Browse
Submit Data
Databases
API
Help

Dataset Information

7 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Prospective identification of hematopoietic lineage choice by deep learning.

ABSTRACT: Differentiation alters molecular properties of stem and progenitor cells, leading to changes in their shape and movement characteristics. We present a deep neural network that prospectively predicts lineage choice in differentiating primary hematopoietic progenitors using image patches from brightfield microscopy and cellular movement. Surprisingly, lineage choice can be detected up to three generations before conventional molecular markers are observable. Our approach allows identification of cells with differentially expressed lineage-specifying genes without molecular labeling.

SUBMITTER: Buggenthin F

PROVIDER: S-EPMC5376497 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Prospective identification of hematopoietic lineage choice by deep learning.

Buggenthin Felix F Buettner Florian F Hoppe Philipp S PS Endele Max M Kroiss Manuel M Strasser Michael M Schwarzfischer Michael M Loeffler Dirk D Kokkaliaris Konstantinos D KD Hilsenbeck Oliver O Schroeder Timm T Theis Fabian J FJ Marr Carsten C

Nature methods 20170220 4

Differentiation alters molecular properties of stem and progenitor cells, leading to changes in their shape and movement characteristics. We present a deep neural network that prospectively predicts lineage choice in differentiating primary hematopoietic progenitors using image patches from brightfield microscopy and cellular movement. Surprisingly, lineage choice can be detected up to three generations before conventional molecular markers are observable. Our approach allows identification of c ...[more]

PMID: 28218899

Similar Datasets

Transcriptional fine-tuning of microRNA-223 levels directs lineage choice of human hematopoietic progenitors.

Project description:MicroRNAs (miRNAs) regulate cell proliferation, differentiation and death during development and postnatal life. The expression level of mature miRNAs results from complex molecular mechanisms, including the transcriptional regulation of their genes. MiR-223 is a hematopoietic-specific miRNA participating in regulatory signaling networks involving lineage-specific transcription factors (TFs). However, the transcriptional mechanisms governing its expression levels and its functional role in lineage fate decision of human hematopoietic progenitors (HPCs) have not yet been clarified. We found that in CD34(+)HPCs undergoing unilineage differentiation/maturation, miR-223 is upregulated more than 10-fold during granulopoiesis, 3-fold during monocytopoiesis and maintained at low levels during erythropoiesis. Chromatin immunoprecipitation and promoter luciferase assays showed that the lineage-specific expression level of mature miR-223 is controlled by the coordinated binding of TFs to their DNA-responsive elements located in 'distal' and 'proximal' regulatory regions of the miR-223 gene, differentially regulating the transcription of two primary transcripts (pri-miRs). All this drives myeloid progenitor maturation into specific lineages. Accordingly, modulation of miR-223 activity in CD34(+)HPCs and myeloid cell lines significantly affects their differentiation/maturation into erythroid, granulocytic and monocytic/macrophagic lineages. MiR-223 overexpression increases granulopoiesis and impairs erythroid and monocytic/macrophagic differentiation. Its knockdown, meanwhile, impairs granulopoiesis and facilitates erythropoiesis and monocytic/macrophagic differentiation. Overall, our data reveal that transcriptional pathways acting on the differential regulation of two pri-miR transcripts results in the fine-tuning of a single mature miRNA expression level, which dictates the lineage fate decision of hematopoietic myeloid progenitors.

| S-EPMC3890951 | biostudies-literature

Prospective identification and lineage tracing of top-level hematopoietic stem cells that sustain adult hematopoiesis

Project description:Hematopoietic stem cells (HSC) sustain long-term reconstitution of hematopoiesis in primary transplantation recipients. Few HSC can serially reconstitute secondary recipients, and their identity and contribution to normal hematopoiesis remain moot. We directed transgene expression to a distinct fraction of HSC in the adult bone marrow. Epxression of the reporter transgene segregated with reconstituting activity during secondary transplantations. The labeled cells had an undifferentiated phenotype and expression profile, were slow-cycling and localized to the vascular niche. Inducible genetic labeling showed the transgene-expressing HSC gave rise to other cells within the HSC populations, confirming their top position in the differentiation hierarchy. Importantly, labeled HSC gave rise to more than two-thirds of all myeloid cells and platelets in adult mice, and this contribution could be further accelerated by interferon response. Thus, the rare "top-level" HSC with serial reconstitution capacity also serve as the major source of endogenous hematopoiesis in adult animals.

2016-08-30 | GSE78855 | GEO

Solo: doublet identification via semi-supervised deep learning

Project description:We developed a semi-supervised deep learning framework for the identification of doublets in scRNA-seq analysis called Solo. To validate our method, we used MULTI-seq, cholesterol modified oligos (CMOs), to experimentally identify doublets in a solid tissue with diverse cell types, mouse kidney, and showed Solo recapitulated experimentally identified doublets.

2019-11-13 | GSE140262 | GEO

DeLTA: Automated cell segmentation, tracking, and lineage reconstruction using deep learning.

Project description:Microscopy image analysis is a major bottleneck in quantification of single-cell microscopy data, typically requiring human oversight and curation, which limit both accuracy and throughput. To address this, we developed a deep learning-based image analysis pipeline that performs segmentation, tracking, and lineage reconstruction. Our analysis focuses on time-lapse movies of Escherichia coli cells trapped in a "mother machine" microfluidic device, a scalable platform for long-term single-cell analysis that is widely used in the field. While deep learning has been applied to cell segmentation problems before, our approach is fundamentally innovative in that it also uses machine learning to perform cell tracking and lineage reconstruction. With this framework we are able to get high fidelity results (1% error rate), without human intervention. Further, the algorithm is fast, with complete analysis of a typical frame containing ~150 cells taking <700msec. The framework is not constrained to a particular experimental set up and has the potential to generalize to time-lapse images of other organisms or different experimental configurations. These advances open the door to a myriad of applications including real-time tracking of gene expression and high throughput analysis of strain libraries at single-cell resolution.

| S-EPMC7153852 | biostudies-literature

Generalized Radiographic View Identification with Deep Learning.

Project description:To explore the feasibility of an automatic machine-learning algorithm-based quality control system for the practice of diagnostic radiography, performance of a convolutional neural networks (CNN)-based algorithm for identifying radiographic (X-ray) views at different levels was examined with a retrospective, HIPAA-compliant, and IRB-approved study performed on 15,046 radiographic images acquired between 2013 and 2018 from nine clinical sites affiliated with our institution. Images were labeled according to four classification levels: level 1 (anatomy level, 25 classes), level 2 (laterality level, 41 classes), level 3 (projection level, 108 classes), and level 4 (detailed level, 143 classes). An Inception V3 model pre-trained with ImageNet dataset was trained with transfer learning to classify the image at all levels. Sensitivity and positive predictive value were reported for each class, and overall accuracy was reported for each level. Accuracy was also reported when we allowed for "reasonable errors". The overall accuracy was 0.96, 0.93, 0.90, and 0.86 at levels 1, 2, 3, and 4, respectively. Overall accuracy increased to 0.99, 0.97, 0.94, and 0.88 when "reasonable errors" were allowed. Machine learning algorithms resulted in reasonable model performance for identifying radiographic views with acceptable accuracy when "reasonable errors" were allowed. Our findings demonstrate the feasibility of building a quality-control program based on machine-learning algorithms to identify radiographic views with acceptable accuracy at lower levels, which could be applied in a clinical setting.

| S-EPMC7887112 | biostudies-literature

DeNovo Peptide Identification Deep Learning Training Set

Project description:A benchmark set of bottom-up proteomics data for training deep learning networks. It has data from 51 organisms and includes nearly 1 million peptides.

2018-06-13 | PXD010000 | Pride

DeNovo Peptide Identification Deep Learning Test Set

Project description:A set of bottom-up proteomics data for testing the deep learning network trained with data in PXD010000

2022-09-25 | PXD010613 | Pride

Solo: doublet identification via semi-supervised deep learning

Project description:Solo: doublet identification via semi-supervised deep learning

| PRJNA589061 | ENA

Co-culture of human hematopoietic stem cells with osteoblasts affects mono/macrophage versus erythroid lineage choice.

Project description:Hematopoietic stem cells (HSCs) are located in the bone marrow in a specific microenvironment referred as the hematopoietic stem cell niche, where HSCs interact with a variety of stromal cells. Though several components of the stem cell niche have been identified, the regulatory mechanisms through which such components regulate the stem cell fate are still unknown. In order to address this issue, we investigated how osteoblasts (OBs) can affect the molecular and functional phenotype of HSCs and vice versa. Our data showed that CD34+ cells cultured with OBs give rise to higher total cell numbers, produce more CFU and maintain a higher percentage of CD34+CD38- cells compared to control culture. Moreover, clonogenic assay and long-term culture results showed that OBs enhance HSC differentiation towards the mono/macrophage lineage at the expense of the granulocytic and erythroid ones. Finally, GEP analysis allowed us to identify several cytokine-receptor networks, such as WNT pathway, and transcription factors, as TWIST1 and FOXC1, that could be activated by co-culture with OBs and could be responsible for the biological effects reported above. Altogether our results indicate that OBs are able to affect both HPC maintenance and differentiation capacity by modulating mono/macrophage and erythroid commitment. We set up a co-culture system composed of human CD34+ cells in culture with human OBs. After coculture, CD34+ cells and the hematopoietic cell fraction were separated from OBs and analyzed by gene expression profiling (GEP), clonogenic assay and long-term culture.

2013-05-10 | E-GEOD-38091 | biostudies-arrayexpress

Graph Embedding Deep Learning Guides Microbial Biomarkers' Identification.

Project description:The microbiome-wide association studies are to figure out the relationship between microorganisms and humans, with the goal of discovering relevant biomarkers to guide disease diagnosis. However, the microbiome data is complex, with high noise and dimensions. Traditional machine learning methods are limited by the models' representation ability and cannot learn complex patterns from the data. Recently, deep learning has been widely applied to fields ranging from text processing to image recognition due to its efficient flexibility and high capacity. But the deep learning models must be trained with enough data in order to achieve good performance, which is impractical in reality. In addition, deep learning is considered as black box and hard to interpret. These factors make deep learning not widely used in microbiome-wide association studies. In this work, we construct a sparse microbial interaction network and embed this graph into deep model to alleviate the risk of overfitting and improve the performance. Further, we explore a Graph Embedding Deep Feedforward Network (GEDFN) to conduct feature selection and guide meaningful microbial markers' identification. Based on the experimental results, we verify the feasibility of combining the microbial graph model with the deep learning model, and demonstrate the feasibility of applying deep learning and feature selection on microbial data. Our main contributions are: firstly, we utilize different methods to construct a variety of microbial interaction networks and combine the network via graph embedding deep learning. Secondly, we introduce a feature selection method based on graph embedding and validate the biological meaning of microbial markers. The code is available at https://github.com/MicroAVA/GEDFN.git.

| S-EPMC6883002 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data