Sean will attend the EMBO course Integrative analysis of multi-omics data.
Ammar presents at WCPG
Ammar will present a poster based on his preprint “rfPhen2Gen: A machine learning based association study of brain imaging phenotypes to genotypes” at the World Congress of Psychiatric Genetics
NORA-Turing exchange fellowship to Mariyam
Congratulations to Mariyam for being selected for the 2022 NORA.ai Research Exchange Enrichment Scheme with the Alan Turing Institute! The award will allow Mariyam to spend 6 months at the Turing Institute to work with Chris Holmes.
Congratulations to Ammar for successfully defending his PhD thesis “Machine learning approaches for high-dimensional genome-wide association studies”!
You can find more information about the defense and a copy of the thesis on UiB’s pages.
Ammar will now continue in the group as a postdoctoral fellow on the NeuroConvergence project.
Congrats again Dr Malik!
Welcome Bendik, Ørjan, and Daniel!
A warm welcome to our new master students: Bendik (master in machine learning) will do a project with Ramin and Gutama about missing data prediction in causal networks, Ørjan (master in bioinformatics) will do a joint project with Anagha Joshi about spatial transcriptomics, and Daniel (master in bioinformatics) will do a joint project with Susanna Röblitz about comparing ML and classical dynamical systems methods for learning networks from time series data.
eQTL networks review
Congrats to Sean for the publication of his review article “eQTLs as causal instruments for the reconstruction of hormone linked gene networks”! The review is part of a special issue “Insights in Systems Endocrinology: 2021” in Frontiers in Endocrinology.
Preprint by Ammar
Ammar has posted a preprint of his paper “rfPhen2Gen: A machine learning based association study of brain imaging phenotypes to genotypes” on arXiv. In this paper, Ammar evaluated random forest regression as a method to identify biologically relevant associations by learning models to predict SNPs from imaging features, using data for 518,484 SNPs and 56 brain imaging traits from the ADNI study.
Postdoc position available
A postdoc position is available in my group on the NeuroConvergence project in collaboration with Jan Haavik and colleagues at the Neurotargeting group. In the NeuroConvergence project, we will use a range of machine learning and causal inference methods on unique large-scale genetic and functional genomic datasets and chemical libraries to identify novel druggable target proteins for neuropsychiatric disorders. The postdoc will also contribute to the in silico protein structural screening and optimization of candidate targets using modern AI tools (RoseTTAfold, Alphafold2). See the job advertisement for more details and application instructions.
A warm welcome to Gutama Ibrahim who joins the group as a PhD student. Gutama has a master in Applied Physics and Mathematics from the University of Tromsø and he will work on the “Intelligent systems for disease risk prediction” project.
Our paper “Restricted maximum-likelihood method for learning latent variance components in gene expression data with known and unknown confounders” has been published in G3. In this paper we analyse the mathematical structure of a class of statistical models for learning hidden factors influencing gene expression data and show that a new algorithm based on the analytical results is orders of magnitude faster than the standard algorithms for solving this class of models.