN) is adopted to predict the trend of all of the components obtained in the decomposition stage. In the final ensemble prediction stage, the forecasting results of all of the IMF and residual components obtained in the third stage are combined to generate the final prediction results, using a linear neural network (LNN) model. For illustration and verification, six hydrological cases with different characteristics are used to test the effectiveness of the proposed model. The proposed hybrid model performs better than conventional single models, the hybrid models without denoising or decomposition and the hybrid models based on other methods, such as the wavelet analysis (WA)-based hybrid models. In addition, the denoising and decomposition strategies decrease the complexity of the series and reduce the difficulties of the forecasting. With its effective denoising and accurate decomposition ability, high prediction precision and wide applicability, the new model is very promising for complex time series forecasting. This new forecast model is an extension of nonlinear prediction models.     

Typology of shallow lakes of the Salado River basin (Argentina), based on phytoplankton communities

The phytoplankton communities of eleven shallow lakes from Buenos Aires Province, Argentina, were studied seasonally from 1987 to 1989. Several physical and chemical properties were measured in each lake (pH, temperature, dissolved oxygen, transparency, nutrients), in order to interpret the structural and dynamic traits of the phytoplankton community.Important differences between the lakes studied were put in evidence by means of multivariate techniques (Cluster Analysis and PCA). The shallow lakes densely populated by macrophytes hosted lowest phytoplanktonic densities, with average values ranging from 690 to 16500 algae ml^–1. High species diversities were observed in these lakes (4.0–4.8). Lakes less colonized by macrophytes had higher phytoplankton densities. In some of them important blooms of Cyanophyceae were recorded, with between 60 000 and 179 000 algae ml^–1, and concomitant low diversities.The results of this investigation support the hypothesis that the phytoplankton community is strongly influenced by the macrophytes, by direct competition and/or by competition from periphytic algae associated with higher plants.     

中国蒺藜科植物黄酮类化学成分分析 及其化学分类学意义

采用薄层层析和高效毛细管电泳(HPCE)等方法,对中国蒺藜科5属的代表性植物中的黄酮类成分进行了分析研究,并结合其它分类学性状进行了初步讨论,我们同意(1)支持Engler(1931)骆驼蓬亚科(Peganoideae)地位;(2)支持Takhtajan(1987)白刺科(Nitrariaceae)的恢复;(3)支持EI-Hadidi(1977)刺蒺藜科(Tribulaceae)的建立。     

淡水藻类在监测水质和净化污水中的应用

淡水藻类作为水体中的初级生产者,分布广泛,适应性强,在水生生态系统食物链中占据着十分重要的地位,在水质监测中起着关键的作用。通过对藻类生长与水环境之间的相互关系进行简要的概述,探讨了pH值和氮磷对淡水藻类的生长的影响,以及淡水藻类的生长对外界环境的影响。藻类不但应用于水质监测,而且还能去除水体中的氮、磷等营养物质和其它有机物,对自然水域中的污水有良好的净化作用。重点论述淡水藻类在水质监测和污水净化中的作用以及利用淡水藻类来处理污水的方法。并提出了保护水资源的相关建议,为综合监测和治理水环境提供一定的理论依据和支持。     

Remote sampling of harmful algal blooms: A case study on the Washington State coast

Strategic placement of moorings as an integrated element of ocean observing systems will be essential in the effective monitoring of harmful algal blooms that impact the sustainability of seafood harvest as well as human and marine animal health. Recent efforts have focused on in situ collection and analysis of biological samples, an arguably more difficult task than the measurement of chemical and physical parameters that has been automated for many years. Remote sampling and preservation of samples for later analysis can fill a gap that will allow analysis of time-series data that are essential for establishing interannual trends in coastal regions and provide timely warning of approaching harmful algal blooms. In addition, stored samples for subsequent laboratory analysis will provide important control samples needed to validate in situ, robotic analysis of biological samples. This monitoring for harmful algae and their toxins on moorings, gliders and other autonomous platforms as part of ocean observing systems requires consideration of sampling locations as well other factors such as preservative type used for sample collection and storage combined with a compatible method for toxin analysis. To that end, Pseudo-nitzschia abundance and domoic acid concentrations in seawater were measured from samples collected with a remote sampler moored in Willapa Bay, Washington, during the spring and summer from 2002 through 2006, and compared to data from two adjacent beach sites, Twin Harbors Beach and Long Beach, by Olympic Region Harmful Algal Bloom (ORHAB) personnel. Using enzyme-linked immunosorbent assay (ELISA), total toxin measurements in formalin-preserved whole water samples from Willapa Bay were shown to correlate well with changes in particulate domoic acid concentrations in filtered (particulate) seawater samples from adjacent beaches. A series of experiments confirm, for the first time, that formalin, but not Lugol's iodine or glutaraldehyde, is an effective preservative for phytoplankton samples that are stored for later analysis of domoic acid by ELISA. Together, these data confirm that placement of moorings for in situ sampling of biological and environmental parameters in the sheltered environment of Willapa Bay can accurately detect the arrival of harmful algal blooms that originate from offshore hotspots to shellfish harvesting beaches.     

Statistical analysis of big data: an approach based on support vector machines for classification and regression problems

A new type of learning algorithms with the supervisor for estimating multidimensional functions is considered. These methods based on Support Vector Machines are widely used due to their ability to deal with high-dimensional and large datasets, and their flexibility in modeling diverse sources of data. Support vector machines and related kernel methods are extremely good at solving prediction problems in computational biology. A background about statistical learning theory and kernel feature spaces is given including practical and algorithmic considerations.     

两种预测模型在地下水动态中的比较与应用

预测陕西洛惠渠灌区地下水动态变化情况,在综合分析了各种地下水动态研究方法的基础上,提出了基于支持向量机和改进的BP神经网络模型的灌区地下水动态预测方法,并在MATLAB中编制了相应的计算机程序,建立了相应的地下水动态预测模型。以灌区多年实例数据为学习样本和测试样本,比较了两种模型的地下水动态预测优劣性。研究表明,支持向量机模型和BP网络模型在样本训练学习过程中都具较高的模拟精度,而在样本学习阶段,支持向量机的预测精度明显优于BP网络,可以很好的描述地下水动态复杂的耦合关系。支持向量机方法切实可行,更加适合大型灌区地下水动态预测,是对传统地下水动态研究方法的补充与完善。