AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport

Mehmet Yigit Balik, Harri Lähdesmäki

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Generative latent models for single-cell data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use GP-modeled heteroscedastic noise instead of fixed noise ς(t)=0.1 (ablation)LGP-OT · DR/Medium t=10Wasserstein distance W2: 37.41 -> 36.51Improved
use GP-modeled heteroscedastic noise instead of fixed noise ς(t)=0.1 (ablation)LGP-OT · DR/Easy t=8Wasserstein distance W2: 31.90 -> 30.74Improved
add cell-specific latent time (ablation)LGP-OT · DR/Medium t=10Wasserstein distance W2: 36.51 -> 36.33Improved
add cell type conditioning (ablation)LGP-OT · DR/Hard t=2Wasserstein distance W2: 29.40 -> 28.75Improved
add cell type conditioning (ablation)LGP-OT · DR/Easy t=8Wasserstein distance W2: 30.74 -> 30.59No clear effect
add both latent time and cell type conditioning (ablation)LGP-OT · DR/Hard t=10Wasserstein distance W2: 38.17 -> 37.88No clear effect
use LGP-OT instead of strongest baselineLGP-OT (w. time) · SC Hard t=17 and t=18Wasserstein distance W2: 17.26 -> 15.05 (t=17); 18.14 -> 15.53 (t=18)Improved
use LGP-OT instead of MIOFlowLGP-OT · DR/Hard t=10Wasserstein distance W2: 41.43 -> 38.17Improved
use LGP-OT instead of PRESCIENT in interpolationLGP-OT · DR/Easy t=8Wasserstein distance W2: 32.48 -> 30.74Improved
perturb more lineage-specific DE genes via gradient-based trajectory optimizationLGP-OT · ZB perturbation, terminal cell type fractionsfraction of cells classified as target type: classifier identified 0.93 ±0.01 Hindbrain and 0.92 ±0.02 PSMImproved
perturb non-DE genes (ablation)LGP-OT · ZB perturbationfraction of cells classified as target typeNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy