J
Johanna Mazur
Researcher at Merck KGaA
Publications - 5
Citations - 39
Johanna Mazur is an academic researcher from Merck KGaA. The author has contributed to research in topics: Feature selection & Cancer. The author has an hindex of 2, co-authored 5 publications receiving 13 citations. Previous affiliations of Johanna Mazur include Merck & Co..
Papers
More filters
Journal ArticleDOI
Feature selection strategies for drug sensitivity prediction.
TL;DR: Standard, data-driven feature selection approaches to feature selection driven by prior knowledge of drug targets, target pathways, and gene expression signatures are compared, finding small feature sets selected using prior knowledge are more predictive for drugs targeting specific genes and pathways, while models with wider feature sets perform better for drugs affecting general cellular mechanisms.
Posted ContentDOI
CONET: Copy number event tree model of evolutionary tumor history for single-cell data
Markowska M,Markowska M,Cąkała T,Błażej Miasojedow,Dilafruz Juraeva,Johanna Mazur,Ross E,Eike Staub,Ewa Szczurek +8 more
TL;DR: In this article, a probabilistic model for joint inference of the evolutionary tree on copy number events and copy number calling is proposed, which employs an efficient MCMC procedure to search the space of possible model structures and parameters and utilizes both perbin and per-breakpoint data.
Journal ArticleDOI
Genetic Interactions and Tissue Specificity Modulate the Association of Mutations with Drug Response
Dina Cramer,Dina Cramer,Dina Cramer,Johanna Mazur,Octavio Espinosa,Matthias Schlesner,Daniel Hübschmann,Roland Eils,Roland Eils,Roland Eils,Eike Staub +10 more
TL;DR: It is found that TP53 mutations decrease sensitivity to BRAF inhibitors in BRAF-mutated cell lines and patient tumors, suggesting a therapeutic benefit of combining inhibition of oncogenic BRAF with reactivation of the tumor suppressor TP53.
Journal ArticleDOI
RosettaSX: Reliable gene expression signature scoring of cancer models and patients.
Julian Kreis,Boro Nedić,Johanna Mazur,Miriam Urban,Sven-Eric Schelhorn,Thomas Grombacher,Felix Geist,Benedikt Brors,Michael Zühlsdorf,Eike Staub +9 more
TL;DR: In this paper, the authors apply a methodology that utilizes the previously developed concept of coherent expression of genes in signatures to identify translatable signatures before scoring their activity in single tumors and present a web interface (www.rosettasx.com) that applies their methodology to expression data from the Cancer Cell Line Encyclopaedia and The Cancer Genome Atlas.
Posted ContentDOI
Feature selection strategies for drug sensitivity prediction
TL;DR: Based on GDSC drug data, it is found that feature selection driven by prior knowledge tends to yield better results for drugs targeting specific genes and pathways, while models with the genome-wide features perform better for drugs affecting general mechanisms such as metabolism and DNA replication.