How to maintain relative high diversity is important to avoid premature convergence in population-based optimization methods. Island model is widely considered as a major approach to achieve this because of its flexibility and high efficiency. The model maintains a group of sub-populations on different islands and allows sub-populations to interact with each other via predefined migration policies. However, current island model has some drawbacks. One is that after a certain number of generations, different islands may retain quite similar, converged sub-populations thereby losing diversity and decreasing efficiency. Another drawback is that determining the number of islands to maintain is also very challenging. Meanwhile initializing many sub-populations increases the randomness of island model. To address these issues, we proposed a dynamic island model (DIM-SP) which can force each island to maintain different sub-populations, control the number of islands dynamically and starts with one sub-population. The proposed island model outperforms the other three state-of-the-art island models in three baseline optimization problems including job shop scheduler, travelling salesmen, and quadratic multiple knapsack.

BACKGROUND: The incomplete ground truth of training data of B-cell epitopes is a demanding issue in computational epitope prediction. The challenge is that only a small fraction of the surface residues of an antigen are confirmed as antigenic residues (positive training data); the remaining residues are unlabeled. As some of these uncertain residues can possibly be grouped to form novel but currently unknown epitopes, it is misguided to unanimously classify all the unlabeled residues as negative training data following the traditional supervised learning scheme. RESULTS: We propose a positive-unlabeled learning algorithm to address this problem. The key idea is to distinguish between epitope-likely residues and reliable negative residues in unlabeled data. The method has two steps: (1) identify reliable negative residues using a weighted SVM with a high recall; and (2) construct a classification model on the positive residues and the reliable negative residues. Complex-based 10-fold cross-validation was conducted to show that this method outperforms those commonly used predictors DiscoTope 2.0, ElliPro and SEPPA 2.0 in every aspect. We conducted four case studies, in which the approach was tested on antigens of West Nile virus, dihydrofolate reductase, beta-lactamase, and two Ebola antigens whose epitopes are currently unknown. All the results were assessed on a newly-established data set of antigen structures not bound by antibodies, instead of on antibody-bound antigen structures. These bound structures may contain unfair binding information such as bound-state B-factors and protrusion index which could exaggerate the epitope prediction performance. Source codes are available on request.

UNLABELLED: We present Vacceed, a highly configurable and scalable framework designed to automate the process of high-throughput in silico vaccine candidate discovery for eukaryotic pathogens. Given thousands of protein sequences from the target pathogen as input, the main output is a ranked list of protein candidates determined by a set of machine learning algorithms. Vacceed has the potential to save time and money by reducing the number of false candidates allocated for laboratory validation. Vacceed, if required, can also predict protein sequences from the pathogen's genome. AVAILABILITY AND IMPLEMENTATION: Vacceed is tested on Linux and can be freely downloaded from https://github.com/sgoodswe/vacceed/releases (includes a worked example with sample data). Vacceed User Guide can be obtained from https://github.com/sgoodswe/vacceed.

MOTIVATION: B-cell epitope is a small area on the surface of an antigen that binds to an antibody. Accurately locating epitopes is of critical importance for vaccine development. Compared with wet-lab methods, computational methods have strong potential for efficient and large-scale epitope prediction for antigen candidates at much lower cost. However, it is still not clear which features are good determinants for accurate epitope prediction, leading to the unsatisfactory performance of existing prediction methods. METHOD AND RESULTS: We propose a much more accurate B-cell epitope prediction method. Our method uses a new feature B factor (obtained from X-ray crystallography), combined with other basic physicochemical, statistical, evolutionary and structural features of each residue. These basic features are extended by a sequence window and a structure window. All these features are then learned by a two-stage random forest model to identify clusters of antigenic residues and to remove isolated outliers. Tested on a dataset of 55 epitopes from 45 tertiary structures, we prove that our method significantly outperforms all three existing structure-based epitope predictors. Following comprehensive analysis, it is found that features such as B factor, relative accessible surface area and protrusion index play an important role in characterizing B-cell epitopes. Our detailed case studies on an HIV antigen and an influenza antigen confirm that our second stage learning is effective for clustering true antigenic residues and for eliminating self-made prediction errors introduced by the first-stage learning. AVAILABILITY AND IMPLEMENTATION: Source codes are available on request.

In this article, a framework for an in silico pipeline is presented as a guide to high-throughput vaccine candidate discovery for eukaryotic pathogens, such as helminths and protozoa. Eukaryotic pathogens are mostly parasitic and cause some of the most damaging and difficult to treat diseases in humans and livestock. Consequently, these parasitic pathogens have a significant impact on economy and human health. The pipeline is based on the principle of reverse vaccinology and is constructed from freely available bioinformatics programs. There are several successful applications of reverse vaccinology to the discovery of subunit vaccines against prokaryotic pathogens but not yet against eukaryotic pathogens. The overriding aim of the pipeline, which focuses on eukaryotic pathogens, is to generate through computational processes of elimination and evidence gathering a ranked list of proteins based on a scoring system. These proteins are either surface components of the target pathogen or are secreted by the pathogen and are of a type known to be antigenic. No perfect predictive method is yet available; therefore, the highest-scoring proteins from the list require laboratory validation.

BACKGROUND: An in silico vaccine discovery pipeline for eukaryotic pathogens typically consists of several computational tools to predict protein characteristics. The aim of the in silico approach to discovering subunit vaccines is to use predicted characteristics to identify proteins which are worthy of laboratory investigation. A major challenge is that these predictions are inherent with hidden inaccuracies and contradictions. This study focuses on how to reduce the number of false candidates using machine learning algorithms rather than relying on expensive laboratory validation. Proteins from Toxoplasma gondii, Plasmodium sp., and Caenorhabditis elegans were used as training and test datasets. RESULTS: The results show that machine learning algorithms can effectively distinguish expected true from expected false vaccine candidates (with an average sensitivity and specificity of 0.97 and 0.98 respectively), for proteins observed to induce immune responses experimentally. CONCLUSIONS: Vaccine candidates from an in silico approach can only be truly validated in a laboratory. Given any in silico output and appropriate training data, the number of false candidates allocated for validation can be dramatically reduced using a pool of machine learning algorithms. This will ultimately save time and money in the laboratory.

ADL/ADS is a testbed user interface tool for experimentation with critical research and design issues associated with distributed processing. One significant class of problems well-suited for investigation in a testbed are data engineering concepts. ADL/ADS provides a graphics interface for expressing a candidate distributed architecture at the Processor-Memory-Switch (PMS) level of hardware detail and the task-message-file level of software detail. Then the ADL/ADS support software is used to construct an existing model of the described architecture and to execute and monitor the model on the testbed. The testbed software runtime environment to support the execution of the model is described in this paper.