Biological Datasets Research Articles

Deep Learning-Based Imbalanced Classification With Fuzzy Support Vector Machine.

Imbalanced classification is widespread in the fields of medical diagnosis, biomedicine, smart city and Internet of Things. The imbalance of data distribution makes traditional classification methods more biased towards majority classes and ignores the importance of minority class. It makes the traditional classification methods ineffective in imbalanced classification. In this paper, a novel imbalance classification method based on deep learning and fuzzy support vector machine is proposed and named as DFSVM. DFSVM first uses a deep neural network to obtain an embedding representation of the data. This deep neural network is trained by using triplet loss to enhance similarities within classes and differences between classes. To alleviate the effects of imbalanced data distribution, oversampling is performed in the embedding space of the data. In this paper, we use an oversampling method based on feature and center distance, which can obtain more diverse new samples and prevent overfitting. To enhance the impact of minority class, we use a fuzzy support vector machine (FSVM) based on cost-sensitive learning as the final classifier. FSVM assigns a higher misclassification cost to minority class samples to improve the classification quality. Experiments were performed on multiple biological datasets and real-world datasets. The experimental results show that DFSVM has achieved promising classification performance.

Searching and Analyzing Patent-relevant COVID-19 Information

The COVID-19 pandemic has prompted several institutions to offer free, dedicated websites and tools to foster research and access to urgently needed innovative solutions by facilitating the search and analysis of information within the large amount of scientific and patent literature which was published since January 2020. This situation is clearly exceptional and challenging for patent information users searching for relevant disclosures at a given date in a reliable manner. This article provides an overview of search criteria and strategies, main databases and websites, number of publications, biological sequence information and experimental data sets covering COVID-19 findings within scientific and patent literature have been disclosed between January and August 2020. The analysis of non-patent literature has been focused on the identification, date assignment, disambiguation, and access to experimental data. The analysis of patent literature has been focused on the trends found within the earliest filed and published patent documents in representative jurisdictions worldwide. Some practical advice and strategies for technical, medical, or patentability assessment of COVID-19-related innovations across different information formats and resources are proposed.

Bringing bioinformatics to schools with the 4273pi project

Over the last few decades, the nature of life sciences research has changed enormously, generating a need for a workforce with a variety of computational skills such as those required to store, manage, and analyse the large biological datasets produced by next-generation sequencing. Those with such expertise are increasingly in demand for employment in both research and industry. Despite this, bioinformatics education has failed to keep pace with advances in research. At secondary school level, computing is often taught in isolation from other sciences, and its importance in biological research is not fully realised, leaving pupils unprepared for the computational component of Higher Education and, subsequently, research in the life sciences. The 4273pi Bioinformatics at School project (https://4273pi.org) aims to address this issue by designing and delivering curriculum-linked, hands-on bioinformatics workshops for secondary school biology pupils, with an emphasis on equitable access. So far, we have reached over 180 schools across Scotland through visits or teacher events, and our open education resources are used internationally. Here, we describe our project, our aims and motivations, and the practical lessons we have learned from implementing a successful bioinformatics education project over the last 5 years.

Robust multi-class feature selection via l2,0-norm regularization minimization

Feature selection is an important data preprocessing in data mining and machine learning, that can reduce the number of features without deteriorating model’s performance. Recently, sparse regression has received considerable attention in feature selection task due to its good performance. However, because the l2,0-norm regularization term is non-convex, this problem is hard to solve, and most of the existing methods relaxed it by l2,1-norm. Unlike the existing methods, this paper proposes a novel method to solve the l2,0-norm regularized least squares problem directly based on iterative hard thresholding, which can produce exact row-sparsity solution for weights matrix, and features can be selected more precisely. Furthermore, two homotopy strategies are derived to reduce the computational time of the optimization method, which are more practical for real-world applications. The proposed method is verified on eight biological datasets, experimental results show that our method can achieve higher classification accuracy with fewer number of selected features than the approximate convex counterparts and other state-of-the-art feature selection methods.

Feature selection for kernel methods in systems biology.

The substantial development of high-throughput biotechnologies has rendered large-scale multi-omics datasets increasingly available. New challenges have emerged to process and integrate this large volume of information, often obtained from widely heterogeneous sources. Kernel methods have proven successful to handle the analysis of different types of datasets obtained on the same individuals. However, they usually suffer from a lack of interpretability since the original description of the individuals is lost due to the kernel embedding. We propose novel feature selection methods that are adapted to the kernel framework and go beyond the well-established work in supervised learning by addressing the more difficult tasks of unsupervised learning and kernel output learning. The method is expressed under the form of a non-convex optimization problem with a ℓ1 penalty, which is solved with a proximal gradient descent approach. It is tested on several systems biology datasets and shows good performances in selecting relevant and less redundant features compared to existing alternatives. It also proved relevant for identifying important governmental measures best explaining the time series of Covid-19 reproducing number evolution during the first months of 2020. The proposed feature selection method is embedded in the R package mixKernel version 0.8, published on CRAN. Installation instructions are available at http://mixkernel.clementine.wf/.

BaredSC: Bayesian approach to retrieve expression distribution of single-cell data

BackgroundThe number of studies using single-cell RNA sequencing (scRNA-seq) is constantly growing. This powerful technique provides a sampling of the whole transcriptome of a cell. However, sparsity of the data can be a major hurdle when studying the distribution of the expression of a specific gene or the correlation between the expressions of two genes.ResultsWe show that the main technical noise associated with these scRNA-seq experiments is due to the sampling, i.e., Poisson noise. We present a new tool named baredSC, for Bayesian Approach to Retrieve Expression Distribution of Single-Cell data, which infers the intrinsic expression distribution in scRNA-seq data using a Gaussian mixture model. baredSC can be used to obtain the distribution in one dimension for individual genes and in two dimensions for pairs of genes, in particular to estimate the correlation in the two genes’ expressions. We apply baredSC to simulated scRNA-seq data and show that the algorithm is able to uncover the expression distribution used to simulate the data, even in multi-modal cases with very sparse data. We also apply baredSC to two real biological data sets. First, we use it to measure the anti-correlation between Hoxd13 and Hoxa11, two genes with known genetic interaction in embryonic limb. Then, we study the expression of Pitx1 in embryonic hindlimb, for which a trimodal distribution has been identified through flow cytometry. While other methods to analyze scRNA-seq are too sensitive to sampling noise, baredSC reveals this trimodal distribution.ConclusionbaredSC is a powerful tool which aims at retrieving the expression distribution of few genes of interest from scRNA-seq data.

Zero-preserving imputation of single-cell RNA-seq data

A key challenge in analyzing single cell RNA-sequencing data is the large number of false zeros, where genes actually expressed in a given cell are incorrectly measured as unexpressed. We present a method based on low-rank matrix approximation which imputes these values while preserving biologically non-expressed genes (true biological zeros) at zero expression levels. We provide theoretical justification for this denoising approach and demonstrate its advantages relative to other methods on simulated and biological datasets.

NetNMSP: Nonoverlapping maximal sequential pattern mining.

Nonoverlapping sequential pattern mining, as a kind of repetitive sequential pattern mining with gap constraints, can find more valuable patterns. Traditional algorithms focused on finding all frequent patterns and found lots of redundant short patterns. However, it not only reduces the mining efficiency, but also increases the difficulty in obtaining the demand information. To reduce the frequent patterns and retain its expression ability, this paper focuses on the Nonoverlapping Maximal Sequential Pattern (NMSP) mining which refers to finding frequent patterns whose super-patterns are infrequent. In this paper, we propose an effective mining algorithm, Nettree for NMSP mining (NetNMSP), which has three key steps: calculating the support, generating the candidate patterns, and determining NMSPs. To efficiently calculate the support, NetNMSP employs the backtracking strategy to obtain a nonoverlapping occurrence from the leftmost leaf to its root with the leftmost parent node method in a Nettree. To reduce the candidate patterns, NetNMSP generates candidate patterns by the pattern join strategy. Furthermore, to determine NMSPs, NetNMSP adopts the screening method. Experiments on biological sequence datasets verify that not only does NetNMSP outperform the state-of-the-arts algorithms, but also NMSP mining has better compression performance than closed pattern mining. On sales datasets, we validate that our algorithm guarantees the best scalability on large scale datasets. Moreover, we mine NMSPs and frequent patterns in SARS-CoV-1, SARS-CoV-2 and MERS-CoV. The results show that the three viruses are similar in the short patterns but different in the long patterns. More importantly, NMSP mining is easier to find the differences between the virus sequences.

Attention-based Long Short Term Memory Model for DNA Damage Prediction in Mammalian Cells

The understanding of DNA damage intensity – concentration-level is critical for biological and biomedical research, such as cellular homeostasis, tumor suppression, immunity, and gametogenesis. Therefore, recognizing and quantifying DNA damage intensity levels is a substantial issue, which requires further robust and effective approaches. DNA damage has several intensity levels. These levels of DNA damage in malignant cells and in other unhealthy cells are significant in the assessment of lesion stages located in normal cells. There is a need to get more insight from the available biological data to predict, explore and classify DNA damage intensity levels. Herein, the development process relied on the available biological dataset related to DNA damage signaling pathways, which plays a crucial role in DNA damage in the mammalian cell system. The biological dataset that was used in the proposed model consists of 15000 records intensity – concentration-level for a set of five proteins which regulate DNA damage. This research paper proposes an innovative deep learning model, which consists of an attention-based long short term-memory (AT-LSTM) model for DNA damage multi class predictions. The proposed model splits the prediction procedure into dual stages. For the first stage, we adopt the related feature sequences which are inserted as input to the LSTM neural network. In the next stage, the attention feature is applied efficiently to adopt the related feature sequences which are inserted as input to the softmax layer for prediction in the following frame. Our developed framework not only solves the long-term dependence problem of prediction effectively, but also enhances the interpretability of the prediction methods that was established on the neural network. We conducted a novel proposed model on big and complex biological datasets to perform prediction and multi classification tasks. Indeed, the (AT-LSTM) model has the ability to predict and classify the DNA damage in several classes: No-Damage, Low-damage, Medium-damage, High-damage, and Excess-damage. The experimental results show that our framework for DNA damage intensity level can be considered as state of the art for the biological DNA damage prediction domain.

MMMF: Multimodal Multitask Matrix Factorization for Classification and Feature Selection

Integration of multiple biological datasets is crucial to understand comprehensive biological mechanisms with the aid of a rapid development of biomedical technology. However, the predictive modeling for such an integrated dataset faces two major challenges, namely, heterogeneity and imbalance in the acquired data. Thus, in this study, we present a method for the integration of multiple biological datasets called multimodal multitask matrix factorization (MMMF) to address these issues. The MMMF uses matrix factorization (MF) to integrate data from multiple heterogeneous biological datasets, and oversampling is applied to resolve the imbalanced data during the training step. Moreover, gradient surgery is used for multitask (MF and classification) learning to increase the quantity of classification information by projecting the gradients of the MF that conflict with the classification gradient onto the normal plane of a classification gradient. We demonstrate that MMMF outperforms other state-of-the-art biomedical classification models in binary and multi-class classification problems using five biological datasets. We also show that MMMF can be used as a feature selection approach for finding biomarkers that help in classification. The source code of the MMMF is available at https://github.com/DMCB-GIST/MMMF.

A New Flexible Logarithmic‐X Family of Distributions with Applications to Biological Systems

Probability distributions play an essential role in modeling and predicting biomedical datasets. To have the best description and accurate prediction of the biomedical datasets, numerous probability distributions have been introduced and implemented. We investigate a novel family of lifetime probability distributions to represent biological datasets in this paper. The proposed family is called a new flexible logarithmic‐X (NFLog‐X) family. The suggested NFLog‐X family is obtained by applying the T‐X method together with the exponential model having the PDF m(t) = e−t. Based on the NFLog‐X approach, a three parameters probability distribution, namely, a new flexible logarithmic‐Weibull (NFLog‐Wei) distribution is introduced. The method of maximum likelihood estimation is adopted for estimating the parameters of the NFLog‐X family. In the end, we examine three different biological datasets in order to give a thorough numerical research that illustrates the NFLog‐Wei distribution. Comparisons are made between the analytical goodness‐of‐fit metrics of the suggested distribution. We made comparison with the (i) alpha power transformed Weibull, (ii) exponentiated Weibull, (iii) Weibull, (iv) flexible reduced logarithmic‐Weibull, and (v) Marshall–Olkin Weibull distributions. After performing the analyses, we observe that the proposed method outclassed other competitive distributions.

Interpreting Neural Networks for Biological Sequences by Learning Stochastic Masks.

Sequence-based neural networks can learn to make accurate predictions from large biological datasets, but model interpretation remains challenging. Many existing feature attribution methods are optimized for continuous rather than discrete input patterns and assess individual feature importance in isolation, making them ill-suited for interpreting non-linear interactions in molecular sequences. Building on work in computer vision and natural language processing, we developed an approach based on deep learning - Scrambler networks - wherein the most salient sequence positions are identified with learned input masks. Scramblers learn to predict Position-Specific Scoring Matrices (PSSMs) where unimportant nucleotides or residues are scrambled by raising their entropy. We apply Scramblers to interpret the effects of genetic variants, uncover non-linear interactions between cis-regulatory elements, explain binding specificity for protein-protein interactions, and identify structural determinants of de novo designed proteins. We show that Scramblers enable efficient attribution across large datasets and result in high-quality explanations, often outperforming state-of-the-art methods.

Modeling and Simulation of Cell Signaling Networks for Subsequent Analytics Processes Using Big Data and Machine Learning.

This work explores how much the traditional approach to modeling and simulation of biological systems, specifically cell signaling networks, can be increased and improved by integrating big data, data mining, and machine learning techniques. Specifically, we first model, simulate, validate, and calibrate the behavior of the PI3K/AKT/mTOR cancer-related signaling pathway. Subsequently, once the behavior of the simulated signaling network matches the expected behavior, the capacity of the computational simulation is increased to grow data (data farming). First, we use big data techniques to extract, collect, filter, and store large volumes of data describing all the interactions among the simulated cell signaling system components over time. Afterward, we apply data mining and machine learning techniques—specifically, exploratory data analysis, feature selection techniques, and supervised neural network models—to the resulting biological dataset to obtain new inferences and knowledge about this biological system. The results showed how the traditional approach to the simulation of biological systems could be enhanced and improved by incorporating big data, data mining, and machine learning techniques, which significantly contributed to increasing the predictive power of the simulation.

The Reasonable Effectiveness of Randomness in Scalable and Integrative Gene Regulatory Network Inference and Beyond

Gene regulation is orchestrated by a vast number of molecules, including transcription factors and co-factors, chromatin regulators, as well as epigenetic mechanisms, and it has been shown that transcriptional misregulation, e.g., caused by mutations in regulatory sequences, is responsible for a plethora of diseases, including cancer, developmental or neurological disorders. As a consequence, decoding the architecture of gene regulatory networks has become one of the most important tasks in modern (computational) biology. However, to advance our understanding of the mechanisms involved in the transcriptional apparatus, we need scalable approaches that can deal with the increasing number of large-scale, high-resolution, biological datasets. In particular, such approaches need to be capable of efficiently integrating and exploiting the biological and technological heterogeneity of such datasets in order to best infer the underlying, highly dynamic regulatory networks, often in the absence of sufficient ground truth data for model training or testing. With respect to scalability, randomized approaches have proven to be a promising alternative to deterministic methods in computational biology. As an example, one of the top performing algorithms in a community challenge on gene regulatory network inference from transcriptomic data is based on a random forest regression model. In this concise survey, we aim to highlight how randomized methods may serve as a highly valuable tool, in particular, with increasing amounts of large-scale, biological experiments and datasets being collected. Given the complexity and interdisciplinary nature of the gene regulatory network inference problem, we hope our survey maybe helpful to both computational and biological scientists. It is our aim to provide a starting point for a dialogue about the concepts, benefits, and caveats of the toolbox of randomized methods, since unravelling the intricate web of highly dynamic, regulatory events will be one fundamental step in understanding the mechanisms of life and eventually developing efficient therapies to treat and cure diseases.

Batch effect reduction of microarray data with dependent samples using an empirical Bayes approach (BRIDGE).

Batch-effects present challenges in the analysis of high-throughput molecular data and are particularly problematic in longitudinal studies when interest lies in identifying genes/features whose expression changes over time, but time is confounded with batch. While many methods to correct for batch-effects exist, most assume independence across samples; an assumption that is unlikely to hold in longitudinal microarray studies. We propose Batch effect Reduction of mIcroarray data with Dependent samples usinGEmpirical Bayes (BRIDGE), a three-step parametric empirical Bayes approach that leverages technical replicate samples profiled at multiple timepoints/batches, so-called "bridge samples", to inform batch-effect reduction/attenuation in longitudinal microarray studies. Extensive simulation studies and an analysis of a real biological data set were conducted to benchmark the performance of BRIDGE against both ComBat and longitudinalComBat. Our results demonstrate that while all methods perform well in facilitating accurate estimates of time effects, BRIDGE outperforms both ComBat and longitudinal ComBat in the removal of batch-effects in data sets with bridging samples, and perhaps as a result, was observed to have improved statistical power for detecting genes with a time effect. BRIDGE demonstrated competitive performance in batch effect reduction of confounded longitudinal microarray studies, both in simulated and a real data sets, and may serve as a useful preprocessing method for researchers conducting longitudinal microarray studies that include bridging samples.

TascCODA: Bayesian Tree-Aggregated Analysis of Compositional Amplicon and Single-Cell Data.

Accurate generative statistical modeling of count data is of critical relevance for the analysis of biological datasets from high-throughput sequencing technologies. Important instances include the modeling of microbiome compositions from amplicon sequencing surveys and the analysis of cell type compositions derived from single-cell RNA sequencing. Microbial and cell type abundance data share remarkably similar statistical features, including their inherent compositionality and a natural hierarchical ordering of the individual components from taxonomic or cell lineage tree information, respectively. To this end, we introduce a Bayesian model for tree-aggregated amplicon and single-cell compositional data analysis (tascCODA) that seamlessly integrates hierarchical information and experimental covariate data into the generative modeling of compositional count data. By combining latent parameters based on the tree structure with spike-and-slab Lasso penalization, tascCODA can determine covariate effects across different levels of the population hierarchy in a data-driven parsimonious way. In the context of differential abundance testing, we validate tascCODA’s excellent performance on a comprehensive set of synthetic benchmark scenarios. Our analyses on human single-cell RNA-seq data from ulcerative colitis patients and amplicon data from patients with irritable bowel syndrome, respectively, identified aggregated cell type and taxon compositional changes that were more predictive and parsimonious than those proposed by other schemes. We posit that tascCODA 1 constitutes a valuable addition to the growing statistical toolbox for generative modeling and analysis of compositional changes in microbial or cell population data.

Bridging the gap: Using biological data from teeth to comment on social identity of archeological populations from early Anglo-Saxon, England

Human teeth are storytellers, in that, through analysis of their size and shape osteoarchaeologists are able to ‘talk’ to the dead and translate biological data into social meaning. This concept has been explored in parts of the world through investigations of biological similarity and kinship, but few have focused in depth on early medieval populations who emphasized the importance of family and kinship. This paper presents the results from four early Anglo-Saxon cemeteries which highlight the utility of dental metrics in identifying biological similarity within the skeletal assemblages. 5988 mesiodistal and buccolingual measurements were recorded from the identifiable permanent dentition of adult individuals from early Anglo-Saxon cemeteries in the UK counties of Cambridgeshire and Kent. Results from statistical hierarchical cluster analysis of dental metric data revealed that it was possible to identify individuals within the cemetery sites that were more similar to one another according to their dental metrics. This similarity was not attributed statistically to biological sex or shared familial environment, as similarity between individuals could be found between males and females and few significant differences were found across the sites sampled. It was found that tooth metrics provided a meaningful biological dataset from which current theories regarding the identity of Anglo-Saxon individuals and families could be refined and improved. These types of data are useful as building blocks which help to bridge the gap between social constructs and human skeletal remains in order to substantiate interpretations about past populations in more significant ways. This work supports the need for multidisciplinary approaches to bioarchaeological investigations of past people while highlighting the utility of human dentition to enhance such areas of study.

CNV-P: a machine-learning framework for predicting high confident copy number variations

BackgroundCopy-number variants (CNVs) have been recognized as one of the major causes of genetic disorders. Reliable detection of CNVs from genome sequencing data has been a strong demand for disease research. However, current software for detecting CNVs has high false-positive rates, which needs further improvement.MethodsHere, we proposed a novel and post-processing approach for CNVs prediction (CNV-P), a machine-learning framework that could efficiently remove false-positive fragments from results of CNVs detecting tools. A series of CNVs signals such as read depth (RD), split reads (SR) and read pair (RP) around the putative CNV fragments were defined as features to train a classifier.ResultsThe prediction results on several real biological datasets showed that our models could accurately classify the CNVs at over 90% precision rate and 85% recall rate, which greatly improves the performance of state-of-the-art algorithms. Furthermore, our results indicate that CNV-P is robust to different sizes of CNVs and the platforms of sequencing.ConclusionsOur framework for classifying high-confident CNVs could improve both basic research and clinical diagnosis of genetic diseases.

A survey on data integration for multi-omics sample clustering

Due to the current high availability of omics, data-driven biology has greatly expanded, and several papers have reviewed state-of-the-art technologies. Nowadays, two main types of investigation are available for a multi-omics dataset: extraction of relevant features for a meaningful biological interpretation and clustering of the samples. In the latter case, a few reviews refer to some outdated or no longer available methods, whereas others lack the description of relevant clustering metrics to compare the main approaches. This work provides a general overview of the major techniques in this area, divided into four groups: graph, dimensionality reduction, statistical and neural-based. Besides, eight tools have been tested both on a synthetic and a real biological dataset. An extensive performance comparison has been provided using four clustering evaluation scores: Peak Signal-to-Noise Ratio (PSNR), Davies-Bouldin(DB) index, Silhouette value and the harmonic mean of cluster purity and efficiency. The best results were obtained by using the dimensionality reduction, either explicitly or implicitly, as in the neural architecture.

Evolutionary analysis of candidate non-coding elements regulating neurodevelopmental genes in vertebrates

Many non-coding regulatory elements conserved in vertebrates regulate the expression of genes involved in development and play an important role in the evolution of morphology through the rewiring of developmental gene networks. Available biological datasets allow the identification of non-coding regulatory elements with high confidence; furthermore, chromatin conformation data can be used to confirm enhancer-promoter interactions in specific tissue types and developmental stages. We have devised an analysis pipeline that integrates datasets about gene expression, enhancer activity, chromatin accessibility, epigenetic marks, and Hi-C contact frequencies in various brain tissues and developmental stages, leading to the identification of eight non-coding elements that might regulate the expression of three genes with important roles in brain development in vertebrates. We have then performed comparative sequence and microsynteny analyses in order to reconstruct the evolutionary history of the regulatory landscape around these genes; we observe a general pattern of ancient regulatory elements conserved across most vertebrate lineages, together with younger elements that appear to be mammal and primate innovations.