<b>HyperMap: An Efficient Meta-Learning Framework for Transferring Perturbation Responses Across Diverse Biological Contexts</b>

dhaka, bhavya;gao, jiahao;ideker, trey

Description

HyperMapDB is a unified resource of predicted transcriptional responses to 19,036 genetic and chemical perturbations across 19 human cell lines. Predictions were generated using HyperMap, a meta-learning framework that transfers perturbation response knowledge from existing atlases to new biological contexts. The dataset contains predicted single-cell gene expression deltas for 2,500 genes.

Citations (0)

Mentions (0)

Metrics

Dataset Index

0.5

FAIR Score

85%

Citations

0

Mentions

0

Metrics Over Time

Publication Details

DOI

Publisher

figshare

License

Creative Commons Attribution 4.0 International

Assigned Domain

Subfield

Molecular Biology

Field

Biochemistry, Genetics and Molecular Biology

Domain

Life Sciences

Confidence Score

50%

Source

Scholar Data Model

Keywords

Deep learningGene expression (incl. microarray and other genome-wide approaches)

Normalization Factors

FT

53.85

CTw

1.00

MTw

1.00