2025 Hyper Recent •CC0 1.0 Universal

This work is dedicated to the public domain. No rights reserved.

Access Preprint From Server
July 2nd, 2025
Version: 2
Aix Marseille Univ, INSERM, MMG, Marseille, France
bioinformatics
biorxiv

MOTL: enhancing multi-omics matrix factorization with transfer learning

Hirst, D.Open in Google Scholar•Terezol, M.Open in Google Scholar•Cantini, L.Open in Google Scholar•Villoutreix, P.Open in Google Scholar•Vignes, M.Open in Google Scholar•Baudot, A.Open in Google Scholar

Joint matrix factorization is popular for extracting lower dimensional representations of multi-omics data but loses effectiveness with limited samples. Addressing this limitation, we introduce MOTL (Multi-Omics Transfer Learning), a framework that enhances MOFA (Multi-Omics Factor Analysis) by inferring latent factors for small multi-omics target datasets with respect to those inferred from a large heterogeneous learning dataset. We evaluated MOTL by designing simulated and real data protocols and demonstrated that MOTL improves the factorization of limited-sample multi-omics datasets when compared to factorization without transfer learning. When applied to actual glioblastoma samples, MOTL enhances delineation of cancer status and subtype.

Similar Papers

biorxiv
Wed Jul 02 2025
A systematic assessment of phylogenomic approaches for microbial species tree reconstruction
A key challenge in microbial phylogenomics is that microbial gene families are often affected by extensive horizontal gene transfer (HGT). As a result, most existing methods for microbial phylogenomics can only make use of a small subset of the gene families present in the microbial genomes under consideration, potentially biasing their results and affecting their accuracy. To address this challen...
Weiner, S.
•
Feng, Y.
•
Gogarten, J. P.
•
Bansal, M. S.
biorxiv
Wed Jul 02 2025
XtractPAV: An Automated Pipeline for Identifying Presence-Absence Variations Across Multiple Genomes
Motivation: Presence-absence variations (PAVs) significantly influence phenotypic diversity across and within species by modulating functional modules involved in stress responsiveness, adaptation, and developmental processes. This modulation ultimately contributes to genetic diversity at both inter- and intra-species levels. However, existing tools for detecting PAVs offer limitations in achievin...
Ahmad, R. S.
•
Sadaqat, M.
•
Tahir ul Qamar, M.
biorxiv
Wed Jul 02 2025
MORPH Predicts the Single-Cell Outcome of Genetic Perturbations Across Conditions and Data Modalities
Modeling cellular responses to genetic perturbations is a significant challenge in computational biology. Measuring all gene perturbations and their combinations across cell types and conditions is experimentally challenging, highlighting the need for predictive models that generalize across data types to support this task. Here we present MORPH, a MOdular framework for predicting Responses to Per...
He, C.
•
Zhang, J.
•
Dahleh, M. A.
•
Uhler, C.
biorxiv
Wed Jul 02 2025
hoodscanR: profiling single-cell neighborhoods in spatial transcriptomics data
Understanding complex cellular niches and neighborhoods have provided new insights into tissue biology. Thus, accurate neighborhood identification is crucial, yet existing methodologies often struggle to detect informative neighborhoods and generate cell-specific neighborhood profiles. To address these limitations, we developed hoodscanR, a Bioconductor package designed for neighborhood identifica...
Liu, N.
•
Martin, J.
•
Bhuva, D. D.
•
Chen, J.
...•
Davis, M. J.
biorxiv
Wed Jul 02 2025
Inferring metabolite states from spatial transcriptomes using multiple graph neural network
Metabolism serves as the pivotal interface connecting genotype and phenotype in various contexts, such as cancer reprogramming and immune metabolic reprogramming. Compared to the transcriptome, the development of the single-cell metabolome faces significant challenges. While various methods exist for predicting metabolite levels from transcriptome, their efficacy remains limited. We developed an e...
Jiaxu, L.
•
Daosheng, A.
•
Sun, W.
biorxiv
Wed Jul 02 2025
Uncovering smooth structures in single-cell data with PCS-guided neighbor embeddings
Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional representations from inherently noisy, high-dimensional single-cell data. Neighbor embedding (NE) algorithms, such as t-SNE and UMAP, are widely used to embed hi...
Ma, R.
•
Li, X.
•
Hu, J.
•
Yu, B.
biorxiv
Wed Jul 02 2025
Confidence: A Web App for Cross-Platform Differential Gene Expression Analysis, Gene Scoring, and Enrichment Analysis
RNA sequencing (RNA-seq) is used to quantify transcript levels through measurement of nucleotide sequences. To evaluate statistically significant changes in gene expression, transcript counts between samples are compared using differential expression analysis methods. However, three of the most pressing challenges in transcriptomics analyses are: 1) analytical packages produce a distinct number of...
Shastry, A.
•
Ott, B.
•
Paterson, A.
•
Simpson, M.
...•
Hindmarch, C. C. T.
biorxiv
Wed Jul 02 2025
nf-core/viralmetagenome: A Novel Pipeline for Untargeted Viral Genome Reconstruction
Motivation: Eukaryotic viruses present significant challenges for genome reconstruction and variant analysis due to their extensive diversity and potential genome segmentation. While de novo assembly followed by reference database matching and scaffolding is a commonly used approach, the manual execution of this workflow is extremely time-consuming, particularly due to the extensive reference cura...
Klaps, J.
•
Lemey, P.
•
nf-core community,
•
Kafetzopoulou, L. E.
biorxiv
Wed Jul 02 2025
Benchmarking Large Language Models for Pathogen-Disease Classification in Post-Acute Infection Syndromes
Post-Acute Infection Syndromes (PAIS) are medical conditions that persist following acute infections from pathogens such as SARS-CoV-2, Epstein-Barr virus, and Influenza virus. Despite growing global awareness of PAIS and the exponential increase in biomedical literature, only a small fraction of this literature pertains specifically to PAIS, making the identification of pathogen-disease associati...
Khalid, S. M.
•
Woelker, T.
•
Molano, L.-A. G.
•
Graf, S.
•
Keller, A.