gammaBOriS: Identification and Taxonomic Classification of Origins of Replication in Gammaproteobacteria using Motif-based Machine Learning

The biology of bacterial cells is, in general, based on information encoded on circular chromosomes. Regulation of chromosome replication is an essential process that mostly takes place at the origin of replication (oriC), a locus unique per chromosome. Identification of high numbers of oriC is a prerequisite for systematic studies that could lead to insights into oriC functioning as well as the identification of novel drug targets for antibiotic development. Current methods for identifying oriC sequences rely on chromosome-wide nucleotide disparities and are therefore limited to fully sequenced genomes, leaving a large number of genomic fragments unstudied. Here, we present gammaBOriS (Gammaproteobacterial oriC Searcher), which identifies oriC sequences on gammaproteobacterial chromosomal fragments. It does so by employing motif-based machine learning methods. Using gammaBOriS, we created BOriS DB, which currently contains 25,827 gammaproteobacterial oriC sequences from 1,217 species, thus making it the largest available database for oriC sequences to date. Furthermore, we present gammaBOriTax, a machine-learning based approach for taxonomic classification of oriC sequences, which was trained on the sequences in BOriS DB. Finally, we extracted the motifs relevant for identification and classification decisions of the models. Our results suggest that machine learning sequence classification approaches can offer great support in functional motif identification.

Deep learning on chaos game representation for proteins

Motivation

Classification of protein sequences is one big task in bioinformatics and has many applications. Different machine learning methods exist and are applied on these problems, such as support vector machines (SVM), random forests (RF) and neural networks (NN). All of these methods have in common that protein sequences have to be made machine-readable and comparable in the first step, for which different encodings exist. These encodings are typically based on physical or chemical properties of the sequence. However, due to the outstanding performance of deep neural networks (DNN) on image recognition, we used frequency matrix chaos game representation (FCGR) for encoding of protein sequences into images. In this study, we compare the performance of SVMs, RFs and DNNs, trained on FCGR encoded protein sequences. While the original chaos game representation (CGR) has been used mainly for genome sequence encoding and classification, we modified it to work also for protein sequences, resulting in n-flakes representation, an image with several icosagons.

Results

We could show that all applied machine learning techniques (RF, SVM and DNN) show promising results compared to the state-of-the-art methods on our benchmark datasets, with DNNs outperforming the other methods and that FCGR is a promising new encoding method for protein sequences.

Availability and implementation

https://cran.r-project.org/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Phi-Delta-Diagrams: Software Implementation of a Visual Tool for Assessing Classifier and Feature Performance

In this article, a two-tiered 2D tool is described, called ⟨φ,δ⟩ diagrams, and this tool has been devised to support the assessment of classifiers in terms of accuracy and bias. In their standard versions, these diagrams provide information, as the underlying data were in fact balanced. Their generalization, i.e., ability to account for the imbalance, will be also briefly described. In either case, the isometrics of accuracy and bias are immediately evident therein, as—according to a specific design choice—they are in fact straight lines parallel to the x-axis and y-axis, respectively. ⟨φ,δ⟩ diagrams can also be used to assess the importance of features, as highly discriminant ones are immediately evident therein. In this paper, a comprehensive introduction on how to adopt ⟨φ,δ⟩ diagrams as a standard tool for classifier and feature assessment is given. In particular, with the goal of illustrating all relevant details from a pragmatic perspective, their implementation and usage as Python and R packages will be described.

Variable-order sequence modeling improves bacterial strain discrimination for Ion Torrent DNA reads

Background

Genome sequencing provides a powerful tool for pathogen detection and can help resolve outbreaks that pose public safety and health risks. Mapping of DNA reads to genomes plays a fundamental role in this approach, where accurate alignment and classification of sequencing data is crucial. Standard mapping methods crudely treat bases as independent from their neighbors. Accuracy might be improved by using higher order paired hidden Markov models (HMMs), which model neighbor effects, but introduce design and implementation issues that have typically made them impractical for read mapping applications. We present a variable-order paired HMM that we term VarHMM, which addresses central issues involved with higher order modeling for sequence alignment.

Results

Compared with existing alignment methods, VarHMM is able to model higher order distributions and quantify alignment probabilities with greater detail and accuracy. In a series of comparison tests, in which Ion Torrent sequenced DNA was mapped to similar bacterial strains, VarHMM consistently provided better strain discrimination than any of the other alignment methods that we compared with.

Conclusions

Our results demonstrate the advantages of higher ordered probability distribution modeling and also suggest that further development of such models would benefit read mapping in a range of other applications as well.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1710-0) contains supplementary material, which is available to authorized users.

Genotypic Prediction of Co-receptor Tropism of HIV-1 Subtypes A and C

Antiretroviral treatment of Human Immunodeficiency Virus type-1 (HIV-1) infections with CCR5-antagonists requires the co-receptor usage prediction of viral strains. Currently available tools are mostly designed based on subtype B strains and thus are in general not applicable to non-B subtypes. However, HIV-1 infections caused by subtype B only account for approximately 11% of infections worldwide. We evaluated the performance of several sequence-based algorithms for co-receptor usage prediction employed on subtype A V3 sequences including circulating recombinant forms (CRFs) and subtype C strains. We further analysed sequence profiles of gp120 regions of subtype A, B and C to explore functional relationships to entry phenotypes. Our analyses clearly demonstrate that state-of-the-art algorithms are not useful for predicting co-receptor tropism of subtype A and its CRFs. Sequence profile analysis of gp120 revealed molecular variability in subtype A viruses. Especially, the V2 loop region could be associated with co-receptor tropism, which might indicate a unique pattern that determines co-receptor tropism in subtype A strains compared to subtype B and C strains. Thus, our study demonstrates that there is a need for the development of novel algorithms facilitating tropism prediction of HIV-1 subtype A to improve effective antiretroviral treatment in patients.

In Acute Myocardial Infarction Liver Parameters Are Associated With Stenosis Diameter

Detection of high-risk subjects in acute myocardial infarction (AMI) by noninvasive means would reduce the need for intracardiac catheterization and associated complications. Liver enzymes are associated with cardiovascular disease risk. A potential predictive value for liver serum markers for the severity of stenosis in AMI was analyzed.Patients with AMI undergoing percutaneous coronary intervention (PCI; n = 437) were retrospectively evaluated. Minimal lumen diameter (MLD) and percent stenosis diameter (SD) were determined from quantitative coronary angiography. Patients were classified according to the severity of stenosis (SD ≥ 50%, n = 357; SD < 50%, n = 80). Routine heart and liver parameters were associated with SD using random forests (RF). A prediction model (M10) was developed based on parameter importance analysis in RF.Age, alkaline phosphatase (AP), aspartate aminotransferase (AST), and MLD differed significantly between SD ≥ 50 and SD < 50. Age, AST, alanine aminotransferase (ALT), and troponin correlated significantly with SD, whereas MLD correlated inversely with SD. M10 (age, BMI, AP, AST, ALT, gamma-glutamyltransferase, creatinine, troponin) reached an AUC of 69.7% (CI 63.8-75.5%, P < 0.0001).Routine liver parameters are associated with SD in AMI. A small set of noninvasively determined parameters can identify SD in AMI, and might avoid unnecessary coronary angiography in patients with low risk. The model can be accessed via http://stenosis.heiderlab.de.

Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction

MOTIVATION

Antiretroviral treatment regimens can sufficiently suppress viral replication in human immunodeficiency virus (HIV)-infected patients and prevent the progression of the disease. However, one of the factors contributing to the progression of the disease despite ongoing antiretroviral treatment is the emergence of drug resistance. The high mutation rate of HIV can lead to a fast adaptation of the virus under drug pressure, thus to failure of antiretroviral treatment due to the evolution of drug-resistant variants. Moreover, cross-resistance phenomena have been frequently found in HIV-1, leading to resistance not only against a drug from the current treatment, but also to other not yet applied drugs. Automatic classification and prediction of drug resistance is increasingly important in HIV research as well as in clinical settings, and to this end, machine learning techniques have been widely applied. Nevertheless, cross-resistance information was not taken explicitly into account, yet.

RESULTS

In our study, we demonstrated the use of cross-resistance information to predict drug resistance in HIV-1. We tested a set of more than 600 reverse transcriptase sequences and corresponding resistance information for six nucleoside analogues. Based on multilabel classification models and cross-resistance information, we were able to significantly improve overall prediction accuracy for all drugs, compared with single binary classifiers without any additional information. Moreover, we identified drug-specific patterns within the reverse transcriptase sequences that can be used to determine an optimal order of the classifiers within the classifier chains. These patterns are in good agreement with known resistance mutations and support the use of cross-resistance information in such prediction models.

CONTACT

dominik.heider@uni-due.de

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Computational Design of a DNA- and Fc-Binding Fusion Protein

Computational design of novel proteins with well-defined functions is an ongoing topic in computational biology. In this work, we generated and optimized a new synthetic fusion protein using an evolutionary approach. The optimization was guided by directed evolution based on hydrophobicity scores, molecular weight, and secondary structure predictions. Several methods were used to refine the models built from the resulting sequences. We have successfully combined two unrelated naturally occurring binding sites, the immunoglobin Fc-binding site of the Z domain and the DNA-binding motif of MyoD bHLH, into a novel stable protein.

Prediction of thermostability from amino acid attributes by combination of clustering with attribute weighting: a new vista in engineering enzymes

The engineering of thermostable enzymes is receiving increased attention. The paper, detergent, and biofuel industries, in particular, seek to use environmentally friendly enzymes instead of toxic chlorine chemicals. Enzymes typically function at temperatures below 60°C and denature if exposed to higher temperatures. In contrast, a small portion of enzymes can withstand higher temperatures as a result of various structural adaptations. Understanding the protein attributes that are involved in this adaptation is the first step toward engineering thermostable enzymes. We employed various supervised and unsupervised machine learning algorithms as well as attribute weighting approaches to find amino acid composition attributes that contribute to enzyme thermostability. Specifically, we compared two groups of enzymes: mesostable and thermostable enzymes. Furthermore, a combination of attribute weighting with supervised and unsupervised clustering algorithms was used for prediction and modelling of protein thermostability from amino acid composition properties. Mining a large number of protein sequences (2090) through a variety of machine learning algorithms, which were based on the analysis of more than 800 amino acid attributes, increased the accuracy of this study. Moreover, these models were successful in predicting thermostability from the primary structure of proteins. The results showed that expectation maximization clustering in combination with uncertainly and correlation attribute weighting algorithms can effectively (100%) classify thermostable and mesostable proteins. Seventy per cent of the weighting methods selected Gln content and frequency of hydrophilic residues as the most important protein attributes. On the dipeptide level, the frequency of Asn-Glu was the key factor in distinguishing mesostable from thermostable enzymes. This study demonstrates the feasibility of predicting thermostability irrespective of sequence similarity and will serve as a basis for engineering thermostable enzymes in the laboratory.

Interpol: An R package for preprocessing of protein sequences

BACKGROUND

Most machine learning techniques currently applied in the literature need a fixed dimensionality of input data. However, this requirement is frequently violated by real input data, such as DNA and protein sequences, that often differ in length due to insertions and deletions. It is also notable that performance in classification and regression is often improved by numerical encoding of amino acids, compared to the commonly used sparse encoding.

RESULTS

The software "Interpol" encodes amino acid sequences as numerical descriptor vectors using a database of currently 532 descriptors (mainly from AAindex), and normalizes sequences to uniform length with one of five linear or non-linear interpolation algorithms. Interpol is distributed with open source as platform independent R-package. It is typically used for preprocessing of amino acid sequences for classification or regression.

CONCLUSIONS

The functionality of Interpol widens the spectrum of machine learning methods that can be applied to biological sequences, and it will in many cases improve their performance in classification and regression.

Machine learning on normalized protein sequences

BACKGROUND

Machine learning techniques have been widely applied to biological sequences, e.g. to predict drug resistance in HIV-1 from sequences of drug target proteins and protein functional classes. As deletions and insertions are frequent in biological sequences, a major limitation of current methods is the inability to handle varying sequence lengths.

FINDINGS

We propose to normalize sequences to uniform length. To this end, we tested one linear and four different non-linear interpolation methods for the normalization of sequence lengths of 19 classification datasets. Classification tasks included prediction of HIV-1 drug resistance from drug target sequences and sequence-based prediction of protein function. We applied random forests to the classification of sequences into "positive" and "negative" samples. Statistical tests showed that the linear interpolation outperforms the non-linear interpolation methods in most of the analyzed datasets, while in a few cases non-linear methods had a small but significant advantage. Compared to other published methods, our prediction scheme leads to an improvement in prediction accuracy by up to 14%.

CONCLUSIONS

We found that machine learning on sequences normalized by simple linear interpolation gave better or at least competitive results compared to state-of-the-art procedures, and thus, is a promising alternative to existing methods, especially for protein sequences of variable length.

Insights into the classification of small GTPases

In this study we used a Random Forest-based approach for an assignment of small guanosine triphosphate proteins (GTPases) to specific subgroups. Small GTPases represent an important functional group of proteins that serve as molecular switches in a wide range of fundamental cellular processes, including intracellular transport, movement and signaling events. These proteins have further gained a special emphasis in cancer research, because within the last decades a huge variety of small GTPases from different subgroups could be related to the development of all types of tumors. Using a random forest approach, we were able to identify the most important amino acid positions for the classification process within the small GTPases superfamily and its subgroups. These positions are in line with the results of earlier studies and have been shown to be the essential elements for the different functionalities of the GTPase families. Furthermore, we provide an accurate and reliable software tool (GTPasePred) to identify potential novel GTPases and demonstrate its application to genome sequences.

A predicted physicochemically distinct sub-proteome associated with the intracellular organelle of the anammox bacterium Kuenenia stuttgartiensis

BACKGROUND

Anaerobic ammonium-oxidizing (anammox) bacteria perform a key step in global nitrogen cycling. These bacteria make use of an organelle to oxidize ammonia anaerobically to nitrogen (N2) and so contribute approximately 50% of the nitrogen in the atmosphere. It is currently unknown which proteins constitute the organellar proteome and how anammox bacteria are able to specifically target organellar and cell-envelope proteins to their correct final destinations. Experimental approaches are complicated by the absence of pure cultures and genetic accessibility. However, the genome of the anammox bacterium Candidatus "Kuenenia stuttgartiensis" has recently been sequenced. Here, we make use of these genome data to predict the organellar sub-proteome and address the molecular basis of protein sorting in anammox bacteria.

RESULTS

Two training sets representing organellar (30 proteins) and cell envelope (59 proteins) proteins were constructed based on previous experimental evidence and comparative genomics. Random forest (RF) classifiers trained on these two sets could differentiate between organellar and cell envelope proteins with ~89% accuracy using 400 features consisting of frequencies of two adjacent amino acid combinations. A physicochemically distinct organellar sub-proteome containing 562 proteins was predicted with the best RF classifier. This set included almost all catabolic and respiratory factors encoded in the genome. Apparently, the cytoplasmic membrane performs no catabolic functions. We predict that the Tat-translocation system is located exclusively in the organellar membrane, whereas the Sec-translocation system is located on both the organellar and cytoplasmic membranes. Canonical signal peptides were predicted and validated experimentally, but a specific (N- or C-terminal) signal that could be used for protein targeting to the organelle remained elusive.

CONCLUSIONS

A physicochemically distinct organellar sub-proteome was predicted from the genome of the anammox bacterium K. stuttgartiensis. This result provides strong in silico support for the existing experimental evidence for the existence of an organelle in this bacterium, and is an important step forward in unravelling a geochemically relevant case of cytoplasmic differentiation in bacteria. The predicted dual location of the Sec-translocation system and the apparent absence of a specific N- or C-terminal signal in the organellar proteins suggests that additional chaperones may be necessary that act on an as-yet unknown property of the targeted proteins.

Predicting Bevirimat resistance of HIV-1 from genotype

BACKGROUND

Maturation inhibitors are a new class of antiretroviral drugs. Bevirimat (BVM) was the first substance in this class of inhibitors entering clinical trials. While the inhibitory function of BVM is well established, the molecular mechanisms of action and resistance are not well understood. It is known that mutations in the regions CS p24/p2 and p2 can cause phenotypic resistance to BVM. We have investigated a set of p24/p2 sequences of HIV-1 of known phenotypic resistance to BVM to test whether BVM resistance can be predicted from sequence, and to identify possible molecular mechanisms of BVM resistance in HIV-1.

RESULTS

We used artificial neural networks and random forests with different descriptors for the prediction of BVM resistance. Random forests with hydrophobicity as descriptor performed best and classified the sequences with an area under the Receiver Operating Characteristics (ROC) curve of 0.93 +/- 0.001. For the collected data we find that p2 sequence positions 369 to 376 have the highest impact on resistance, with positions 370 and 372 being particularly important. These findings are in partial agreement with other recent studies. Apart from the complex machine learning models we derived a number of simple rules that predict BVM resistance from sequence with surprising accuracy. According to computational predictions based on the data set used, cleavage sites are usually not shifted by resistance mutations. However, we found that resistance mutations could shorten and weaken the alpha-helix in p2, which hints at a possible resistance mechanism.

CONCLUSIONS

We found that BVM resistance of HIV-1 can be predicted well from the sequence of the p2 peptide, which may prove useful for personalized therapy if maturation inhibitors reach clinical practice. Results of secondary structure analysis are compatible with a possible route to BVM resistance in which mutations weaken a six-helix bundle discovered in recent experiments, and thus ease Gag cleavage by the retroviral protease.