Salient

Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE

Du, J. T., Chartrand, T., Jayadev, S., Prater, K. E., Lin, K. Z.
10.1101/2025.11.19.689368 · was preprinted
method development code ↗ benchmarked
Surfaced because: unusual independent discussion, open code, benchmarked against baselines.
relevance 0.38 openness 0.50 novelty 0.38 attention 0.73

Abstract

BackgroundCellular morphological transitions are observed across many diseases, yet their functional role remains unclear because few technologies profile form and function in the same cell. Linking single-cell morphology to transcriptomics is difficult: the two modalities share no feature correspondence and are typically measured in different cells. MethodsWe present GeoAdvAE, a geometry-aware adversarial autoencoder for diagonal (unpaired) integration of single-cell morphology and single-cell RNA sequencing. GeoAdvAE couples modality-specific variational autoencoders with a Gromov-Wasserstein regularizer and an adversarial discriminator to embed unpaired morphologies and transcriptomes into a shared latent space that preserves both reconstruction fidelity and cross-modal geometry. ResultsUsing patch-seq neurons with joint morphology-RNA measurements as ground truth, GeoAdvAE attains the best cross-modal cell-type matching accuracy among diagonal integration methods, outperforming optimal-transport, latent-alignment, and adversarial baselines. Applied to 98 CAJAL-quantified microglial morphologies and 31,948 single-cell transcriptomes from the 5xFAD Alzheimers disease model, GeoAdvAE recovers a one-dimensional axis that aligns the two modalities. Integrated-gradient attribution highlights transcriptomic shifts (DNA repair in ramified microglia; cell killing in amoeboid microglia), nominates gene markers (Ms4a6b; Ftl1 /Fth1), and reveals disease-associated microglia signatures that are decoupled from morphology. ConclusionsGeoAd-vAE provides a scalable and interpretable approach to connecting cellular "form" and "function" when joint profiling of morphology and transcriptomics is impractical. Our method is publicly available at https://github.com/turbodu222/GeoAdVAE.

Lifecycle

Discussion

Moderated digest of third-party discussion on Bluesky — substantive endorsement and critique.

  • #NeuroDegeneration preprints @prepub-neurodegen.bsky.social · 230 followers neutral

    Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE #NeuroDegeneration 🧪🧠 https://www.biorxiv.org/content/10.1101/2025.11.19.689368v1

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗
  • #SingleCell preprints @prepub-singlecell.bsky.social · 721 followers neutral

    Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE #SingleCell 🧪🧬🖥️ https://www.biorxiv.org/content/10.1101/2025.11.19.689368v1

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗
  • AI x Bio Discovery @aixbiobot.bsky.social · 787 followers neutral

    Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE [updated] aligns cell form & function in shared latent space, uncovers transcr. shifts & gene markers corr. w/ morph changes.

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗
  • bioRxiv Genomics @biorxiv-genomic.bsky.social · 6974 followers neutral

    Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE https://www.biorxiv.org/content/10.1101/2025.11.19.689368v1

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗
  • bioRxivpreprint @biorxivpreprint.bsky.social · 8895 followers neutral

    Integrating morphology and gene expression of neural cells in unpaired single-cell data using GeoAdvAE https://www.biorxiv.org/content/10.1101/2025.11.19.689368v1

    ♡ 0 ⇄ 0 💬 0 view on Bluesky ↗