PhenoFeatureFinder: a python package for linking developmental phenotypes to omics features

Lissy-Anne M. Denkers, Marc D. Galland, Annabel Dekker, Valerio Bianchi, Petra M. Bleeker

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

PhenoFeatureFinder is designed to facilitate the analyses required to analyse quantitative and/or progressive phenotypic- and omics data, and link those using Machine Learning with the aim to identify causal features, in one package. It can be used for 1) evaluation and visualisation of phenotype progression over multiple stages and between groups (e.g. treatments,
genotypes), 2) pre-processing of omics data, and 3) prediction of features that explain the
phenotypic classification. To facilitate usability, each step in the pipeline can also be performed independently, hence has been assigned a class in the package (Figure 1). We provide an example of implementation below that focuses on insect development through time and the
selection of metabolic features causal to the observed phenotype, but different input data could be used, provided it has a similar structure. This could be any phenotype that is scored in progressive stages over time. Also, PhenoFeatureFinder was developed initially with metabolomics data, but users can evaluate its fit applying other types of omics data.
Original languageEnglish
Article number7264
JournalThe Journal of Open Source Software
Volume9
Issue number103
DOIs
Publication statusPublished - 23 Nov 2024

Fingerprint

Dive into the research topics of 'PhenoFeatureFinder: a python package for linking developmental phenotypes to omics features'. Together they form a unique fingerprint.

Cite this