BackgroundAlterations of metabolism, including changes in mitochondrial metabolism as well as glutathione (GSH) metabolism are a well appreciated hallmark of many cancers. Mitochondrial GSH (mGSH) transport is a poorly characterized aspect of GSH metabolism, which we investigate in the context of cancer. Existing functional annotation approaches from machine (ML) or deep learning (DL) models based only on protein sequences, were unable to annotate functions in biological contexts.ResultsWe develop a flexible ML framework for functional annotation from diverse feature data. This hybrid ML framework leverages cancer cell line multi-omics data and other biological knowledge data as features, to uncover potential genes involved in mGSH metabolism and membrane transport in cancers. This framework achieves strong performance across functional annotation tasks and several cell line and primary tumor cancer samples. For our application, classification models predict the known mGSH transporter SLC25A39 but not SLC25A40 as being highly probably related to mGSH metabolism in cancers. SLC25A10, SLC25A50, and orphan SLC25A24, SLC25A43 are predicted to be associated with mGSH metabolism in multiple biological contexts and structural analysis of these proteins reveal similarities in potential substrate binding regions to the binding residues of SLC25A39.ConclusionThese findings have implications for a better understanding of cancer cell metabolism and novel therapeutic targets with respect to GSH metabolism through potential novel functional annotations of genes. The hybrid ML framework proposed here can be applied to other biological function classifications or multi-omics datasets to generate hypotheses in various biological contexts. Code and a tutorial for generating models and predictions in this framework are available at: https://github.com/lkenn012/mGSH_cancerClassifiers.

BackgroundComprehensively mapping the hierarchical structure of breast cancer protein communities and identifying potential biomarkers from them is a promising way for breast cancer research. Existing approaches are subjective and fail to take information from protein sequences into consideration. Deep learning can automatically learn features from protein sequences and protein–protein interactions for hierarchical clustering.ResultsUsing a large amount of publicly available proteomics data, we created a hierarchical tree for breast cancer protein communities using a novel hierarchical graph neural network, with the supervision of gene ontology terms and assistance of a pre-trained deep contextual language model. Then, a group-lasso algorithm was applied to identify protein communities that are under both mutation burden and survival burden, undergo significant alterations when targeted by specific drug molecules, and show cancer-dependent perturbations. The resulting hierarchical map of protein communities shows how gene-level mutations and survival information converge on protein communities at different scales. Internal validity of the model was established through the convergence on BRCA2 as a breast cancer hotspot. Further overlaps with breast cancer cell dependencies revealed SUPT6H and RAD21, along with their respective protein systems, HOST:37 and HOST:861, as potential biomarkers. Using gene-level perturbation data of the HOST:37 and HOST:861 gene sets, three FDA-approved drugs with high therapeutic value were selected as potential treatments to be further evaluated. These drugs include mercaptopurine, pioglitazone, and colchicine.ConclusionThe proposed graph neural network approach to analyzing breast cancer protein communities in a hierarchical structure provides a novel perspective on breast cancer prognosis and treatment. By targeting entire gene sets, we were able to evaluate the prognostic and therapeutic value of genes (or gene sets) at different levels, from gene-level to system-level biology. Cancer-specific gene dependencies provide additional context for pinpointing cancer-related systems and drug-induced alterations can highlight potential therapeutic targets. These identified protein communities, in conjunction with other protein communities under strong mutation and survival burdens, can potentially be used as clinical biomarkers for breast cancer.

BackgroundPacific Biosciences (PacBio) circular consensus sequencing (CCS), also known as high fidelity (HiFi) technology, has revolutionized modern genomics by producing long (10 + kb) and highly accurate reads. This is achieved by sequencing circularized DNA molecules multiple times and combining them into a consensus sequence. Currently, the accuracy and quality value estimation provided by HiFi technology are more than sufficient for applications such as genome assembly and germline variant calling. However, there are limitations in the accuracy of the estimated quality scores when it comes to somatic variant calling on single reads.ResultsTo address the challenge of inaccurate quality scores for somatic variant calling, we introduce TopoQual, a novel tool designed to enhance the accuracy of base quality predictions. TopoQual leverages techniques including partial order alignments (POA), topologically parallel bases, and deep learning algorithms to polish consensus sequences. Our results demonstrate that TopoQual corrects approximately 31.9% of errors in PacBio consensus sequences. Additionally, it validates base qualities up to q59, which corresponds to one error in 0.9 million bases. These improvements will significantly enhance the reliability of somatic variant calling using HiFi data.ConclusionTopoQual represents a significant advancement in genomics by improving the accuracy of base quality predictions for PacBio HiFi sequencing data. By correcting a substantial proportion of errors and achieving high base quality validation, TopoQual enables confident and accurate somatic variant calling. This tool not only addresses a critical limitation of current HiFi technology but also opens new possibilities for precise genomic analysis in various research and clinical applications.

BackgroundDeoxyribozymes or DNAzymes represent artificial short DNA sequences bearing many catalytic properties. In particular, DNAzymes able to cleave RNA sequences have a huge potential in gene therapy and sequence-specific analytic detection of disease markers. This activity is provided by catalytic cores able to perform site-specific hydrolysis of the phosphodiester bond of an RNA substrate. However, the vast majority of existing DNAzyme catalytic cores have low efficacy in in vivo experiments, whereas SELEX based on in vitro screening offers long and expensive selection cycle with the average success rate of ~ 30%, moreover not allowing the direct selection of chemically modified DNAzymes, which were previously shown to demonstrate higher activity in vivo. Therefore, there is a huge need in in silico approach for exploratory analysis of RNA-cleaving DNAzyme cores to drastically ease the discovery of novel catalytic cores with superior activities.ResultsIn this work, we develop a machine learning based open-source platform SequenceCraft allowing experimental scientists to perform DNAzyme exploratory analysis via quantitative observed rate constant (kobs) estimation as well as statistical and clustering data analysis. This became possible with the development of a unique curated database of > 350 RNA-cleaving catalytic cores, property-based sequence representations allowing to work with both conventional and chemically modified nucleotides, and optimized kobs predicting algorithm achieving Q2 > 0.9 on experimental data published to date.ConclusionsThis work represents a significant advancement in DNAzyme research, providing a tool for more efficient discovery of RNA-cleaving DNAzymes. The SequenceCraft platform offers an in silico alternative to traditional experimental approaches, potentially accelerating the development of DNAzymes.

BackgroundCRISPRi screening has become a powerful approach for functional genomic research. However, the off-target effects resulting from the mismatch tolerance between sgRNAs and their intended targets is a primary concern in CRISPRi applications.ResultsWe introduce Guide Library Designer (GLiDe), a web-based tool specifically created for the genome-scale design of sgRNA libraries tailored for CRISPRi screening in prokaryotic organisms. GLiDe incorporates a robust quality control framework, rooted in prior experimental knowledge, ensuring the accurate identification of off-target hits. It boasts an extensive built-in database, encompassing 1,397 common prokaryotic species as a comprehensive design resource. It also provides the capability to design sgRNAs for newly discovered organisms by accepting uploaded design resource. We further demonstrated that GLiDe exhibits enhanced precision in identifying off-target binding sites for the CRISPRi system.ConclusionsWe present a web server that allows the construction of genome-scale CRISPRi sgRNA libraries for prokaryotes. It mitigates off-target effects through a robust quality control framework, leveraging prior experimental knowledge within an end-to-end, user-friendly pipeline.

BackgroundCancer classification has consistently been a challenging problem, with the main difficulties being high-dimensional data and the collection of patient samples. Concretely, obtaining patient samples is a costly and resource-intensive process, and imbalances often exist between samples. Moreover, expression data is characterized by high dimensionality, small samples and high noise, which could easily lead to struggles such as dimensionality catastrophe and overfitting. Thus, we incorporate prior knowledge from the pathway and combine AutoEncoder and Generative Adversarial Network (GAN) to solve these difficulties.ResultsIn this study, we propose an effective and efficient deep learning method, named AEGAN, which combines the capabilities of AutoEncoder and GAN to generate synthetic samples of the minority class in imbalanced gene expression data. The proposed data balancing technique has been demonstrated to be useful for cancer classification and improving the performance of classifier models. Additionally, we integrate prior knowledge from the pathway and employ the pathifier algorithm to calculate pathway scores for each sample. This data augmentation approach, referred to as AEGAN-Pathifier, not only preserves the biological functionality of the data but also possesses dimensional reduction capabilities. Through validation with various classifiers, the experimental results show an improvement in classifier performance.ConclusionAEGAN-Pathifier shows improved performance on the imbalanced datasets GSE25066, GSE20194, BRCA and Liver24. Results from various classifiers indicate that AEGAN-Pathifier has good generalization capability.

High-dimensional datasets with low sample sizes (HDLSS) are pivotal in the fields of biology and bioinformatics. One of core objective of HDLSS is to select most informative features and discarding redundant or irrelevant features. This is particularly crucial in bioinformatics, where accurate feature (gene) selection can lead to breakthroughs in drug development and provide insights into disease diagnostics. Despite its importance, identifying optimal features is still a significant challenge in HDLSS. To address this challenge, we propose an effective feature selection method that combines gradual permutation filtering with a heuristic tribrid search strategy, specifically tailored for HDLSS contexts. The proposed method considers inter-feature interactions and leverages feature rankings during the search process. In addition, a new performance metric for the HDLSS that evaluates both the number and quality of selected features is suggested. Through the comparison of the benchmark dataset with existing methods, the proposed method reduced the average number of selected features from 37.8 to 5.5 and improved the performance of the prediction model, based on the selected features, from 0.855 to 0.927. The proposed method effectively selects a small number of important features and achieves high prediction performance.

BackgroundUsing information measures to infer biological regulatory networks can capture nonlinear relationships between variables. However, it is computationally challenging, and there is a lack of convenient tools.ResultsWe introduce Informeasure, an R package designed to quantify nonlinear dependencies in biological regulatory networks from an information theory perspective. This package compiles a comprehensive set of information measurements, including mutual information, conditional mutual information, interaction information, partial information decomposition, and part mutual information. Mutual information is used for bivariate network inference, while the other four estimators are dedicated to trivariate network analysis.ConclusionsInformeasure is a turnkey solution, allowing users to utilize these information measures immediately upon installation. Informeasure is available as an R/Bioconductor package at https://bioconductor.org/packages/Informeasure.

BackgroundExisting software for comparison of species delimitation models do not provide a (true) metric or distance functions between species delimitation models, nor a way to compare these models in terms of relative clustering differences along a lattice of partitions.ResultsPiikun is a Python package for analyzing and visualizing species delimitation models in an information theoretic framework that, in addition to classic measures of information such as the entropy and mutual information [1], provides for the calculation of the Variation of Information (VI) criterion [2], a true metric or distance function for species delimitation models that is aligned with the lattice of partitions.ConclusionsPiikun is available under the MIT license from its public repository ( https://github.com/jeetsukumaran/piikun), and can be installed locally using the Python package manager ‘pip‘.

BackgroundMethods to call, analyze and visualize copy number variations (CNVs) from massive parallel sequencing data have been widely adopted in clinical practice and genetic research. To enable a streamlined analysis of CNV data, comprehensive annotations and good visualizations are indispensable. The ability to detect single exon CNVs is another important feature for genetic testing. Nonetheless, most available open-source tools come with limitations in at least one of these areas. One additional drawback is that available tools deliver data in an unstructured and static format which requires subsequent visualization and formatting efforts.ResultsHere we present CNVizard, an interactive Streamlit app allowing a comprehensive visualization of CNVkit data. Furthermore, combining CNVizard with the CNVand pipeline allows the annotation and visualization of CNV or SV VCF files from any CNV caller.ConclusionCNVizard, in combination with CNVand, enables the comprehensive and streamlined analysis of short- and long-read sequencing data and provide an intuitive webapp-like experience enabling an interactive visualization of CNV data.