Machine learning for predicting the effects of genetic variation in plants

During his PhD studies, Behrooz Vahedi Torghabeh researched how machine learning, biological language models, and quantitative methods can be used to predict the functional effects of genetic variation in plants. Large-scale genome sequencing makes it possible to detect millions of variants, but it remains difficult to identify which variants affect plant fitness, gene expression, or breeding-relevant traits.

Behrooz Vahedi Torghabeh developed and evaluated machine learning approaches for variant effect prediction in plant genomes, including models based on biological language models, evolutionary conservation, regulatory sequence information, and gene expression context. The work investigated deleterious coding variants in rice, regulatory variants affecting gene expression across plant species, and allele fixation across generations in a Brachypodium distachyon mutant population.

The new research findings contribute to the development of computational tools for prioritizing functionally relevant plant variants and support future precision breeding by helping identify variants with potential biological and agronomic importance.

The PhD study was completed at "Center for Quantitative Genetics and Genomics (QGG)", Faculty of Technical Sciences, Aarhus University.

This summary was prepared by the PhD student.

Time: Wednesday, 3 August 2026, at 09:00 – 11:00
Place: 1110-223, C. F. Møllers Allé 8 , 8000 Aarhus C
Title of PhD thesis: Quantitative Methods and Machine Learning Models in Evolutionary Plant Population Genomics for Analysis of Variant Effects
Contact information: Behrooz Vahedi Torghabeh, e-mail: behroozvahedi@qgg.au.dk, tel.: +45 52729950
Members of the assessment committee:
Senior Researcher Jedrzej Jakub Szymanski, Leibniz Institute of Plant Genetics and Crop Plant Research, Germany
Associate Professor Henrik Nielsen, Department of Health Technology, Technical University of Denmark, Denmark
Professor Goutam Sahana (chair), Center for Quantitative Genetics and Genomics (QGG), Aarhus University, Denmark
Main supervisor: Professor Torben Asp, Center for Quantitative Genetics and Genomics (QGG), Aarhus University, Denmark
Co-supervisor: Assistant Professor Guillaume Ramstein, Center for Quantitative Genetics and Genomics (QGG), Aarhus University, Denmark
Language: The PhD dissertation will be defended in English

The defence is public.
The PhD thesis is available for reading at the Graduate School of Technical Sciences/GSTS, Ny Munkegade 120, building 1521, 8000 Aarhus C.