AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice

Ankita Vaishnobi Bisoi; Bharath Ramsundar

q-bio.GNFeb 19, 2026

AgriVariant: Variant Effect Prediction using DeepChem-Variant for Precision Breeding in Rice

Authors: Ankita Vaishnobi Bisoi, Bharath Ramsundar

Organizations: BITS Pilani Goa Campus, India Goa, India · Deep Forest Sciences California, USA

Abstract

Predicting functional consequences of genetic variants in crop genes remains a critical bottleneck for precision breeding programs. We present AgriVariant, an end-to-end pipeline for variant-effect prediction in rice (Oryza sativa) that addresses the lack of crop-specific variant-interpretation tools and can be extended to any crop species with available reference genomes and gene annotations. Our approach integrates deep learning-based variant calling (DeepChem-Variant) with custom plant genomics annotation using RAP-DB gene models and database-independent deleteriousness scoring that combines the Grantham distance and the BLOSUM62 substitution matrix. We validate the pipeline through targeted mutations in stress-response genes (OsDREB2a, OsDREB1F, SKC1), demonstrating correct classification of stop-gained, missense, and synonymous variants with appropriate HIGH / MODERATE / LOW impact assignments. An exhaustive mutagenesis study of OsMT-3a analyzed all 1,509 possible single-nucleotide variants in 10 days, identifying 353 high-impact, 447 medium-impact, and 709 low-impact variants - an analysis that would have required 2-4 years using traditional wet-lab approaches. This computational framework enables breeders to prioritize variants for experimental validation across diverse crop species, reducing screening costs and accelerating development of climate-resilient crop varieties.

Figures & tables

Figure 1. AgriVariant pipeline integrating deep learning-based variant calling, plant-specific functional annotation, and quantitative deleteriousness scoring.

Figure 2. OsDREB-mediated drought stress response pathway includes stress-induced gene activation, transcription factor production, downstream target gene regulation, and resulting drought tolerance.

Figure 3. SKC1-mediated salt stress response pathway. Salt stress activates SKC1 gene expression, producing HKT1;5 transporter protein that regulates Na+/K+ homeostasis by reducing sodium accumulation in shoots while maintaining potassium levels, resulting in salt tolerance.

Figure 4. OsMT-3a-mediated heavy metal stress response pathway. Heavy metal exposure (Cd, Cu, Zn) induces OsMT-3a expression, producing metallothionein protein that binds and sequesters toxic metal ions while scavenging reactive oxygen species, conferring heavy metal tolerance.

Figure 5. DeepChem-Variant workflow: Reference genome and aligned reads are processed through candidate detection, pileup image generation (6-channel tensors), CNN classification (MobileNetV2 or InceptionV3), and VCF conversion to produce annotated variant calls.

Figure 6. Functional annotation workflow mapping variants from genomic position through codon extraction and translation to amino acid change

Figure 7. Composite Scoring combining Grantham Score and BLOSUM62 Score

Background Context (Known from Simulation)
Gene ID	Os01g0165000
Gene Name	DREB2A
Chromosome:Position	chr01:3358191
Ref $\rightarrow$ Alt Nucleotide	G $\rightarrow$ A
AgriVariant Predictions (Validated Outputs)
Ref $\rightarrow$ Alt Codon	G G G $\rightarrow$ G A G

Table 1. AgriVariant validation of a missense OsDREB2a variant. Simulated gene context (top) and automated functional annotation with MODERATE-impact classification (bottom). Green highlights denote correct predictions.

Background Context (Known from Simulation)
Gene ID	Os01g0968800
Gene Name	DREB1F
Chromosome:Position	chr01:42727659
Ref $\rightarrow$ Alt Nucleotide	G $\rightarrow$ A
AgriVariant Predictions (Validated Outputs)
Ref $\rightarrow$ Alt Codon	GG G $\rightarrow$ GG A

Table 2. AgriVariant validation of a synonymous OsDREB1F variant. Simulated gene context (top) and automated functional annotation with LOW-impact classification (bottom). Green highlights denote correct predictions.

Background Context (Known from Simulation)
Gene ID	Os01g0307500
Gene Name	SKC1
Chromosome:Position	chr01:11462201
Ref $\rightarrow$ Alt Nucleotide	T $\rightarrow$ A
AgriVariant Predictions (Validated Outputs)
Ref $\rightarrow$ Alt Codon	T GT $\rightarrow$ A GT

Table 3. AgriVariant validation of a missense SKC1 variant. Simulated gene context (top) and automated functional annotation with MODERATE-impact classification (bottom). Green highlights denote correct predictions.

Variant Type	High Impact	Medium Impact	Low Impact	Total
Substitutions (SNVs)	112	171	284	567
Insertions	157	238	361	756
Deletions	84	38	64	186
Total	353	447	709	1,509

Table 4. Deleteriousness distribution across mutation types for OsMT-3a variants.

Dataset	Accuracy	Precision	Recall	F1-Score
Training/Validation	0.9537	0.9529	0.9537	0.9532
Test Set (Same Subspecies)	0.9530	0.9539	0.9530	0.9532
Test Set (Different Subspecies)	0.9594	0.9606	0.9594	0.9598

Table 5. Model performance across training and test datasets. The training subspecies was Indica, while the different subspecies tested was Temperate Japonica. Precision, Recall, and F1-Scores are weighted averages.

Genomics

Genomics uses computational and experimental methods to study genomes, genetic variation, gene regulation, and their links to traits and disease.

See all 125 papers

MixINN: Accelerating Plant Breeding by Combining Mixed Models and Deep Learning for Interaction Prediction
May 6, 2026Aike Potze, Fred van Eeuwijk, Ioannis N. AthanasiadisMixed-Effects Models Crop Yield Prediction
Artificial Intelligence Group, Wageningen University & Research · Mathematical & Statistical Methods Group (Biometris), Wageningen University & Research
ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction
Feb 28, 2026Kuldeep Pathak, Kapil Ahuja, Eric de SturlerGenomics Convolutional Neural Networks
Department of Computer Science and Engineering, Indian Institute of Technology Indore, India 453552 · Department of Mathematics, Virginia Tech, Blacksburg, USA 24061
Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants
Oct 8, 2026Pratik Dutta, Matthew B. Obusan, Max Chao +3Genomics Large Language Model-Guided Scientific Discovery
Stony Brook University, Stony Brook, NY, USA · Renaissance School of Medicine at Stony Brook University, Stony Brook, NY, USA

May 6, 2026J/K move · Enter open · S save

MixINN: Accelerating Plant Breeding by Combining Mixed Models and Deep Learning for Interaction Prediction

Aike Potze, Fred van Eeuwijk, Ioannis N. Athanasiadis

Artificial Intelligence Group, Wageningen University & Research · Mathematical & Statistical Methods Group (Biometris), Wageningen University & Research

Mixed-Effects Models Crop Yield Prediction

Open paper AskPDF arXiv

Plant breeding underpins global food security through incremental, accumulating improvements in crop yield, quality and sustainability, achieved via repeated cycles of crop ranking, selection and crossing. Climate change disrupts this process by altering local growing conditions, thereby shifting the relative performance of crop genotypes. Predicting these relative changes in yield is critical for food security. Yet, this problem remains an open challenge in plant breeding, and relatively unexplored within the AI community. We propose MixINN, an approach that first isolates high-quality genotype-environment interaction labels using mixed models, and then predicts these interactions for new crop varieties in future environmental conditions with a deep neural network. We evaluate our method on a corn multi-environment trial across the continental United States and show improved prediction of genotype ranking over current plant breeding methods. MixINN demonstrated superior performance in identifying the 20% most productive corn genotypes, leading to a 5.8% higher average yield, which further improved to 7.2% when targeting specific growing environments. These are competitive results for real-world breeding programs, demonstrating the potential of AI research in accelerating the development of climate-adapted crops, and improving future food security under climate change.

Abstract

Genomics

Explore similar work

MixINN: Accelerating Plant Breeding by Combining Mixed Models and Deep Learning for Interaction Prediction

ResGene-T: A Tensor-Based Residual Network Approach for Genomic Prediction

Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants