Search

Among various types of protein post-translational modifications (PTMs), lysine PTMs play an important role in regulating a wide range of functions and biological processes. Due to the generation and accumulation of enormous amount of protein sequence data by ongoing whole-genome sequencing projects, systematic identification of different types of lysine PTM substrates and their specific PTM sites in the entire proteome is increasingly important and has therefore received much attention. Accordingly, a variety of computational methods for lysine PTM identification have been developed based on the combination of various handcrafted sequence features and machine-learning techniques. In this chapter, we first briefly review existing computational methods for lysine PTM identification and then introduce a recently developed deep learning-based method, termed MUscADEL (Multiple Scalable Accurate Deep Learner for lysine PTMs). Specifically, MUscADEL employs bidirectional long short-term memory (BiLSTM) recurrent neural networks and is capable of predicting eight major types of lysine PTMs in both the human and mouse proteomes. The web server of MUscADEL is publicly available at http://muscadel.erc.monash.edu/ for the research community to use.

In recent years, many new ensemble-based time series classification (TSC) algorithms have been proposed. Each of them is significantly more accurate than their predecessors. The Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) is currently the most accurate TSC algorithm when assessed on the UCR repository. It is a meta-ensemble of 5 state-of-the-art ensemble-based classifiers. The time complexity of HIVE-COTE—particularly for training—is prohibitive for most datasets. There is thus a critical need to speed up the classifiers that compose HIVE-COTE. This paper focuses on speeding up one of its components: Ensembles of Elastic Distances (EE), which is the classifier that leverages on the decades of research into the development of time-dedicated measures. Training EE can be prohibitive for many datasets. For example, it takes a month on the ElectricDevices dataset with 9000 instances. This is because EE needs to cross-validate the hyper-parameters used for the 11 similarity measures it encompasses. In this work, Fast Ensembles of Elastic Distances is proposed to train EE faster. There are two versions to it. The exact version makes it possible to train EE 10 times faster. The approximate version is 40 times faster than EE without significantly impacting the classification accuracy. This translates to being able to train EE on ElectricDevices in 13 h.

In online-learning, the data is incrementally received and the distributions from which it is drawn may keep changing over time. This phenomenon is widely known as concept drift. Such changes may affect the generalization of a learned model to future data. This problem may be exacerbated by the form of the drift itself changing over time. Quantitative measures to describe and analyze the concept drift have been proposed in previous work. A description composed from these measures is called a concept drift map. We believe that these maps could be useful for guiding how much knowledge in the old model should be forgotten. Therefore, this paper presents an adaptive online learning model that uses a concept drift map to regulate the forgetting factor of an extreme learning machine. Specifically, when a batch of new instances are labeled, the distribution of each class on each attribute is firstly estimated, and then it is compared with the distribution estimated in the previous batch to calculate the magnitude of concept drift, which is further used to regulate the forgetting factor and to update the learning model. Therefore, the novelty of this paper lies in that a quantitative distance metric between two distributions constructed on continuous attribute space is presented to construct concept drift map which can be further associated with the forgetting factor to make the learning model adapt the concept drift. Experimental results on several benchmark stream data sets show the proposed model is generally superior to several previous algorithms when classifying a variety of data streams subject to drift, indicating its effectiveness and feasibility.

Multi-drug resistance (MDR) has become one of the greatest threats to human health worldwide, and novel treatment methods of infections caused by MDR bacteria are urgently needed. Phage therapy is a promising alternative to solve this problem, to which the key is correctly matching target pathogenic bacteria with the corresponding therapeutic phage. Deep learning is powerful for mining complex patterns to generate accurate predictions. In this study, we develop PredPHI ( Pred icting P hage- H ost I nteractions), a deep learning-based tool capable of predicting the host of phages from sequence data. We collect >3000 phage-host pairs along with their protein sequences from PhagesDB and GenBank databases and extract a set of features. Then we select high-quality negative samples based on the K-Means clustering method and construct a balanced training set. Finally, we employ a deep convolutional neural network to build the predictive model. The results indicate that PredPHI can achieve a predictive performance of 81 percent in terms of the area under the receiver operating characteristic curve on the test set, and the clustering-based method is significantly more robust than that based on randomly selecting negative samples. These results highlight that PredPHI is a useful and accurate tool for identifying phage-host interactions from sequence data.

Motivation Digital pathology supports analysis of histopathological images using deep learning methods at a large-scale. However, applications of deep learning in this area have been limited by the complexities of configuration of the computational environment and of hyperparameter optimization, which hinder deployment and reduce reproducibility. Results Here, we propose HEAL, a deep learning-based automated framework for easy, flexible and multi-faceted histopathological image analysis. We demonstrate its utility and functionality by performing two case studies on lung cancer and one on colon cancer. Leveraging the capability of Docker, HEAL represents an ideal end-to-end tool to conduct complex histopathological analysis and enables deep learning in a broad range of applications for cancer image analysis. Availability and implementation The docker image of HEAL is available at https://hub.docker.com/r/docurdt/heal and related documentation and datasets are available at http://heal.erc.monash.edu.au. Supplementary information Supplementary data are available at Bioinformatics online.

Land cover maps are vitally important to many elements of environmental management. However the machine learning algorithms used to produce them require a substantive quantity of labelled training data to reach the best levels of accuracy. When researchers wish to map an area where no labelled training data are available, one potential solution is to use a classifier trained on another geographical area and adapting it to the target location-this is known as Unsupervised Domain Adaptation (DA). In this paper we undertake the first experiments using unsupervised DA methods for the classification of satellite image time series (SITS) data. Our experiments draw the interesting conclusion that existing methods provide no benefit when used on SITS data, and that this is likely due to the temporal nature of the data and the change in class distributions between the regions. This suggests that an unsupervised domain adaptation technique for SITS would be extremely beneficial for land cover mapping.

This paper studies time series extrinsic regression (TSER): a regression task of which the aim is to learn the relationship between a time series and a continuous scalar variable; a task closely related to time series classification (TSC), which aims to learn the relationship between a time series and a categorical class label. This task generalizes time series forecasting, relaxing the requirement that the value predicted be a future value of the input series or primarily depend on more recent values. In this paper, we motivate and study this task, and benchmark existing solutions and adaptations of TSC algorithms on a novel archive of 19 TSER datasets which we have assembled. Our results show that the state-of-the-art TSC algorithm Rocket, when adapted for regression, achieves the highest overall accuracy compared to adaptations of other TSC algorithms and state-of-the-art machine learning (ML) algorithms such as XGBoost, Random Forest and Support Vector Regression. More importantly, we show that much research is needed in this field to improve the accuracy of ML models. We also find evidence that further research has excellent prospects of improving upon these straightforward baselines.

The roles of proteolytic cleavage have been intensively investigated and discussed during the past two decades. This irreversible chemical process has been frequently reported to influence a number of crucial biological processes (BPs), such as cell cycle, protein regulation and inflammation. A number of advanced studies have been published aiming at deciphering the mechanisms of proteolytic cleavage. Given its significance and the large number of functionally enriched substrates targeted by specific proteases, many computational approaches have been established for accurate prediction of protease-specific substrates and their cleavage sites. Consequently, there is an urgent need to systematically assess the state-of-the-art computational approaches for protease-specific cleavage site prediction to further advance the existing methodologies and to improve the prediction performance. With this goal in mind, in this article, we carefully evaluated a total of 19 computational methods (including 8 scoring function-based methods and 11 machine learning-based methods) in terms of their underlying algorithm, calculated features, performance evaluation and software usability. Then, extensive independent tests were performed to assess the robustness and scalability of the reviewed methods using our carefully prepared independent test data sets with 3641 cleavage sites (specific to 10 proteases). The comparative experimental results demonstrate that PROSPERous is the most accurate generic method for predicting eight protease-specific cleavage sites, while GPS-CCD and LabCaS outperformed other predictors for calpain-specific cleavage sites. Based on our review, we then outlined some potential ways to improve the prediction performance and ease the computational burden by applying ensemble learning, deep learning, positive unlabeled learning and parallel and distributed computing techniques. We anticipate that our study will serve as a practical and useful guide for interested readers to further advance next-generation bioinformatics tools for protease-specific cleavage site prediction.

As a newly discovered post-translational modification (PTM), lysine malonylation (Kmal) regulates a myriad of cellular processes from prokaryotes to eukaryotes and has important implications in human diseases. Despite its functional significance, computational methods to accurately identify malonylation sites are still lacking and urgently needed. In particular, there is currently no comprehensive analysis and assessment of different features and machine learning (ML) methods that are required for constructing the necessary prediction models. Here, we review, analyze and compare 11 different feature encoding methods, with the goal of extracting key patterns and characteristics from residue sequences of Kmal sites. We identify optimized feature sets, with which four commonly used ML methods (random forest, support vector machines, K-nearest neighbor and logistic regression) and one recently proposed [Light Gradient Boosting Machine (LightGBM)] are trained on data from three species, namely, Escherichia coli, Mus musculus and Homo sapiens, and compared using randomized 10-fold cross-validation tests. We show that integration of the single method-based models through ensemble learning further improves the prediction performance and model robustness on the independent test. When compared to the existing state-of-the-art predictor, MaloPred, the optimal ensemble models were more accurate for all three species (AUC: 0.930, 0.923 and 0.944 for E. coli, M. musculus and H. sapiens, respectively). Using the ensemble models, we developed an accessible online predictor, kmal-sp, available at http://kmalsp.erc.monash.edu/. We hope that this comprehensive survey and the proposed strategy for building more accurate models can serve as a useful guide for inspiring future developments of computational methods for PTM site prediction, expedite the discovery of new malonylation and other PTM types and facilitate hypothesis-driven experimental validation of novel malonylated substrates and malonylation sites.

This paper introduces a novel parameter estimation method for the probability tables of Bayesian network classifiers (BNCs), using hierarchical Dirichlet processes (HDPs). The main result of this paper is to show that improved parameter estimation allows BNCs to outperform leading learning methods such as Random Forest for both 0-1 loss and RMSE, albeit just on categorical datasets. As data assets become larger, entering the hyped world of "big", efficient accurate classification requires three main elements: (1) classifiers with low-bias that can capture the fine-detail of large datasets (2) out-of-core learners that can learn from data without having to hold it all in main memory and (3) models that can classify new data very efficiently. The latest Bayesian network classifiers (BNCs) satisfy these requirements. Their bias can be controlled easily by increasing the number of parents of the nodes in the graph. Their structure can be learned out of core with a limited number of passes over the data. However, as the bias is made lower to accurately model classification tasks, so is the accuracy of their parameters' estimates, as each parameter is estimated from ever decreasing quantities of data. In this paper, we introduce the use of Hierarchical Dirichlet Processes for accurate BNC parameter estimation. We conduct an extensive set of experiments on 68 standard datasets and demonstrate that our resulting classifiers perform very competitively with Random Forest in terms of prediction, while keeping the out-of-core capability and superior classification time.

Regulation of proteolysis plays a critical role in a myriad of important cellular processes. The key to better understanding the mechanisms that control this process is to identify the specific substrates that each protease targets. To address this, we have developed iProt-Sub, a powerful bioinformatics tool for the accurate prediction of protease-specific substrates and their cleavage sites. Importantly, iProt-Sub represents a significantly advanced version of its successful predecessor, PROSPER. It provides optimized cleavage site prediction models with better prediction performance and coverage for more species-specific proteases (4 major protease families and 38 different proteases). iProt-Sub integrates heterogeneous sequence and structural features and uses a two-step feature selection procedure to further remove redundant and irrelevant features in an effort to improve the cleavage site prediction accuracy. Features used by iProt-Sub are encoded by 11 different sequence encoding schemes, including local amino acid sequence profile, secondary structure, solvent accessibility and native disorder, which will allow a more accurate representation of the protease specificity of approximately 38 proteases and training of the prediction models. Benchmarking experiments using cross-validation and independent tests showed that iProt-Sub is able to achieve a better performance than several existing generic tools. We anticipate that iProt-Sub will be a powerful tool for proteome-wide prediction of protease-specific substrates and their cleavage sites, and will facilitate hypothesis-driven functional interrogation of protease-specific substrate cleavage and proteolytic events.

Determining the catalytic residues in an enzyme is critical to our understanding the relationship between protein sequence, structure, function, and enhancing our ability to design novel enzymes and their inhibitors. Although many enzymes have been sequenced, and their primary and tertiary structures determined, experimental methods for enzyme functional characterization lag behind. Because experimental methods used for identifying catalytic residues are resource- and labor-intensive, computational approaches have considerable value and are highly desirable for their ability to complement experimental studies in identifying catalytic residues and helping to bridge the sequence-structure-function gap. In this study, we describe a new computational method called PREvaIL for predicting enzyme catalytic residues. This method was developed by leveraging a comprehensive set of informative features extracted from multiple levels, including sequence, structure, and residue-contact network, in a random forest machine-learning framework. Extensive benchmarking experiments on eight different datasets based on 10-fold cross-validation and independent tests, as well as side-by-side performance comparisons with seven modern sequence- and structure-based methods, showed that PREvaIL achieved competitive predictive performance, with an area under the receiver operating characteristic curve and area under the precision-recall curve ranging from 0.896 to 0.973 and from 0.294 to 0.523, respectively. We demonstrated that this method was able to capture useful signals arising from different levels, leveraging such differential but useful types of features and allowing us to significantly improve the performance of catalytic residue prediction. We believe that this new method can be utilized as a valuable tool for both understanding the complex sequence-structure-function relationships of proteins and facilitating the characterization of novel enzymes lacking functional annotations.

With large quantities of data typically available nowadays, forecasting models that are trained across sets of time series, known as Global Forecasting Models (GFM), are regularly outperforming traditional univariate forecasting models that work on isolated series. As GFMs usually share the same set of parameters across all time series, they often have the problem of not being localised enough to a particular series, especially in situations where datasets are heterogeneous. We study how ensembling techniques can be used with generic GFMs and univariate models to solve this issue. Our work systematises and compares relevant current approaches, namely clustering series and training separate submodels per cluster, the so-called ensemble of specialists approach, and building heterogeneous ensembles of global and local models. We fill some gaps in the existing GFM localisation approaches, in particular by incorporating varied clustering techniques such as feature-based clustering, distance-based clustering and random clustering, and generalise them to use different underlying GFM model types. We then propose a new methodology of clustered ensembles where we train multiple GFMs on different clusters of series, obtained by changing the number of clusters and cluster seeds. Using Feed-forward Neural Networks, Recurrent Neural Networks, and Pooled Regression models as the underlying GFMs, in our evaluation on eight publicly available datasets, the proposed models are able to achieve significantly higher accuracy than baseline GFM models and univariate forecasting methods., 37 pages, 6 figures, 6 tables

Recent advances have demonstrated substantial benefits from learning with both generative and discriminative parameters. On the one hand, generative approaches address the estimation of the parameters of the joint distribution--$$\mathrm{P}(y,\mathbf{x})$$P(y,x), which for most network types is very computationally efficient (a notable exception to this are Markov networks) and on the other hand, discriminative approaches address the estimation of the parameters of the posterior distribution--and, are more effective for classification, since they fit $$\mathrm{P}(y|\mathbf{x})$$P(y|x) directly. However, discriminative approaches are less computationally efficient as the normalization factor in the conditional log-likelihood precludes the derivation of closed-form estimation of parameters. This paper introduces a new discriminative parameter learning method for Bayesian network classifiers that combines in an elegant fashion parameters learned using both generative and discriminative methods. The proposed method is discriminative in nature, but uses estimates of generative probabilities to speed-up the optimization process. A?second contribution is to propose a simple framework to characterize the parameter learning task for Bayesian network classifiers. We conduct an extensive set of experiments on 72 standard datasets and demonstrate that our proposed discriminative parameterization provides an efficient alternative to other state-of-the-art parameterizations.

International audience; This paper brings deep learning at the forefront of research into Time Series Classification (TSC). TSC is the area of machine learning tasked with the categorization (or labelling) of time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE cannot be applied to many real-world datasets because of its high training time complexity in O(N 2 • T 4) for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 8 days to learn from a small dataset with N = 1500 time series of short length T = 46. Meanwhile deep learning has received enormous attention because of its high accuracy and scalability. Recent approaches to deep learning for TSC have been scalable, but less accurate than HIVE-COTE. We introduce InceptionTime-an ensemble of deep Convolutional Neural Network (CNN) models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime is on par with HIVE-COTE in terms of accuracy while being much more scalable: not only can it learn from 1,500 time series in one hour but it can also learn from 8M time series in 13 hours, a quantity of data that is fully out of reach of HIVE-COTE.

International audience; Land cover maps are a vital input variable in all types of environmental research and management. However the modern state-of-the-art machine learning techniques used to create them require substantial training data to produce optimal accuracy. Domain Adaptation is one technique researchers might use when labelled training data are unavailable or scarce. This paper looks at the result of training a convolutional neural network model on a region where data are available (source domain), and then adapting this model to another region (target domain) by retraining it on the available labelled data, and in particular how these results change with increasing data availability. Our experiments performing domain adaptation on satellite image time series, draw three interesting conclusions: (1) a model trained only on data from the source domain delivers 73.0% test accuracy on the target domain; (2) when all of the weights are retrained on the target data, over 16,000 instances were required to improve upon the accuracy of the source-only model; and (3) even if sufficient data is available in the target domain, using a model pretrained on a source domain will result in better overall test accuracy compared to a model trained on target domain data only-88.9% versus 84.7%.

Satellite image time series (SITS) have proven to be essential for accurate and up-to-date land cover mapping over large areas. Most works about SITS have focused on the use of traditional classification algorithms such as Random Forests (RFs). Deep learning algorithms have been very successful for supervised tasks, in particular for data that exhibit a structure between attributes, such as space or time. In this work, we compare for the first time RFs to the two leading deep learning algorithms for handling temporal data: Recurrent Neural Networks (RNNs) and temporal Convolutional Neural Networks (TempCNNs). We carry out a large experiment using Sentinel-2 time series. We compare both accuracy and computational times to classify 10,980 km2 over Australia. The results highlights the good performance of TemCNNs that obtain the highest accuracy. They also show that RNNs might be less suited for large scale study as they have higher runtime complexity.

With the explosive growth of biological sequences generated in the post-genomic era, one of the most challenging problems in bioinformatics and computational biology is to computationally characterize sequences, structures and functions in an efficient, accurate and high-throughput manner. A number of online web servers and stand-alone tools have been developed to address this to date; however, all these tools have their limitations and drawbacks in terms of their effectiveness, user-friendliness and capacity. Here, we present iLearn, a comprehensive and versatile Python-based toolkit, integrating the functionality of feature extraction, clustering, normalization, selection, dimensionality reduction, predictor construction, best descriptor/model selection, ensemble learning and results visualization for DNA, RNA and protein sequences. iLearn was designed for users that only want to upload their data set and select the functions they need calculated from it, while all necessary procedures and optimal settings are completed automatically by the software. iLearn includes a variety of descriptors for DNA, RNA and proteins, and four feature output formats are supported so as to facilitate direct output usage or communication with other computational tools. In total, iLearn encompasses 16 different types of feature clustering, selection, normalization and dimensionality reduction algorithms, and five commonly used machine-learning algorithms, thereby greatly facilitating feature analysis and predictor construction. iLearn is made freely available via an online web server and a stand-alone toolkit.

Sequence-based analysis and prediction are fundamental bioinformatic tasks that facilitate understanding of the sequence(-structure)-function paradigm for DNAs, RNAs and proteins. Rapid accumulation of sequences requires equally pervasive development of new predictive models, which depends on the availability of effective tools that support these efforts. We introduce iLearnPlus, the first machine-learning platform with graphical- and web-based interfaces for the construction of machine-learning pipelines for analysis and predictions using nucleic acid and protein sequences. iLearnPlus provides a comprehensive set of algorithms and automates sequence-based feature extraction and analysis, construction and deployment of models, assessment of predictive performance, statistical analysis, and data visualization; all without programming. iLearnPlus includes a wide range of feature sets which encode information from the input sequences and over twenty machine-learning algorithms that cover several deep-learning approaches, outnumbering the current solutions by a wide margin. Our solution caters to experienced bioinformaticians, given the broad range of options, and biologists with no programming background, given the point-and-click interface and easy-to-follow design process. We showcase iLearnPlus with two case studies concerning prediction of long noncoding RNAs (lncRNAs) from RNA transcripts and prediction of crotonylation sites in protein chains. iLearnPlus is an open-source platform available at https://github.com/Superzchen/iLearnPlus/ with the webserver at http://ilearnplus.erc.monash.edu/.

In association rule mining, the trade-off between avoiding harmful spurious rules and preserving authentic ones is an ever critical barrier to obtaining reliable and useful results. The statistically sound technique for evaluating statistical significance of association rules is superior in preventing spurious rules, yet can also cause severe loss of true rules in presence of data error. This study presents a new and improved method for statistical test on association rules with uncertain erroneous data. An original mathematical model was established to describe data error propagation through computational procedures of the statistical test. Based on the error model, a scheme combining analytic and simulative processes was designed to correct the statistical test for distortions caused by data error. Experiments on both synthetic and real-world data show that the method significantly recovers the loss in true rules (reduces type-2 error) due to data error occurring in original statistically sound method. Meanwhile, the new method maintains effective control over the familywise error rate, which is the distinctive advantage of the original statistically sound technique. Furthermore, the method is robust against inaccurate data error probability information and situations not fulfilling the commonly accepted assumption on independent error probabilities of different data items. The method is particularly effective for rules which were most practically meaningful yet sensitive to data error. The method proves promising in enhancing values of association rule mining results and helping users make correct decisions.

Naive Bayes is one of the most popular data mining algorithms. Its efficiency comes from the assumption of attribute independence, although this might be violated in many real-world data sets. Many efforts have been done to mitigate the assumption, among which attribute selection is an important approach. However, conventional efforts to perform attribute selection in naive Bayes suffer from heavy computational overhead. This paper proposes an efficient selective naive Bayes algorithm, which adopts only some of the attributes to construct selective naive Bayes models. These models are built in such a way that each one is a trivial extension of another. The most predictive selective naive Bayes model can be selected by the measures of incremental leave-one-out cross validation. As a result, attributes can be selected by efficient model selection. Empirical results demonstrate that the selective naive Bayes shows superior classification accuracy, yet at the same time maintains the simplicity and efficiency.

Research into the classification of time series has made enormous progress in the last decade. The UCR time series archive has played a significant role in challenging and guiding the development of new learners for time series classification. The largest dataset in the UCR archive holds 10 thousand time series only; which may explain why the primary research focus has been in creating algorithms that have high accuracy on relatively small datasets. This paper introduces Proximity Forest, an algorithm that learns accurate models from datasets with millions of time series, and classifies a time series in milliseconds. The models are ensembles of highly randomized Proximity Trees. Whereas conventional decision trees branch on attribute values (and usually perform poorly on time series), Proximity Trees branch on the proximity of time series to one exemplar time series or another; allowing us to leverage the decades of work into developing relevant measures for time series. Proximity Forest gains both efficiency and accuracy by stochastic selection of both exemplars and similarity measures. Our work is motivated by recent time series applications that provide orders of magnitude more time series than the UCR benchmarks. Our experiments demonstrate that Proximity Forest is highly competitive on the UCR archive: it ranks among the most accurate classifiers while being significantly faster. We demonstrate on a 1M time series Earth observation dataset that Proximity Forest retains this accuracy on datasets that are many orders of magnitude greater than those in the UCR repository, while learning its models at least 100,000 times faster than current state of the art models Elastic Ensemble and COTE., 30 pages, 12 figures

Kernel methods are powerful supervised machine learning models for their strong generalization ability, especially on limited data to effectively generalize on unseen data. However, most kernel methods, including the state-of-the-art LIBSVM, are vulnerable to the curse of kernelization, making them infeasible to apply to large-scale datasets. This issue is exacerbated when kernel methods are used in conjunction with a grid search to tune their kernel parameters and hyperparameters which brings in the question of model robustness when applied to real datasets. In this paper, we propose a robust Bayesian Kernel Machine (BKM) - a Bayesian kernel machine that exploits the strengths of both the Bayesian modelling and kernel methods. A key challenge for such a formulation is the need for an efficient learning algorithm. To this end, we successfully extended the recent Stein variational theory for Bayesian inference for our proposed model, resulting in fast and efficient learning and prediction algorithms. Importantly our proposed BKM is resilient to the curse of kernelization, hence making it applicable to large-scale datasets and robust to parameter tuning, avoiding the associated expense and potential pitfalls with current practice of parameter tuning. Our extensive experimental results on 12 benchmark datasets show that our BKM without tuning any parameter can achieve comparable predictive performance with the state-of-the-art LIBSVM and significantly outperforms other baselines, while obtaining significantly speedup in terms of the total training time compared with its rivals

We introduce a novel incremental decision tree learning algorithm, Hoeffding Anytime Tree, that is statistically more efficient than the current state-of-the-art, Hoeffding Tree. We demonstrate that an implementation of Hoeffding Anytime Tree---"Extremely Fast Decision Tree", a minor modification to the MOA implementation of Hoeffding Tree---obtains significantly superior prequential accuracy on most of the largest classification datasets from the UCI repository. Hoeffding Anytime Tree produces the asymptotic batch tree in the limit, is naturally resilient to concept drift, and can be used as a higher accuracy replacement for Hoeffding Tree in most scenarios, at a small additional computational cost., Submitted to KDD'2018

Lysine post-translational modifications (PTMs) play a crucial role in regulating diverse functions and biological processes of proteins. However, because of the large volumes of sequencing data generated from genome-sequencing projects, systematic identification of different types of lysine PTM substrates and PTM sites in the entire proteome remains a major challenge. In recent years, a number of computational methods for lysine PTM identification have been developed. These methods show high diversity in their core algorithms, features extracted and feature selection techniques and evaluation strategies. There is therefore an urgent need to revisit these methods and summarize their methodologies, to improve and further develop computational techniques to identify and characterize lysine PTMs from the large amounts of sequence data. With this goal in mind, we first provide a comprehensive survey on a large collection of 49 state-of-the-art approaches for lysine PTM prediction. We cover a variety of important aspects that are crucial for the development of successful predictors, including operating algorithms, sequence and structural features, feature selection, model performance evaluation and software utility. We further provide our thoughts on potential strategies to improve the model performance. Second, in order to examine the feasibility of using deep learning for lysine PTM prediction, we propose a novel computational framework, termed MUscADEL (Multiple Scalable Accurate Deep Learner for lysine PTMs), using deep, bidirectional, long short-term memory recurrent neural networks for accurate and systematic mapping of eight major types of lysine PTMs in the human and mouse proteomes. Extensive benchmarking tests show that MUscADEL outperforms current methods for lysine PTM characterization, demonstrating the potential and power of deep learning techniques in protein PTM prediction. The web server of MUscADEL, together with all the data sets assembled in this study, is freely available at http://muscadel.erc.monash.edu/. We anticipate this comprehensive review and the application of deep learning will provide practical guide and useful insights into PTM prediction and inspire future bioinformatics studies in the related fields.

Summary Structural and physiochemical descriptors extracted from sequence data have been widely used to represent sequences and predict structural, functional, expression and interaction profiles of proteins and peptides as well as DNAs/RNAs. Here, we present iFeature, a versatile Python-based toolkit for generating various numerical feature representation schemes for both protein and peptide sequences. iFeature is capable of calculating and extracting a comprehensive spectrum of 18 major sequence encoding schemes that encompass 53 different types of feature descriptors. It also allows users to extract specific amino acid properties from the AAindex database. Furthermore, iFeature integrates 12 different types of commonly used feature clustering, selection and dimensionality reduction algorithms, greatly facilitating training, analysis and benchmarking of machine-learning models. The functionality of iFeature is made freely available via an online web server and a stand-alone toolkit. Availability and implementation http://iFeature.erc.monash.edu/; https://github.com/Superzchen/iFeature/. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation: Glycosylation is a ubiquitous type of protein post-translational modification (PTM) in eukaryotic cells, which plays vital roles in various biological processes (BPs) such as cellular communication, ligand recognition and subcellular recognition. It is estimated that >50% of the entire human proteome is glycosylated. However, it is still a significant challenge to identify glycosylation sites, which requires expensive/laborious experimental research. Thus, bioinformatics approaches that can predict the glycan occupancy at specific sequons in protein sequences would be useful for understanding and utilizing this important PTM. Results: In this study, we present a novel bioinformatics tool called GlycoMine, which is a comprehensive tool for the systematic in silico identification of C-linked, N-linked, and O-linked glycosylation sites in the human proteome. GlycoMine was developed using the random forest algorithm and evaluated based on a well-prepared up-to-date benchmark dataset that encompasses all three types of glycosylation sites, which was curated from multiple public resources. Heterogeneous sequences and functional features were derived from various sources, and subjected to further two-step feature selection to characterize a condensed subset of optimal features that contributed most to the type-specific prediction of glycosylation sites. Five-fold cross-validation and independent tests show that this approach significantly improved the prediction performance compared with four existing prediction tools: NetNGlyc, NetOGlyc, EnsembleGly and GPP. We demonstrated that this tool could identify candidate glycosylation sites in case study proteins and applied it to identify many high-confidence glycosylation target proteins by screening the entire human proteome. Availability and implementation: The webserver, Java Applet, user instructions, datasets, and predicted glycosylation sites in the human proteome are freely available at http://www.structbioinfor.org/Lab/GlycoMine/. Contact: Jiangning.Song@monash.edu or James.Whisstock@monash.edu or zhangyang@nwsuaf.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Statistically sound pattern discovery harnesses the rigour of statistical hypothesis testing to overcome many of the issues that have hampered standard data mining approaches to pattern discovery. Most importantly, application of appropriate statistical tests allows precise control over the risk of false discoveries -- patterns that are found in the sample data but do not hold in the wider population from which the sample was drawn. Statistical tests can also be applied to filter out patterns that are unlikely to be useful, removing uninformative variations of the key patterns in the data. This tutorial introduces the key statistical and data mining theory and techniques that underpin this fast developing field. We concentrate on two general classes of patterns: dependency rules that express statistical dependencies between condition and consequent parts and dependency sets that express mutual dependence between set elements. We clarify alternative interpretations of statistical dependence and introduce appropriate tests for evaluating statistical significance of patterns in different situations. We also introduce special techniques for controlling the likelihood of spurious discoveries when multitudes of patterns are evaluated. The paper is aimed at a wide variety of audiences. It provides the necessary statistical background and summary of the state-of-the-art for any data mining researcher or practitioner wishing to enter or understand statistically sound pattern discovery research or practice. It can serve as a general introduction to the field of statistically sound pattern discovery for any reader with a general background in data sciences., 51 pages. This is a prepublication version of an open-access journal paper. This version presents the original math notations that were compromised in the published version

Purpose Prospective epidemiologic surveillance of invasive mold disease (IMD) in hematology patients is hampered by the absence of a reliable laboratory prompt. This study develops an expert system for electronic surveillance of IMD that combines probabilities using natural language processing (NLP) of computed tomography (CT) reports with microbiology and antifungal drug data to improve prediction of IMD. Methods Microbiology indicators and antifungal drug–dispensing data were extracted from hospital information systems at three tertiary hospitals for 123 hematology-oncology patients. Of this group, 64 case patients had 26 probable/proven IMD according to international definitions, and 59 patients were uninfected controls. Derived probabilities from NLP combined with medical expertise identified patients at high likelihood of IMD, with remaining patients processed by a machine-learning classifier trained on all available features. Results Compared with the baseline text classifier, the expert system that incorporated the best performing algorithm (naïve Bayes) improved specificity from 50.8% (95% CI, 37.5% to 64.1%) to 74.6% (95% CI, 61.6% to 85.0%), reducing false positives by 48% from 29 to 15; improved sensitivity slightly from 96.9% (95% CI, 89.2% to 99.6%) to 98.4% (95% CI, 91.6% to 100%); and improved receiver operating characteristic area from 73.9% (95% CI, 67.1% to 80.6%) to 92.8% (95% CI, 88% to 97.5%). Conclusion An expert system that uses multiple sources of data (CT reports, microbiology, antifungal drug dispensing) is a promising approach to continuous prospective surveillance of IMD in the hospital, and demonstrates reduced false notifications (positives) compared with NLP of CT reports alone. Our expert system could provide decision support for IMD surveillance, which is critical to antifungal stewardship and improving supportive care in cancer.

In the course of infecting their hosts, pathogenic bacteria secrete numerous effectors, namely, bacterial proteins that pervert host cell biology. Many Gram-negative bacteria, including context-dependent human pathogens, use a type IV secretion system (T4SS) to translocate effectors directly into the cytosol of host cells. Various type IV secreted effectors (T4SEs) have been experimentally validated to play crucial roles in virulence by manipulating host cell gene expression and other processes. Consequently, the identification of novel effector proteins is an important step in increasing our understanding of host-pathogen interactions and bacterial pathogenesis. Here, we train and compare six machine learning models, namely, Naive Bayes (NB), K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector machines (SVMs) and multilayer perceptron (MLP), for the identification of T4SEs using 10 types of selected features and 5-fold cross-validation. Our study shows that: (1) including different but complementary features generally enhance the predictive performance of T4SEs; (2) ensemble models, obtained by integrating individual single-feature models, exhibit a significantly improved predictive performance and (3) the 'majority voting strategy' led to a more stable and accurate classification performance when applied to predicting an ensemble learning model with distinct single features. We further developed a new method to effectively predict T4SEs, Bastion4 (Bacterial secretion effector predictor for T4SS), and we show our ensemble classifier clearly outperforms two recent prediction tools. In summary, we developed a state-of-the-art T4SE predictor by conducting a comprehensive performance evaluation of different machine learning algorithms along with a detailed analysis of single- and multi-feature selections.

Summary Evolutionary information in the form of a Position-Specific Scoring Matrix (PSSM) is a widely used and highly informative representation of protein sequences. Accordingly, PSSM-based feature descriptors have been successfully applied to improve the performance of various predictors of protein attributes. Even though a number of algorithms have been proposed in previous studies, there is currently no universal web server or toolkit available for generating this wide variety of descriptors. Here, we present POSSUM (Position-Specific Scoring matrix-based feature generator for machine learning), a versatile toolkit with an online web server that can generate 21 types of PSSM-based feature descriptors, thereby addressing a crucial need for bioinformaticians and computational biologists. We envisage that this comprehensive toolkit will be widely used as a powerful tool to facilitate feature extraction, selection, and benchmarking of machine learning-based models, thereby contributing to a more effective analysis and modeling pipeline for bioinformatics research. Availability and implementation http://possum.erc.monash.edu/. Supplementary information Supplementary data are available at Bioinformatics online.

Learning from data that are too big to fit into memory poses great challenges to currently available learning approaches. Averaged n-Dependence Estimators (AnDE) allows for a flexible learning from out-of-core data, by varying the value of n (number of super parents). Hence, AnDE is especially appropriate for learning from large quantities of data. Memory requirement in AnDE, however, increases combinatorially with the number of attributes and the parameter n. In large data learning, number of attributes is often large and we also expect high n to achieve low-bias classification. In order to achieve the lower bias of AnDE with higher n but with less memory requirement, we propose a memory constrained selective AnDE algorithm, in which two passes of learning through training examples are involved. The first pass performs attribute selection on super parents according to available memory, whereas the second one learns an AnDE model with parents only on the selected attributes. Extensive experiments show that the new selective AnDE has considerably lower bias and prediction error relative to An′DE, where n′= n- 1 , while maintaining the same space complexity and similar time complexity. The proposed algorithm works well on categorical data. Numerical data sets need to be discretized first.

Learning algorithms that learn linear models often have high representation bias on real-world problems. In this paper, we show that this representation bias can be greatly reduced by discretization. Discretization is a common procedure in machine learning that is used to convert a quantitative attribute into a qualitative one. It is often motivated by the limitation of some learners to qualitative data. Discretization loses information, as fewer distinctions between instances are possible using discretized data relative to undiscretized data. In consequence, where discretization is not essential, it might appear desirable to avoid it. However, it has been shown that discretization often substantially reduces the error of the linear generative Bayesian classifier naive Bayes. This motivates a systematic study of the effectiveness of discretizing quantitative attributes for other linear classifiers. In this work, we study the effect of discretization on the performance of linear classifiers optimizing three distinct discriminative objective functions --- logistic regression (optimizing negative log-likelihood), support vector classifiers (optimizing hinge loss) and a zero-hidden layer artificial neural network (optimizing mean-square-error). We show that discretization can greatly increase the accuracy of these linear discriminative learners by reducing their representation bias, especially on big datasets. We substantiate our claims with an empirical study on $42$ benchmark datasets.

From understanding the structure of data, to classification and topic modeling, graphical models are core tools in machine learning and data mining. They combine probability and graph theories to form a compact representation of probability distributions. In the last decade, as data stores became larger and higher-dimensional, traditional algorithms for learning graphical models from data, with their lack of scalability, became less and less usable, thus directly decreasing the potential benefits of this core technology. To scale graphical modeling techniques to the size and dimensionality of most modern data stores, data science researchers and practitioners now have to meld the most recent advances in numerous specialized fields including graph theory, statistics, pattern mining and graphical modeling. This tutorial covers the core building blocks that are necessary to build and use scalable graphical modeling technologies on large and high-dimensional data.

Statistical hypothesis testing is a popular and powerful tool for inferring knowledge from data. For every such test performed, there is always a non-zero probability of making a false discovery, i.e.~rejecting a null hypothesis in error. Familywise error rate (FWER) is the probability of making at least one false discovery during an inference process. The expected FWER grows exponentially with the number of hypothesis tests that are performed, almost guaranteeing that an error will be committed if the number of tests is big enough and the risk is not managed; a problem known as the multiple testing problem. State-of-the-art methods for controlling FWER in multiple comparison settings require that the set of hypotheses be predetermined. This greatly hinders statistical testing for many modern applications of statistical inference, such as model selection, because neither the set of hypotheses that will be tested, nor even the number of hypotheses, can be known in advance. This paper introduces Subfamilywise Multiple Testing, a multiple-testing correction that can be used in applications for which there are repeated pools of null hypotheses from each of which a single null hypothesis is to be rejected and neither the specific hypotheses nor their number are known until the final rejection decision is completed. To demonstrate the importance and relevance of this work to current machine learning problems, we further refine the theory to the problem of model selection and show how to use Subfamilywise Multiple Testing for learning graphical models. We assess its ability to discover graphical models on more than 7,000 datasets, studying the ability of Subfamilywise Multiple Testing to outperform the state of the art on data with varying size and dimensionality, as well as with varying density and power of the present correlations. Subfamilywise Multiple Testing provides a significant improvement in statistical efficiency, often requiring only half as much data to discover the same model, while strictly controlling FWER.

Periplasmic expression of soluble proteins in Escherichia coli not only offers a much-simplified downstream purification process, but also enhances the probability of obtaining correctly folded and biologically active proteins. Different combinations of signal peptides and target proteins lead to different soluble protein expression levels, ranging from negligible to several grams per litre. Accurate algorithms for rational selection of promising candidates can serve as a powerful tool to complement with current trial-and-error approaches. Accordingly, proteomics studies can be conducted with greater efficiency and cost-effectiveness. Here, we developed a predictor with a two-stage architecture, to predict the real-valued expression level of target protein in the periplasm. The output of the first-stage support vector machine (SVM) classifier determines which second-stage support vector regression (SVR) classifier to be used. When tested on an independent test dataset, the predictor achieved an overall prediction accuracy of 78% and a Pearson’s correlation coefficient (PCC) of 0.77. We further illustrate the relative importance of various features with respect to different models. The results indicate that the occurrence of dipeptide glutamine and aspartic acid is the most important feature for the classification model. Finally, we provide access to the implemented predictor through the Periscope webserver, freely accessible at http://lightning.med.monash.edu/periscope/.

The failure of multi-step experimental procedures to yield diffraction-quality crystals is a major bottleneck in protein structure determination. Accordingly, several bioinformatics methods have been successfully developed and employed to select crystallizable proteins. Unfortunately, the majority of existing in silico methods only allow the prediction of crystallization propensity, seldom enabling computational design of protein mutants that can be targeted for enhancing protein crystallizability. Here, we present Crysalis, an integrated crystallization analysis tool that builds on support-vector regression (SVR) models to facilitate computational protein crystallization prediction, analysis, and design. More specifically, the functionality of this new tool includes: (1) rapid selection of target crystallizable proteins at the proteome level, (2) identification of site non-optimality for protein crystallization and systematic analysis of all potential single-point mutations that might enhance protein crystallization propensity, and (3) annotation of target protein based on predicted structural properties. We applied the design mode of Crysalis to identify site non-optimality for protein crystallization on a proteome-scale, focusing on proteins currently classified as non-crystallizable. Our results revealed that site non-optimality is based on biases related to residues, predicted structures, physicochemical properties, and sequence loci, which provides in-depth understanding of the features influencing protein crystallization. Crysalis is freely available at http://nmrcen.xmu.edu.cn/crysalis/.

Averaged n-Dependence Estimators (AnDE) is an approach to probabilistic classification learning that learns by extrapolation from marginal to full-multivariate probability distributions. It utilizes a single parameter that transforms the approach between a low-variance high-bias learner (Naive Bayes) and a high-variance low-bias learner with Bayes optimal asymptotic error. It extends the underlying strategy of Averaged One-Dependence Estimators (AODE), which relaxes the Naive Bayes independence assumption while retaining many of Naive Bayes' desirable computational and theoretical properties. AnDE further relaxes the independence assumption by generalizing AODE to higher-levels of dependence. Extensive experimental evaluation shows that the bias-variance trade-off for Averaged 2-Dependence Estimators results in strong predictive accuracy over a wide range of data sets. It has training time linear with respect to the number of examples, learns in a single pass through the training data, supports incremental learning, handles directly missing values, and is robust in the face of noise. Beyond the practical utility of its lower-dimensional variants, AnDE is of interest in that it demonstrates that it is possible to create low-bias high-variance generative learners and suggests strategies for developing even more powerful classifiers.

This paper introduces a new ensemble approach, Feature-Subspace Aggregating (Feating), which builds local models instead of global models. Feating is a generic ensemble approach that can enhance the predictive performance of both stable and unstable learners. In contrast, most existing ensemble approaches can improve the predictive performance of unstable learners only. Our analysis shows that the new approach reduces the execution time to generate a model in an ensemble through an increased level of localisation in Feating. Our empirical evaluation shows that Feating performs significantly better than Boosting, Random Subspace and Bagging in terms of predictive accuracy, when a stable learner SVM is used as the base learner. The speed up achieved by Feating makes feasible SVM ensembles that would otherwise be infeasible for large data sets. When SVM is the preferred base learner, we show that Feating SVM performs better than Boosting decision trees and Random Forests. We further demonstrate that Feating also substantially reduces the error of another stable learner, k-nearest neighbour, and an unstable learner, decision tree.

Standard pattern discovery techniques, such as association rules, suffer an extreme risk of finding very large numbers of spurious patterns for many knowledge discovery tasks. The direct-adjustment approach to controlling this risk applies a statistical test during the discovery process, using a critical value adjusted to take account of the size of the search space. However, a problem with the direct-adjustment strategy is that it may discard numerous true patterns. This paper investigates the assignment of different critical values to different areas of the search space as an approach to alleviating this problem, using a variant of a technique originally developed for other purposes. This approach is shown to be effective at increasing the number of discoveries while still maintaining strict control over the risk of false discoveries.

This project seeked to develop new learning algorithms specifically tailored to be efficient and effective in learning from big data. It exploited the capacity of generative learning to efficiently extract useful summary statistics and used discriminative learning to meld them into a highly accurate classifier. Two classes of learning algorithm were developed. The first uses discriminative learning to select a generative model (selective ANDE and selective KDB). Very effective feature selection was achieved with a single pass through the training data for each attribute that is finally selected. The second combines generatively and discriminatively learned parameters (WANBIA, WANBIA-C,WANJE). It uses discriminative learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very competitive to Logistic Regression but much more efficient in learning the model. WNANJE can model higher-order attribute interdependencies.

Ensemble learning strategies, especially boosting and bagging decision trees, have demonstrated impressive capacities to improve the prediction accuracy of base learning algorithms. Further gains have been demonstrated by strategies that combine simple ensemble formation approaches. We investigate the hypothesis that the improvement in accuracy of multistrategy approaches to ensemble learning is due to an increase in the diversity of ensemble members that are formed. In addition, guided by this hypothesis, we develop three new multistrategy ensemble learning techniques. Experimental results in a wide variety of natural domains suggest that these multistrategy ensemble learning techniques are, on average, more accurate than their component ensemble learning techniques.

We propose an alternative parameterization of Logistic Regression (LR) for the categorical data, multi-class setting. LR optimizes the conditional log-likelihood over the training data and is based on an iterative optimization procedure to tune this objective function. The optimization procedure employed may be sensitive to scale and hence an effective pre-conditioning method is recommended. Many problems in machine learning involve arbitrary scales or categorical data (where simple standardization of features is not applicable). The problem can be alleviated by using optimization routines that are invariant to scale such as (second-order) Newton methods. However, computing and inverting the Hessian is a costly procedure and not feasible for big data. Thus one must often rely on first-order methods such as gradient descent (GD), stochastic gradient descent (SGD) or approximate second-order such as quasi-Newton (QN) routines, which are not invariant to scale. This paper proposes a simple yet effective pre-conditioner for speeding-up LR based on naive Bayes conditional probability estimates. The idea is to scale each attribute by the log of the conditional probability of that attribute given the class. This formulation substantially speeds-up LR's convergence. It also provides a weighted naive Bayes formulation which yields an effective framework for hybrid generative-discriminative classification. © 2014 IEEE., This research has been supported by the Australian Research Council (ARC) under grant DP140100087 and Asian Office of Aerospace Research and Development, Air Force Office of Scientific Research under contract FA23861214030.

Log-linear analysis is the primary statistical approach to discovering conditional dependencies between the variables of a dataset. A good log-linear analysis method requires both high precision and statistical efficiency. High precision means that the risk of false discoveries should be kept very low. Statistical efficiency means that the method should discover actual associations with as few samples as possible. Classical approaches to log-linear analysis make use of a#x03C7;2 tests to control this balance between quality and complexity. We present an information-theoretic approach to log-linear analysis. We show that our approach 1) requires significantly fewer samples to discover the true associations than statistical approaches -- statistical efficiency -- 2) controls for the risk of false discoveries as well as statistical approaches -- high precision - and 3) can perform the discovery on datasets with hundreds of variables on a standard desktop computer -- computational efficiency.

At first blush, user modeling appears to be a prime candidate for straightforward application of standard machine learning techniques. Observations of the user's behavior can provide training examples that a machine learning system can use to form a model designed to predict future actions. However, user modeling poses a number of challenges for machine learning that have hindered its application in user modeling, including: the need for large data sets; the need for labeled data; concept drift; and computational complexity. This paper examines each of these issues and reviews approaches to resolving them.