Your search
Results 197 resources
-
As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases. Our optimal model SSL-GCN is hosted on an online server accessible through: https://app.cbbio.online/ssl-gcn/home.
-
Mangroves are a unique group of plants growing along tropical and sub-tropical coastlines, with the ability to remove several types of contaminants such as heavy metals and other persistent organic compounds in coastal waters. However, little attention has been given to the possible role of mangroves in the removal of organochlorinated pesticides (OCPs) from the environment. Used worldwide, these pesticides were banned in the late 80s, withal they can still be quantified in aquatic environments due to their high stability. Moreover, as persistent and lipophilic compounds, OCPs are known for their tendency to bioaccumulate and biomagnify through the food chain, affecting local ecosystems, and potentially human health. This work aimed to investigate the potential benefits of mangrove ecosystems as OCP phytoremediators. For this purpose, a total of seventy-three articles from non-mangrove and mangrove areas around the world were gathered, integrated and re-analysed as a whole. These data include information from four different matrices (water, sediment, benthic fauna and mangrove plants). A common trend of less pesticide contamination in mangrove areas was observed for all the selected matrices. As a complement, average concentrations were discussed considering International Directives, such as the European legislation 2013/39/EU for water policy and the Dutch List together with the International Sediment Quality Guideline, for sediments. Additionally, theoretical risk assessments were also included. Since information regarding OCPs in mangroves ecosystem is very scarce compared to non-mangrove areas, this review provides valuable insights regarding these environments, and the importance of preserving them as a relevant remediation unit.
-
Aggression clearly has an adaptive value as it is necessary to secure resources for survival, growth, and reproduction. The Siamese fighting fish, Betta splendens, have endured a prolonged process of artificial selection for winning paired-fight contests across Southeast Asia, resulting in strains of short-fin aggressive “fighters”. Across centuries, Thai breeders have been selecting these strains by discarding loser batches and allowing winner batches to breed, claiming that they are significantly more aggressive than wild-types. This natural experiment provides a powerful context to investigate the biological basis of aggressive behaviour in fish, the topic of this thesis. To study aggression, it is important to validate and standardize behavioural assays appropriate for the species under study. Further, different aggression-eliciting stimuli, such as live opponents, 3D models, video playback, or mirror images, may elicit non-equivalent behavioural and physiological responses. For B. splendens, in particular, quantifying aggression from live fights is not ethically acceptable as the high levels of aggression of this species usually result in injuries or even death of the opponent. In Chapter II, it was shown that mirror images elicit very similar aggressive displays and endocrine responses to an interacting opponent behind a transparent partition, validating the use of this test to measure aggression in this model species. Further, it was shown that circulating levels of both androgens (11-ketotestosterone and testosterone) and corticosteroids (cortisol) increased in response to the aggression challenge, even in the absence of conflict resolution, questioning the role of these hormones during present and future aggressive contests. Using the previously validated mirror assay and also tests with live conspecifics, we assessed the impact of selection for winning by comparing, in Chapter III, male and female aggressive behaviour of lab-raised fighter and wild-type strains. The hypothesis that selection for male winners enhanced aggressive displays was confirmed, suggesting that the duration and frequency of threat and attack behaviour correlates with winning probability. However, females of the fighter strain, which are not selected for fights, were also more aggressive than wild-type females. This suggests that male and female aggression share common genetic pathways and physiological mechanisms and raises the possibility that selection for alleles that favour male aggression may have promoted intersexual genetic conflict in this species. After confirming the expected differences in aggressive behaviour between fighter and wild-type fish, the following question was whether endocrine systems, in particular those previously shown to respond to aggression, could have been targeted by the selection process. From previous studies in fish and other vertebrates, it was hypothesised that selection for winners could have increased constitutive levels of androgens or led to an enhanced androgen response to a social challenge. However, in chapter IV, it was shown that levels of 11-ketotestosterone and its response to aggression was similar in males of both strains, questioning the role of androgens in the modulation of aggression in B. splendens. On the contrary, constitutive levels of cortisol and the response of this hormone to an aggression challenge were higher in wild-type compared with fighter fish, supporting previous findings that associated high aggression with a blunted cortisol response. Overall, results from Chapter IV suggest that selection for winning had a stronger impact on the hypothalamus-pituitary-interrenal axis than in the hypothalamus-pituitary-gonadal axis. My results support the assumption of the “Challenge Hypothesis” proposed by John Wingfield and collaborators in 1990 to explain the relationship between androgens and aggression, according to which androgen levels above a reproductive baseline are a consequence of the frequency and intensity of social interactions, in particular of male-male agonistic encounters. It is becoming clear that androgens increase rapidly after an aggressive contest, independently of fight outcome. However, the function of this increase remains unclear as the frequency of aggressive displays was unrelated with post-fight androgen levels and constitutive levels of androgens, and androgen responsiveness, were similar between fighter and wild-type males. Results obtained for cortisol agree with a “corticosteroid-mediated dominance hypothesis” whereby low baseline levels and a blunted response of corticosteroids would be associated with a dominant status and high aggression. The work advances our knowledge about the endocrine regulation of aggressive behaviour in B. splendens and opens several testable hypotheses about the role of androgens and corticosteroids in the regulation of fish aggressive behaviour
-
In this essay, we respond to Dustin Crummett’s argument that one cannot consistently appeal to body count reasoning to justify being a single-issue pro-life voter if one is also committed to the usual response to the embryo rescue case. Specifically, we argue that a modified version of BCR we call BCR* is consistent with the usual response. We then move to address concerns about the relevance of BCR* to Crummett’s original thesis.
-
The role of hormones as modulators of aggressive behavior in fish remains poorly understood. Androgens and corticosteroids, in particular, have been associated with aggressive behavior in fish but it is still not clear if animals adjust the secretion of these hormones to regulate behavior during ongoing fights, in response to fight outcomes in order to adjust aggressive behavior in subsequent fights, or both. With its stereotyped displays and high aggression levels, the Siamese fighting fish Betta splendens is an excellent model to investigate this question. Here, we compared the behavioral and endocrine response of male B. splendens to fights where there is no winner or loser by presenting them with a size-matched live interacting conspecific behind a transparent partition or with a mirror image. The aggressive response started with threat displays that were overall similar in frequency and duration towards both types of stimuli. Fights transitioned to overt attacks and interacting with a live conspecific elicited a higher frequency of attempted bites and head hits, as compared with the mirror image. There was a pronounced increase in plasma androgens (11-ketotestosterone and testosterone) and corticosteroids (cortisol) levels in response to the aggression challenge, independent of stimulus type. Post-fight intra-group levels of these hormones did not correlate with measures of physical activity or aggressive behavior. A linear discriminant analysis including all behavioral and endocrine data was a poor classifier of fish from the conspecific and mirror trials, showing that overall the behavioral and endocrine response to mirror images and conspecifics was similar. The results show that fight resolution is not necessary to induce an evident increase in peripheral levels of androgens and corticosteroids in B. splendens. However, the function of these hormones during present and future aggressive contests remains to be clarified.
-
There are a large number of symptom consultation texts in medical and healthcare Internet communities, and Chinese health segmentation is more complex, which leads to the low accuracy of the existing algorithms for medical text classification. The deep learning model has advantages in extracting abstract features of text effectively. However, for a large number of samples of complex text data, especially for words with ambiguous meanings in the field of Chinese medical diagnosis, the word-level neural network model is insufficient. Therefore, in order to solve the triage and precise treatment of patients, we present an improved Double Channel (DC) mechanism as a significant enhancement to Long Short-Term Memory (LSTM). In this DC mechanism, two channels are used to receive word-level and char-level embedding, respectively, at the same time. Hybrid attention is proposed to combine the current time output with the current time unit state and then using attention to calculate the weight. By calculating the probability distribution of each timestep input data weight, the weight score is obtained, and then weighted summation is performed. At last, the data input by each timestep is subjected to trade-off learning to improve the generalization ability of the model learning. Moreover, we conduct an extensive performance evaluation on two different datasets: cMedQA and Sentiment140. The experimental results show that the DC-LSTM model proposed in this paper has significantly superior accuracy and ROC compared with the basic CNN-LSTM model.
-
To solve the problem of one-sided pursuit of the shortest distance but ignoring the tourist experience in the process of tourism route planning, an improved ant colony optimization algorithm is proposed for tourism route planning. Contextual information of scenic spots significantly effect people’s choice of tourism destination, so the pheromone update strategy is combined with the contextual information such as weather and comfort degree of the scenic spot in the process of searching the global optimal route, so that the pheromone update tends to the path suitable for tourists. At the same time, in order to avoid falling into local optimization, the sub-path support degree is introduced. The experimental results show that the optimized tourism route has greatly improved the tourist experience, the route distance is shortened by 20.5% and the convergence speed is increased by 21.2% compared with the basic algorithm, which proves that the improved algorithm is notably effective.
Explore
USJ Theses and Dissertations
- Doctorate Theses (2)
- Master Dissertations (67)
Academic Units
Resource type
- Book (11)
- Book Section (15)
- Conference Paper (14)
- Journal Article (56)
- Magazine Article (5)
- Manuscript (1)
- Newspaper Article (9)
- Presentation (10)
- Radio Broadcast (2)
- Report (4)
- Thesis (70)