The identification of individuals with hatchery and natural origin in a mixed sample of Amur River chum salmon by Otolith microchemistry

We estimated the proportion of hatchery and natural fall spawning chum salmon returning to the Amur River using chemical markers specific to hatchery-origin fry.We used otolith microchemistry technique to identify fish with artificial origin among returning spawners.First,we found that juveniles of artificial origin had higher values of the Sr:Ca molar ratio of the otoliths’edge zone compared with juveniles of natural origin,what can be related to the use of rearing feed produced from raw materials of marine origin rich in strontium.Then we observed that most of the spawners from Anyuisky Hatchery and from the Amur River mouth at the start of the spawning migration has also the higher value of Sr:Ca molar ratio of the juvenile zone of otoliths.Also,adults with higher values of the Sr:Ca molar ratio are characterized by a skewed right in the peak of the age distribution.Both,the age structure and phenological shift in the time of spawning migration of individuals with higher value of the used chemical marker corresponds to results of studies on hatchery-produced chum salmon completed at different parts on Northern Pacific.The results of this study will be used in the management of Amur fall chum salmon fisheries,and also demonstrates the necessity of the development of specific measures for increasing the survival of juvenile anadromous salmonids released at large rivers and exposed to prolonged freshwater migration to the ocean.As a further application of the methodology,we plan to identify the markers specific to each of the hatcheries and main spawning tributaries belonging to Amur River catchments.This will be an important step in the evaluation of the contribution of different stocks in mixed fisheries and also in the estimation of the effect of hatchery releases on naturally spawning stocks of Amur fall chum.Following to,our results may indicate the applicability of this approach for the determination of artificial-origin fish in a mixed sample of the Amur fall chum salmon.

Biomedical Event Extraction Using a New Error Detection Learning Approach Based on Neural Network

Supervised machine learning approaches are effective in text mining,but their success relies heavily on manually annotated corpora.However,there are limited numbers of annotated biomedical event corpora,and the available datasets contain insufficient examples for training classifiers;the common cure is to seek large amounts of training samples from unlabeled data,but such data sets often contain many mislabeled samples,which will degrade the performance of classifiers.Therefore,this study proposes a novel error data detection approach suitable for reducing noise in unlabeled biomedical event data.First,we construct the mislabeled dataset through error data analysis with the development dataset.The sample pairs’vector representations are then obtained by the means of sequence patterns and the joint model of convolutional neural network and long short-term memory recurrent neural network.Following this,the sample identification strategy is proposed,using error detection based on pair representation for unlabeled data.With the latter,the selected samples are added to enrich the training dataset and improve the classification performance.In the BioNLP Shared Task GENIA,the experiments results indicate that the proposed approach is competent in extract the biomedical event from biomedical literature.Our approach can effectively filter some noisy examples and build a satisfactory prediction model.