Home | Research | Groups | Julien Gagneur

Research Group Julien Gagneur

Link to Julien Gagneur

Julien Gagneur

Prof. Dr.

Principal Investigator

Computational Molecular Medicine

Julien Gagneur

is Assistant Professor for Computational Biology at TU Munich.

His research focuses on delineating the genetic basis of gene regulation and its implication in diseases. To this end, he is developing statistical and machine learning algorithms and works with experimentalists to design novel experimental approaches. His group is also developing strategies to pinpoint the cause of genetic disorders by integrating data from genetics and 'multiomics' disciplines such as transcriptomics and proteomics.

Team members @MCML

Link to Pedro Tomaz da Silva

Pedro Tomaz da Silva

Computational Molecular Medicine

Link to Johannes Hingerl

Johannes Hingerl

Computational Molecular Medicine

Link to Alexander Karollus

Alexander Karollus

Computational Molecular Medicine

Publications @MCML

[3]
F. Brechtmann, T. Bechtler, S. Londhe, C. Mertes and J. Gagneur.
Evaluation of input data modality choices on functional gene embeddings.
NAR Genomics and Bioinformatics 5.4 (Dec. 2023). DOI.
Abstract

Functional gene embeddings, numerical vectors capturing gene function, provide a promising way to integrate functional gene information into machine learning models. These embeddings are learnt by applying self-supervised machine-learning algorithms on various data types including quantitative omics measurements, protein–protein interaction networks and literature. However, downstream evaluations comparing alternative data modalities used to construct functional gene embeddings have been lacking. Here we benchmarked functional gene embeddings obtained from various data modalities for predicting disease-gene lists, cancer drivers, phenotype–gene associations and scores from genome-wide association studies. Off-the-shelf predictors trained on precomputed embeddings matched or outperformed dedicated state-of-the-art predictors, demonstrating their high utility. Embeddings based on literature and protein–protein interactions inferred from low-throughput experiments outperformed embeddings derived from genome-wide experimental data (transcriptomics, deletion screens and protein sequence) when predicting curated gene lists. In contrast, they did not perform better when predicting genome-wide association signals and were biased towards highly-studied genes. These results indicate that embeddings derived from literature and low-throughput experiments appear favourable in many existing benchmarks because they are biased towards well-studied genes and should therefore be considered with caution. Altogether, our study and precomputed embeddings will facilitate the development of machine-learning models in genetics and related fields.

MCML Authors
Link to Julien Gagneur

Julien Gagneur

Prof. Dr.

Computational Molecular Medicine


[2]
P. T. da Silva, Y. Zhang, E. Theodorakis, L. D. Martens, V. A. Yépez, V. Pelechano and J. Gagneur.
Cellular energy regulates mRNA translation and degradation in a codon-specific manner.
Preprint at bioRxiv (2023). DOI.
MCML Authors
Link to Pedro Tomaz da Silva

Pedro Tomaz da Silva

Computational Molecular Medicine

Link to Julien Gagneur

Julien Gagneur

Prof. Dr.

Computational Molecular Medicine


[1]
A. Karollus, J. Hingerl, D. Gankin, M. Grosshauser, K. Klemon and J. Gagneur.
Species-aware DNA language models capture regulatory elements and their evolution.
Preprint at bioRxiv (2023). DOI.
MCML Authors
Link to Alexander Karollus

Alexander Karollus

Computational Molecular Medicine

Link to Johannes Hingerl

Johannes Hingerl

Computational Molecular Medicine

Link to Julien Gagneur

Julien Gagneur

Prof. Dr.

Computational Molecular Medicine