# Reciprocal BLUP: A Predictability-Guided Multi-Omics Framework for Plant Phenotype Prediction

## TL;DR

This paper introduces a new method called Reciprocal BLUP that improves plant phenotype prediction by integrating genomic, metabolomic, and microbiomic data.

## Contribution

The novel contribution is a predictability-guided multi-omics framework that enhances phenotype prediction by analyzing cross-layer relationships.

## Key findings

- Metabolome features were highly predictable from microbiome data, showing an asymmetric relationship.
- Phenotype prediction models using metabolomic or microbiomic data outperformed genomic models under drought conditions.
- Reciprocal BLUP improves prediction accuracy by selecting features with high cross-omics predictability.

## Abstract

Sustainable improvement of crop performance requires integrative approaches that link genomic variation to phenotypic expression through intermediate molecular pathways. Here, we present Reciprocal Best Linear Unbiased Prediction (Reciprocal BLUP), a predictability-guided multi-omics framework that quantifies the cross-layer relationships among the genome, metabolome, and microbiome to enhance phenotype prediction. Using a panel of 198 soybean accessions grown under well-watered and drought conditions, we first evaluated four direction-specific prediction models (genome → microbiome, genome → metabolome, metabolome → microbiome, and microbiome → metabolome) to estimate the predictability of individual omics features. We evaluated whether subsets of features with high cross-omics predictability improved phenotype prediction. These cross-layer models identify features that play physiologically meaningful roles within multi-omics systems, enabling the prioritization of variables that capture coherent biological signals enriched with phenotype-relevant information. Consequently, metabolome features were highly predictable from microbiome data, whereas microbiome predictability from metabolomic data was weaker and more environmentally dependent, revealing an asymmetric relationship between these layers. In the subsequent phenotype prediction analysis, the model incorporating predictability-based feature selection substantially outperformed models using randomly selected features and achieved prediction accuracies comparable to those of the full-feature model. Under drought conditions, the phenotype prediction models based on metabolomic or microbiomic kernels (MetBLUP or MicroBLUP) outperformed the genomic baseline (GBLUP) for several biomass-related traits, indicating that the environment-responsive omics layers captured phenotypic variations that were not explained by additive genetic effects. Our results highlight the hierarchical interactions among genomic, metabolic, and microbial systems, with the metabolome functioning as an integrative mediator linking the genotype, environment, and microbiome composition. The Reciprocal BLUP framework provides a biologically interpretable and practical approach for integrating multi-omics data, improving phenotype prediction, and guiding omics-based feature selection in plant breeding.