Multi-omics analyses and machine learning prediction of oviductal responses in the presence of gametes and embryos

Опубликована: Фев. 13, 2025

The oviduct is the site of fertilization and preimplantation embryo development in mammals. Evidence suggests that gametes alter oviductal gene expression. To delineate adaptive interactions between gamete/embryo, we performed a multi-omics characterization tissues utilizing bulk RNA-sequencing (RNA-seq), single-cell (scRNA-seq), proteomics collected from distal proximal at various stages after mating mice. We observed robust region-specific transcriptional signatures. Specifically, presence sperm induces genes involved pro-inflammatory responses region 0.5 days post-coitus (dpc). Genes inflammatory were produced specifically by secretory epithelial cells oviduct. At 1.5 2.5 dpc, pyruvate glycolysis enriched region, potentially providing metabolic support for developing embryos. Abundant proteins fluid differentially naturally fertilized superovulated samples. RNA-seq data used to identify transcription factors predicted influence protein abundance proteomic via novel machine learning model based on transformers integrating transcriptomics data. identified influential correlated predictive expressions alignment with vivo -derived Lastly, found some differences sperm-exposed mouse oviducts compared hydrosalpinx fallopian tubes patients. In conclusion, our subsequent confirmation proteins/RNAs indicate responsive embryos spatiotemporal manner.

Язык: Английский

---

Artificial intelligence for life sciences: A comprehensive guide and future trends

The Innovation Life, Год журнала: 2024, Номер unknown, С. 100105 - 100105

Опубликована: Янв. 1, 2024

<p>Artificial intelligence has had a profound impact on life sciences. This review discusses the application, challenges, and future development directions of artificial in various branches sciences, including zoology, plant science, microbiology, biochemistry, molecular biology, cell developmental genetics, neuroscience, psychology, pharmacology, clinical medicine, biomaterials, ecology, environmental science. It elaborates important roles aspects such as behavior monitoring, population dynamic prediction, microorganism identification, disease detection. At same time, it points out challenges faced by application data quality, black-box problems, ethical concerns. The are prospected from technological innovation interdisciplinary cooperation. integration Bio-Technologies (BT) Information-Technologies (IT) will transform biomedical research into AI for Science paradigm.</p>

Язык: Английский

---

WCSGNet: a graph neural network approach using weighted cell-specific networks for cell-type annotation in scRNA-seq

Frontiers in Genetics, Год журнала: 2025, Номер 16

Опубликована: Фев. 17, 2025

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for understanding cellular heterogeneity, providing unprecedented resolution in molecular regulation analysis. Existing supervised learning approaches cell type annotation primarily utilize gene expression profiles from scRNA-seq data. Although some methods incorporated interaction network information, they fail to use cell-specific association networks. This limitation overlooks the unique patterns within individual cells, potentially compromising accuracy of classification. We introduce WCSGNet, graph neural network-based algorithm automatic cell-type that leverages Weighted Cell-Specific Networks (WCSNs). These networks are constructed based on highly variable genes and inherently capture both structure features. Extensive experimental validation demonstrates WCSGNet consistently achieves superior classification performance, ranking among top-performing while maintaining robust stability across diverse datasets. Notably, exhibits distinct advantage handling imbalanced datasets, outperforming existing these challenging scenarios. All datasets codes reproducing this work were deposited GitHub repository ( https://github.com/Yi-ellen/WCSGNet ).

Язык: Английский

---

Multi-omics analyses and machine learning prediction of oviductal responses in the presence of gametes and embryos

eLife, Год журнала: 2025, Номер 13

Опубликована: Фев. 26, 2025

The oviduct is the site of fertilization and preimplantation embryo development in mammals. Evidence suggests that gametes alter oviductal gene expression. To delineate adaptive interactions between gamete/embryo, we performed a multi-omics characterization tissues utilizing bulk RNA-sequencing (RNA-seq), single-cell (scRNA-seq), proteomics collected from distal proximal at various stages after mating mice. We observed robust region-specific transcriptional signatures. Specifically, presence sperm induces genes involved pro-inflammatory responses region 0.5 days post-coitus (dpc). Genes inflammatory were produced specifically by secretory epithelial cells oviduct. At 1.5 2.5 dpc, pyruvate glycolysis enriched region, potentially providing metabolic support for developing embryos. Abundant proteins fluid differentially naturally fertilized superovulated samples. RNA-seq data used to identify transcription factors predicted influence protein abundance proteomic via novel machine learning model based on transformers integrating transcriptomics data. identified influential correlated predictive expressions alignment with vivo-derived Lastly, found some differences sperm-exposed mouse oviducts compared hydrosalpinx Fallopian tubes patients. In conclusion, our subsequent vivo confirmation proteins/RNAs indicate responsive embryos spatiotemporal manner.

Язык: Английский

---

Graph neural networks for single-cell omics data: a review of approaches and applications

Briefings in Bioinformatics, Год журнала: 2025, Номер 26(2)

Опубликована: Март 1, 2025

Abstract Rapid advancement of sequencing technologies now allows for the utilization precise signals at single-cell resolution in various omics studies. However, massive volume, ultra-high dimensionality, and high sparsity nature data have introduced substantial difficulties to traditional computational methods. The intricate non-Euclidean networks intracellular intercellular signaling molecules within datasets, coupled with complex, multimodal structures arising from multi-omics joint analysis, pose significant challenges conventional deep learning operations reliant on Euclidean geometries. Graph neural (GNNs) extended data, allowing cells their features datasets be modeled as nodes a graph structure. GNNs been successfully applied across broad range tasks analysis. In this survey, we systematically review 107 successful applications six variants tasks. We begin by outlining fundamental principles variants, followed systematic GNN-based models epigenomics, transcriptomics, spatial proteomics, multi-omics. each section dedicated specific type, summarized publicly available commonly utilized articles reviewed that section, totaling 77 datasets. Finally, summarize potential shortcomings current research explore directions future anticipate will serve guiding resource researchers deepen application omics.

Язык: Английский

---

Transcriptionally distinct malignant neuroblastoma populations show selective response to adavosertib treatment

Neurotherapeutics, Год журнала: 2025, Номер unknown, С. e00575 - e00575

Опубликована: Март 1, 2025

Язык: Английский

---

Perspectives on integrating artificial intelligence and single‐cell omics for cellular plasticity research

Quantitative Biology, Год журнала: 2025, Номер 13(4)

Опубликована: Апрель 24, 2025

Abstract Cellular plasticity enables cells to dynamically adapt environmental changes by altering their phenotype. This plays a crucial role in tissue repair and regeneration contributes pathological processes such as cancer metastasis. Advances single‐cell omics have significantly advanced the study of cellular states provided new opportunities for accurate cell classification uncovering transitions. In this perspective, we emphasize integrating chromatin accessibility data extrinsic factors, microenvironmental cues, with transcriptomic develop holistic models identifying plastic states. Additionally, coupling artificial intelligence offers transformative potential address existing challenges fill gaps characterizing cells. We envision development universal metric, standardized metric quantifying plasticity. would enable consistent measurement across diverse studies, creating unified framework that bridges fields developmental biology, research, regenerative medicine. Fostering innovative approaches analyzing promises not only deepen our understanding but also accelerate therapeutic advancements, paving way novel precision medicine strategies treat complex diseases cancer.

Язык: Английский

---

Harnessing the deep learning power of foundation models in single-cell omics

Nature Reviews Molecular Cell Biology, Год журнала: 2024, Номер 25(8), С. 593 - 594

Опубликована: Июнь 26, 2024

Язык: Английский

---

Integrative approach of omics and imaging data to discover new insights for understanding brain diseases

Brain Communications, Год журнала: 2024, Номер 6(4)

Опубликована: Янв. 1, 2024

Abstract Treatments that can completely resolve brain diseases have yet to be discovered. Omics is a novel technology allows researchers understand the molecular pathways underlying diseases. Multiple omics, including genomics, transcriptomics and proteomics, imaging technologies, such as MRI, PET EEG, contributed disease-related therapeutic target detection. However, new treatment discovery remains challenging. We focused on establishing multi-molecular maps using an integrative approach of omics provide insights into disease diagnosis treatment. This requires precise data collection processing normalization. Incorporating map with advanced technologies through artificial intelligence will help establish system for regulation at level.

Язык: Английский

---

scCAD: Cluster decomposition-based anomaly detection for rare cell identification in single-cell expression data

Nature Communications, Год журнала: 2024, Номер 15(1)

Опубликована: Авг. 30, 2024

Single-cell RNA sequencing (scRNA-seq) technologies have become essential tools for characterizing cellular landscapes within complex tissues. Large-scale single-cell transcriptomics holds great potential identifying rare cell types critical to the pathogenesis of diseases and biological processes. Existing methods often rely on one-time clustering using partial or global gene expression. However, these may be overlooked during phase, posing challenges their accurate identification. In this paper, we propose a Cluster decomposition-based Anomaly Detection method (scCAD), which iteratively decomposes clusters based most differential signals in each cluster effectively separate achieve We benchmark scCAD 25 real-world scRNA-seq datasets, demonstrating its superior performance compared 10 state-of-the-art methods. In-depth case studies across diverse including mouse airway, brain, intestine, human pancreas, immunology data, clear renal carcinoma, showcase scCAD's efficiency scenarios. Furthermore, can correct annotation identify immune subtypes associated with disease, thereby offering valuable insights into disease progression.

Язык: Английский

---