Extract Biological Knowledge Research Articles

A FAIR and modular image‐based workflow for knowledge discovery in the emerging field of imageomics

Abstract Image‐based machine learning tools are an ascendant ‘big data’ research avenue. Citizen science platforms, like iNaturalist, and museum‐led initiatives provide researchers with an abundance of data and knowledge to extract. These include extraction of metadata, species identification, and phenomic data. Ecological and evolutionary biologists are increasingly using complex, multi‐step processes on data. These processes often include machine learning techniques, often built by others, that are difficult to reuse by other members in a collaboration. We present a conceptual workflow model for machine learning applications using image data to extract biological knowledge in the emerging field of imageomics. We derive an implementation of this conceptual workflow for a specific imageomics application that adheres to FAIR principles as a formal workflow definition that allows fully automated and reproducible execution, and consists of reusable workflow components. We outline technologies and best practices for creating an automated, reusable and modular workflow, and we show how they promote the reuse of machine learning models and their adaptation for new research questions. This conceptual workflow can be adapted: it can be semi‐automated, contain different components than those presented here, or have parallel components for comparative studies. We encourage researchers—both computer scientists and biologists—to build upon this conceptual workflow that combines machine learning tools on image data to answer novel scientific questions in their respective fields.

SHARE-Topic: Bayesian interpretable modeling of single-cell multi-omic data

Multi-omic single-cell technologies, which simultaneously measure the transcriptional and epigenomic state of the same cell, enable understanding epigenetic mechanisms of gene regulation. However, noisy and sparse data pose fundamental statistical challenges to extract biological knowledge from complex datasets. SHARE-Topic, a Bayesian generative model of multi-omic single cell data using topic models, aims to address these challenges. SHARE-Topic identifies common patterns of co-variation between different omic layers, providing interpretable explanations for the data complexity. Tested on data from different technological platforms, SHARE-Topic provides low dimensional representations recapitulating known biology and defines associations between genes and distal regulators in individual cells.

Dex-Benchmark: datasets and code to evaluate algorithms for transcriptomics data analysis.

Many tools and algorithms are available for analyzing transcriptomics data. These include algorithms for performing sequence alignment, data normalization and imputation, clustering, identifying differentially expressed genes, and performing gene set enrichment analysis. To make the best choice about which tools to use, objective benchmarks can be developed to compare the quality of different algorithms to extract biological knowledge maximally and accurately from these data. The Dexamethasone Benchmark (Dex-Benchmark) resource aims to fill this need by providing the community with datasets and code templates for benchmarking different gene expression analysis tools and algorithms. The resource provides access to a collection of curated RNA-seq, L1000, and ChIP-seq data from dexamethasone treatment as well as genetic perturbations of its known targets. In addition, the website provides Jupyter Notebooks that use these pre-processed curated datasets to demonstrate how to benchmark the different steps in gene expression analysis. By comparing two independent data sources and data types with some expected concordance, we can assess which tools and algorithms best recover such associations. To demonstrate the usefulness of the resource for discovering novel drug targets, we applied it to optimize data processing strategies for the chemical perturbations and CRISPR single gene knockouts from the L1000 transcriptomics data from the Library of Integrated Network Cellular Signatures (LINCS) program, with a focus on understudied proteins from the Illuminating the Druggable Genome (IDG) program. Overall, the Dex-Benchmark resource can be utilized to assess the quality of transcriptomics and other related bioinformatics data analysis workflows. The resource is available from: https://maayanlab.github.io/dex-benchmark.

A Novel Calibration Step in Gene Co-Expression Network Construction.

High-throughput technologies such as DNA microarrays and RNA-sequencing are used to measure the expression levels of large numbers of genes simultaneously. To support the extraction of biological knowledge, individual gene expression levels are transformed to Gene Co-expression Networks (GCNs). In a GCN, nodes correspond to genes, and the weight of the connection between two nodes is a measure of similarity in the expression behavior of the two genes. In general, GCN construction and analysis includes three steps; 1) calculating a similarity value for each pair of genes 2) using these similarity values to construct a fully connected weighted network 3) finding clusters of genes in the network, commonly called modules. The specific implementation of these three steps can significantly impact the final output and the downstream biological analysis. GCN construction is a well-studied topic. Existing algorithms rely on relatively simple statistical and mathematical tools to implement these steps. Currently, software package WGCNA appears to be the most widely accepted standard. We hypothesize that the raw features provided by sequencing data can be leveraged to extract modules of higher quality. A novel preprocessing step of the gene expression data set is introduced that in effect calibrates the expression levels of individual genes, before computing pairwise similarities. Further, the similarity is computed as an inner-product of positive vectors. In experiments, this provides a significant improvement over WGCNA, as measured by aggregate p-values of the gene ontology term enrichment of the computed modules.

A Novel Fuzzy Frequent Itemsets Mining Approach for the Detection of Breast Cancer

Breast cancer, a type of malignant tumor, affects women more than men. About one-third of women with breast cancer die of this disease. Hence, it is imperative to find a tool for the proper identification and early treatment of breast cancer. Unlike the conventional data mining algorithms, fuzzy logic-based approaches help in the mining of association rules from quantitative transactions. In this study, a novel fuzzy methodology, IFFP (improved fuzzy frequent pattern mining), based on a fuzzy association rule mining for biological knowledge extraction, is introduced to analyze the dataset in order to find the core factors that cause breast cancer. It is determined that the factor, mitoses, has low range of values on both malignant and benign, and hence it does not contribute to the detection of breast cancer. On the other hand, the high range of bare nuclei shows more chances for the presence of breast cancer. Experimental evaluations on real datasets show that the proposed method outperforms recently proposed state-of-the-art algorithms in terms of runtime and memory usage.

PyHIST: A Histological Image Segmentation Tool.

The development of increasingly sophisticated methods to acquire high-resolution images has led to the generation of large collections of biomedical imaging data, including images of tissues and organs. Many of the current machine learning methods that aim to extract biological knowledge from histopathological images require several data preprocessing stages, creating an overhead before the proper analysis. Here we present PyHIST (https://github.com/manuel-munoz-aguirre/PyHIST), an easy-to-use, open source whole slide histological image tissue segmentation and preprocessing command-line tool aimed at tile generation for machine learning applications. From a given input image, the PyHIST pipeline i) optionally rescales the image to a different resolution, ii) produces a mask for the input image which separates the background from the tissue, and iii) generates individual image tiles with tissue content.

Detection of Breast Cancer Based on Fuzzy Frequent Itemsets Mining

Background: Breast cancer, a type of malignant tumor, affects women more than men. About one third of women with breast cancer die of this disease. Hence, it is imperative to find a tool for the proper identification and early treatment of breast cancer. Unlike the conventional data mining algorithms, fuzzy logic based approaches help in the mining of association rules from quantitative transactions.Methods: In this study a novel fuzzy methodology IFFP (Improved Fuzzy Frequent Pattern Mining), based on a fuzzy association rule mining for biological knowledge extraction, is introduced to analyze the dataset in order to find the core factors that cause breast cancer. This method consists of two phases. During the first phase, fuzzy frequent itemsets are mined using the proposed algorithm IFFP. Fuzzy association rules are formed during the second phase, indicating whether a person belongs to benign or malignant. This algorithm is applied on WBCD (Wisconsin Breast Cancer Database) to detect the presence of breast cancer.Results: It is determined that the factor, Mitoses has low range of values on both malignant and benign and hence it does not contribute to the detection of breast cancer. On the other hand, the high range of Bare Nuclei shows more chances for the presence of breast cancer.Conclusion: Experimental evaluations on real datasets show that our proposed method outperforms recently proposed state-of-the-art algorithms in terms of runtime and memory usage.

Extraction of Biological Knowledge by Clustering Data Mining Techniques

Extraction of Biological Knowledge by Clustering Data Mining Techniques

Leveraging multiple gene networks to prioritize GWAS candidate genes via network representation learning.

Genome-wide association studies (GWAS) have successfully discovered a number of disease-associated genetic variants in the past decade, providing an unprecedented opportunity for deciphering genetic basis of human inherited diseases. However, it is still a challenging task to extract biological knowledge from the GWAS data, due to such issues as missing heritability and weak interpretability. Indeed, the fact that the majority of discovered loci fall into noncoding regions without clear links to genes has been preventing the characterization of their functions and appealing for a sophisticated approach to bridge genetic and genomic studies. Towards this problem, network-based prioritization of candidate genes, which performs integrated analysis of gene networks with GWAS data, has emerged as a promising direction and attracted much attention. However, most existing methods overlook the sparse and noisy properties of gene networks and thus may lead to suboptimal performance. Motivated by this understanding, we proposed a novel method called REGENT for integrating multiple gene networks with GWAS data to prioritize candidate genes for complex diseases. We leveraged a technique called the network representation learning to embed a gene network into a compact and robust feature space, and then designed a hierarchical statistical model to integrate features of multiple gene networks with GWAS data for the effective inference of genes associated with a disease of interest. We applied our method to six complex diseases and demonstrated the superior performance of REGENT over existing approaches in recovering known disease-associated genes. We further conducted a pathway analysis and showed that the ability of REGENT to discover disease-associated pathways. We expect to see applications of our method to a broad spectrum of diseases for post-GWAS analysis. REGENT is freely available at https://github.com/wmmthu/REGENT.

Understanding Human Autoimmunity and Autoinflammation Through Transcriptomics.

Transcriptomics, the high-throughput characterization of RNAs, has been instrumental in defining pathogenic signatures in human autoimmunity and autoinflammation. It enabled the identification of new therapeutic targets in IFN-, IL-1- and IL-17-mediated diseases. Applied to immunomonitoring, transcriptomics is starting to unravel diagnostic and prognostic signatures that stratify patients, track molecular changes associated with disease activity, define personalized treatment strategies, and generally inform clinical practice. Herein, we review the use of transcriptomics to define mechanistic, diagnostic, and predictive signatures in human autoimmunity and autoinflammation. We discuss some of the analytical approaches applied to extract biological knowledge from high-dimensional data sets. Finally, we touch upon emerging applications of transcriptomics to study eQTLs, B and T cell repertoire diversity, and isoform usage.

Editorial: Protein Interaction Networks in Health and Disease.

Editorial: Protein Interaction Networks in Health and Disease.

TAKES: Two-step Approach for Knowledge Extraction in Biomedical Digital Libraries

This paper proposes a novel knowledge extraction system, TAKES (Two-step Approach for Knowledge Extraction System), which integrates advanced techniques from Information Retrieval (IR), Information Extraction (IE), and Natural Language Processing (NLP). In particular, TAKES adopts a novel keyphrase extraction-based query expansion technique to collect promising documents. It also uses a Conditional Random Field-based machine learning technique to extract important biological entities and relations. TAKES is applied to biological knowledge extraction, particularly retrieving promising documents that contain Protein-Protein Interaction (PPI) and extracting PPI pairs. TAKES consists of two major components: DocSpotter, which is used to query and retrieve promising documents for extraction, and a Conditional Random Field (CRF)-based entity extraction component known as FCRF. The present paper investigated research problems addressing the issues with a knowledge extraction system and conducted a series of experiments to test our hypotheses. The findings from the experiments are as follows: First, the author verified, using three different test collections to measure the performance of our query expansion technique, that DocSpotter is robust and highly accurate when compared to Okapi BM25 and SLIPPER. Second, the author verified that our relation extraction algorithm, FCRF, is highly accurate in terms of F-Measure compared to four other competitive extraction algorithms: Support Vector Machine, Maximum Entropy, Single POS HMM, and Rapier.

Mining gene-centric relationships from literature: the roles of gene mutation and gene expression in supporting drug discovery.

Identifying drug target candidates is an important task for early development throughout the drug discovery process. This process is supported by the development of new high-throughput technologies that enable better understanding of disease mechanism. It becomes critical to facilitate effective analysis of the large amount of biological data. However, with much of the biological knowledge represented in the literature in the form of natural text, analysis and interpretation of high-throughput data has not reached its potential effectiveness. In this paper, we describe our solution in employing text mining as a technique in finding scientific information for target and biomarker discovery from the biomedical literature. Our approach utilises natural language processing techniques to capture linguistic patterns for the extraction of biological knowledge from text. Additionally, we discuss how the extracted knowledge is used for the analysis of biological data such as next-generation sequencing and gene expression data.

Elucidating Xylose Metabolism of Scheffersomyces stipitis for Lignocellulosic Ethanol Production

The conversion of pentose to ethanol is one of the major barriers of industrializing the lignocellulosic ethanol processes. As one of the most promising native strains for pentose fermentation, Scheffersomyces stipitis (formerly known as Pichia stipitis) has been widely studied for its xylose fermentation. In spite of the abundant experimental evidence regarding ethanol and byproducts production under various aeration conditions, the mathematical descriptions of the processes are rare. In this work, a constraint-based metabolic network model for the central carbon metabolism of S. stipitis was reconstructed by integrating genomic (S. stipitis v2.0, KEGG), biochemical (ChEBI, PubChem), and physiological information available for this microorganism and other related yeast. The model consists of the stoichiometry of metabolic reactions, biosynthetic requirements for growth, and other constraints. Flux balance analysis is applied to characterize the phenotypic behavior of S. stipitis grown on xylose. The model predictions are in good agreement with published experimental results. To understand the effect of redox balance on xylose fermentation, we propose a system identification-based metabolic analysis framework to extract biological knowledge embedded in a series of designed in silico experiments. In the proposed framework, we first design in silico experiments to perturb the metabolic network in order to investigate the interested properties and then perform system identification, whereby applying principal component analysis (PCA) to the data generated by the designed in silico experiments. By combining the in silico perturbation experiments with system identification tools, biologically meaningful information contained in the complex network structure can be decomposed and translated into easily interpretable information that is useful for biologist. The PCA analysis identifies the phenotypic changes caused by oxygen supply and reveals key metabolic reactions related to redox homeostasis in different phenotypes. In addition, the influence of the cofactor preference of key enzyme (xylose reductase) in xylose metabolism is investigated using the proposed approach, and the results provide important insights on cofactor engineering of xylose metabolism.

PARSEC: PAtteRn SEarch and Contextualization

We present PARSEC (PAtteRn Search and Contextualization), a new open source platform for guided discovery, allowing localization and biological characterization of short genomic sites in entire eukaryotic genomes. PARSEC can search for a sequence or a degenerated pattern. The retrieved set of genomic sites can be characterized in terms of (i) conservation in model organisms, (ii) genomic context (proximity to genes) and (iii) function of neighboring genes. These modules allow the user to explore, visualize, filter and extract biological knowledge from a set of short genomic regions such as transcription factor binding sites. Web site implemented in Java, JavaScript and C++, with all major browsers supported. Freely available at lbgi.fr/parsec. Source code is freely available at sourceforge.net/projects/genomicparsec.

O-miner: an integrative platform for automated analysis and mining of -omics data

High-throughput profiling has generated massive amounts of data across basic, clinical and translational research fields. However, open source comprehensive web tools for analysing data obtained from different platforms and technologies are still lacking. To fill this gap and the unmet computational needs of ongoing research projects, we developed O-miner, a rapid, comprehensive, efficient web tool that covers all the steps required for the analysis of both transcriptomic and genomic data starting from raw image files through in-depth bioinformatics analysis and annotation to biological knowledge extraction. O-miner was developed from a biologist end-user perspective. Hence, it is as simple to use as possible within the confines of the complexity of the data being analysed. It provides a strong analytical suite able to overlay and harness large, complicated, raw and heterogeneous sets of profiles with biological/clinical data. Biologists can use O-miner to analyse and integrate different types of data and annotations to build knowledge of relevant altered mechanisms and pathways in order to identify and prioritize novel targets for further biological validation. Here we describe the analytical workflows currently available using O-miner and present examples of use. O-miner is freely available at www.o-miner.org.

Finding a Needle in the Virus Metagenome Haystack - Micro-Metagenome Analysis Captures a Snapshot of the Diversity of a Bacteriophage Armoire

Viruses are ubiquitous in the oceans and critical components of marine microbial communities, regulating nutrient transfer to higher trophic levels or to the dissolved organic pool through lysis of host cells. Hydrothermal vent systems are oases of biological activity in the deep oceans, for which knowledge of biodiversity and its impact on global ocean biogeochemical cycling is still in its infancy. In order to gain biological insight into viral communities present in hydrothermal vent systems, we developed a method based on deep-sequencing of pulsed field gel electrophoretic bands representing key viral fractions present in seawater within and surrounding a hydrothermal plume derived from Loki's Castle vent field at the Arctic Mid-Ocean Ridge. The reduction in virus community complexity afforded by this novel approach enabled the near-complete reconstruction of a lambda-like phage genome from the virus fraction of the plume. Phylogenetic examination of distinct gene regions in this lambdoid phage genome unveiled diversity at loci encoding superinfection exclusion- and integrase-like proteins. This suggests the importance of fine-tuning lyosgenic conversion as a viral survival strategy, and provides insights into the nature of host-virus and virus-virus interactions, within hydrothermal plumes. By reducing the complexity of the viral community through targeted sequencing of prominent dsDNA viral fractions, this method has selectively mimicked virus dominance approaching that hitherto achieved only through culturing, thus enabling bioinformatic analysis to locate a lambdoid viral “needle" within the greater viral community “haystack". Such targeted analyses have great potential for accelerating the extraction of biological knowledge from diverse and poorly understood environmental viral communities.

Efficient Computational Construction of Weighted Protein-Protein Interaction Networks Using Adaptive Filtering Techniques Combined with Natural Selection-Based Heuristic Algorithms

The analysis of protein-protein interactions (PPIs) is crucial to the understanding of cellular processes. In recent years, a variety of computational methods have been developed to supplement the interactions that have been detected experimentally. The article’s main objective is to present a novel classification framework for predicting PPIs combining the advantages of two algorithmic methods’ categories. State-of-the-art adaptive filtering techniques were combined with the most contemporary heuristic methods which are based in the natural selection process. The authors’ goal is to find a simple mathematical equation that governs the best classifier enabling the extraction of biological knowledge. The proposed methodology assigns a confidence score to each protein pair and as a result a weighted PPI network is constructed. All possible combinations of the selected adaptive filtering and heuristic techniques were used and comparisons were made to explore the classifiers with the highest performance and interpretability.

Epigenetic Control of Reprogramming and Cellular Differentiation

Epigenetic Control of Reprogramming and Cellular Differentiation

A Data-Driven Integrative Model of Sepal Primordium Polarity in Arabidopsis

Flower patterning is determined by a complex molecular network but how this network functions remains to be elucidated. Here, we develop an integrative modeling approach that assembles heterogeneous data into a biologically coherent model to allow predictions to be made and inconsistencies among the data to be found. We use this approach to study the network underlying sepal development in the young flower of Arabidopsis thaliana. We constructed a digital atlas of gene expression and used it to build a dynamical molecular regulatory network model of sepal primordium development. This led to the construction of a coherent molecular network model for lateral organ polarity that fully recapitulates expression and interaction data. Our model predicts the existence of three novel pathways involving the HD-ZIP III genes and both cytokinin and ARGONAUTE family members. In addition, our model provides predictions on molecular interactions. In a broader context, this approach allows the extraction of biological knowledge from diverse types of data and can be used to study developmental processes in any multicellular organism.