[KongchangAI]
Model

GeneFlow

A gene expression prediction framework for spatial transcriptomics (ST) that combines flow-matching generative modeling with structured multimodal fusion to infer the expression of large gene panels directly from histology images without complex generative pipelines.

Timeline (last 90 days)

Nov 16

GeneFlow is a framework that unifies flow-matching generative modeling with structured multimodal fusion for predicting gene expression from tissue images in spatial transcriptomics.

Unverified50%
Nov 16

GeneFlow uses a histology tokenizer and a gene tokenizer to encode tissue morphology information and cross-gene interactions within spatial spots, respectively.

Unverified50%
Nov 16

GeneFlow directly predicts spatial gene expression rather than an intermediate velocity field, and does not run the full generative trajectory at inference.

Unverified50%
Nov 16

GeneFlow achieved state-of-the-art performance across multiple spatial transcriptomics benchmarks.

Unverified50%
Nov 16

According to the paper, GeneFlow improves performance by up to 56.8% on the task of predicting 1000 genes.

Unverified50%
Nov 16

GeneFlow reduces computational cost by several orders of magnitude.

Unverified50%
Nov 16

The spot expression profiles generated by GeneFlow are biologically meaningful, not merely numerically fitted.

Unverified50%
Nov 16

GeneFlow's code is publicly available on GitHub at https://github.com/ZZhangsm/GeneFlow.

Unverified50%
Nov 16

GeneFlow is expected to promote the widespread application of spatial transcriptomics in clinical and research settings.

Unverified50%

All Facts (9)

Source Articles