Large Biological Data Research Articles

Sub-sampling graph neural networks for genomic prediction of quantitative phenotypes.

In genomics, use of deep learning (DL) is rapidly growing and DL has successfully demonstrated its ability to uncover complex relationships in large biological and biomedical data sets. With the development of high-throughput sequencing techniques, genomic markers can now be allocated to large sections of a genome. By analysing allele sharing between individuals, one may calculate realized genomic relationships from single nucleotide polymorphisms (SNPs) data rather than relying on known pedigree relationships under polygenic model. The traditional approaches in genome-wide prediction (GWP) of quantitative phenotypes utilise genomic relationships in fixed global covariance modelling, possibly with some non-linear kernel mapping (for example Gaussian processes). On the other hand, the DL approaches proposed so far for GWP fail to take into account the non-Euclidean graph structure of relationships between individuals over several generations. In this paper, we propose one global convolutional neural network (GCN) and one local sub-sampling architecture (GCN-RS) that are specifically designed to perform regression analysis based on genomic relationship information. A GCN is tailored to non-Euclidean spaces and consists of several layers of graph convolutions. The GCN-RS architecture is designed to further improve the GCN's performance by sub-sampling the graph to reduce the dimensionality of the input data. Through these graph convolutional layers, the GCN maps input genomic markers to their quantitative phenotype values. The graphs are constructed using an iterative nearest neighbour approach. Comparisons show that the GCN-RS outperforms the popular Genomic Best Linear Unbiased Predictor (GBLUP) method on one simulated and three real data sets from wheat, mice and pig with a predictive improvement of 4.4% to 49.4% in terms of test mean squared error (MSE). This indicates that GCN-RS is a promising tool for genomic predictions in plants and animals. Furthermore, GCN-RS is computationally efficient, making it a viable option for large-scale applications.

Revisiting barriers to implementation of bioinformatics into life sciences education

IntroductionBioinformatics is an interdisciplinary field at the intersection of computational and biological sciences that focuses on the analysis and interpretation of large biological data sets. Although recognized as essential in the life sciences, bioinformatics is not commonly integrated in undergraduate life science education programs. Based on a national survey in 2016, the Network for Integrating Bioinformatics into Life Sciences Education (NIBLSE) published a community-sourced set of core competencies in bioinformatics education. The survey also identified barriers that prevent incorporation of these competencies into the curriculum. In the current study, the NIBLSE group reports the findings of a new survey to 509 life science educators across the US in 2022 to identify current barriers of bioinformatics integration and to determine if the landscape of bioinformatics education has changed since the 2016 survey.ResultsSimilar to previous results, a majority of respondents who currently teach bioinformatics or plan to teach bioinformatics report barriers. The top two barriers reported are students lacking prerequisite skills/knowledge and instructors lacking time to restructure course content. As in 2016, women reported experiencing barriers to bioinformatics teaching significantly more often than men; faculty from underrepresented minority backgrounds reported barriers more often than non-URM faculty; and educators at minority-serving institutions (MSIs) reported barriers more frequently than colleagues at non-MSIs. For additional insight into the barriers facing these educators, we conducted focus groups which provided qualitative data that supported the survey findings and revealed common themes including faculty perceptions of the relevance of bioinformatics in the curriculum. Despite the perceived value of bioinformatics education, many focus group members cited lack of student preparation and interest, and technological access as barriers. Participants also discussed how professional development and community support would enhance and sustain bioinformatics teaching.DiscussionTaken all together, this study indicates that challenges remain, which vary among faculty types and settings, but that more educators are attempting to integrate bioinformatics into life sciences education. In summary, our results suggest that redoubled efforts to provide training and community support to life sciences faculty is necessary.

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics

We seek to transform how new and emergent variants of pandemic-causing viruses, specifically SARS-CoV-2, are identified and classified. By adapting large language models (LLMs) for genomic data, we build genome-scale language models (GenSLMs) which can learn the evolutionary landscape of SARS-CoV-2 genomes. By pre-training on over 110 million prokaryotic gene sequences and fine-tuning a SARS-CoV-2-specific model on 1.5 million genomes, we show that GenSLMs can accurately and rapidly identify variants of concern. Thus, to our knowledge, GenSLMs represents one of the first whole-genome scale foundation models which can generalize to other prediction tasks. We demonstrate scaling of GenSLMs on GPU-based supercomputers and AI-hardware accelerators utilizing 1.63 Zettaflops in training runs with a sustained performance of 121 PFLOPS in mixed precision and peak of 850 PFLOPS. We present initial scientific insights from examining GenSLMs in tracking evolutionary dynamics of SARS-CoV-2, paving the path to realizing this on large biological data.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies.

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

Tight basis cycle representatives for persistent homology of large biological data sets.

Persistent homology (PH) is a popular tool for topological data analysis that has found applications across diverse areas of research. It provides a rigorous method to compute robust topological features in discrete experimental observations that often contain various sources of uncertainties. Although powerful in theory, PH suffers from high computation cost that precludes its application to large data sets. Additionally, most analyses using PH are limited to computing the existence of nontrivial features. Precise localization of these features is not generally attempted because, by definition, localized representations are not unique and because of even higher computation cost. Such a precise location is a sine qua non for determining functional significance, especially in biological applications. Here, we provide a strategy and algorithms to compute tight representative boundaries around nontrivial robust features in large data sets. To showcase the efficiency of our algorithms and the precision of computed boundaries, we analyze the human genome and protein crystal structures. In the human genome, we found a surprising effect of the impairment of chromatin loop formation on loops through chromosome 13 and the sex chromosomes. We also found loops with long-range interactions between functionally related genes. In protein homologs with significantly different topology, we found voids attributable to ligand-interaction, mutation, and differences between species.

Column storage enables edge computation of biological big data on 5G networks.

With the continuous improvement of biological detection technology, the scale of biological data is also increasing, which overloads the central-computing server. The use of edge computing in 5G networks can provide higher processing performance for large biological data analysis, reduce bandwidth consumption and improve data security. Appropriate data compression and reading strategy becomes the key technology to implement edge computing. We introduce the column storage strategy into mass spectrum data so that part of the analysis scenario can be completed by edge computing. Data produced by mass spectrometry is a typical biological big data based. A blood sample analysed by mass spectrometry can produce a 10 gigabytes digital file. By introducing the column storage strategy and combining the related prior knowledge of mass spectrometry, the structure of the mass spectrum data is reorganized, and the result file is effectively compressed. Data can be processed immediately near the scientific instrument, reducing the bandwidth requirements and the pressure of the central server. Here, we present Aird-Slice, a mass spectrum data format using the column storage strategy. Aird-Slice reduces volume by 48% compared to vendor files and speeds up the critical computational step of ion chromatography extraction by an average of 116 times over the test dataset. Aird-Slice provides the ability to analyze biological data using an edge computing architecture on 5G networks.

Bayesian bi-clustering methods with applications in computational biology

Bi-clustering is a useful approach in analyzing large biological data sets when the observations come from heterogeneous groups and have a large number of features. We outline a general Bayesian approach in tackling bi-clustering problems in moderate to high dimensions and propose three Bayesian bi-clustering models on categorical data which increase in complexities in their modeling of the distributions of features across bi-clusters. Our proposed methods apply to a wide range of scenarios: from situations where data are cluster-distinguishable only among a small subset of features but masked by a large amount of noise to situations where different groups of data are identified by different sets of features or data exhibit hierarchical structures. Through simulation studies we show that our methods outperform existing (bi-)clustering methods in both identifying clusters and recovering feature distributional patterns across bi-clusters. We further apply the developed approaches to a human genetic dataset, a human single-cell genomic dataset, and a collection of 1774 mouse genomic datasets with a focus on 58 genes from two pathways.

Differences between Bioinformatics and Computational Biology

Technology has a great influence on biological science and with the help of biological science and programming bioinformatics and computational biology has the capability of changing the future of Healthcare. Bioinformatics and computational biology are the inclusive and interesting fields of biology. It is evident that both the subjects have some similarities but both have prominent dissimilarities to a great extent. Bioinformatics helps the scientists to organise large biological data apart from that it also facilitates DNA sequencing, structure anticipation and identification of function of proteins and so on. On the other hand, computational biology makes the biological ideology rigorous and experimental and at the same time provides better insight about the respective field. Computational biology allows the researchers to make the procedure of drug discovery more efficiently and seamless. In addition, it allows researchers to develop precise models with the help of 3D modelling to ensure a greater Healthcare system. Computational medicine has the ability to upgrade the overall Healthcare sector through est Keyword : Bioinformatics, Computational Biology, DNA, Healthcare.

Workflow to Mine Frequent DNA Co-methylation Clusters in DNA Methylome Data.

The advances in high-throughput nucleotide sequencing technology revolutionized biomedical research. Vast amount of genomic data rapidly accumulates in a daily basis, which in turn calls for the development of powerful bioinformatics tools and efficient workflows to analyze them. One of the approaches to address the "big data" issue is to mine highly correlated clusters/networks of biological molecules, which may provide rich yet hidden information about the underlying functional, regulatory, or structural relationships among genes, proteins, genomic loci or various types of biological molecules or events. A network mining algorithm lmQCM has recently been developed, which can be applied to mine tightly connected correlation clusters (networks) in large biological data with big sample size, and it guarantees a lower bound of the cluster density. This algorithm has been used in a variety of cancer transcriptomic data to mine gene co-expression networks (GCNs), but it can be applied to any correlational matrix. lmQCM is available through R package lmQCM as well as the online tool package TSUNAMI ( https://biolearns.medicine.iu.edu ).In this study, the purpose is to establish an analytical workflow to apply lmQCM for frequent (consensus)cluster mining in multiple DNA methylation datasets in different cancers and extract the underlying common co-methylation networks for genes.Specifically, the workflow is applied to analyze DNA methylome data across different cancer types using lmQCM. It mines frequent DNA methylation clusters based on individual clustering mining results, identifying common as well as distinctive DNA methylation patterns among different cancer types. This workflow has successfully identified frequent GCNs in 33 types of cancers, thus proven to be a powerful tool to analyze large biological data. It helps to identify common features as well as distinctions among different diseases, disease subtypes, or among different biological processes. The resulted frequent clusters may provide new insights on the pathway/function networks. In the case of disease study, the results lead to new directions for biomarker and drug target discovery. The advantages of this workflow include the highly efficient processing of large biological data generated from high-throughput experiments, quick identification of highly correlated interaction networks, substantial reduction of the data dimensionality to a manageable number of variables for downstream comparative analysis, and consequently increased statistical power for detecting differences between conditions.

Discriminating Neoplastic from Nonneoplastic Tissues Using an miRNA-Based Deep Cancer Classifier

Next-generation sequencing has enabled the collection of large biological data sets, allowing novel molecular-based classification methods to be developed for increased understanding of disease. miRNAs are small regulatory RNA molecules that can be quantified using next-generation sequencing and are excellent classificatory markers. Herein, a deep cancer classifier (DCC) was adapted to differentiate neoplastic from nonneoplastic samples using comprehensive miRNA expression profiles from 1031 human breast and skin tissue samples. The classifier was fine-tuned and evaluated using 750 neoplastic and 281 nonneoplastic breast and skin tissue samples. Performance of the DCC was compared with two machine-learning classifiers: support vector machine and random forests. In addition, performance of feature extraction through the DCC was also compared with a developed feature selection algorithm, cancer specificity. The DCC had the highest performance of area under the receiver operating curve and high performance in both sensitivity and specificity, unlike machine-learning and feature selection models, which often performed well in one metric compared with the other. In particular, deep learning had noticeable advantages with highly heterogeneous data sets. In addition, our cancer specificity algorithm identified candidate biomarkers for differentiating neoplastic and nonneoplastic tissue samples (eg, miR-144 and miR-375 in breast cancer and miR-375 and miR-451 in skin cancer).

Bioinformatics in Sudan: Status and challenges case study: The National University-Sudan.

The ever increasing applications of bioinformatics in providing effective interpretation of large and complex biological data require expertise in the use of sophisticated computational tools and advanced statistical tests, skills that are mostly lacking in the Sudanese research community. This can be attributed to paucity in the development and promotion of bioinformatics, lack of senior bioinformaticians, and the general status quo of inadequate research funding in Sudan. In this paper, we describe the challenges that have encountered the development of bioinformatics as a discipline in Sudan. Additionally, we highlight on specific actions that may help develop and promote its education and training. The paper takes the National University Biomedical Research Institute (NUBRI) as an example of an institute that has tackled many of these challenges and strives to drive powerful efforts in the development of bioinformatics in the country.

Understanding large and complex biological data sets using visualization

Molecular biology experiments are generating an unprecedented amount of information from a variety of different experimental modalities. DNA sequencing machines, proteomics mass cytometry and microscopes generate huge amounts of data every day. Not only is the data large, but it is also multidimensional. Understanding trends and getting actionable insights from these data requires techniques that allow comprehension at a high level but also insight into what underlies these trends. Lots of small errors or poor summarization can lead to false results and reproducibility issues in large data sets. Hence it is essential we do not cherry-pick results to suit a hypothesis but instead examine all data and publish accurate insights in a data-driven way. This article will give an overview of some of the problems faced by the researcher in understanding epigenetic changes (which are related to changes in the physical structure of DNA) when presented with raw analysis results using visualization methods. We will also discuss the new challenges faced by using machine learning which can be helped by visualization.

Species Tree Inference Methods Intended to Deal with Incomplete Lineage Sorting Are Robust to the Presence of Paralogs.

Many recent phylogenetic methods have focused on accurately inferring species trees when there is gene tree discordance due to incomplete lineage sorting (ILS). For almost all of these methods, and for phylogenetic methods in general, the data for each locus are assumed to consist of orthologous, single-copy sequences. Loci that are present in more than a single copy in any of the studied genomes are excluded from the data. These steps greatly reduce the number of loci available for analysis. The question we seek to answer in this study is: what happens if one runs such species tree inference methods on data where paralogy is present, in addition to or without ILS being present? Through simulation studies and analyses of two large biological data sets, we show that running such methods on data with paralogs can still provide accurate results. We use multiple different methods, some of which are based directly on the multispecies coalescent model, and some of which have been proven to be statistically consistent under it. We also treat the paralogous loci in multiple ways: from explicitly denoting them as paralogs, to randomly selecting one copy per species. In all cases, the inferred species trees are as accurate as equivalent analyses using single-copy orthologs. Our results have significant implications for the use of ILS-aware phylogenomic analyses, demonstrating that they do not have to be restricted to single-copy loci. This will greatly increase the amount of data that can be used for phylogenetic inference.[Gene duplication and loss; incomplete lineage sorting; multispecies coalescent; orthology; paralogy.]

Biological crust in sand and dust storm source areas of Asia and its impact on dust emission

Even though the biological crusts are critical to dust emissions, no sand and dust forecast model have considered the impacts of the biological crust in dust emission scheme. This situation mainly comes from two scientific difficulties: there is no large scale regional biological crust data available that can be used in the forecast model; there is no quantification of how biological crusts impact on sand emission. In this way, we studied the distribution of biological soil crust in sand and dust storm source areas of Central and East Asia using Moderate Resolution Imaging Spectroradiometer satellite surface reflectance data collected in 2000–2019 to determine its potential impact on dust emission according to two empirical schemes. We further evaluated the relationships between soil crust coverage, roughness length, and dust emission to study SDS source areas. We found that biological crust is widely distributed in SDS source areas of Central and East Asia, with coverage rates of 19.8% in Central Asian deserts, 23.1% in the Gobi Desert, and 17.3%–32.8% in Chinese deserts (p > 0.05). Cyanobacteria and lichen coverage has increased in Chinese deserts, reflecting the recent impacts of the Project of Returning Farmland to Grassland and Farmland to Forests. However, biological soil crust coverage has not increased in Central Asian deserts or the Gobi Desert, and that in Central Asian deserts continues to decrease, demonstrating the complexity of the combined effects of human activities and climate change on its distribution. Biological soil crust increased the roughness length of Central and East Asian SDS source areas by 0.14–0.62 mm. The suppression of dust emission due to biological soil crust did not change among years during the study period. The horizontal and vertical dust flux inhibition coefficient (DFIC) were 2.0–11.0 and 1.7–2.9 (p > 0.05), respectively, clearly showing a suppressive effect. Improvement of the ecological environment in some deserts can lead to the ability of these crusts to inhibit dust erosion errors that must be considered in the dust emission scheme for areas where crust coverage has improved.

Information enhanced model selection for Gaussian graphical model with application to metabolomic data.

In light of the low signal-to-noise nature of many large biological data sets, we propose a novel method to learn the structure of association networks using Gaussian graphical models combined with prior knowledge. Our strategy includes two parts. In the first part, we propose a model selection criterion called structural Bayesian information criterion, in which the prior structure is modeled and incorporated into Bayesian information criterion. It is shown that the popular extended Bayesian information criterion is a special case of structural Bayesian information criterion. In the second part, we propose a two-step algorithm to construct the candidate model pool. The algorithm is data-driven and the prior structure is embedded into the candidate model automatically. Theoretical investigation shows that under some mild conditions structural Bayesian information criterion is a consistent model selection criterion for high-dimensional Gaussian graphical model. Simulation studies validate the superiority of the proposed algorithm over the existing ones and show the robustness to the model misspecification. Application to relative concentration data from infant feces collected from subjects enrolled in a large molecular epidemiological cohort study validates that metabolic pathway involvement is a statistically significant factor for the conditional dependence between metabolites. Furthermore, new relationships among metabolites are discovered which can not be identified by the conventional methods of pathway analysis. Some of them have been widely recognized in biological literature.

RSWeeP: An R/Bioconductor package to represent large biological sequences data sets in compact vectors.

rSWeeP: An R/Bioconductor package to represent large biological sequences data sets in compact vectors.

Optimized Attribute Selection Using Artificial Plant (AP) Algorithm with ESVM Classifier (AP-ESVM) and Improved Singular Value Decomposition (ISVD)-Based Dimensionality Reduction for Large Micro-array Biological Data.

In the tremendous field of the bioinformatics look into, enormous volume of genetic information has been produced. Higher throughput gadgets are made accessible at lower cost made the age of Big data. In a time of developing information multifaceted nature and volume and the approach of huge information, feature selection has a key task to carry out in decreasing high dimensionality in AI issues. Dealing with such huge data has turned out to be incredibly testing strategy for choosing the exact features in enormous medical databases. Large clinical data frequently comprise of an enormous number of identifiers of the disease. Data mining when applied to clinical data for identification of diseases, a few identifiers are will not be much useful and sometimes may even have negative impacts. Consequently, when the FS is applied, it is vital as it can expel those insignificant disease identifiers. It likewise builds the adequacy of decision by a physician emotionally supportive network by viably diminishing the time of learning of the framework. In this paper, a unique approach is presented for the feature selection utilizing the Artificial Plant algorithm which uses the Enhanced Support Vector Machine classifier. The features got are additionally dimensionally decreased by presenting the Improved Singular Value Decomposition strategy; finally, enhancement is done by the outstanding BAT streamlining method. The examinations are completed with real-time large cervical cancer data and it demonstrated to be more effective than the current methods.

A scalable multiple pairwise protein sequence alignment acceleration using hybrid CPU–GPU approach

Bioinformatics is an interdisciplinary field that applies trending techniques in information technology, mathematics, and statistics in studying large biological data. Bioinformatics involves several computational techniques such as sequence and structural alignment, data mining, macromolecular geometry, prediction of protein structure and gene finding. Protein structure and sequence analysis are vital to the understanding of cellular processes. Understanding cellular processes contributes to the development of drugs for metabolic pathways. Protein sequence alignment is concerned with identifying the similarities and the relationships among different protein structures. In this paper, we target two well-known protein sequence alignment algorithms, the Needleman–Wunsch and the Smith–Waterman algorithms. These two algorithms are computationally expensive which hinders their applicability for large data sets. Thus, we propose a hybrid parallel approach that combines the capabilities of multi-core CPUs and the power of contemporary GPUs, and significantly speeds up the execution of the target algorithms. The validity of our approach is tested on real protein sequences. Moreover, the scalability of the approach is verified on randomly generated sequences with predefined similarity levels. The results showed that the proposed hybrid approach was up to 242 times faster than the sequential approach.

PyBDA: a command line tool for automated analysis of big biological data sets

BackgroundAnalysing large and high-dimensional biological data sets poses significant computational difficulties for bioinformaticians due to lack of accessible tools that scale to hundreds of millions of data points.ResultsWe developed a novel machine learning command line tool called PyBDA for automated, distributed analysis of big biological data sets. By using Apache Spark in the backend, PyBDA scales to data sets beyond the size of current applications. It uses Snakemake in order to automatically schedule jobs to a high-performance computing cluster. We demonstrate the utility of the software by analyzing image-based RNA interference data of 150 million single cells.ConclusionPyBDA allows automated, easy-to-use data analysis using common statistical methods and machine learning algorithms. It can be used with simple command line calls entirely making it accessible to a broad user base. PyBDA is available at https://pybda.rtfd.io.

BEKVAEM: INTEGRATIVE DATA EXPLORER FOR HI-C DATA

Motivation: The browser-based visualization of Hi-C contact maps alongside complementary data tracks is a computationally challenging task and requires an efficient software implementation to run on small clients. Few software packages have yet been shared with the community to address this problem and modification of these is cumbersome. Results: We introduce Bekvaem that addresses these problems by using high-level Python interfaces. Wrapping several libraries for online visualizations at the front-end and the organization of large biological data sets at the server-side allows for setting up a high-performance user-defined browser visualization for Hi-C data with just a few changes in the code. Availability and implementation: The source code, written in Python, of Bekvaem alongside its documentation and sample data is freely available on heiDATA . A demonstration server is available here .