1
|
Tsukiyama S, Hasan MM, Kurata H. CNN6mA: Interpretable neural network model based on position-specific CNN and cross-interactive network for 6mA site prediction. Comput Struct Biotechnol J 2022; 21:644-654. [PMID: 36659917 PMCID: PMC9826936 DOI: 10.1016/j.csbj.2022.12.043] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2022] [Revised: 12/26/2022] [Accepted: 12/27/2022] [Indexed: 12/29/2022] Open
Abstract
N6-methyladenine (6mA) plays a critical role in various epigenetic processing including DNA replication, DNA repair, silencing, transcription, and diseases such as cancer. To understand such epigenetic mechanisms, 6 mA has been detected by high-throughput technologies on a genome-wide scale at single-base resolution, together with conventional methods such as immunoprecipitation, mass spectrometry and capillary electrophoresis, but these experimental approaches are time-consuming and laborious. To complement these problems, we have developed a CNN-based 6 mA site predictor, named CNN6mA, which proposed two new architectures: a position-specific 1-D convolutional layer and a cross-interactive network. In the position-specific 1-D convolutional layer, position-specific filters with different window sizes were applied to an inquiry sequence instead of sharing the same filters over all positions in order to extract the position-specific features at different levels. The cross-interactive network explored the relationships between all the nucleotide patterns within the inquiry sequence. Consequently, CNN6mA outperformed the existing state-of-the-art models in many species and created the contribution score vector that intelligibly interpret the prediction mechanism. The source codes and web application in CNN6mA are freely accessible at https://github.com/kuratahiroyuki/CNN6mA.git and http://kurata35.bio.kyutech.ac.jp/CNN6mA/, respectively.
Collapse
Key Words
- 6mA, N6-methyladenine
- AUCs, Area under the curves
- BERT, Bidirectional Encoder Representations from Transformers
- CNN
- CNN, Convolutional neural network
- DNA modification
- Deep learning
- Interpretable prediction
- LSTM, Long short-term memory
- MCC, Matthews correlation coefficient
- Machine learning
- N6-methyladenine
- RF, Random forest
- SMRT, Single-molecule real-time
- SN, Sensitivity
- SP, Specificity
- UMAP, Uniform manifold approximation and projection
- t-SNE, t-distributed stochastic neighbor embedding
Collapse
Affiliation(s)
- Sho Tsukiyama
- Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680–4 Kawazu, Iizuka, Fukuoka 820-8502, Japan
| | - Md Mehedi Hasan
- Tulane Center for Aging and Department of Medicine, Tulane University Health Sciences Center, New Orleans, LA 70112, USA
| | - Hiroyuki Kurata
- Department of Bioscience and Bioinformatics, Kyushu Institute of Technology, 680–4 Kawazu, Iizuka, Fukuoka 820-8502, Japan,Corresponding author.
| |
Collapse
|
2
|
Kleino I, Frolovaitė P, Suomi T, Elo LL. Computational solutions for spatial transcriptomics. Comput Struct Biotechnol J 2022; 20:4870-4884. [PMID: 36147664 PMCID: PMC9464853 DOI: 10.1016/j.csbj.2022.08.043] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 08/18/2022] [Accepted: 08/18/2022] [Indexed: 11/18/2022] Open
Abstract
Transcriptome level expression data connected to the spatial organization of the cells and molecules would allow a comprehensive understanding of how gene expression is connected to the structure and function in the biological systems. The spatial transcriptomics platforms may soon provide such information. However, the current platforms still lack spatial resolution, capture only a fraction of the transcriptome heterogeneity, or lack the throughput for large scale studies. The strengths and weaknesses in current ST platforms and computational solutions need to be taken into account when planning spatial transcriptomics studies. The basis of the computational ST analysis is the solutions developed for single-cell RNA-sequencing data, with advancements taking into account the spatial connectedness of the transcriptomes. The scRNA-seq tools are modified for spatial transcriptomics or new solutions like deep learning-based joint analysis of expression, spatial, and image data are developed to extract biological information in the spatially resolved transcriptomes. The computational ST analysis can reveal remarkable biological insights into spatial patterns of gene expression, cell signaling, and cell type variations in connection with cell type-specific signaling and organization in complex tissues. This review covers the topics that help choosing the platform and computational solutions for spatial transcriptomics research. We focus on the currently available ST methods and platforms and their strengths and limitations. Of the computational solutions, we provide an overview of the analysis steps and tools used in the ST data analysis. The compatibility with the data types and the tools provided by the current ST analysis frameworks are summarized.
Collapse
Key Words
- AOI, area of illumination
- BICCN, Brain Initiative Cell Census Network
- BOLORAMIS, barcoded oligonucleotides ligated on RNA amplified for multiplexed and parallel in situ analyses
- Baysor, Bayesian Segmentation of Spatial Transcriptomics Data
- BinSpect, Binary Spatial Extraction
- CCC, cell–cell communication
- CCI, cell–cell interactions
- CNV, copy-number variation
- Computational biology
- DSP, digital spatial profiling
- DbiT-Seq, Deterministic Barcoding in Tissue for spatial omics sequencing
- FA, factor analysis
- FFPE, formalin-fixed, paraffin-embedded
- FISH, fluorescence in situ hybridization
- FISSEQ, fluorescence in situ sequencing of RNA
- FOV, Field of view
- GRNs, gene regulation networks
- GSEA, gene set enrichment analysis
- GSVA, gene set variation analysis
- HDST, high definition spatial transcriptomics
- HMRF, hidden Markov random field
- ICG, interaction changed genes
- ISH, in situ hybridization
- ISS, in situ sequencing
- JSTA, Joint cell segmentation and cell type annotation
- KNN, k-nearest neighbor
- LCM, Laser Capture Microdissection
- LCM-seq, laser capture microdissection coupled with RNA sequencing
- LOH, loss of heterozygosity analysis
- MC, Molecular Cartography
- MERFISH, multiplexed error-robust FISH
- NMF (NNMF), Non-negative matrix factorization
- PCA, Principal Component Analysis
- PIXEL-seq, Polony (or DNA cluster)-indexed library-sequencing
- PL-lig, padlock ligation
- QC, quality control
- RNAseq, RNA sequencing
- ROI, region of interest
- SCENIC, Single-Cell rEgulatory Network Inference and Clustering
- SME, Spatial Morphological gene Expression normalization
- SPATA, SPAtial Transcriptomic Analysis
- ST Pipeline, Spatial Transcriptomics Pipeline
- ST, Spatial transcriptomics
- STARmap, spatially-resolved transcript amplicon readout mapping
- Single-cell analysis
- Spatial data analysis frameworks
- Spatial deconvolution
- Spatial transcriptomics
- TIVA, Transcriptome in Vivo Analysis
- TMA, tissue microarray
- TME, tumor micro environment
- UMAP, Uniform Manifold Approximation and Projection for Dimension Reduction
- UMI, unique molecular identifier
- ZipSeq, zipcoded sequencing.
- scRNA-seq, single-cell RNA sequencing
- scvi-tools, single-cell variational inference tools
- seqFISH, sequential fluorescence in situ hybridization
- sequ-smFISH, sequential single-molecule fluorescent in situ hybridization
- smFISH, single molecule FISH
- t-SNE, t-distributed stochastic neighbor embedding
Collapse
Affiliation(s)
- Iivari Kleino
- Turku Bioscience Centre, University of Turku and Åbo Akademi University Turku, Turku, Finland
| | - Paulina Frolovaitė
- Turku Bioscience Centre, University of Turku and Åbo Akademi University Turku, Turku, Finland
| | - Tomi Suomi
- Turku Bioscience Centre, University of Turku and Åbo Akademi University Turku, Turku, Finland
| | - Laura L. Elo
- Turku Bioscience Centre, University of Turku and Åbo Akademi University Turku, Turku, Finland
- Institute of Biomedicine, University of Turku, Turku, Finland
| |
Collapse
|
3
|
Gao J, Wu Z, Zhao M, Zhang R, Li M, Sun D, Cheng H, Qi X, Shen Y, Xu Q, Chen H, Chen D, Sun Y. Allosteric inhibition reveals SHP2-mediated tumor immunosuppression in colon cancer by single-cell transcriptomics. Acta Pharm Sin B 2022; 12:149-66. [PMID: 35127377 DOI: 10.1016/j.apsb.2021.08.006] [Citation(s) in RCA: 22] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2021] [Revised: 07/27/2021] [Accepted: 07/30/2021] [Indexed: 12/20/2022] Open
Abstract
Colorectal cancer (CRC), a malignant tumor worldwide consists of microsatellite instability (MSI) and stable (MSS) phenotypes. Although SHP2 is a hopeful target for cancer therapy, its relationship with innate immunosuppression remains elusive. To address that, single-cell RNA sequencing was performed to explore the role of SHP2 in all cell types of tumor microenvironment (TME) from murine MC38 xenografts. Intratumoral cells were found to be functionally heterogeneous and responded significantly to SHP099, a SHP2 allosteric inhibitor. The malignant evolution of tumor cells was remarkably arrested by SHP099. Mechanistically, STING-TBK1-IRF3-mediated type I interferon signaling was highly activated by SHP099 in infiltrated myeloid cells. Notably, CRC patients with MSS phenotype exhibited greater macrophage infiltration and more potent SHP2 phosphorylation in CD68+ macrophages than MSI-high phenotypes, suggesting the potential role of macrophagic SHP2 in TME. Collectively, our data reveals a mechanism of innate immunosuppression mediated by SHP2, suggesting that SHP2 is a promising target for colon cancer immunotherapy.
Collapse
Key Words
- APC, antigen-presenting cell
- BTLA, B- and T-lymphocyte attenuator
- CNVs, copy number variations
- CRC, colorectal cancer
- Colorectal cancer
- DSBs, double-strand breaks
- GSEA, gene set enrichment analysis
- KRAS, Kirsten rat sarcoma viral oncogene homolog
- MAPK, mitogen-activated kinase
- MSI, microsatellite instability
- MSS, microsatellite stable
- Macrophage
- PCA, principal component analysis
- PD-1, programmed cell death 1
- PTPN11
- SHP099
- STING
- STING, stimulator of interferon genes
- TME, tumor microenvironment
- Tumor microenvironment
- Type I interferon
- scRNA-seq
- scRNA-seq, single-cell RNA-sequencing
- t-SNE, t-distributed stochastic neighbor embedding
Collapse
|
4
|
Sewer A, Zanetti F, Iskandar AR, Guedj E, Dulize R, Peric D, Bornand D, Mathis C, Martin F, Ivanov NV, Peitsch MC, Hoeng J. A meta-analysis of microRNAs expressed in human aerodigestive epithelial cultures and their role as potential biomarkers of exposure response to nicotine-containing products. Toxicol Rep 2020; 7:1282-1295. [PMID: 33014713 PMCID: PMC7522043 DOI: 10.1016/j.toxrep.2020.09.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2020] [Revised: 08/24/2020] [Accepted: 09/01/2020] [Indexed: 11/03/2022] Open
Abstract
The expression of some microRNAs (miRNA) is modulated in response to cigarette smoke (CS), which is a leading cause of major preventable diseases. However, whether miRNA expression is also modulated by the aerosol/extract from potentially reduced-risk products is not well studied. The present work is a meta-analysis of 12 in vitro studies in human organotypic epithelial cultures of the aerodigestive tract (buccal, gingival, bronchial, nasal, and small airway epithelia). These studies compared the effects of exposure to aerosols from electronic vapor (e-vapor) products and heated tobacco products, and to extracts from Swedish snus products (in the present work, will be referred to as reduced-risk products [RRPs]) on miRNA expression with the effects of exposure to CS or its total particulate matter fraction. This meta-analysis evaluated 12 datasets of a total of 736 detected miRNAs and 2775 exposed culture inserts. The t-distributed stochastic neighbor embedding method was used to find similarities across the diversity of miRNA responses characterized by tissue type, exposure type, and product concentration. The CS-induced changes in miRNA expression in gingival cultures were close to those in buccal cultures; similarly, the alterations in miRNA expression in small airway, bronchial, and nasal tissues resembled each other. A supervised clustering was performed to identify miRNAs exhibiting particular response patterns. The analysis identified a set of miRNAs whose expression was altered in specific tissues upon exposure to CS (e.g., miR-125b-5p, miR-132-3p, miR-99a-5p, and 146a-5p). Finally, we investigated the impact of RRPs on miRNA expression in relation to that of CS by calculating the response ratio r between the RRP- and CS-induced alterations at an individual miRNA level, showing reduced alterations in miRNA expression following RRP exposure relative to CS exposure (94 % relative reduction). No specific miRNA response pattern indicating exposure to aerosols from heated tobacco products and e-vapor products, or extracts from Swedish snus was identifiable.
Collapse
Key Words
- 2D, two-dimensional
- AKT, protein kinase B
- ALI, air-liquid interface
- CHTP 1.2, Carbon Heated Tobacco Product 1.2
- COPD, chronic obstructive pulmonary disease
- CRP, CORESTA Reference Product
- CS, cigarette smoke and its TPM fraction
- FDA, Food & Drug Administration
- FDR, false discovery rate
- GCW, General Classic White
- HCI, Health Canada intense
- HTP, heated tobacco product
- Heated tobacco product
- IL-1β, interleukin 1β
- MMP-1, matrix metalloproteinase 1
- N/A, not applicable
- Organotypic aerodigestive culture
- RRP, reduced-risk product
- Systems toxicology
- THS 2.2, Tobacco Heating System 2.2
- TPM, total particulate matter
- Tobacco Heating System 2.2
- e-vapor
- e-vapor, electronic vapor
- mRNA, messenger RNA
- mTOR, mammalian target of rapamycin
- miRNA
- miRNA, microRNA
- t-SNE, t-distributed stochastic neighbor embedding
Collapse
Affiliation(s)
- Alain Sewer
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Filippo Zanetti
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Anita R Iskandar
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Emmanuel Guedj
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Remi Dulize
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Dariusz Peric
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - David Bornand
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Carole Mathis
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Florian Martin
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Nikolai V Ivanov
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Manuel C Peitsch
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| | - Julia Hoeng
- PMI R&D, Philip Morris Products S.A., Quai Jeanrenaud 5, CH-2000 Neuchâtel, Switzerland
| |
Collapse
|
5
|
Herring CA, Chen B, McKinley ET, Lau KS. Single-Cell Computational Strategies for Lineage Reconstruction in Tissue Systems. Cell Mol Gastroenterol Hepatol 2018; 5:539-548. [PMID: 29713661 PMCID: PMC5924749 DOI: 10.1016/j.jcmgh.2018.01.023] [Citation(s) in RCA: 27] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/02/2018] [Accepted: 01/31/2018] [Indexed: 12/21/2022]
Abstract
Function at the organ level manifests itself from a heterogeneous collection of cell types. Cellular heterogeneity emerges from developmental processes by which multipotent progenitor cells make fate decisions and transition to specific cell types through intermediate cell states. Although genetic experimental strategies such as lineage tracing have provided insights into cell lineages, recent developments in single-cell technologies have greatly increased our ability to interrogate distinct cell types, as well as transitional cell states in tissue systems. From single-cell data that describe these intermediate cell states, computational tools have been developed to reconstruct cell-state transition trajectories that model cell developmental processes. These algorithms, although powerful, are still in their infancy, and attention must be paid to their strengths and weaknesses when they are used. Here, we review some of these tools, also referred to as pseudotemporal ordering algorithms, and their associated assumptions and caveats. We hope to provide a rational and generalizable workflow for single-cell trajectory analysis that is intuitive for experimental biologists.
Collapse
Affiliation(s)
- Charles A. Herring
- Epithelial Biology Center, Vanderbilt University Medical Center, Nashville, Tennessee,Program in Chemical and Physical Biology, Vanderbilt University School of Medicine, Nashville, Tennessee
| | - Bob Chen
- Epithelial Biology Center, Vanderbilt University Medical Center, Nashville, Tennessee,Department of Cell and Developmental Biology, Vanderbilt University School of Medicine, Nashville, Tennessee
| | - Eliot T. McKinley
- Epithelial Biology Center, Vanderbilt University Medical Center, Nashville, Tennessee,Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee
| | - Ken S. Lau
- Epithelial Biology Center, Vanderbilt University Medical Center, Nashville, Tennessee,Program in Chemical and Physical Biology, Vanderbilt University School of Medicine, Nashville, Tennessee,Department of Cell and Developmental Biology, Vanderbilt University School of Medicine, Nashville, Tennessee,Correspondence Address correspondence to: Ken S. Lau, PhD, Epithelial Biology Center, Vanderbilt University Medical Center, 2213 Garland Avenue, 10475 MRB IV, Nashville, Tennessee 37232-0441. fax: (615) 343-1591.
| |
Collapse
|