Skip to main content

Model reference — AI Medical · Genomics

AI models for Genomic sequence analysis

Two reported results anchor this group: about 0.95 AUROC classifying pathogenic against benign BRCA1 variants zero-shot for the long-context genome model, and 95 percent top-k accuracy for the splice-site tool that is already standard in clinical variant pipelines.

The models divide by what they consume. Long-context genome models read up to a megabase and score variants without task-specific training. Sequence encoders produce embeddings for your own predictors. Rule-and-ML hybrids take a VCF plus phenotype terms and return a ranked gene list.

Every model on this page runs as part of a managed AI pipeline in our GPU clusters, with a dedicated private cluster in our cloud or an on-premise installation where medical governance requires it. Output is decision support for a qualified professional to review, not a diagnosis.

Genomic sequence analysis service AI Medical services Pricing

Input type — DNA and RNA sequence

Models in this group take nucleotide sequence, a VCF, or sequence plus phenotype terms. Each table gives three hardware tiers — Minimum, the smallest configuration on which the model runs correctly; Medium, the usual production configuration; and High, a configuration sized for peak volume. The rate is what one server of that tier processes per hour. Use these figures for initial sizing only. Before production we benchmark your own data to confirm accuracy, latency, throughput and cost.

Evo 2 (1B / 7B / 40B, 1M-token context)

Vendor: Arc Institute with NVIDIA and Stanford

What it does: reads up to a megabase of sequence in one context and scores variants with no task-specific training — about 0.95 AUROC separating pathogenic from benign BRCA1 variants zero-shot, and strong where classical tools are weakest, outside coding regions.

About 0.95 AUROC classifying pathogenic against benign BRCA1 variants zero-shot; strong non-coding variant performance (developer-reported, Nature 2026).

RequirementMinimumMediumHigh
GPU typeA100 80 GBA100 80 GB ×2H100 80 GB ×4
VRAM80 GB160 GB320 GB
vCPUs244896
RAM128 GB256 GB512 GB
Server1× A100 SXM 80 GB2× A100 SXM 80 GB4× H100 SXM 80 GB
Rate (sequences/hour)≈ 300≈ 1,100≈ 2,700

Evo

Vendor: Arc Institute

What it does: is the first-generation genome model, for sequence likelihoods, embeddings and generation at a lower hardware cost than Evo 2.

Task-dependent across genomic modelling and generation tasks.

RequirementMinimumMediumHigh
GPU typeL40S 48 GBA100 80 GBH100 80 GB ×2
VRAM48 GB80 GB160 GB
vCPUs163264
RAM64 GB128 GB256 GB
Server1× L40S 48 GB1× A100 SXM 80 GB2× H100 SXM 80 GB
Rate (sequences/hour)≈ 800≈ 2,800≈ 7,200

Nucleotide Transformer v2 (50M–2.5B)

Vendor: InstaDeep with NVIDIA

What it does: matches or beats specialised models across 18 genomics tasks from one encoder, with sizes from 50M to 2.5B so the footprint can follow the budget.

Matches or beats specialised models on 18 genomics prediction tasks (independent).

RequirementMinimumMediumHigh
GPU typeRTX 3090L40S 48 GBA100 80 GB
VRAM24 GB48 GB80 GB
vCPUs81632
RAM32 GB64 GB128 GB
Server1× RTX 3090 24 GB1× L40S 48 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 2,500≈ 8,800≈ 22,500

DNABERT-2

Vendor: DNABERT-2 authors

What it does: encodes DNA efficiently for classification and regression, a practical base when your labelled set is small.

Task-dependent across genomic sequence classification and regression benchmarks.

RequirementMinimumMediumHigh
GPU typeRTX 3060RTX 4090A100 80 GB
VRAM12 GB24 GB80 GB
vCPUs61224
RAM16 GB32 GB64 GB
Server1× RTX 3060 12 GB1× RTX 4090 24 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 8,000≈ 28,000≈ 72,000

HyenaDNA

Vendor: Hazy Research / Stanford

What it does: handles very long sequences at low cost, which is what long-range regulatory work needs.

Task-dependent across long-range genomics benchmarks.

RequirementMinimumMediumHigh
GPU typeRTX 3090L40S 48 GBA100 80 GB
VRAM24 GB48 GB80 GB
vCPUs81632
RAM32 GB64 GB128 GB
Server1× RTX 3090 24 GB1× L40S 48 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 2,500≈ 8,800≈ 22,500

Enformer

Vendor: Google DeepMind

What it does: predicts expression and epigenomic tracks from about 200 kb of sequence, at r around 0.85 across tracks — the reference for sequence-to-expression work.

Substantial improvement over prior models for gene expression prediction from sequence, r about 0.85 across tracks (independent).

RequirementMinimumMediumHigh
GPU typeRTX 3090L40S 48 GBA100 80 GB
VRAM24 GB48 GB80 GB
vCPUs81632
RAM32 GB64 GB128 GB
Server1× RTX 3090 24 GB1× L40S 48 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 2,500≈ 8,800≈ 22,500

GET

Vendor: GET authors

What it does: predicts transcription and regulatory activity using cellular context alongside the sequence, rather than sequence alone.

Task-dependent across transcription and regulatory-genomics benchmarks.

RequirementMinimumMediumHigh
GPU typeRTX 3090L40S 48 GBA100 80 GB
VRAM24 GB48 GB80 GB
vCPUs81632
RAM32 GB64 GB128 GB
Server1× RTX 3090 24 GB1× L40S 48 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 2,500≈ 8,800≈ 22,500

SpliceAI

Vendor: Illumina

What it does: predicts splice gain and loss at 95 percent top-k accuracy and is already standard in clinical variant pipelines — the least speculative model on this page.

95 percent top-k accuracy for splice site prediction; standard tool in clinical variant pipelines (independent, Cell 2019).

RequirementMinimumMediumHigh
GPU typeRTX 3060RTX 4090A100 80 GB
VRAM12 GB24 GB80 GB
vCPUs61224
RAM16 GB32 GB64 GB
Server1× RTX 3060 12 GB1× RTX 4090 24 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 8,000≈ 28,000≈ 72,000

AlphaMissense

Vendor: Google DeepMind

What it does: scores missense variants for pathogenicity from the protein sequence, for triage inside a variant pipeline.

Benchmark-dependent; high pathogenic against benign discrimination reported, no single universal accuracy.

RequirementMinimumMediumHigh
GPU typeRTX 3060RTX 4090A100 80 GB
VRAM12 GB24 GB80 GB
vCPUs61224
RAM16 GB32 GB64 GB
Server1× RTX 3060 12 GB1× RTX 4090 24 GB1× A100 SXM 80 GB
Rate (sequences/hour)≈ 8,000≈ 28,000≈ 72,000

Exomiser

Vendor: Monarch Initiative / Jackson Laboratory

What it does: ranks candidate causal variants against the patient’s own phenotype terms, putting the causative variant first in 70–97 percent of solved rare-disease cases. A rule-and-ML hybrid, fully on-premise, and the most defensible option in a clinical pipeline.

Causative variant in the top rank in about 70–97 percent of solved rare-disease cases depending on cohort (independent).

RequirementMinimumMediumHigh
GPU typeRTX 3060RTX 4090L40S 48 GB
VRAM12 GB24 GB48 GB
vCPUs4816
RAM16 GB32 GB64 GB
Server1× RTX 3060 12 GB1× RTX 4090 24 GB1× L40S 48 GB
Rate (sequences/hour)≈ 20,000≈ 70,000≈ 180,000

Choosing between them

For a clinical rare-disease pipeline, the phenotype-driven tool is the one with cohort-level evidence — causative variant in the top rank in 70–97 percent of solved cases. For research on non-coding and regulatory variants, the long-context models are the substantive advance. Several are non-commercial, and one is GPL, which we check against your intended use.

Accuracy figures above are those the producers and independent evaluations report, on their own test sets. They are a shortlist tool, not a prediction of what you will see. At the start of a project we run a short proof of concept on a sample of your own data, which replaces them with real figures — so the cost and the schedule for the full engagement are known before anything is committed.

Genomic sequence analysis service AI Medical services Pricing

From benchmark to production

Send a representative sample, your expected volume and your latency target for genomic sequence analysis. We benchmark the shortlisted models, recommend the lowest-cost GPU configuration that meets the target, and scale it from pilot capacity to a dedicated production cluster — with the cost per unit of work known before you commit.