From DNA to Harvest
Digital Seed is the AI-powered, end-to-end crop genomics platform connecting breeding workflows, stress-resistance discovery, and yield prediction — all in one place. Built for farmers, breeders, and agricultural researchers.
45
Analysis modules
15
Crop reference genomes
6
Sequencing pipelines
THE PLATFORM
A working glossary of genome-to-field analysis.
Every module is production-accurate, callable via API and covered by SLAs. Grouped by what you're trying to answer — not by algorithm family.
See what's new →
31 of 31 modules
01 / Genome-to-field
Core research modules
The workhorse pipelines every project starts from — upload real data, get validated statistics back.
02 / Deep methods
Advanced genomics
Peer-reviewed algorithms for haplotype structure, association mapping and genomic selection.
03 / Raw reads to results
Sequencing pipelines & big-data compute
Nextflow pipelines, reduced-representation genotyping and WGS downstream analysis — with cloud compute and GB-scale uploads.
04 / Operate at scale
Platform tooling
Everything around the science — search, quotas, benchmarks, and organisation for your data.
Lab tier · 11 extensionsNew
Advanced module extensions
Advanced analyses embedded in their host modules — each tile jumps to the runner that hosts it.
ADE-GBLUP variance components
40 samples × 200 markers
Finlay–Wilkinson G×E stability
6 genotypes × 5 envs
Smith–Hazel selection index
3 traits
Colocalisation (ABF, PP0–PP4)
30 SNPs · 2 traits
Cox-PH survival GWAS
200 samples × 3 markers
Pairwise epistasis (G×G, BH q)
300 samples × 5 markers
Regional plot (LocusZoom-style)
40 SNPs · 5 kb window
IM/CIM QTL mapping
200 samples × 12 loci
Stratified HWE (Wigginton · Fisher-combined)
2 SNPs × 2 strata
Sex check (X-heterozygosity F-stat)
20 samples × 25 X-markers
π windows + block-bootstrap CI
300 sites · 5 kb windows
LIVE PIPELINE PREVIEW
From raw genotypes to field-ready GEBVs in five stages
The same pipeline your production runs use — visualized in real time so you can see exactly where each dataset is right now.
Held-out r² (rolling)
last 28 runs · wheat-599
r²
—
RMSE
—
runs
—
PRICING · USD
Plans that grow with your breeding program
Start free. Upgrade when you're ready to scale. Cancel anytime — no trials, monthly billing only.
Lab-tier analyses like ADE-GBLUP, Finlay–Wilkinson G×E, Smith–Hazel selection index, Coloc-ABF, Cox-PH survival GWAS, epistasis, LocusZoom, IM/CIM QTL, stratified HWE and π-windows are wired into their subject modules (GBLUP, MET, Multi-trait GS, Fine-map, GWAS+/ext, Deep Genomics, HWE/MAF and Diversity) — included on the Lab and Institute plans.
Sprout
For students
Try the platform on small datasets — no card required.
Freeforever5K tokens / mo
Start free- 1 project · 1 collaborator
- 1 GB storage · 10 runs / mo
- GWAS & Kinship (core)
- Bioinformatics Toolkit (Ensembl, NCBI, KEGG)
- Experiments history & re-run
- Omics upload with basic QC · CSV export
- Community support
Seedling
For independent researchers
Small teams running routine GWAS and GS on modest datasets.
$39/ user / month50K tokens / mo
Subscribe- 3 projects · 20 GB storage
- 100 runs / mo · uploads up to 500 MB
- GWAS, GS, GBLUP, Kinship & BLUES/BLUPs
- Diversity & Neutrality (π · θ · Tajima's D)
- 2-file Comparative Genomics
- Async job queue with live progress
- PDF & CSV reports · experiments history
- Email support · 72h SLA
Most popular
Breeder
For working breeders
Production pipelines with imputation, stress models and drilldown.
$149/ user / month250K tokens / mo
Subscribe- 10 projects · 100 GB · 500 runs / mo
- Resumable uploads up to 2 GB
- GWAS+, GS+, Multi-trait GS, Imputation, GWAS-CC
- GWAS Multi-locus (FarmCPU · MLMM)
- Population Core (AMOVA · Mantel IBD · Ne)
- Yield, Stress & Breeding Lab AI models
- 4-file Comparative Genomics + variant drilldown
- Variant Annotation & reference-genome selector
- ZIP export bundles with provenance + SHA-256 hashes
- Reproducibility bundles · 48h support
Suspended
Lab
For research teams
Multi-user collaboration and advanced population modules.
$349/ user / month1M tokens / mo
- Unlimited projects · 5 team members
- 500 GB storage · 2,000 runs / mo
- MET, Pangenome, PopGen, Structure & Field Trial
- GS Bayesian (BayesA · BayesB · Bayesian LASSO)
- Full Diversity & Neutrality (Fay–Wu H · Fu–Li D/F)
- HWE/MAF QC Lab · Kinship matrix
- Shared collections & lab notebook
- Advanced analyses in-module: ADE-GBLUP in gBLUP · Finlay–Wilkinson G×E in MET · Smith–Hazel in Multi-trait GS · Coloc-ABF in Fine-map · Cox-PH & LocusZoom in GWAS+/ext · epistasis in GWAS+ · IM/CIM QTL in Deep Genomics · stratified HWE + sex-check in HWE/MAF · π-windows in Diversity
- Audit log · basic API access · pipelines
- Priority support · 24h SLA
Suspended
Institute
For institutions
Deep genomics, QG Lab and trial design at scale.
$899/ user / month5M tokens / mo
- Unlimited members · 2 TB storage
- Unlimited runs · bulk job queue
- Deep Genomics, QG Lab, Trial Design, PRS, Field Trials
- LD decay · ROH · Fst · iHS · XP-EHH · SuSiE fine-mapping
- All advanced module extensions (Coloc-ABF · Cox-GWAS · epistasis · LocusZoom · IM/CIM · stratified HWE · π-windows) available in every host page
- API keys, webhooks & SDK
- SSO (SAML) & role-based access
- 12h support SLA
COMPARE PLANS
What changes between tiers
Every plan includes the core platform — this table shows where each tier unlocks more scale, analyses, and controls.
| Feature | Sprout | Seedling | Breeder Popular | Lab | Institute |
|---|---|---|---|---|---|
| Usage & limits | |||||
| Projects | 1 | 3 | 10 | Unlimited | Unlimited |
| Team members | 1 | 1 | 1 | 5 | Unlimited |
| Storage | 1 GB | 20 GB | 100 GB | 500 GB | 2 TB |
| Analysis runs / mo | 10 | 100 | 500 | 2,000 | Unlimited |
| Max upload size | 100 MB | 500 MB | 2 GB (resumable) | 5 GB | 20 GB |
| Genomics analyses | |||||
| GWAS, GWAS+ & GWAS-CC | Core | Full | GWAS+ | GWAS+ | GWAS+ |
| Genomic Selection (GS, GS+, GBLUP) | GS+ Multi-trait | GS+ Multi-trait | GS+ Multi-trait | ||
| BLUES / BLUPs & Kinship matrix | |||||
| Imputation & Variant Annotation | |||||
| Comparative Genomics & Pangenome | 2 files | 4 files + drilldown | 4 files + drilldown | Unlimited | |
| Yield, Stress & Breeding Lab AI | |||||
| MET · PopGen · Structure · Field Trial | |||||
| Population Core (AMOVA · Mantel IBD · Ne) | |||||
| GWAS Multi-locus (FarmCPU · MLMM) | |||||
| GS Bayesian (BayesA · BayesB · BLASSO) | |||||
| Diversity & Neutrality (π · θ · Tajima's D · Fay–Wu H · Fu–Li) | |||||
| Deep Genomics · QG Lab · Trial Design · PRS | |||||
| Bioinformatics Toolkit (Ensembl, NCBI, KEGG) | |||||
| Advanced module extensions (ADE-GBLUP · FW · Smith–Hazel · Coloc-ABF · Cox-GWAS · Epistasis · LocusZoom · IM/CIM · Stratified HWE · π-windows) | |||||
| Analysis capabilities (depth per run) | |||||
| Max samples per GWAS / GS run | 300 | 2,000 | 10,000 | 50,000 | Unlimited |
| Max markers per run | 50k | 500k | 2M | 10M | 50M |
| Traits per multi-trait job | 1 | 2 | 5 | 20 | Unlimited |
| Permutations / bootstraps | 100 | 1,000 | 10,000 | 100,000 | Unlimited |
| Cross-validation folds | 3 | 5 | 10 | 20 | Custom |
| Bayesian MCMC iterations (BayesA/B/BLASSO) | 5k | 20k | 100k | Unlimited | |
| Populations per AMOVA / pairwise Fst | 2 | 8 | 32 | 128 | Unlimited |
| MET environments per trial | 10 | 50 | Unlimited | ||
| Data inputs & formats | |||||
| CSV genotype / phenotype | |||||
| VCF (bgzipped + tabix) | |||||
| PLINK BED/BIM/FAM | |||||
| HapMap / Hapmap-Diploid | |||||
| GFF3 · GTF annotations | |||||
| FASTA / FASTQ · BAM / CRAM | |||||
| Expression matrix (RNA-seq / microarray) | |||||
| Ancestral-allele column (unfolded SFS) | |||||
| Environmental covariates (weather API) | |||||
| Pedigree / kinship uploads | |||||
| Custom reference panel / pangenome | |||||
| Collaboration & export | |||||
| CSV export | |||||
| PDF reports & printable summaries | |||||
| ZIP export bundles (provenance + SHA-256) | |||||
| Experiments history & one-click re-run | |||||
| Async job queue with live progress | |||||
| Reproducibility bundles | |||||
| Shared collections & notebook | |||||
| API access · webhooks · SDK · Bulk jobs | Basic | Full | |||
| SSO (SAML) & RBAC | |||||
| Export & queue limits | |||||
| PDF report exports / mo | 5 | 50 | 200 | 1,000 | Unlimited |
| ZIP package exports / mo | 0 | 20 | 100 | 500 | Unlimited |
| Concurrent export jobs | 1 | 2 | 3 | 5 | 10 |
| Concurrent queued analyses | 1 | 2 | 5 | 10 | 25 |
| Export job retention | 24 h | 7 days | 30 days | 90 days | 1 year |
| Job priority | Low | Standard | Standard | High | Highest |
| Support & deployment | |||||
| Support SLA | Community | 72h email | 48h | 24h priority | 12h |
| Audit log & retention | Basic | Advanced | |||
| Deployment | Shared cloud | Shared cloud | Shared cloud | Shared cloud | Shared cloud |
| Uptime SLA | — | — | 99.5% | 99.5% | 99.9% |
| Performance & reliability SLAs (p95 wall time) | |||||
| Upload p95 | 12s | 12s | 8s | 5s | 3s |
| Imputation p95 | 5s | 5s | 3s | 2s | 1.5s |
| QC pipeline p95 | 8s | 8s | 5s | 3s | 2s |
| GWAS p95 | 60s | 60s | 30s | 20s | 12s |
| Genomic prediction p95 | 30s | 30s | 15s | 10s | 7s |
| Live perf regression dashboard | |||||
| Concurrent load-test reports | |||||
| CPU / memory flamegraph profiles | |||||
GLOSSARY
Feature glossary
Plain-language definitions for every analysis module and export/queue capability.
GWAS, GWAS+ & GWAS-CC
Genome-wide association: baseline (GWAS), advanced with covariates & annotation (GWAS+), and case–control binary phenotypes (GWAS-CC).
Genomic Selection (GS, GS+, GBLUP)
Predict breeding values from genotypes. GS uses rrBLUP; GS+ adds kernel/Bayesian priors; GBLUP uses the genomic relationship matrix.
BLUES / BLUPs & Kinship matrix
Best linear unbiased estimates/predictions for field phenotypes plus realized kinship (GRM) computation.
Imputation & Variant Annotation
Impute missing genotypes against a reference panel and annotate variants with gene, consequence, and functional impact.
Comparative Genomics & Pangenome
Cross-genome synteny, orthologs, and core/accessory (PAV) analysis across a pangenome.
Yield, Stress & Breeding Lab AI
Applied ML pipelines for yield prediction, stress tolerance, and pedigree/genotype-based breeding decisions.
MET · PopGen · Structure · Field Trial
Multi-environment trials with G×E, population genetics (Fst, LD, diversity), ancestry/PCA structure, and field trial design.
Population Core (AMOVA · Mantel IBD · Ne)
Analysis of molecular variance, Mantel isolation-by-distance tests with permutation p-values, and LD-based effective population size (Ne) estimation.
GWAS Multi-locus (FarmCPU · MLMM)
Multi-locus association mapping: FarmCPU iterative fixed/random and MLMM stepwise selection with extended BIC.
GS Bayesian (BayesA · BayesB · BLASSO)
Bayesian genomic prediction via Gibbs sampling: BayesA, BayesB (with π), and Bayesian LASSO with cross-validation.
Diversity & Neutrality (π · θ · Tajima's D · Fay–Wu H · Fu–Li)
Nucleotide diversity π, Watterson's θ, Tajima's D, and unfolded Fay–Wu H / Fu–Li D & F when ancestral alleles are provided.
Deep Genomics · QG Lab · Trial Design · PRS
Fine-mapping (SuSiE), selection signatures, quantitative-genetics workbench, randomized trial layouts, and polygenic risk/merit scores.
Bioinformatics Toolkit (Ensembl, NCBI, KEGG)
Query external biological databases directly from the app: Ensembl gene lookups, NCBI records, KEGG pathways.
Advanced module extensions (ADE-GBLUP · FW · Smith–Hazel · Coloc-ABF · Cox-GWAS · Epistasis · LocusZoom · IM/CIM · Stratified HWE · π-windows)
Ten advanced analyses embedded directly into their host modules (gBLUP, MET, Multi-trait GS, Fine-map, GWAS+/ext, Deep Genomics, HWE/MAF, Diversity): additive+dominance+epistasis GBLUP variance, Finlay–Wilkinson G×E stability, Smith–Hazel selection index, Giambartolomei ABF colocalisation (PP0–PP4), Efron-equivalent Cox-PH survival GWAS, pairwise A×A epistasis with BH q-values, LocusZoom-style regional plots, IM/CIM QTL with Churchill–Doerge permutation thresholds, Wigginton exact + Fisher-combined stratified HWE with PLINK-style sex check, and sliding-window nucleotide diversity π with moving-block bootstrap CIs.
CSV export
Download raw tables (SNP hits, EBVs, QC stats) as CSV files.
PDF reports & printable summaries
One-click styled PDF reports with plots and result tables, ready to share.
ZIP export bundles (provenance + SHA-256)
Full result bundle: report.pdf, results.json, metadata.csv, dataset/pipeline IDs and SHA-256 integrity hashes for every file.
Experiments history & one-click re-run
Every run is saved with its parameters and inputs; re-run any experiment with a single click.
Async job queue with live progress
Heavy runs execute in a background queue; progress streams to the UI with retries on transient failures.
Reproducibility bundles
Signed export packages that capture inputs, parameters, versions, and outputs so any collaborator can reproduce the run.
Shared collections & notebook
Team-shared collections of datasets and results plus a collaborative lab notebook.
API access · webhooks · SDK · Bulk jobs
Programmatic REST access, outbound webhooks on job events, typed SDK, and bulk job submission.
SSO (SAML) & RBAC
SAML single sign-on with fine-grained role-based access control.
PDF report exports / mo
Number of standalone PDF report downloads permitted per month.
ZIP package exports / mo
Number of full ZIP result bundles (PDF + JSON + metadata + hashes) permitted per month.
Concurrent export jobs
How many export packages can be built in parallel by a single user.
Concurrent queued analyses
How many heavy analyses can run at once for your workspace.
Export job retention
How long completed export artifacts remain downloadable.
Job priority
Queue priority tier — higher tiers preempt lower-tier jobs during peak load.
Support SLA
Guaranteed first-response time for support tickets.
Audit log & retention
Immutable log of user and system actions with configurable retention.
Deployment
Where the platform runs — shared multi-tenant cloud or your own private/on-prem environment.
Uptime SLA
Contractual monthly uptime guarantee.
Projects
Distinct workspaces isolating datasets, runs, and members.
Team members
Seats included in the plan.
Storage
Total data at rest across datasets and result bundles.
Analysis runs / mo
Number of analysis jobs you can launch each month.
Max upload size
Largest single file the uploader accepts (resumable on higher tiers).
All plans include SOC 2-ready infrastructure · GDPR compliant · Data export anytime
READY WHEN YOU ARE
From DNA to harvest — in one platform.
Join the researchers, breeders and seed companies shipping the next generation of crops with Digital Seed.