Farhad Zamani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Farhad Zamani has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Anders Krogh
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
1 shared publication - Asta Mannstaedt Rasmussen
Department of Clinical Medicine, Aarhus University, Denmark
1 shared publication - Jakob Skou Pedersen
Department of Clinical Medicine, Aarhus University, Denmark
1 shared publication - Mathilde Hartvig Diekema
Department of Clinical Medicine, Aarhus University, Denmark
1 shared publication - Viktoria Schuster
Department of Computer Science, University of Copenhagen, Denmark
1 shared publication
Latest Publications
- Open Access
miDGD: a multi-modal deep generative model predicts microRNA expression from bulk or single-cell mRNA expression
MicroRNAs (miRNAs) are important post-transcriptional regulators, yet their expression is typically unobserved in single-cell and most bulk RNA-seq datasets. We present miDGD, a deep generative decoder model that predicts miRNA abundance directly from gene expression alone. Trained on bulk and single-cell datasets from TCGA, GTEx, and human cell lines, miDGD learned a shared latent representation of matched mRNA and miRNA profiles that organized samples into biologically meaningful clusters reflecting tissue and cancer types. The model reconstructed both tissue-specific and broadly expressed miRNAs, recapitulated known miRNA-target relationships, and showed robust performance in sparse and single-cell data. miDGD outperformed miRSCAPE and recent miRNA activity inference methods, with improved cross-dataset generalization. These results establish a deep generative model as an improved framework for predicting miRNA expression when direct measurements are unavailable.
Open AccessmiDGD: a multi-modal deep generative model predicts microRNA expression from bulk or single-cell mRNA expression
MicroRNAs (miRNAs) are important post-transcriptional regulators, yet their expression is typically unobserved in single-cell and most bulk RNA-seq datasets. We present miDGD, a deep generative decoder model that predicts miRNA abundance directly from gene expression alone. Trained on bulk and single-cell datasets from TCGA, GTEx, and human cell lines, miDGD learned a shared latent representation of matched mRNA and miRNA profiles that organized samples into biologically meaningful clusters reflecting tissue and cancer types. The model reconstructed both tissue-specific and broadly expressed miRNAs, recapitulated known miRNA-target relationships, and showed robust performance in sparse and single-cell data. miDGD outperformed miRSCAPE and recent miRNA activity inference methods, with improved cross-dataset generalization. These results establish a deep generative model as an improved framework for predicting miRNA expression when direct measurements are unavailable.