bioRxiv - Bioinformatics最新文献

{"title":"Pangenomics to understand prophage dynamics in the Pectobacterium genus and the radiating lineages of P. brasiliense","authors":"Lakhansing A. Pardeshi, Inge van Duivenbode, Michiel J.C. Pel, Eef M. Jonkheer, Anne Kupczok, Dick de Ridder, Sandra Smit, Theo van der Lee","doi":"10.1101/2024.09.02.610764","DOIUrl":"https://doi.org/10.1101/2024.09.02.610764","url":null,"abstract":"Bacterial pathogens of the genus Pectobacterium are responsible for soft rot and blackleg disease in a wide range of crops and have a global impact on food production. The emergence of new lineages and their competitive succession is frequently observed in Pectobacterium species, in particular in P. brasiliense. With a focus on one such recently emerged P. brasiliense lineage in the Netherlands that causes blackleg in potatoes, we studied genome evolution in this genus using a reference-free graph-based pangenome approach. We clustered 1,977,865 proteins from 454 Pectobacterium spp. genomes into 30,156 homology groups. The Pectobacterium genus pangenome is open and its growth is mainly contributed by the accessory genome. Bacteriophage genes were enriched in the accessory genome and contributed 16% of the pangenome. Blackleg-causing P. brasiliense isolates had increased genome size with high levels of prophage integration. To study the diversity and dynamics of these prophages across the pangenome, we developed an approach to trace prophages across genomes using pangenome homology group signatures. We identified lineage-specific as well as generalist bacteriophages infecting Pectobacterium species. Our results capture the ongoing dynamics of mobile genetic elements, even in the clonal lineages. The observed lineage-specific prophage dynamics provide mechanistic insights into Pectobacterium pangenome growth and contribution to the radiating lineages of P. brasiliense.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"29 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mouse-Geneformer: A Deep Learning Model for Mouse Single-Cell Transcriptome and Its Cross-Species Utility","authors":"Keita Ito, Tsubasa Hirakawa, Shuji Shigenobu, Hironobu Fujiyoshi, Takayoshi Yamashita","doi":"10.1101/2024.09.09.611960","DOIUrl":"https://doi.org/10.1101/2024.09.09.611960","url":null,"abstract":"Deep learning techniques are increasingly utilized to analyze large-scale single-cell RNA sequencing (scRNA-seq) data, offering valuable insights from complex transcriptome datasets. Geneformer, a pre-trained model using a Transformer Encoder architecture and human scRNA-seq datasets, has demonstrated remarkable success in human transcriptome analysis. However, given the prominence of the mouse, Mus musculus, as a primary mammalian model in biological and medical research, there is an acute need for a mouse-specific version of Geneformer. In this study, we developed a mouse-specific Geneformer (mouse-Geneformer) by constructing a large transcriptome dataset consisting of 21 million mouse scRNA-seq profiles and pre-training Geneformer on this dataset. The mouse-Geneformer effectively models the mouse transcriptome and, upon fine-tuning for downstream tasks, enhances the accuracy of cell type classification. In silico perturbation experiments using mouse-Geneformer successfully identified disease-causing genes that have been validated in in vivo experiments. These results demonstrate the feasibility of analyzing mouse data with mouse-Geneformer and highlight the robustness of the Geneformer architecture, applicable to any species with large-scale transcriptome data available. Furthermore, we found that mouse-Geneformer can analyze human transcriptome data in a cross-species manner. After the ortholog-based gene name conversion, the analysis of human scRNA-seq data using mouse-Geneformer, followed by fine-tuning with human data, achieved cell type classification accuracy comparable to that obtained using the original human Geneformer. In in silico simulation experiments using human disease models, we obtained results similar to human-Geneformer for the myocardial infarction model but only partially consistent results for the COVID-19 model, a trait unique to humans (laboratory mice are not susceptible to SARS-CoV-2). These findings suggest the potential for cross-species application of the Geneformer model while emphasizing the importance of species-specific models for capturing the full complexity of disease mechanisms. Despite the existence of the original Geneformer tailored for humans, human research could benefit from mouse-Geneformer due to its inclusion of samples that are ethically or technically inaccessible for humans, such as embryonic tissues and certain disease models. Additionally, this cross-species approach indicates potential use for non-model organisms, where obtaining large-scale single-cell transcriptome data is challenging.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"50 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Network-based estimation of therapeutic efficacy and adverse reaction potential for prioritisation of anti-cancer drug combinations","authors":"Arindam Ghosh, Vittorio Fortino","doi":"10.1101/2024.09.17.613439","DOIUrl":"https://doi.org/10.1101/2024.09.17.613439","url":null,"abstract":"Drug combinations, although a key therapeutic agent against cancer, are yet to reach their full applicability potential due to the challenges involved in the identification of effective and safe drug pairs. In vitro or in vivo screening would have been the optimal approach if combinatorial explosion was not an issue. In silico methods, on the other hand, can enable rapid screening of drug pairs to prioritise for experimental validation. Here we present a novel network medicine approach that systematically models the proximity of drug targets to disease-associated genes and adverse effect-associated genes, through the combination of network propagation algorithm and gene set enrichment analysis. The proposed approach is applied in the context of identifying effective drug combinations for cancer treatment starting from a training set of drug combinations curated from DrugComb and DrugBank databases. We observed that effective drug combinations usually enrich disease-related gene sets while adverse drug combinations enrich adverse-effect gene sets. We use this observation to systematically train classifiers distinguishing drug combinations with higher therapeutic effects and no known adverse reaction from combinations with lower therapeutic effects and potential adverse reactions in six cancer types. The approach is tested and validated using drug combinations curated from in vitro screening data and clinical reports. Trained classification models are also used to identify novel potential anti-cancer drug combinations for experimental validation. We believe our framework would be a key addition to the anti-cancer drug combination identification pipeline by enabling rapid yet robust estimation of therapeutic efficacy or adverse reaction potential.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Guide for Active Learning in Synergistic Drug Discovery","authors":"Shuhui Wang, Alexandre Allauzen, Philippe Nghe, Vaitea Opuu","doi":"10.1101/2024.09.13.612819","DOIUrl":"https://doi.org/10.1101/2024.09.13.612819","url":null,"abstract":"Synergistic drug combination screening is a promising strategy in drug discovery, but it involves navigating a costly and complex search space. While AI, particularly deep learning, has advanced synergy predictions, its effectiveness is limited by the low occurrence of synergistic drug pairs. Active learning, which integrates experimental testing into the learning process, has been proposed to address this challenge. In this work, we explore the key components of active learning to provide recommendations for its implementation. We find that molecular encoding has a limited impact on performance, while the cellular environment features significantly enhance predictions. Additionally, active learning can discover 60% of synergistic drug pairs with only exploring 10% of combinatorial space. The synergy yield ratio is observed to be even higher with smaller batch sizes, where dynamic tuning of the exploration-exploitation strategy can further enhance performance.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"37 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pan-Cancer Genetic Analysis of Mitochondrial DNA Repair Gene Set","authors":"Angela Dong, Ayana Meegol Rasteh, Hengrui Liu","doi":"10.1101/2024.09.14.613048","DOIUrl":"https://doi.org/10.1101/2024.09.14.613048","url":null,"abstract":"Background: The mitochondrial DNA repair has gained attention for its potential impact on pan-cancer genetic analysis. This study investigates the clinical relevance of mitochondrial DNA repair genes: PARP1, DNA 2, PRIMPOL, TP53, MGME1. Methods: Using multi-omics profiling data and Gene Set Cancer Analysis (GSCA) with normalized SEM mRNA expression, this research analyzes differential expression, gene mutation, and drug correlation. Results: TP53 was the most commonly mutated mitochondrial-related gene in cancer, with UCS and OV having the highest mutation rates. CPG mutations linked to lowest survival rates. Breast cancer, with various subtypes, was potentially influenced by mitochondrial DNA repair genes. ACC was shown to be high in gene survival analysis. BRCA, USC, LUCS, COAD, and OV showed CNV levels impacting survival. A negative gene expression-methylation correlation was observed and was weakest in KIRC. Mitochondrial DNA repair genes were linked to Cell cycle_A activation. A weak correlation was found between immune infiltration and mitochondrial genes. Few drug compounds were shown to be affected by mitochondrial-related genes. Conclusion: Understanding mitochondrial-related genes could redefine cancer diagnosis, and prognosis, and serve as therapeutic biomarkers, potentially altering cancer cell behavior and treatment outcomes.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"138 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comparison of Tokenization Impact in Attention Based and State Space Genomic Language Models","authors":"LeAnn M Lindsey, Nicole L Pershing, Anisa Habib, W. Zac Stephens, Anne J Blaschke, Hari Sundar","doi":"10.1101/2024.09.09.612081","DOIUrl":"https://doi.org/10.1101/2024.09.09.612081","url":null,"abstract":"Genomic language models have recently emerged as powerful tools to decode and interpret genetic sequences. Existing genomic language models have utilized various tokenization methods including character tokenization, overlapping and non-overlapping k-mer tokenization, and byte-pair encoding, a method widely used in natural language models. Genomic models have significant differences from natural language and protein language models because of their low character variability, complex and overlapping features, and inconsistent directionality. These differences make sub-word tokenization in genomic language models significantly different from traditional language models. This study explores the impact of tokenization in attention-based and state-space genomic language models by evaluating their downstream performance on various fine-tuning tasks. We propose new definitions for fertility, the token per word ratio, in the context of genomic language models, and introduce tokenization parity, which measures how consistently a tokenizer parses homologous sequences. We also perform an ablation study on the state-space model, Mamba, to evaluate the impact of character-based tokenization compared to byte-pair encoding. Our results indicate that the choice of tokenizer significantly impacts model performance and that when experiments control for input sequence length, character tokenization is the best choice in state-space models for all evaluated task categories except epigenetic mark prediction.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"24 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerating Ligand Discovery for Insect Odorant Receptors","authors":"Arthur Comte, Maxence Lalis, Ludivine Brajon, Riccardo Moracci, Nicolas Montagné, Jérémie Topin, Emmanuelle Jacquin Joly, Sébastien Fiorucci","doi":"10.1101/2024.09.12.612620","DOIUrl":"https://doi.org/10.1101/2024.09.12.612620","url":null,"abstract":"Odorant receptors (ORs) are main actors of the insects peripheral olfactory system, making them prime targets for pest control through olfactory disruption. Traditional methods employed in the context of chemical ecology for identifying OR ligands rely on analyzing compounds present in the insect′s environment or screening molecules with structures similar to known ligands. However, these approaches can be time-consuming and constrained by the limited chemical space they explore. Recent advances in OR structural understanding, coupled with scientific breakthroughs in protein structure prediction, have facilitated the application of structure-based virtual screening (SBVS) techniques for accelerated ligand discovery. Here, we report the first successful application of SBVS to insect ORs. We developed a unique workflow that combines molecular docking predictions, in vivo validation and behavioral assays to identify new behaviorally active volatiles for non-pheromonal receptors. This work serves as a proof of concept, laying the groundwork for future studies and highlighting the need for improved computational approaches. Finally, we propose a simple model for predicting receptor response spectra based on the hypothesis that the binding pocket properties partially encode this information, as suggested by our results on Spodoptera littoralis ORs.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Evolutionary Statistics Toolkit for Simplified Sequence Analysis on Web with Client-Side Processing","authors":"Alper Karagöl, Taner Karagöl","doi":"10.1101/2024.08.01.606148","DOIUrl":"https://doi.org/10.1101/2024.08.01.606148","url":null,"abstract":"We present the Evolutionary Statistics Toolkit, a user-friendly web-based platform designed for specialized analysis of genetic sequences, which integrates multiple evolutionary statistics. The toolkit focuses on a selection of specialized tools, including Tajima's D calculator with Site Frequency Spectrum (SFS), Shannon's Entropy (H), alignment re-formatting, HGSV to FASTA conversion, pair-wise frequency analysis, FASTA to SEQRES, RNA 2D structure alignment, Kyte-Doolittle hydrophilicity plot tool and kurtosis coefficient calculator. Tajima's D is calculated using the reference formula: D = (π - θ_W)/sqrt(V_D), where π corresponds to the average number of differences, θ_W is Watterson's estimator of θ, and V_D is the variance of π - θ_W. Shannon's Entropy is defined as H = -∑ p_i* log₂(p_i), where p_i is the probability of occurrence of each unique character (nucleotide or amino acid) in the sequence. The toolkit facilitates streamlined workflows for early researchers in evolutionary biology, genomics, and related fields. With comparing with existing codes, we propose it also emerges as an educational interactive website for beginners in evolutionary statistics. The source code for each tool in the toolkit is available through GitHub links provided on the website. This open-source approach allows users to inspect the code, suggest improvements, or further adapt the tools for their specific usage and research needs. This article describes the functionalities, and validation of each tool within the platform, along with comparison with accessible existing statistical utilities. The toolkit is freely accessible on: https://www.alperkaragol.com/toolkit","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"15 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SVbyEye: A visual tool to characterize structural variation among whole-genome assemblies","authors":"David Porubsky, Xavi Guitart, DongAhn Yoo, Philip C. Dishuck, William T. Harvey, Evan E. Eichler","doi":"10.1101/2024.09.11.612418","DOIUrl":"https://doi.org/10.1101/2024.09.11.612418","url":null,"abstract":"Motivation\u0000We are now in the era of being able to routinely generate highly contiguous (near telomere-to-telomere) genome assemblies of human and nonhuman species. Complex structural variation and regions of rapid evolutionary turnover are being discovered for the first time. Thus, efficient and informative visualization tools are needed to evaluate and directly observe structural differences between two or more genomes.\u0000Results\u0000We developed SVbyEye, an open-source R package to visualize and annotate sequence-to-sequence alignments along with various functionalities to process alignments in PAF format. The tool facilitates the characterization of complex structural variants in the context of sequence homology helping resolve the mechanisms underlying their formation.\u0000Availability and implementation\u0000SVbyEye is available at https://github.com/daewoooo/SVbyEye.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"95 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CRAK-Velo: Chromatin Accessibility Kinetics integration improves RNA Velocity estimation","authors":"Nour El Kazwini, Mingze Gao, Idris Kouadri Boudjelthia, Fangxin Cai, Yuanhua Huang, Guido Sanguinetti","doi":"10.1101/2024.09.12.612736","DOIUrl":"https://doi.org/10.1101/2024.09.12.612736","url":null,"abstract":"RNA velocity has recently emerged as a key tool in the analysis of single-cell transcriptomic data, yet connecting RNA velocity analyses to underlying regulatory processes has proved challenging. Here we propose CRAK-Velo, a semi-mechanistic model which integrates chromatin accessibility data in the estimation of RNA velocities. CRAK-Velo provides biologically consistent estimates of developmental flows and enables accurate cell-type deconvolution, while additionally shining light on regulatory processes at the level of interactions between genes and chromatin regions.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"65 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142250172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}