Skip to main content

Feature extraction approach in single-cell gene expression profiling for cell-type marker identification.

Project description

MICTI- Marker gene Identification for Cell Type Identity

Recent advances in single-cell gene expression profiling technology have revolutionized the understanding of molecular processes underlying developmental cell and tissue differentiation, enabling the discovery of novel cell types and molecular markers that characterize developmental trajectories. Common approaches for identifying marker genes are based on pairwise statistical testing for differential gene expression between cell types in heterogeneous cell populations, which is challenging due to unequal sample sizes and variance between groups resulting in little statistical power and inflated type I errors.

Overview

We developed an alternative feature extraction method, Marker gene Identification for Cell Type Identity (MICTI), that encodes the cell-type specific expression information to each gene in every single cell. This approach identifies features (genes) that are cell-type specific for a given cell-type in heterogeneous cell population.

Installation

To install the current release:

pip install MICTI

How to use MICTI

Import MICTI:

from MICTI import MARKER

Creating MICTI object for known cell-type cluster label:

mictiObject=MARKER.MICTI(datamatrix, geneName, cellName, cluster_assignment=cell_type, k=None, th=0, ensembel=False, organisum="hsapiens")

2D visualisation with tSNE:

mictiObject.get_Visualization(dim=2, method="tsne")

Get MICTI marker genes:

    cluster_1_markers=mictiObject.get_markers_by_Pvalues_and_Zscore(1, threshold_pvalue=.01,threshold_z_score=0)

Markers heatmap plots:

mictiObject.heatMap()

Markers Radar plots:

mictiObject.get_Radar_plot()

Gene Ontology enrichment analysis for cell-type marker genes in each of cell-type clusters

enrechment_table=mictiObject.get_gene_list_over_representation_analysis(list(cluster_1_markers.index))
enrechment_table #gene-list enrichment analysis result for the cell-type marker genes for cluster-1

Licence

MICTI LICENCE

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

MICTI-0.1.5.tar.gz (17.5 kB view details)

Uploaded Source

Built Distribution

MICTI-0.1.5-py3-none-any.whl (21.4 kB view details)

Uploaded Python 3

File details

Details for the file MICTI-0.1.5.tar.gz.

File metadata

  • Download URL: MICTI-0.1.5.tar.gz
  • Upload date:
  • Size: 17.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/40.6.2 requests-toolbelt/0.8.0 tqdm/4.15.0 CPython/3.5.2

File hashes

Hashes for MICTI-0.1.5.tar.gz
Algorithm Hash digest
SHA256 98624928789dfe2240001ec1a6bf207cd1069fa7bafc39296da7bb5272979ccc
MD5 de2c9e54c73cfabc45ff37b9054f213f
BLAKE2b-256 4e5a6cd6b047ecdd0e85e67e214985ef1b57772314c37b7ae180b2530cdcdf73

See more details on using hashes here.

File details

Details for the file MICTI-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: MICTI-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 21.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/40.6.2 requests-toolbelt/0.8.0 tqdm/4.15.0 CPython/3.5.2

File hashes

Hashes for MICTI-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 ec0592f3a07226135975879d32b59779a901931932815fa5693cfbd118e84e12
MD5 6cd1d3eb3f98136f6be84c1478078ad4
BLAKE2b-256 5e4d46f0bfd150a11179857197f8f0ee8fbb710be17d6807ebb3503497f5599d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page