Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data.

Antimicrobial peptides (AMPs) are a heterogeneous group of short polypeptides that target not only microorganisms but also viruses and cancer cells. Due to their lower selection for resistance compared with traditional antibiotics, AMPs have been attracting the ever-growing attention from researchers, including bioinformaticians. Machine learning represents the most cost-effective method for novel AMP discovery and consequently many computational tools for AMP prediction have been recently developed. In this article, we investigate the impact of negative data sampling on model performance and benchmarking. We generated 660 predictive models using 12 machine learning architectures, a single positive data set and 11 negative data sampling methods; the architectures and methods were defined on the basis of published AMP prediction software. Our results clearly indicate that similar training and benchmark data set, i.e. produced by the same or a similar negative data sampling method, positively affect model performance. Consequently, all the benchmark analyses that have been performed for AMP prediction models are significantly biased and, moreover, we do not know which model is the most accurate. To provide researchers with reliable information about the performance of AMP predictors, we also created a web server AMPBenchmark for fair model benchmarking. AMPBenchmark is available at http://BioGenies.info/AMPBenchmark.

countfitteR: efficient selection of count distributions to assess DNA damage.

BACKGROUND: DNA double-strand breaks can be counted as discrete foci by imaging techniques. In personalized medicine and pharmacology, the analysis of counting data is relevant for numerous applications, e.g., for cancer and aging research and the evaluation of drug efficacy. By default, it is assumed to follow the Poisson distribution. This assumption, however, may lead to biased results and faulty conclusions in datasets with excess zero values (zero-inflation), a variance larger than the mean (overdispersion), or both. In such cases, the assumption of a Poisson distribution would skew the estimation of mean and variance, and other models like the negative binomial (NB), zero-inflated Poisson or zero-inflated NB distributions should be employed. The model chosen has an influence on the parameter estimation (mean value and confidence interval). Yet the choice of the suitable distribution model is not trivial. METHODS: To support, simplify and objectify this process, we have developed the countfitteR software as an R package. We used a Bayesian approach for distribution model selection and the shiny web application framework for interactive data analysis. RESULTS: We show the application of our software based on examples of DNA double-strand break count data from phenotypic imaging by multiplex fluorescence microscopy. In analyzing numerous datasets of molecular pharmacological markers (phosphorylated histone H2AX and p53 binding protein), countfitteR demonstrated an equal or superior statistical performance compared to the usually employed two-step procedure, with an overall power of up to 98%. In addition, it still gave information in cases with no result at all from the two-step procedure. In our data sample we found that the NB distribution was the most frequent, with the Poisson distribution taking second place. CONCLUSIONS: countfitteR can perform an automated distribution model selection and thus support the data analysis and lead to objective statistically verifiable estimated values. Originally designed for the analysis of foci in biomedical image data, countfitteR can be used in a variety of areas where non-Poisson distributed counting data is prevalent.

CancerGram: An Effective Classifier for Differentiating Anticancer from Antimicrobial Peptides.

Antimicrobial peptides (AMPs) constitute a diverse group of bioactive molecules that provide multicellular organisms with protection against microorganisms, and microorganisms with weaponry for competition. Some AMPs can target cancer cells; thus, they are called anticancer peptides (ACPs). Due to their small size, positive charge, hydrophobicity and amphipathicity, AMPs and ACPs interact with negatively charged components of biological membranes. AMPs preferentially permeabilize microbial membranes, but ACPs additionally target mitochondrial and plasma membranes of cancer cells. The preference towards mitochondrial membranes is explained by their membrane potential, membrane composition resulting from α-proteobacterial origin and the fact that mitochondrial targeting signals could have evolved from AMPs. Taking into account the therapeutic potential of ACPs and millions of deaths due to cancer annually, it is of vital importance to find new cationic peptides that selectively destroy cancer cells. Therefore, to reduce the costs of experimental research, we have created a robust computational tool, CancerGram, that uses n-grams and random forests for predicting ACPs. Compared to other ACP classifiers, CancerGram is the first three-class model that effectively classifies peptides into: ACPs, AMPs and non-ACPs/non-AMPs, with AU1U amounting to 0.89 and a Kappa statistic of 0.65. CancerGram is available as a web server and R package on GitHub.