bioRxiv - Bioinformatics最新文献

{"title":"Deep learning detection of dynamic exocytosis events in fluorescence TIRF microscopy","authors":"Hugo Lachuer, Emmanuel Moebel, Anne-Sophie Mace, Arthur Masson, Kristine Schauer, Charles Kervrann","doi":"10.1101/2024.09.09.611975","DOIUrl":"https://doi.org/10.1101/2024.09.09.611975","url":null,"abstract":"Segmentation and detection of biological objects in fluorescence microscopy is of paramount importance in cell imaging. Deep learning approaches have recently shown promise to advance, automatize and accelerate analysis. However, most of the interest has been given to the segmentation of static objects of 2D/3D images whereas the segmentation of dynamic processes obtained from time-lapse acquisitions has been less explored. Here we adapted DeepFinder, a U-net originally designed for 3D noisy cryo-electron tomography (cryo-ET) data, for the detection of rare dynamic exocytosis events (termed ExoDeepFinder) observed in temporal series of 2D Total Internal Reflection Fluorescent Microscopy (TIRFM) images. ExoDeepFinder achieved good absolute performances with a relatively small training dataset of 60 cells/~12000 events. We rigorously compared deep learning performances with unsupervised conventional methods from the literature. ExoDeepFinder outcompeted the tested methods, but also exhibited a greater plasticity to the experimental conditions when tested under drug treatments and after changes in cell line or imaged reporter. This robustness to unseen experimental conditions did not require re-training demonstrating generalization capability of ExoDeepFinder. ExoDeepFinder, as well as the annotated training datasets, were made transparent and available through an open-source software as well as a Napari plugin and can directly be applied to custom user data. The apparent plasticity and performances of ExoDeepFinder to detect dynamic events open new opportunities for future deep-learning guided analysis of dynamic processes in live-cell imaging.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185494","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":"BioLP-bench: Measuring understanding of biological lab protocols by large language models","authors":"Igor Ivanov","doi":"10.1101/2024.08.21.608694","DOIUrl":"https://doi.org/10.1101/2024.08.21.608694","url":null,"abstract":"Language models rapidly become more capable in many domains, including biology. Both AI developers and policy makers are in need of benchmarks that evaluate their proficiency in conducting biological research. However, there are only a handful of such benchmarks, and all of them have their limitations. This paper introduces the Biological Lab Protocol benchmark (BioLP-bench) that evaluates the ability of language models to find and correct mistakes in a diverse set of laboratory protocols commonly used in biological research. To evaluate understanding of the protocols by AI models, we introduced in these protocols numerous mistakes that would still allow them to function correctly. After that we introduced in each protocol a single mistake that would cause it to fail. We then gave these modified protocols to an LLM, prompting it to identify the mistake that would cause it to fail, and measured the accuracy of a model in identifying such mistakes across many test cases. State-of-the-art language models demonstrated poor performance compared to human experts, and in most cases couldn't correctly identify the mistake.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142227733","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":"NucBalancer: Streamlining Barcode Sequence Selection for Optimal Sample Pooling for Sequencing","authors":"Saurabh Gupta, Ankur Sharma","doi":"10.1101/2024.09.06.611747","DOIUrl":"https://doi.org/10.1101/2024.09.06.611747","url":null,"abstract":"Recent advancements in next-generation sequencing (NGS) technologies have brought to the forefront the necessity for versatile, cost-effective tools capable of adapting to a rapidly evolving landscape. The emergence of numerous new sequencing platforms, each with unique sample preparation and sequencing requirements, underscores the importance of efficient barcode balancing for successful pooling and accurate demultiplexing of samples. Recently launched new sequencing systems claim better affordability comparable to more established platforms further exemplifies these challenges, especially when libraries originally prepared for one platform need conversion to another. In response to this dynamic environment, we introduce NucBalancer, a Shiny app developed for the optimal selection of barcode sequences. While initially tailored to meet the nucleotide, composition challenges specific to G400 and T7 series sequencers, NucBalancer's utility significantly broadens to accommodate the varied demands of these new sequencing technologies. Its application is particularly crucial in single-cell genomics, enabling the adaptation of libraries, such as those prepared for 10x technology, to various sequencers including G400 and T7 series sequencers. By facilitating the efficient balancing of nucleotide composition and the accommodation of differing sample concentrations, NucBalancer plays a pivotal role in reducing biases in nucleotide composition. This enhances the fidelity and reliability of NGS data across multiple platforms. As the NGS field continues to expand with the introduction of new sequencing technologies, the adaptability and wide-ranging applicability of NucBalancer render it an invaluable asset in genomic research. This tool addresses the current sequencing challenges ensuring that researchers can effectively balance barcodes for sample pooling regardless of the sequencing platform used.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224345","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 near-tight lower bound on the density of forward sampling schemes","authors":"Bryce Kille, Ragnar Groot Koerkamp, Drake McAdams, Alan Liu, Todd Treangen","doi":"10.1101/2024.09.06.611668","DOIUrl":"https://doi.org/10.1101/2024.09.06.611668","url":null,"abstract":"Motivation: Sampling <em>k</em>-mers is a ubiquitous task in sequence analysis algorithms. Sampling schemes such as the often-used random minimizer scheme are particularly appealing as they guarantee that at least one <em>k</em>-mer is selected out of every <em>w</em> consecutive <em>k</em>-mers. Sampling fewer <em>k</em>-mers often leads to an increase in efficiency of downstream methods. Thus, developing schemes that have low density, i.e., have a small proportion of sampled <em>k</em>-mers, is an active area of research. After over a decade of consistent efforts in both decreasing the density of practical schemes and increasing the lower bound on the best possible density, there is still a large gap between the two.\u0000Results: We prove a near-tight lower bound on the density of forward sampling schemes, a class of schemes that generalizes minimizer schemes. For small <em>w</em> and <em>k</em>, we find optimal schemes and observe that our bound is tight when <em>k</em> ≡ 1 (mod <em>w</em>). For large <em>w</em> and <em>k</em>, the bound can be approximated by 1/(<em>w</em>+<em>k</em>)·⌈(<em>w</em>+<em>k</em>)/<em>w</em>⌉. Importantly, our lower bound implies that existing schemes are much closer to achieving optimal density than previously known. For example, with the default minimap2 HiFi settings <em>w</em>=19 and <em>k</em>=19, we show that the best known scheme for these parameters, the double decycling-set-based minimizer of Pellow et al., is at most 3% denser than optimal, compared to the previous gap of at most 50%. Furthermore, when <em>k</em> ≡ 1 (mod <em>w</em>) and σ →∞, we show that mod-minimizers introduced by Groot Koerkamp and Pibiri achieve optimal density matching our lower bound.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185452","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":"CryoTEN: Efficiently Enhancing Cryo-EM Density Maps Using Transformers","authors":"Joel Selvaraj, Liguo Wang, Jianlin Cheng","doi":"10.1101/2024.09.06.611715","DOIUrl":"https://doi.org/10.1101/2024.09.06.611715","url":null,"abstract":"Cryogenic Electron Microscopy (cryo-EM) is a core experimental technique used to determine the structure of macromolecules such as proteins. However, the effectiveness of cryo-EM is often hindered by the noise and missing density values in cryo-EM density maps caused by experimental conditions such as low contrast and conformational heterogeneity. Although various global and local map sharpening techniques are widely employed to improve cryo-EM density maps, it is still challenging to efficiently improve their quality for building better protein structures from them. In this study, we introduce CryoTEN - a three-dimensional U-Net style transformer to improve cryo-EM maps effectively. CryoTEN is trained using a diverse set of 1,295 cryo-EM maps as inputs and their corresponding simulated maps generated from known protein structures as targets. An independent test set containing 150 maps is used to evaluate CryoTEN, and the results demonstrate that it can robustly enhance the quality of cryo-EM density maps. In addition, the automatic de novo protein structure modeling shows that the protein structures built from the density maps processed by CryoTEN have substantially better quality than those built from the original maps. Compared to the existing state-of-the-art deep learning methods for enhancing cryo-EM density maps, CryoTEN ranks second in improving the quality of density maps, while running &gt; 10 times faster and requiring much less GPU memory than them.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185453","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":"Structure-Based Computational Analysis of Interactions between Insulin Receptor and Insulin Inhibitory Receptor","authors":"Victor Li, Yinghao Wu","doi":"10.1101/2024.09.06.611694","DOIUrl":"https://doi.org/10.1101/2024.09.06.611694","url":null,"abstract":"The recently discovered insulin inhibitory receptor (inceptor) plays a crucial role in insulin resistance and diabetes by reducing the insulin receptor count on cell membranes, resulting in higher blood glucose levels and decreased insulin sensitivity. Therefore, understanding the mechanism of how the inceptor insulin receptor complex interacts is exceedingly important. This study uses computational drug discovery to inhibit this interaction. Initially, we employed AlphaFold-Multimer to model the inceptor-insulin receptor protein complex and subsequently identified specific inceptor residues likely involved in binding to the insulin receptor. Through virtual screening, thousands of potential small molecules were found to bind to the inceptor, and 10 with the highest probability were chosen for docking. Beta-L-fucose, beta-D-fucose, and alpha-L-fucose showed the most promising binding energies, meaning these three small molecules can effectively interrupt the binding between the complex. We also computationally mutated the binding site of the insulin receptor and calculated the change in binding energy of the inceptor insulin receptor complex, the most dramatic being a 0.4 kcal mol^-1 change when Arginine mutated to Tryptophan at residue 926. Our study suggests that the mutations led to disease primarily due to the change in interactions of the inceptor insulin receptor complex.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"125 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185454","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":"Learning phenotype associated signature in spatial transcriptomics with PASSAGE","authors":"Chen-Kai Guo, Chen-Rui Xia, Guangdun Peng, Zhi-Jie Cao, Ge Gao","doi":"10.1101/2024.09.06.611564","DOIUrl":"https://doi.org/10.1101/2024.09.06.611564","url":null,"abstract":"Spatially resolved transcriptomics (SRT) is poised to advance our understanding of cellular organization within complex tissues under various physiological and pathological conditions at unprecedented resolution. Despite the development of numerous computational tools that facilitate the automatic identification of statistically significant intra-/inter-slice patterns (like spatial domains), these methods typically operate in an unsupervised manner, without leveraging sample characteristics like physiological/pathological states. Here we present PASSAGE (Phenotype Associated Spatial Signature Analysis with Graph-based Embedding), a rationally-designed deep learning framework for characterizing phenotype-associated signatures across multiple heterogeneous spatial slices effectively. In addition to its outstanding performance in systematic benchmarks, we have demonstrated PASSAGE's unique capability in calling sophisticated signatures in multiple real-world cases. The full package of PASSAGE is available at https://github.com/gao-lab/PASSAGE.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"2677 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185457","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":"Scalable identification of lineage-specific gene regulatory networks from metacells with NetID","authors":"Weixu Wang, Yichen Wang, Ruiqi Lyu, Dominic Grün","doi":"10.1101/2024.09.08.611796","DOIUrl":"https://doi.org/10.1101/2024.09.08.611796","url":null,"abstract":"The identification of gene regulatory networks (GRN) governing distinct cell fates in multilineage cellular differentiation systems is of critical importance for understanding cell fate decision. Single-cell RNA-sequencing (scRNA-seq) provides a powerful tool for the quantification of gene-level co-variation across the cell state manifold. However, accurate GRN reconstruction is hampered by the sparsity of scRNA-seq data introducing substantial technical noise. Moreover, the high dimensionality of typical scRNA-seq datasets limits the scalability of available approaches. To overcome these challenges, and to facilitate the inference of lineage-specific GRNs with directed regulator-target relations, we introduce NetID. This approach optimizes coverage of the cell state manifold by homogenous metacells and avoids spurious gene-gene correlations observed with available imputation methods. Benchmarking demonstrates superior performance of NetID compared to imputation-based GRN inference. By incorporating cell fate probability information, NetID facilitates prediction of lineage-specific GRNs and recovers known network motifs centered around lineage-determining transcription factors governing bone marrow hematopoiesis, making it a powerful toolkit for deciphering the gene regulatory control of cellular differentiation from large-scale single-cell transcriptome data.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185458","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":"Massive Compression for High Data Rate Macromolecular Crystallography (HDRMX): Impact on Diffraction Data and Subsequent Structural Analysis","authors":"Herbert J. Bernstein, Alexei S Soares, Kimberly Horvat, Jean Jakoncic","doi":"10.1101/2024.09.06.611720","DOIUrl":"https://doi.org/10.1101/2024.09.06.611720","url":null,"abstract":"New higher-count-rate, integrating, large area X-ray detectors with framing rates as high as 17,400 images per second are beginning to be available. These will soon be used for specialized MX experiments but will require optimal lossy compression algorithms to enable systems to keep up with data throughput. Some information may be lost. Can we minimize this loss with acceptable impact on structural information? To explore this question, we have considered several approaches: summing short sequences of images, binning to create the effect of larger pixels, use of JPEG-2000 lossy wavelet-based compression, and use of Hcompress, which is a Haar-wavelet-based lossy compression borrowed from astronomy. We also explore the effect of the combination of summing, binning, and Hcompress or JPEG-2000. In each of these last two methods one can specify approximately how much one wants the result to be compressed from the starting file size. These provide particularly effective lossy compressions that retain essential information for structure solution from Bragg reflections.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224346","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":"xCell 2.0: Robust Algorithm for cell type Proportion Estimation Predicts Response to Immune Checkpoint Blockade","authors":"Almog Angel, Loai Naom, Shir Nabet-Levy, Dvir Aran","doi":"10.1101/2024.09.06.611424","DOIUrl":"https://doi.org/10.1101/2024.09.06.611424","url":null,"abstract":"Background: Accurate estimation of cell type proportions from bulk gene expression data is essential for understanding the cellular heterogeneity underlying complex tissues and diseases. Here, we introduce xCell 2.0, an advanced version of the xCell algorithm, featuring a training function that permits the utilization of any reference dataset. xCell 2.0 generates cell type gene signatures using an improved methodology, including automated handling of cell type dependencies and more robust signature generation.\u0000Methods: We benchmarked xCell 2.0 against ten popular deconvolution methods using nine human and mouse reference sets and 26 validation datasets, encompassing 1,749 samples and 67 cell types. Additionally, we validated xCell 2.0 using the independent Deconvolution DREAM Challenge dataset. As an applicative test case, we curated pan-cancer data of 2,007 patients pre-treated with immune checkpoint blockade (ICB). Features of the tumor microenvironment (TME) were generated using xCell 2.0 and other methods and fed into a LightGBM model using nested cross-validation to obtain robust predictions of ICB response.\u0000Results: Benchmarking results showed that xCell 2.0 outperformed all other tested methods across distinct reference datasets, demonstrating superior accuracy and consistency across diverse biological contexts. xCell 2.0 also showed the best performance in minimizing spillover effects between related cell types. In the ICB response prediction task, xCell 2.0-derived TME features significantly improved prediction accuracy compared to models using only cancer type and treatment information, and outperformed other deconvolution methods and established ICB prediction scores.\u0000Conclusions: xCell 2.0 is a versatile and robust tool for cell type deconvolution that maintains high performance across various reference types and biological contexts. It is available both via a web application and as a Bioconductor-compatible package, equipped with a large collection of pre-trained cell type signatures for human and mouse research. The improved prediction of ICB responses highlights the potential of xCell 2.0 to advance precision medicine in cancer and other diseases.","PeriodicalId":501307,"journal":{"name":"bioRxiv - Bioinformatics","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142185459","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}