High-throughput Molecular Data Research Articles

ITree: a user-driven tool for interactive decision-making with classification trees.

ITree is an intuitive web tool for the manual, semi-automatic, and automatic induction of decision trees. It enables interactive modifications of tree structures and incorporates Relative Expression Analysis for detecting complex patterns in high-throughput molecular data. This makes ITree a versatile tool for both research and education in biomedical data analysis. The tool allows users to instantly see the effects of modifications on decision trees, with updates to predictions and statistics displayed in real time, facilitating a deeper understanding of data classification processes. Available online at https://itree.wi.pb.edu.pl. Source code and documentation are hosted on GitHub at https://github.com/hsokolowski/iTree and in supplement.

Phylogenomics of Neogastropoda: the backbone hidden in the bush.

The molluscan order Neogastropoda encompasses over 15,000 almost exclusively marine species playing important roles in benthic communities and in the economies of coastal countries. Neogastropoda underwent intensive cladogenesis in early stages of diversification, generating a 'bush' at the base of their evolutionary tree, that has been hard to resolve even with high throughput molecular data. In the present study to resolve the bush, we use a variety of phylogenetic inference methods and a comprehensive exon capture dataset of 1,817 loci (79.6% data occupancy) comprising 112 taxa of 48 out of 60 Neogastropoda families. Our results show consistent topologies and high support in all analyses at (super)family level, supporting monophyly of Muricoidea, Mitroidea, Conoidea, and, with some reservations, Olivoidea and Buccinoidea. Volutoidea and Turbinelloidea as currently circumscribed are clearly paraphyletic. Despite our analyses consistently resolving most backbone nodes, three prove problematic: First, uncertain placement of Cancellariidae, as the sister group to either a Ficoidea-Tonnoidea clade, or to the rest of Neogastropoda, leaves monophyly of Neogastropoda unresolved. Second, relationships are contradictory at the base of the major 'core Neogastropoda' grouping. Third, coalescence-based analyses reject monophyly of the Buccinoidea in relation to Vasidae. We analysed phylogenetic signal of targeted loci in relation to potential biases, and we propose most probable resolutions in the latter two recalcitrant nodes. The uncertain placement of Cancellariidae may be explained by orthology violations due to differential paralog loss shortly after the whole genome duplication, which should be resolved with a curated set of longer loci.

PyComBat, a Python tool for batch effects correction in high-throughput molecular data using empirical Bayes methods

BackgroundVariability in datasets is not only the product of biological processes: they are also the product of technical biases. ComBat and ComBat-Seq are among the most widely used tools for correcting those technical biases, called batch effects, in, respectively, microarray and RNA-Seq expression data.ResultsIn this technical note, we present a new Python implementation of ComBat and ComBat-Seq. While the mathematical framework is strictly the same, we show here that our implementations: (i) have similar results in terms of batch effects correction; (ii) are as fast or faster than the original implementations in R and; (iii) offer new tools for the bioinformatics community to participate in its development. pyComBat is implemented in the Python language and is distributed under GPL-3.0 (https://www.gnu.org/licenses/gpl-3.0.en.html) license as a module of the inmoose package. Source code is available at https://github.com/epigenelabs/inmoose and Python package at https://pypi.org/project/inmoose.ConclusionsWe present a new Python implementation of state-of-the-art tools ComBat and ComBat-Seq for the correction of batch effects in microarray and RNA-Seq data. This new implementation, based on the same mathematical frameworks as ComBat and ComBat-Seq, offers similar power for batch effect correction, at reduced computational cost.

Integrated Network Analysis of microRNAs, mRNAs, and Proteins Reveals the Regulatory Interaction between hsa-mir-200b and CFL2 Associated with Advanced Stage and Poor Prognosis in Patients with Intestinal Gastric Cancer.

Intestinal gastric cancer (IGC) carcinogenesis results from a complex interplay between environmental and molecular factors, ultimately contributing to disease development. We used integrative bioinformatic analysis to investigate IGC high-throughput molecular data to uncover interactions among differentially expressed genes, microRNAs, and proteins and their roles in IGC. An integrated network was generated based on experimentally validated microRNA-gene/protein interaction data, with three regulatory circuits involved in a complex network contributing to IGC progression. Key regulators were determined, including 23 microRNA and 15 gene/protein hubs. The regulatory circuit networks were associated with hallmarks of cancer, e.g., cell death, apoptosis and the cell cycle, the immune response, and epithelial-to-mesenchymal transition, indicating that different mechanisms of gene regulation impact similar biological functions. Altered expression of hubs was related to the clinicopathological characteristics of IGC patients and showed good performance in discriminating tumors from adjacent nontumor tissues and in relation to T stage and overall survival (OS). Interestingly, expression of upregulated hub hsa-mir-200b and its downregulated target hub gene/protein CFL2 were related not only to pathological T staging and OS but also to changes during IGC carcinogenesis. Our study suggests that regulation of CFL2 by hsa-miR-200b is a dynamic process during tumor progression and that this control plays essential roles in IGC development. Overall, the results indicate that this regulatory interaction is an important component in IGC pathogenesis. Also, we identified a novel molecular interplay between microRNAs, proteins, and genes associated with IGC in a complex biological network and the hubs closely related to IGC carcinogenesis as potential biomarkers.

SMG: self-supervised masked graph learning for cancer gene identification.

Cancer genomics is dedicated to elucidating the genes and pathways that contribute to cancer progression and development. Identifying cancer genes (CGs) associated with the initiation and progression of cancer is critical for characterization of molecular-level mechanism in cancer research. In recent years, the growing availability of high-throughput molecular data and advancements in deep learning technologies has enabled the modelling of complex interactions and topological information within genomic data. Nevertheless, because of the limited labelled data, pinpointing CGs from a multitude of potential mutations remains an exceptionally challenging task. To address this, we propose a novel deep learning framework, termed self-supervised masked graph learning (SMG), which comprises SMG reconstruction (pretext task) and task-specific fine-tuning (downstream task). In the pretext task, the nodes of multi-omic featured protein-protein interaction (PPI) networks are randomly substituted with a defined mask token. The PPI networks are then reconstructed using the graph neural network (GNN)-based autoencoder, which explores the node correlations in a self-prediction manner. In the downstream tasks, the pre-trained GNN encoder embeds the input networks into feature graphs, whereas a task-specific layer proceeds with the final prediction. To assess the performance of the proposed SMG method, benchmarking experiments are performed on three node-level tasks (identification of CGs, essential genes and healthy driver genes) and one graph-level task (identification of disease subnetwork) across eight PPI networks. Benchmarking experiments and performance comparison with existing state-of-the-art methods demonstrate the superiority of SMG on multi-omic feature engineering.

Deep transfer learning for clinical decision-making based on high-throughput data: comprehensive survey with benchmark results.

The rapid growth of omics-based data has revolutionized biomedical research and precision medicine, allowing machine learning models to be developed for cutting-edge performance. However, despite the wealth of high-throughput data available, the performance of these models is hindered by the lack of sufficient training data, particularly in clinical research (in vivo experiments). As a result, translating this knowledge into clinical practice, such as predicting drug responses, remains a challenging task. Transfer learning is a promising tool that bridges the gap between data domains by transferring knowledge from the source to the target domain. Researchers have proposed transfer learning to predict clinical outcomes by leveraging pre-clinical data (mouse, zebrafish), highlighting its vast potential. In this work, we present a comprehensive literature review of deep transfer learning methods for health informatics and clinical decision-making, focusing on high-throughput molecular data. Previous reviews mostly covered image-based transfer learning works, while we present a more detailed analysis of transfer learning papers. Furthermore, we evaluated original studies based on different evaluation settings across cross-validations, data splits and model architectures. The result shows that those transfer learning methods have great potential; high-throughput sequencing data and state-of-the-art deep learning models lead to significant insights and conclusions. Additionally, we explored various datasets in transfer learning papers with statistics and visualization.

A Call for Discovery and Therapeutic Development for Cutaneous Neurofibromas

A Call for Discovery and Therapeutic Development for Cutaneous Neurofibromas

Abstract LB290: Intracranial, intratumoral drug-releasing microdevices in patients with high grade gliomas may identify biomarkers of drug activity and predict tumor response to systemic chemotherapy

Abstract The lack of reliable predictive biomarkers to guide effective therapy is a major obstacle for the advancement of therapy for high grade gliomas (HGG), and particularly glioblastoma (GBM), one of the few cancers whose prognosis has not improved over the past several decades. With this pilot clinical trial we provide first in human evidence that drug-releasing intratumoral microdevices (IMD) can be safely and effectively used to obtain patient-specific, high throughput molecular and histopathological data to inform selection of drugs based on their observed antitumor effect in situ. The use of IMD is seamlessly integrated in standard surgical practice during tumor resection. None of the six enrolled patients experienced adverse events related to the IMD, and the retrieved tissue was usable for downstream analysis for 11 out of 12 retrieved specimens. Molecular analysis of the specimens provided, for the first time in humans, preliminary evidence of the robustness of the readout, with strong correlation between IMD analysis and clinic-radiological responses to temozolomide. We also identified novel transcriptomic and metabolomic biomarkers of response and resistance to a range of targeted and cytotoxic agents used on the IMD. From an investigational aspect, the amount of information obtained with IMD allows unprecedented characterization of tissue effects of any drugs of interest, within the physiological context of the intact tumor. Citation Format: Oliver Jonas, Pier Paolo Peruzzi. Intracranial, intratumoral drug-releasing microdevices in patients with high grade gliomas may identify biomarkers of drug activity and predict tumor response to systemic chemotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB290.

A unified mediation analysis framework for integrative cancer proteogenomics with clinical outcomes.

Multilevel molecular profiling of tumors and the integrative analysis with clinical outcomes have enabled a deeper characterization of cancer treatment. Mediation analysis has emerged as a promising statistical tool to identify and quantify the intermediate mechanisms by which a gene affects an outcome. However, existing methods lack a unified approach to handle various types of outcome variables, making them unsuitable for high-throughput molecular profiling data with highly interconnected variables. We develop a general mediation analysis framework for proteogenomic data that include multiple exposures, multivariate mediators on various scales of effects as appropriate for continuous, binary and survival outcomes. Our estimation method avoids imposing constraints on model parameters such as the rare disease assumption, while accommodating multiple exposures and high-dimensional mediators. We compare our approach to other methods in extensive simulation studies at a range of sample sizes, disease prevalence and number of false mediators. Using kidney renal clear cell carcinoma proteogenomic data, we identify genes that are mediated by proteins and the underlying mechanisms on various survival outcomes that capture short- and long-term disease-specific clinical characteristics. Software is made available in an R package (https://github.com/longjp/mediateR). Supplementary data are available at Bioinformatics online.

CTNI-11. DEEP PHENOTYPING OF MULTI DRUG RESPONSES IN PATIENTS WITH GLIOMAS USING TUMOR-EMBEDDED MICRODEVICES

Abstract The lack of reliable predictive biomarkers to guide effective therapy is a major obstacle for the advancement of therapy for high grade gliomas (HGG), and particularly glioblastoma (GBM), one of the few cancers whose prognosis has not improved over the past several decades. With this pilot clinical trial we provide first in human evidence that drug-releasing intratumoral microdevices (IMD) can be safely and effectively used to obtain patient-specific, high throughput molecular and histopathological data to inform selection of drugs based on their observed antitumor effect in situ. The use of IMD is seamlessly integrated in standard surgical practice during tumor resection. None of the six enrolled patients experienced adverse events related to the IMD, and the retrieved tissue was usable for downstream analysis for 11 out of 12 retrieved specimens. Molecular analysis of the specimens provided, for the first time in humans, preliminary evidence of the robustness of the readout, with strong correlation between IMD analysis and clinic-radiological responses to temozolomide. From an investigational aspect, the amount of information obtained with IMD allows unprecedented characterization of tissue effects of any drugs of interest, within the physiological context of the intact tumor.

15. Standard procedure for the curation and maintenance of cancer-specific gene lists

The efficient analysis and interpretation of high throughput molecular genomics data are contingent upon reliable and current evidence-based resources. Gene lists to identify regions of diagnostic, prognostic, or therapeutic importance have become integral in the analysis of many clinical genomic tests, including chromosomal/SNP microarrays, NGS (Next Generation Sequencing) panels, and targeted whole exome/genome sequencing. Two Cancer Genomics Consortium (CGC) working groups in collaboration with the Mayo Clinic Genomics of Oncology Annotation Team (GOAT) have curated myeloid neoplasms and breast cancer gene lists with vetted annotation.

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.

Prediction of tumor purity from gene expression data using machine learning.

Bulk tumor samples used for high-throughput molecular profiling are often an admixture of cancer cells and non-cancerous cells, which include immune and stromal cells. The mixed composition can confound the analysis and affect the biological interpretation of the results, and thus, accurate prediction of tumor purity is critical. Although several methods have been proposed to predict tumor purity using high-throughput molecular data, there has been no comprehensive study on machine learning-based methods for the estimation of tumor purity. We applied various machine learning models to estimate tumor purity. Overall, the models predicted the tumor purity accurately and showed a high correlation with well-established gold standard methods. In addition, we identified a small group of genes and demonstrated that they could predict tumor purity well. Finally, we confirmed that these genes were mainly involved in the immune system. The machine learning models constructed for this study are available at https://github.com/BonilKoo/ML_purity.

Molecular diet analysis of neotropical bats based on fecal DNA metabarcoding.

Bat communities in the Neotropics are some of the most speciose assemblages of mammals on Earth, with regions supporting more than 100 sympatric species with diverse feeding ecologies. Because bats are small, nocturnal, and volant, it is difficult to directly observe their feeding habits, which has resulted in their classification into broadly defined dietary guilds (e.g., insectivores, carnivores, and frugivores). Apart from these broad guilds, we lack detailed dietary information for many species and therefore have only a limited understanding of interaction networks linking bats and their diet items. In this study, we used DNA metabarcoding of plants, arthropods, and vertebrates to investigate the diets of 25 bat species from the tropical dry forests of Lamanai, Belize. Our results report some of the first detection of diet items for the focal bat taxa, adding rich and novel natural history information to the field of bat ecology. This study represents a comprehensive first effort to apply DNA metabarcoding to bat diets at Lamanai and provides a useful methodological framework for future studies testing hypotheses about coexistence and niche differentiation in the context of modern high‐throughput molecular data.

Integration of multiomics data with graph convolutional networks to identify new cancer genes and their associated molecular mechanisms

The increase in available high-throughput molecular data creates computational challenges for the identification of cancer genes. Genetic as well as non-genetic causes contribute to tumorigenesis, and this necessitates the development of predictive models to effectively integrate different data modalities while being interpretable. We introduce EMOGI, an explainable machine learning method based on graph convolutional networks to predict cancer genes by combining multiomics pan-cancer data—such as mutations, copy number changes, DNA methylation and gene expression—together with protein–protein interaction (PPI) networks. EMOGI was on average more accurate than other methods across different PPI networks and datasets. We used layer-wise relevance propagation to stratify genes according to whether their classification was driven by the interactome or any of the omics levels, and to identify important modules in the PPI network. We propose 165 novel cancer genes that do not necessarily harbour recurrent alterations but interact with known cancer genes, and we show that they correspond to essential genes from loss-of-function screens. We believe that our method can open new avenues in precision oncology and be applied to predict biomarkers for other complex diseases. Identifying cancer driver genes from high-throughput genomic data is an important task to understand the molecular basis of cancer and to develop new treatments including precision medicine. To tackle this challenge, EMOGI, a new deep learning method based on graph convolutional networks is developed, which combines protein–protein interaction networks with multiomics datasets.

The development of a comprehensive toolbox based on multi-level, high-throughput screening of MOFs for CO/N2 separations.

The separation of CO/N2 mixtures is a challenging problem in the petrochemical sector due to the very similar physical properties of these two molecules, such as size, molecular weight and boiling point. To solve this and other challenging gas separations, one requires a holistic approach. The complexity of a screening exercise for adsorption-based separations arises from the multitude of existing porous materials, including metal–organic frameworks. Besides, the multivariate nature of the performance criteria that needs to be considered when designing an optimal adsorbent and a separation process – i.e. an optimal material requires fulfillment of several criteria simultaneously – makes the screening challenging. To address this, we have developed a multi-scale approach combining high-throughput molecular simulation screening, data mining and advanced visualization, as well as process system modelling, backed up by experimental validation. We have applied our recent advances in the engineering of porous materials' morphology to develop advanced monolithic structures. These conformed, shaped monoliths can be used readily in industrial applications, bringing a valuable strategy for the development of advanced materials. This toolbox is flexible enough to be applied to multiple adsorption-based gas separation applications.

Functional analysis of cancer gene subtype from co-clustering and classification

<span lang="EN-MY">Cancer is a heterogeneity genetic disease with huge phenotypic alterations among dissimilar cancers types or even between same cancer types. Recent expansions of genome-wide profiling technologies offer a chance to explore molecular changes variations throughout advancement of cancer. Therefore, various statistical and machine learning algorithms have been designed and developed for the handling and interpretation of high-throughput microarray molecular data. Discovery of molecular subtypes studies have permitted the cancer to be allocated into similar groups that are deliberated to port similar molecular and clinical characteristics. Thus, the main objective of this research is to discover cancer gene subtypes and classify genes to obtain higher accuracy. In particular improved co-clustering algorithm used to discover cancer subtypes. And then supervised infinite feature selection gene selection method was combined with multi class SVM for classification of selected genes and further biological analysis. The analysis on breast cancer and glioblastoma multiforme evidences that top genes involved in cancer and the pathways present in both cancer top genes. The functional analysis is useful in medical and pharmaceutical field for cancer diagnosis and prognosis.</span>

Flexible Data Trimming Improves Performance of Global Machine Learning Methods in Omics-Based Personalized Oncology.

(1) Background: Machine learning (ML) methods are rarely used for an omics-based prescription of cancer drugs, due to shortage of case histories with clinical outcome supplemented by high-throughput molecular data. This causes overtraining and high vulnerability of most ML methods. Recently, we proposed a hybrid global-local approach to ML termed floating window projective separator (FloWPS) that avoids extrapolation in the feature space. Its core property is data trimming, i.e., sample-specific removal of irrelevant features. (2) Methods: Here, we applied FloWPS to seven popular ML methods, including linear SVM, k nearest neighbors (kNN), random forest (RF), Tikhonov (ridge) regression (RR), binomial naïve Bayes (BNB), adaptive boosting (ADA) and multi-layer perceptron (MLP). (3) Results: We performed computational experiments for 21 high throughput gene expression datasets (41–235 samples per dataset) totally representing 1778 cancer patients with known responses on chemotherapy treatments. FloWPS essentially improved the classifier quality for all global ML methods (SVM, RF, BNB, ADA, MLP), where the area under the receiver-operator curve (ROC AUC) for the treatment response classifiers increased from 0.61–0.88 range to 0.70–0.94. We tested FloWPS-empowered methods for overtraining by interrogating the importance of different features for different ML methods in the same model datasets. (4) Conclusions: We showed that FloWPS increases the correlation of feature importance between the different ML methods, which indicates its robustness to overtraining. For all the datasets tested, the best performance of FloWPS data trimming was observed for the BNB method, which can be valuable for further building of ML classifiers in personalized oncology.

Quantitation of Molecular Pathway Activation Using RNA Sequencing Data.

Intracellular molecular pathways (IMPs) control all major events in the living cell. IMPs are considered hotspots in biomedical sciences and thousands of IMPs have been discovered for humans and model organisms. Knowledge of IMPs activation is essential for understanding biological functions and differences between the biological objects at the molecular level. Here we describe the Oncobox system for accurate quantitative scoring activities of up to several thousand molecular pathways based on high throughput molecular data. Although initially designed for gene expression and mainly RNA sequencing data, Oncobox is now also applicable for quantitative proteomics, microRNA and transcription factor binding sites mapping data. The Oncobox system includes modules of gene expression data harmonization, aggregation and comparison and a recursive algorithm for automatic annotation of molecular pathways. The universal rationale of Oncobox enables scoring of signaling, metabolic, cytoskeleton, immunity, DNA repair, and other pathways in a multitude of biological objects. The Oncobox system can be helpful to all those working in the fields of genetics, biochemistry, interactomics, and big data analytics in molecular biomedicine.

Paving the Way to Precision Nutrition Through Metabolomics.

Nutrition is an interdisciplinary science that studies the interactions of nutrients with the body in relation to maintenance of health and well-being. Nutrition is highly complex due to the underlying various internal and external factors that could model it. Thus, hacking this complexity requires more holistic and network-based strategies that could unveil these dynamic system interactions at both time and space scales. The ongoing omics era with its high-throughput molecular data generation is paving the way to embrace this complexity and is deeply reshaping the whole field of nutrition. Understanding the future paths of nutrition science is of importance from both translational and clinical perspectives. Basic nutrients which might include metabolites are important in nutrition science. Moreover, metabolites are key biological communication channels and represent an appealing functional readout at the interface of different major influential factors that define health and disease. Metabolomics is the technology that enables holistic and systematic analyses of metabolites in a biological system. Hence, given its intrinsic functionality, its tight connection to metabolism and its high clinical actionability potential, metabolomics is a very appealing technology for nutrition science. The ultimate goal is to deliver a tailored and clinically relevant nutritional recommendations and interventions to achieve precision nutrition. This work intends to present an update on the applications of metabolomics to personalize nutrition in translational and clinical settings. It also discusses the current conceptual shifts that are remodeling clinical nutrition practices in this Precision Medicine era. Finally, perspectives of clinical nutrition in the ever-growing, data-driven healthcare landscape are presented.