Search

Motivation Multiplexed protein imaging methods use a chosen set of markers and provide valuable information about complex tissue structure and cellular heterogeneity. However, the number of markers that can be measured in the same tissue sample is inherently limited. Results In this paper, we present an efficient method to choose a minimal predictive subset of markers that for the first time allows the prediction of full images for a much larger set of markers. We demonstrate that our approach also outperforms previous methods for predicting cell-level protein composition. Most importantly, we demonstrate that our approach can be used to select a marker set that enables prediction of a much larger set than could be measured concurrently. Availability and implementation All code and intermediate results are available in a Reproducible Research Archive at https://github.com/murphygroup/CODEXPanelOptimization. [ABSTRACT FROM AUTHOR]

Motivation Cancer heterogeneity drastically affects cancer therapeutic outcomes. Predicting drug response in vitro is expected to help formulate personalized therapy regimens. In recent years, several computational models based on machine learning and deep learning have been proposed to predict drug response in vitro. However, most of these methods capture drug features based on a single drug description (e.g. drug structure), without considering the relationships between drugs and biological entities (e.g. target, diseases, and side effects). Moreover, most of these methods collect features separately for drugs and cell lines but fail to consider the pairwise interactions between drugs and cell lines. Results In this paper, we propose a deep learning framework, named MSDRP for drug response prediction. MSDRP uses an interaction module to capture interactions between drugs and cell lines, and integrates multiple associations/interactions between drugs and biological entities through similarity network fusion algorithms, outperforming some state-of-the-art models in all performance measures for all experiments. The experimental results of de novo test and independent test demonstrate the excellent performance of our model for new drugs. Furthermore, several case studies illustrate the rationality for using feature vectors derived from drug similarity matrices from multisource data to represent drugs and the interpretability of our model. Availability and implementation The codes of MSDRP are available at https://github.com/xyzhang-10/MSDRP. [ABSTRACT FROM AUTHOR]

Motivation The secondary structure of RNA is of importance to its function. Over the last few years, several papers attempted to use machine learning to improve de novo RNA secondary structure prediction. Many of these papers report impressive results for intra-family predictions but seldom address the much more difficult (and practical) inter-family problem. Results We demonstrate that it is nearly trivial with convolutional neural networks to generate pseudo-free energy changes, modelled after structure mapping data that improve the accuracy of structure prediction for intra-family cases. We propose a more rigorous method for inter-family cross-validation that can be used to assess the performance of learning-based models. Using this method, we further demonstrate that intra-family performance is insufficient proof of generalization despite the widespread assumption in the literature and provide strong evidence that many existing learning-based models have not generalized inter-family. Availability and implementation Source code and data are available at https://github.com/marcellszi/dl-rna. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation A gradient boosting decision tree (GBDT) is a powerful ensemble machine-learning method that has the potential to accelerate biomarker discovery from high-dimensional molecular data. Recent algorithmic advances, such as extreme gradient boosting (XGB) and light gradient boosting (LGB), have rendered the GBDT training more efficient, scalable and accurate. However, these modern techniques have not yet been widely adopted in discovering biomarkers for censored survival outcomes, which are key clinical outcomes or endpoints in cancer studies. Results In this paper, we present a new R package 'Xsurv' as an integrated solution that applies two modern GBDT training frameworks namely, XGB and LGB, for the modeling of right-censored survival outcomes. Based on our simulations, we benchmark the new approaches against traditional methods including the stepwise Cox regression model and the original gradient boosting function implemented in the package 'gbm'. We also demonstrate the application of Xsurv in analyzing a melanoma methylation dataset. Together, these results suggest that Xsurv is a useful and computationally viable tool for screening a large number of prognostic candidate biomarkers, which may facilitate future translational and clinical research. Availability and implementation 'Xsurv' is freely available as an R package at: https://github.com/topycyao/Xsurv. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation Applications in synthetic and systems biology can benefit from measuring whole-cell response to biochemical perturbations. Execution of experiments to cover all possible combinations of perturbations is infeasible. In this paper, we present the host response model (HRM), a machine learning approach that maps response of single perturbations to transcriptional response of the combination of perturbations. Results The HRM combines high-throughput sequencing with machine learning to infer links between experimental context, prior knowledge of cell regulatory networks, and RNASeq data to predict a gene's dysregulation. We find that the HRM can predict the directionality of dysregulation to a combination of inducers with an accuracy of >90% using data from single inducers. We further find that the use of prior, known cell regulatory networks doubles the predictive performance of the HRM (an R 2 from 0.3 to 0.65). The model was validated in two organisms, Escherichia coli and Bacillus subtilis , using new experiments conducted after training. Finally, while the HRM is trained with gene expression data, the direct prediction of differential expression makes it possible to also conduct enrichment analyses using its predictions. We show that the HRM can accurately classify >95% of the pathway regulations. The HRM reduces the number of RNASeq experiments needed as responses can be tested in silico prior to the experiment. Availability and implementation The HRM software and tutorial are available at https://github.com/sd2e/CDM and the configurable differential expression analysis tools and tutorials are available at https://github.com/SD2E/omics%5ftools. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation: Applied research in machine learning progresses faster when a clean dataset is available and ready to use. Several datasets have been proposed and released over the years for specific tasks such as image classification, speech-recognition and more recently for protein structure prediction. However, for the fundamental problem of RNA structure prediction, information is spread between several databases depending on the level we are interested in: sequence, secondary structure, 3D structure or interactions with other macromolecules. In order to speed-up advances in machine-learning based approaches for RNA secondary and/or 3D structure prediction, a dataset integrating all this information is required, to avoid spending time on data gathering and cleaning. Results: Here, we propose the first attempt of a standardized and automatically generated dataset dedicated to RNA combining together: RNA sequences, homology information (under the form of position-specific scoring matrices) and information derived by annotation of available 3D structures (including secondary structure, canonical and non-canonical interactions and backbone torsion angles). The data are retrieved from public databases PDB, Rfam and SILVA. The paper describes the procedure to build such dataset and the RNA structure descriptors we provide. Some statistical descriptions of the resulting dataset are also provided. Availability and implementation: The dataset is updated every month and available online (in flat-text file format) on the EvryRNA software platform (https://evryrna.ibisc.univ-evry.fr/evryrna/rnanet). An efficient parallel pipeline to build the dataset is also provided for easy reproduction or modification. Supplementary information: Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation Procedures for structural modeling of protein–protein complexes (protein docking) produce a number of models which need to be further analyzed and scored. Scoring can be based on independently determined constraints on the structure of the complex, such as knowledge of amino acids essential for the protein interaction. Previously, we showed that text mining of residues in freely available PubMed abstracts of papers on studies of protein–protein interactions may generate such constraints. However, absence of post-processing of the spotted residues reduced usability of the constraints, as a significant number of the residues were not relevant for the binding of the specific proteins. Results We explored filtering of the irrelevant residues by two machine learning approaches, Deep Recursive Neural Network (DRNN) and Support Vector Machine (SVM) models with different training/testing schemes. The results showed that the DRNN model is superior to the SVM model when training is performed on the PMC-OA full-text articles and applied to classification (interface or non-interface) of the residues spotted in the PubMed abstracts. When both training and testing is performed on full-text articles or on abstracts, the performance of these models is similar. Thus, in such cases, there is no need to utilize computationally demanding DRNN approach, which is computationally expensive especially at the training stage. The reason is that SVM success is often determined by the similarity in data/text patterns in the training and the testing sets, whereas the sentence structures in the abstracts are, in general, different from those in the full text articles. Availabilityand implementation The code and the datasets generated in this study are available at https://gitlab.ku.edu/vakser-lab-public/text-mining/-/tree/2020-09-04. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation Partial atomic charges are usually used to calculate the electrostatic component of energy in many molecular modeling applications, such as molecular docking, molecular dynamics simulations, free energy calculations and so forth. High-level quantum mechanics calculations may provide the most accurate way to estimate the partial charges for small molecules, but they are too time-consuming to be used to process a large number of molecules for high throughput virtual screening. Results We proposed a new molecule descriptor named Atom-Path-Descriptor (APD) and developed a set of APD-based machine learning (ML) models to predict the partial charges for small molecules with high accuracy. In the APD algorithm, the 3D structures of molecules were assigned with atom centers and atom-pair path-based atom layers to characterize the local chemical environments of atoms. Then, based on the APDs, two representative ensemble ML algorithms, i.e. random forest (RF) and extreme gradient boosting (XGBoost), were employed to develop the regression models for partial charge assignment. The results illustrate that the RF models based on APDs give better predictions for all the atom types than those based on traditional molecular fingerprints reported in the previous study. More encouragingly, the models trained by XGBoost can improve the predictions of partial charges further, and they can achieve the average root-mean-square error 0.0116 e on the external test set, which is much lower than that (0.0195 e) reported in the previous study, suggesting that the proposed algorithm is quite promising to be used in partial charge assignment with high accuracy. Availability and implementation The software framework described in this paper is freely available at https://github.com/jkwang93/Atom-Path-Descriptor-based-machine-learning Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation The reconstruction of gene regulatory networks (GRNs) from gene expression data has received increasing attention in recent years, due to its usefulness in the understanding of regulatory mechanisms involved in human diseases. Most of the existing methods reconstruct the network through machine learning approaches, by analyzing known examples of interactions. However, (i) they often produce poor results when the amount of labeled examples is limited, or when no negative example is available and (ii) they are not able to exploit information extracted from GRNs of other (better studied) related organisms, when this information is available. Results In this paper, we propose a novel machine learning method that overcomes these limitations, by exploiting the knowledge about the GRN of a source organism for the reconstruction of the GRN of the target organism, by means of a novel transfer learning technique. Moreover, the proposed method is natively able to work in the positive-unlabeled setting, where no negative example is available, by fruitfully exploiting a (possibly large) set of unlabeled examples. In our experiments, we reconstructed the human GRN, by exploiting the knowledge of the GRN of Mus musculus. Results showed that the proposed method outperforms state-of-the-art approaches and identifies previously unknown functional relationships among the analyzed genes. Availability and implementation http://www.di.uniba.it/∼mignone/systems/biosfer/index.html. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation In high dimensional genetic data analysis, the objective is to select important biomarkers which are involved in some biological processes, such as disease progression, immune response, etc. The experimental data are often collected from different platforms including microarray experiments and proteomic experiments. The conventional single-platform approach lacks the capability to learn from multiple platforms, and the resulted lists of biomarkers vary across different platforms. There is a great need to develop an algorithm which can aggregate information across platforms and provide a consolidated list of biomarkers across different platforms. Results In this paper, we introduce an R package FusionLearn , which implements a fusion learning algorithm to analyze cross-platform data. The consolidated list of biomarkers is selected by the technique of group penalization. We first apply the algorithm on a collection of breast cancer microarray experiments from the NCBI (National Centre for Biotechnology Information) microarray database and the resulted list of selected genes have higher classification accuracy rate across different datasets than the lists generated from each single dataset. Secondly, we use the software to analyze a combined microarray and proteomic dataset for the study of the growth phase versus the stationary phase in Streptomyces coelicolor. The selected biomarkers demonstrate consistent differential behavior across different platforms. Availability and implementation R package: https://cran.r-project.org/package=FusionLearn. [ABSTRACT FROM AUTHOR]

Motivation Learning associations of traits with the microbial composition of a set of samples is a fundamental goal in microbiome studies. Recently, machine learning methods have been explored for this goal, with some promise. However, in comparison to other fields, microbiome data are high-dimensional and not abundant; leading to a high-dimensional low-sample-size under-determined system. Moreover, microbiome data are often unbalanced and biased. Given such training data, machine learning methods often fail to perform a classification task with sufficient accuracy. Lack of signal is especially problematic when classes are represented in an unbalanced way in the training data; with some classes under-represented. The presence of inter-correlations among subsets of observations further compounds these issues. As a result, machine learning methods have had only limited success in predicting many traits from microbiome. Data augmentation consists of building synthetic samples and adding them to the training data and is a technique that has proved helpful for many machine learning tasks. Results In this paper, we propose a new data augmentation technique for classifying phenotypes based on the microbiome. Our algorithm, called TADA, uses available data and a statistical generative model to create new samples augmenting existing ones, addressing issues of low-sample-size. In generating new samples, TADA takes into account phylogenetic relationships between microbial species. On two real datasets, we show that adding these synthetic samples to the training set improves the accuracy of downstream classification, especially when the training data have an unbalanced representation of classes. Availability and implementation TADA is available at https://github.com/tada-alg/TADA. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation Computational prediction of the effect of mutations on protein stability is used by researchers in many fields. The utility of the prediction methods is affected by their accuracy and bias. Bias, a systematic shift of the predicted change of stability, has been noted as an issue for several methods, but has not been investigated systematically. Presence of the bias may lead to misleading results especially when exploring the effects of combination of different mutations. Results Here we use a protocol to measure the bias as a function of the number of introduced mutations. It is based on a self-consistency test of the reciprocity the effect of a mutation. An advantage of the used approach is that it relies solely on crystal structures without experimentally measured stability values. We applied the protocol to four popular algorithms predicting change of protein stability upon mutation, FoldX, Eris, Rosetta and I-Mutant, and found an inherent bias. For one program, FoldX, we manage to substantially reduce the bias using additional relaxation by Modeller. Authors using algorithms for predicting effects of mutations should be aware of the bias described here. Availability and implementation All calculations were implemented by in-house PERL scripts. Supplementary information Supplementary data are available at Bioinformatics online. Note The article 10.1093/bioinformatics/bty348, published alongside this paper, also addresses the problem of biases in protein stability change predictions. [ABSTRACT FROM AUTHOR]

Motivation Bioinformatics tools that predict protein stability changes upon point mutations have made a lot of progress in the last decades and have become accurate and fast enough to make computational mutagenesis experiments feasible, even on a proteome scale. Despite these achievements, they still suffer from important issues that must be solved to allow further improving their performances and utilizing them to deepen our insights into protein folding and stability mechanisms. One of these problems is their bias toward the learning datasets which, being dominated by destabilizing mutations, causes predictions to be better for destabilizing than for stabilizing mutations. Results We thoroughly analyzed the biases in the prediction of folding free energy changes upon point mutations (Δ Δ G 0) and proposed some unbiased solutions. We started by constructing a dataset S sym of experimentally measured Δ Δ G 0 s with an equal number of stabilizing and destabilizing mutations, by collecting mutations for which the structure of both the wild-type and mutant protein is available. On this balanced dataset, we assessed the performances of 15 widely used Δ Δ G 0 predictors. After the astonishing observation that almost all these methods are strongly biased toward destabilizing mutations, especially those that use black-box machine learning, we proposed an elegant way to solve the bias issue by imposing physical symmetries under inverse mutations on the model structure, which we implemented in PoPMuSiCsym. This new predictor constitutes an efficient trade-off between accuracy and absence of biases. Some final considerations and suggestions for further improvement of the predictors are discussed. Supplementary information Supplementary data are available at Bioinformatics online. Note The article 10.1093/bioinformatics/bty340/, published alongside this paper, also addresses the problem of biases in protein stability change predictions. [ABSTRACT FROM AUTHOR]

Motivation Machine learning plays a substantial role in bioscience owing to the explosive growth in sequence data and the challenging application of computational methods. Peptide-recognition domains (PRDs) are critical as they promote coupled-binding with short peptide-motifs of functional importance through transient interactions. It is challenging to build a reliable predictor of peptide-binding residue in proteins with diverse types of PRDs from protein sequence alone. On the other hand, it is vital to cope up with the sequencing speed and to broaden the scope of study. Results In this paper, we propose a machine-learning-based tool, named PBRpredict, to predict residues in peptide-binding domains from protein sequence alone. To develop a generic predictor, we train the models on peptide-binding residues of diverse types of domains. As inputs to the models, we use a high-dimensional feature set of chemical, structural and evolutionary information extracted from protein sequence. We carefully investigate six different state-of-the-art classification algorithms for this application. Finally, we use the stacked generalization approach to non-linearly combine a set of complementary base-level learners using a meta-level learner which outperformed the winner-takes-all approach. The proposed predictor is found competitive based on statistical evaluation. Availability and implementation PBRpredict-Suite software: http://cs.uno.edu/~tamjid/Software/PBRpredict/pbrpredict-suite.zip. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Motivation: Significant improvements in the prediction of protein residue--residue contacts are observed in the recent years. These contacts, predicted using a variety of coevolution-based and machine learning methods, are the key contributors to the recent progress in ab initio protein structure prediction, as demonstrated in the recent CASP experiments. Continuing the development of new methods to reliably predict contact maps is essential to further improve ab initio structure prediction. Results: In this paper we discuss DNCON2, an improved protein contact map predictor based on two-level deep convolutional neural networks. It consists of six convolutional neural networks--the first five predict contacts at 6, 7.5, 8, 8.5 and 10 Å distance thresholds, and the last one uses these five predictions as additional features to predict final contact maps. On the free-modeling datasets in CASP10, 11 and 12 experiments, DNCON2 achieves mean precisions of 35, 50 and 53.4%, respectively, higher than 30.6% by MetaPSICOV on CASP10 dataset, 34% by MetaPSICOV on CASP11 dataset and 46.3% by Raptor-X on CASP12 dataset, when top L/5 long-range contacts are evaluated. We attribute the improved performance of DNCON2 to the inclusion of short- and medium-range contacts into training, two-level approach to prediction, use of the state-of-the-art optimization and activation functions, and a novel deep learning architecture that allows each filter in a convolutional layer to access all the input features of a protein of arbitrary length. [ABSTRACT FROM AUTHOR]

Motivation: Genome sequencing is producing an ever-increasing amount of associated protein sequences. Few of these sequences have experimentally validated annotations, however, and computational predictions are becoming increasingly successful in producing such annotations. One key challenge remains the prediction of the amino acids in a given protein sequence that are involved in protein–protein interactions. Such predictions are typically based on machine learning methods that take advantage of the properties and sequence positions of amino acids that are known to be involved in interaction. In this paper, we evaluate the importance of various features using Random Forest (RF), and include as a novel feature backbone flexibility predicted from sequences to further optimise protein interface prediction. Results: We observe that there is no single sequence feature that enables pinpointing interacting sites in our Random Forest models. However, combining different properties does increase the performance of interface prediction. Our homomeric-trained RF interface predictor is able to distinguish interface from non-interface residues with an area under the ROC curve of 0.72 in a homomeric test-set. The heteromeric-trained RF interface predictor performs better than existing predictors on a independent heteromeric test-set. We trained a more general predictor on the combined homomeric and heteromeric dataset, and show that in addition to predicting homomeric interfaces, it is also able to pinpoint interface residues in heterodimers. This suggests that our random forest model and the features included capture common properties of both homodimer and heterodimer interfaces. [ABSTRACT FROM AUTHOR]

Motivation: The incidence of ageing-related diseases has been constantly increasing in the last decades, raising the need for creating effective methods to analyze ageing-related protein data. These methods should have high predictive accuracy and be easily interpretable by ageing experts. To enable this, one needs interpretable classification models (supervised machine learning) and features with rich biological meaning. In this paper we propose two interpretable feature types based on Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways and compare them with traditional feature types in hierarchical classification (a more challenging classification task regarding predictive performance) and binary classification (a classification task producing easier to interpret classification models). As far as we know, this work is the first to: (i) explore the potential of the KEGG pathway data in the hierarchical classification setting, (i) use the graph structure of KEGG pathways to create a feature type that quantifies the influence of a current protein on another specific protein within a KEGG pathway graph and (iii) propose a method for interpreting the classification models induced using KEGG features. Results: We performed tests measuring predictive accuracy considering hierarchical and binary class labels extracted from the Mouse Phenotype Ontology. One of the KEGG feature types leads to the highest predictive accuracy among five individual feature types across three hierarchical classification algorithms. Additionally, the combination of the two KEGG feature types proposed in this work results in one of the best predictive accuracies when using the binary class version of our datasets, at the same time enabling the extraction of knowledge from ageing-related data using quantitative influence information. [ABSTRACT FROM AUTHOR]

Motivation: Predicting the biological functions of proteins is one of the key challenges in the postgenomic era. Computational models have demonstrated the utility of applying machine learning methods to predict protein function. Most prediction methods explicitly require a set of negative examples-proteins that are known not carrying out a particular function. However, Gene Ontology (GO) almost always only provides the knowledge that proteins carry out a particular function, and functional annotations of proteins are incomplete. GO structurally organizes more than tens of thousands GO terms and a protein is annotated with several (or dozens) of these terms. For these reasons, the negative examples of a protein can greatly help distinguishing true positive examples of the protein from such a large candidate GO space. Results: In this paper, we present a novel approach (called NegGOA) to select negative examples. Specifically, NegGOA takes advantage of the ontology structure, available annotations and potentiality of additional annotations of a protein to choose negative examples of the protein. We compare NegGOA with other negative examples selection algorithms and find that NegGOA produces much fewer false negatives than them. We incorporate the selected negative examples into an efficient function prediction model to predict the functions of proteins in Yeast, Human, Mouse and Fly. NegGOA also demonstrates improved accuracy than these comparing algorithms across various evaluation metrics. In addition, NegGOA is less suffered from incomplete annotations of proteins than these comparing methods. [ABSTRACT FROM AUTHOR]

Motivation: Protein model quality assessment (QA) plays a very important role in protein structure prediction. It can be divided into two groups of methods: single model and consensus QA method. The consensus QA methods may fail when there is a large portion of low quality models in the model pool. Results: In this paper, we develop a novel single-model quality assessment method QAcon utilizing structural features, physicochemical properties, and residue contact predictions. We apply residueresidue contact information predicted by two protein contact prediction methods PSICOV and DNcon to generate a new score as feature for quality assessment. This novel feature and other 11 features are used as input to train a two-layer neural network on CASP9 datasets to predict the quality of a single protein model. We blindly benchmarked our method QAcon on CASP11 dataset as the MULTICOM-CLUSTER server. Based on the evaluation, our method is ranked as one of the top single model QA methods. The good performance of the features based on contact prediction illustrates the value of using contact information in protein quality assessment. [ABSTRACT FROM AUTHOR]

Motivation: Many ChIP-Seq experiments are aimed at developing gold standards for determining the locations of various genomic features such as transcription start or transcription factor binding sites on the whole genome. Many such pioneering experiments lack rigorous testing methods and adequate ‘gold standard’ annotations to compare against as they themselves are the most reliable source of empirical data available. To overcome this problem, we propose a self-consistency test whereby a dataset is tested against itself. It relies on a supervised machine learning style protocol for in silico annotation of a genome and accuracy estimation to guarantee, at least, self-consistency.Results: The main results use a novel performance metric (a calibrated precision) in order to assess and compare the robustness of the proposed supervised learning method across different test sets. As a proof of principle, we applied the whole protocol to two recent ChIP-Seq ENCODE datasets of STAT1 and Pol-II binding sites. STAT1 is benchmarked against in silico detection of binding sites using available position weight matrices. Pol-II, the main focus of this paper, is benchmarked against 17 algorithms for the closely related and well-studied problem of in silico transcription start site (TSS) prediction. Our results also demonstrate the feasibility of in silico genome annotation extension with encouraging results from a small portion of annotated genome to the remainder.Availability: Available from http://www.genomics.csse.unimelb.edu.au/gat.Contact: justin.bedo@nicta.com.au; adam.kowalczyk@nicta.com.auSupplementary Information: Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]