Modelling roach (Rutilus rutilus) microhabitat using linear and nonlinear techniques

• 1 Multiple linear regression (MLR), generalised additive models (GAM) and artificial neural networks (ANN), were used to define young of the year (0+) roach (Rutilus rutilus) microhabitat and to predict its abundance.
• 2 0+ Roach and nine environmental variables were sampled using point abundance sampling by electrofishing in the littoral area of Lake Pareloup (France) during summer 1997. Eight of these variables were used to set up the models after log₁₀ (x+ 1) transformation of the dependent variable (0+ roach density). Model training and testing were performed on independent subsets of the whole data matrix containing 306 records.
• 3 The predictive quality of the models was estimated using the determination coefficient between observed and estimated values of roach densities. The best models were provided by ANN, with a correlation coefficient (r) of 0.83 in the training procedure and 0.62 in the testing procedure. GAM and MLR gave lower prediction in the training set (r = 0.53 for GAM and r = 0.32 for MLR) and in the testing set (r = 0.48 for GAM and r = 0.43 for MLR). In the same way, samples without fish were reliably predicted by ANN whereas GAM and MLR predicted absence unreliably.
• 4 ANN sensitivity analysis of the eight environmental variables in the models revealed that 0+ roach distribution was mainly influenced by five variables: depth, distance from the bank, local slope of the bottom and percentage of mud and flooded vegetation cover. The nonlinear influence of these variables on 0+ roach distribution was clearly shown using nonparametric lowess smoothing procedures.
• 5 Non‐linear modelling methods, such as GAM and ANN, were able to define 0+ fish microhabitat precisely and to provide insight into 0+ roach distribution and abundance in the littoral zone of a large reservoir. The results showed that in lakes, 0+ roach microhabitat is influenced by a complex combination of several environmental variables acting mainly in a nonlinear way.

     

Improvement of protein secondary structure prediction using binary word encoding

We propose a binary word encoding to improve the protein secondary structure prediction. A binary word encoding encodes a local amino acid sequence to a binary word, which consists of 0 or 1. We use an encoding function to map an amino acid to 0 or 1. Using the binary word encoding, we can statistically extract the multiresidue information, which depends on more than one residue. We combine the binary word encoding with the GOR method, its modified version, which shows better accuracy, and the neural network method. The binary word encoding improves the accuracy of GOR by 2.8%. We obtain similar improvement when we combine this with the modified GOR method and the neural network method. When we use multiple sequence alignment data, the binary word encoding similarly improves the accuracy. The accuracy of our best combined method is 68.2%. In this paper, we only show improvement of the GOR and neural network method, we cannot say that the encoding improves the other methods. But the improvement by the encoding suggests that the multiresidue interaction affects the formation of secondary structure. In addition, we find that the optimal encoding function obtained by the simulated annealing method relates to non-polarity. This means that nonpolarity is important to the multiresidue interaction. Proteins 27:36–46 © 1997 Wiley-Liss, Inc.     

Cooperative recurrent modular neural networks for constrained optimization: a survey of models and applications

Constrained optimization problems arise in a wide variety of scientific and engineering applications. Since several single recurrent neural networks when applied to solve constrained optimization problems for real-time engineering applications have shown some limitations, cooperative recurrent neural network approaches have been developed to overcome drawbacks of these single recurrent neural networks. This paper surveys in details work on cooperative recurrent neural networks for solving constrained optimization problems and their engineering applications, and points out their standing models from viewpoint of both convergence to the optimal solution and model complexity. We provide examples and comparisons to shown advantages of these models in the given applications.     

基于卷积神经网络和循环神经网络的环形RNA剪接位点识别研究

本文提出了一种基于卷积神经网络和循环神经网络的深度学习模型,通过分析基因组序列数据,识别人基因组中环形RNA剪接位点.首先,根据预处理后的核苷酸序列,设计了2种网络深度、8种卷积核大小和3种长短期记忆(long short term memory,LSTM)参数,共8组16个模型;其次,进一步针对池化层进行均值池化和最大池化的测试,并加入GC含量提高模型的预测能力;最后,对已经实验验证过的人类精浆中环形RNA进行了预测.结果表明,卷积核尺寸为32×4、深度为1、LSTM参数为32的模型识别率最高,在训练集上为0.9824,在测试数据集上准确率为0.95,并且在实验验证数据上的正确识别率为83%.该模型在人的环形RNA剪接位点识别方面具有较好的性能.     

从线粒体DNA控制区核苷酸序列论达式鲟、亚洲和北美洲中吻鲟的分类地位

尽管古老的鲟形目鱼类的分类及系统演化一直是中外学者感兴趣的研究课题 ,但迄今仍有诸多谜团未解。其中 ,关于亚洲远东地区和北美地区的中吻鲟 (Acipensermedirostris)的分类地位争论已久。长江水系的达式鲟 (A .dabryanus)和中华鲟 (A .sinensis)及其它鲟属 (Acipenser)鱼类之间的亲缘关系近年来也有异议。为了给上述争议提供更多的科学依据 ,作者测定了线粒体DNA (mtDNA)控制区(D loop) 的核苷酸序列 ,并进行了分子系统学和遗传差异分析。研究结果表明 :⑴UPGMA ,NJ和MP分子系统学分析方法以及遗传差异分析都支持了亚洲远东地区中吻鲟和北美中吻鲟为一个有效种的观点 ;⑵同样研究方法并结合相关群体遗传资料表明 ,长江达式鲟与中华鲟关系最近 ,提出了达式鲟为中华鲟的一陆封类群的假说。最后 ,作者认为本文提出的观点和假说还需要更多的研究来证实。     

从线粒体DNA控制区核苷酸序列论达式鲟、亚洲和北美洲中吻鲟的分类地位

尽管古老的鲟形目鱼类的分类及系统演化一直是中外学者感兴趣的研究课题,但迄今仍有诸多谜团未解。其中,关于亚洲远东地区和北美地区的中吻鲟(Acipenser medirostris)的分类地位争论已久。长江水系的达式鲟(A.dabryanus)和中华鲟(A.sinensis)及其它鲟属(Acipenser)鱼类之间的亲缘关系近年来也有异议。为了给上述争议提供更多的科学依据,作者测定了线粒体DNA(mtDNA)控制区 (D-loop) 的核苷酸序列,并进行了分子系统学和遗传差异分析。研究结果表明：⑴UPGMA,NJ和MP分子系统学分析方法以及遗传差异分析都支持了亚洲远东地区中吻鲟和北美中吻鲟为一个有效种的观点;⑵同样研究方法并结合相关群体遗传资料表明,长江达式鲟与中华鲟关系最近,提出了达式鲟为中华鲟的一陆封类群的假说。最后,作者认为本文提出的观点和假说还需要更多的研究来证实。     

具时滞的Hopfield型神经网络模型的全局渐近稳定性

本文研究了具时滞的Hopfield型神经网络模型平衡点的全局渐近稳定性,获得了一系列充分条件。     

鲟鱼类系统进化的研究现状

本文回顾了鲟鱼的分类、起源、性骼系统发育、细胞遗传学的研究、线粒体部分基因的研究,阐述近年年来鲟鱼系统进化的研究现状,从鲟鱼系统进化关系可以推测出尚未有核型报道的S.allnis,S.sullkusi和P.hermanni 3种鲟鱼可能为四倍体,讨论了当前鲟鱼类系统进化研究中存在的问题。     

Ontogenetic Behavior and Migration of Volga River Russian sturgeon, Acipenser gueldenstaedtii, with a Note on Adaptive Significance of Body Color

We conducted laboratory experiments with Volga River Russian sturgeon, Acipenser gueldenstaedtii, to develop a conceptual model of early behavior. We daily observed fish from day-0 (embryos, first life interval after hatching) to day-29 feeding larvae for preference of bright habitat and cover, swimming distance above the bottom, up- and downstream movement, and diel activity. Hatchling embryos initiated a downstream migration, which suggests that predation risk of embryos at spawning sites is high. Migration peaked on days 0–5 and ceased on day 7 (8-day migration). Migrants preferred bright, open habitat and early migrants swam-up far above the bottom (maximum daily median, 140cm) in a vertical swim tube. Post-migrant embryos did not prefer bright illumination but continued to prefer white substrate, increased use of cover habitat, and swam on the bottom. Larvae initiated feeding on day 10 after 170.6 cumulative temperature degree-days. Larvae did not migrate, weakly preferred bright illumination, preferred white substrate and open habitat, and swam near the bottom (daily median 5–78cm). The lack of a strong preference by larvae for bright illumination suggests foraging relies more on olfaction than vision for locating prey. A short migration by embryos would disperse wild sturgeon from a spawning area, but larvae did not migrate, so a second later migration by juveniles disperses young sturgeon to the sea (2-step migration). Embryo and larva body color was light tan and tail color was black. The migration, behavior, and light body color of Russian sturgeon embryos was similar to species of Acipenser and Scaphirhynchus in North America and to Acipenser in Asia that migrate after hatching as embryos. The similarity in migration style and body color among species with diverse phylogenies likely reflects convergence for common adaptations across biogeographic regions.     

Observations on the skulls of sturgeons (Acipenseridae): shared similarities of <Emphasis Type="Italic">Pseudoscaphirhynchus kaufmanni</Emphasis> and juvenile specimens of <Emphasis Type="Italic">Acipenser stellatus</Emphasis>

A novel hypothesis uniting Acipenser stellatus and Pseudoscaphirhynchus as sister groups has recently been proposed based on analysis of DNA sequences. In this paper I compare specimens of A. stellatus and P. kaufmanni, and show that they share several putatively derived similarities in the structure of their skulls, including: the presence of large spines on the dermal bones of skull; lateral extrascapular bones that enclose the confluence of the posttemporal, supratemporal, and otic sensory canals; elongate dorsal rostral bones; border rostral bones distinct in shape from dorsal rostral bones; greatly enlarged jugal that lacks a median flange; rostral canal bones that loop posteriorly at the anterior commissure of the rostral sensory canals; and the presence of an elongate, flat, and broad posterior ventral rostral bone. These similarities support a close relationship between A. stellatus and Pseudoscaphirhynchus, but still remain to be critically tested.