Genemap runs single-step genomic BLUP on your own pedigree, genotypes and records, keeps a time-stamped record of each animal's biological state, and joins every measurement to the season it was taken in, so the animal's state and its season sit beside its breeding values. The national ASBV and EBV catalogue you already pay for is the fastest way to start, and it stays the on-ramp rather than the headline.
| 1 | 230118 · GEBV | +$214 |
| 2 | 220074 · GEBV | +$188 |
| 3 | 231902 · EBV | +$171 |
| 4 | 210556 · GEBV | +$149 |
Two independent streams under one login. Sheep traits, joining systems and wool on one side; beef growth, fertility and carcase on the other. Pick once on sign-in and switch any time.
Built for MerinoSelect and LAMBPLAN producers. Bring your published ASBVs, your genomic test results and your own records; Genemap evaluates them on your own data and prices every trait for your enterprise.
Built for BREEDPLAN, Zoetis Inherit Select, IGS and Igenity Beef users. Bring your EBVs, genomic test results and your own kill-sheet feedback; Genemap evaluates them on your own data and prices every trait for your enterprise.
Genemap holds four kinds of information about an animal and keeps them apart so the evaluation can tell them apart: what it inherited, what state it is in, what season it was in, and what each trait is worth where it lives. The tags say what runs on a producer's data today.
The pedigree, the SNP genotype where one exists, breed composition, and breed-adjusted relationships for composites. Pedigree to five generations, with ancestors that have no record of their own carried as ghost animals so the relationships still count. Breed-adjusted relationships are a per-run option.
Every measurement on the animal, with its date and its context: weights, scans, condition, health and reproduction events, and the physiological scores from a blood sample. Any trait can be recorded any number of times; repeated records are kept as records, not averaged away. Ordinal scores are recorded against the breeder's own registered scale and refused without one.
A daily season snapshot for each property with a location: feed-gap state and pasture path from SeasonRisk where the property is mapped to a SeasonRisk enterprise, rainfall totals and their deciles against 1991 to 2020, temperature, humidity and heat load for any property with a location. Every dated record is joined to its day's snapshot when it is saved.
A dollar weight on each trait for your enterprise, worked out by an economic engine from your herd structure, the grid and the night's market prices, the same way every time, with every input shown and every weight yours to override. An AI-proposed set of weights sits beside it as a labelled comparison.
Genemap solves a single-step genomic BLUP: pedigree relationships and genomic relationships blended into one H matrix, solved by preconditioned conjugate gradient, with the genomic part built from your SNPs after allele-frequency centring.
Traits are coupled through their genetic correlations and solved trait by trait in an outer loop, so a trait with few records borrows from the ones it is correlated with. It is not one joint solve of every trait at once, and we do not call it that.
Repeated records stay as records. An animal weighed six times contributes six observations with their contemporary groups, and the repeatability model uses them as such.
Pedigree runs to five generations. Where an ancestor exists in the pedigree module but has no animal record, it enters the relationship matrix as a ghost so its descendants stay related. On the reference herd that links 129 of 217 animals through 378 ghost ancestors.
Composites and crossbreds can be evaluated on a breed-adjusted relationship matrix, centred within each breed, so a between-breed relationship reads as zero instead of as a spurious negative. It is a per-run option and the run records which matrix it used.
On request, Genemap can estimate a heritability from your data for a single-trait run, using a REML estimator that passed a recovery test on simulated data. Genetic correlations come from the published literature.
Every run reports its basis per trait: estimated by the gated estimator, or supplied from the published literature, and which.
Simulated populations with known parameters, 20 replicates per cell, criteria fixed before the numbers were read. A cell passes only if the estimate is unbiased, its reported standard error is honest, every replicate converged, none sits on a boundary, and the replicates agree with one another.
| Animals | Heritability | Repeatability | Genetic correlation |
|---|---|---|---|
| 500 | passes | passes | not identifiable at this size (replicate spread 0.33 against a true 0.50) |
| 2,000 | passes | passes | passes (bias +0.03, spread 0.11) |
| 5,000 | passes | passes | passes (bias 0.00, spread 0.04) |
Genemap therefore uses no genetic correlation estimated on fewer than 2,000 animals recorded on both traits, and no heritability or repeatability from fewer than 500. Below the floor a run uses the published parameter and says so per trait.
A blood sample goes to any laboratory that returns raw gene counts. The delivery is uploaded as three files: the run's identity, one row per sample, and the count matrix. Each sample is matched to an animal through a worksheet and passes a quality gate that checks mapping rate, read depth, RNA integrity where supplied, and a sex check against the registry, with thresholds that name their source.
Genemap normalises the counts itself, estimates a batch effect where the design allows it and refuses to when it does not, and scores each sample against the definitions registered for that tissue.
A score is placed on a reference range built from the Australian ruminant samples on the platform for the same tissue, age class and, once a breed group holds ten scorable results, the same breed group. A range needs ten scorable results before it exists, and the placement says which range it sits on and why.
What comes back is a value, a percentile and a band, with the full provenance: the run, the normalisation version, the batch model, the reference snapshot, the software version and the engine's commit. It is shown on the animal's page beside its breeding values and never inside them.
Expression is not used in breeding values. No heritability or genetic correlation has been estimated for any expression score, and the table that would register one refuses a genetic parameter by constraint. Before that changes, two things have to happen: enough animals sampled at least twice on a validated definition for the repeatability gate, which is 500, and a definition that has been validated rather than illustrative. Every definition on the platform today is labelled Illustrative.
SeasonRisk produces a season snapshot for each property every day: rainfall and its 30-day and 90-day deciles against the 1991 to 2020 record for that spot, maximum and minimum temperature, humidity, and a heat-load index, plus the feed-gap state, days of feed and pasture-quality path from the SeasonRisk feed-gap model where the property is mapped to a SeasonRisk enterprise.
When a weight, a scan, a score or a blood sample is saved, it is joined to its property's snapshot for that date in the same transaction. Records saved before the channel existed are back-filled after each daily run.
On the animal's page the environment is shaded under every series: green for a feed surplus, red for a deficit, amber for a dry decile, blue for a wet one, so a drop in condition can be read against the season it happened in. The expression profile shows each sampling session against the season it was sampled in.
The reference property has 365 days of snapshots live. Environment is recorded beside the genetics today; it is not yet a term in the evaluation, and the section on what we do not claim says what that would take.
A national index prices every trait once, against an average enterprise, and hands the same weights to everyone. Genemap prices each trait for your enterprise, and you can see every input behind every weight and change any weight you disagree with.
The weights come from an economic engine. It builds a steady-state model of your breeding herd or flock from your farm profile, solves a least-cost ration for each class of animal and reads the shadow prices off that ration, so a kilogram of extra mature cow weight is charged what it costs to feed on your feed base. It prices carcase traits against the grid one threshold at a time, weighted by how much of your drop sits at each threshold, and it values fertility and survival by how far an improvement flows through the herd over the years, discounted back to today. Run on the same inputs it returns the same weights, and each set is stored with a fingerprint of the inputs that made it.
| 1 | 230118 |
| 2 | 220074 |
| 3 | 210556 |
| 1 | 210556 |
| 2 | 230118 |
| 3 | 228841 |
The market prices are read each night from the indicators Meat & Livestock Australia publishes, and every snapshot records the source, the time it was retrieved and the sale date of each number. If an indicator cannot be read, the last value is carried forward and marked as stale, and nothing is estimated. Each set of weights is stored against the snapshot it was computed from.
The engine prices a trait where the link from the breeding value to the farm's money runs inside the model. For cattle that is carcase weight, store weight, mature cow weight, P8 fat against the grid, days to calving through the length of your joining, heifer pregnancy, stayability as a provisional range, and net feed intake at what your finishing ration costs per kilogram of dry matter. For sheep it is sale weight, ewe weight, dressing percentage and lambs born and weaned. Growth is priced once: as a heavier carcase if you sell at a fixed age, or as fewer days on feed if you sell at a fixed weight. Marbling, eye muscle, yield and fat are priced when your grid pays on them and you have entered the grid with the average and spread of your drop. Calving and lambing ease, and milk in cattle, are priced when you enter the two or three figures only you can supply. Where a trait has no channel, or pricing it would count the same money twice, it gets no weight, the row says why, and the ranking keeps its standard weight for that trait.
The economics profile collects every figure the engine reads: herd structure, joining and retention, the sale point and your grid, what you pay for feed and what your pasture can supply. Each one says what it changes, and the page scores how much of the profile is your own. Anything you leave blank runs on a labelled reference value, and the rank page says, trait by trait, which weights rest on a reference value and not on your own figures. Fleece traits are held until the AWEX price guides are licensed, and the pricing of resilience in hard seasons is a framework that is not applied.
A daily check confirms that the night's market snapshot is fresh and that every organisation with animals has a current set of weights, repairs a missing set by running the engine, and writes the result to a ledger. The tag on this section reads Live only when that check has passed within the last day and a half.
Around the engine sit the pieces that were already live: traits with an optimum in the middle, like mature cow weight and birth weight, are priced on a curve rather than a straight line; an animal whose genetic growth potential exceeds what the pasture can feed is discounted by the nutrition fit; the breed class is shifted by your property's heat-load index; and once kill-sheet and sale data build up, a hierarchical model calibrates the weights against what your cohorts actually returned.
Breeding values in, your weights applied, one dollar index out, and the rank change against the national index. The whole chain on a single bull.
The figures in this table are illustrative. On a live account each weight is the engine's where the engine prices the trait and the ranking's standard weight where it does not, stored against the market snapshot it was computed from, and you can change any of them.
| Trait (EBV in) | EBV | Your weight | $ contribution |
|---|---|---|---|
| 400-Day Weight | +72 kg | $1.05 / kg | +$75.60 |
| Intramuscular Fat | +2.4 % | $22.00 / % | +$52.80 |
| Days to Calving | −6.0 days | −$6.00 / day | +$36.00 |
| Carcase Weight | +24 kg | $1.40 / kg | +$33.60 |
| Eye Muscle Area | +5.0 cm² | $7.00 / cm² | +$35.00 |
| Mature Cow Weight | +18 kg | −$0.70 / kg | −$12.60 |
| Genemap $ index | +$220 | ||
Why it moved. The national index is growth-led, and on raw growth this bull is moderate, so it sits mid-pack at #38. This enterprise joins its own heifers and sells on a marbling grid, so short days to calving and high intramuscular fat are worth more here and mature cow weight costs money. On those weights the same bull is #5.
Download your ASBVs or EBVs from MerinoSelect, LAMBPLAN, BREEDPLAN, Angus TACE, Zoetis Inherit Select, IGS or Igenity Beef, drop the file in, and the format is detected.
Every animal ranked under your enterprise's weights, with the weights shown and editable. Load genotypes and the rank can be re-solved on the genomic relationships; the solve writes back to your animals only when you ask it to.
The maximum justifiable bid for a sire under your service-life net present value, with P10, P50 and P90 from a 1,000-sample Monte Carlo.
Minimum-cost-flow mate allocation under per-generation inbreeding caps, with progeny merit broken down by trait.
Rank a listed animal, a partner's animal or your own under your profile and your weights.
Upload the inventory and a budget and get a stratified plan and a paddock-ordered muster list for one yard run.
Record any trait in the registry, one row per event, against a registered scale where the trait is scored. Import a file and the whole delivery is written in one transaction or not at all.
Two businesses that sign a bilateral, revocable consent can pool genotypes and pedigree for one another's solves. Phenotypes and breeding values do not cross. The solve records that pooling was on.
Crossbred and composite animals are credited for heterosis through a Pollak-Quaas covariate, reported per trait.
Switch property and enterprise from a pinned pill; the header always shows which one the ranks belong to.
Every upload, solve, profile change, consent and sampling plan is logged to your account with what it produced.
An assistant that answers questions about your own numbers, such as why an animal ranks where it does. Its answers are generated by a language model from your account's data; the numbers it quotes are yours, the wording is the model's.
Your whole herd or flock as CSV and JSON, source values and Genemap's outputs together, any time.
A breeding value reports the model, the relationship matrix it used, whether the operator or the dense path solved it, and per trait whether the variance components were estimated or supplied and from which source. A score reports its run, normalisation version, batch model and reference snapshot. A season snapshot reports the weather source, the climatology, the formula for the heat-load index and the run that wrote it.
An estimator has to pass a recovery test before its output is shown. The variance-component estimator passed on 8 of 9 simulated cells and failed the ninth honestly. The BayesC marker prior passed its test; BayesR did not and is not used for delivery. The operator path for large populations has a measured agreement gate against the dense solve and does not deliver where the gate has not been met.
After each deploy the live solver's source is downloaded and compared with the commit that was tested; the version, the hash and the commit are written in the deployment ledger.
Every formula on the docs page names its reference, every request option is documented, and heritabilities, genetic correlations and economic weights can be overridden on a run.
A file that partly matches is shown as a refusal with a worksheet, not quietly dropped. A trait that needs a scale and has none is refused at the database. A reference range with fewer than ten results is not built, and the placement says so.
Your data is yours to take as open CSV and JSON, and imports come from any of the seven national evaluations.
Stating this is part of how the platform is meant to work.
Download your ASBVs or EBVs, drop them in, and see every animal ranked for your enterprise.