Generative multiomic modeling with Omnii-1
A unified multimodal language model for the human genome
We built Omnii-1 to jointly model DNA and multimodal experimental assay data as a first-of-its-kind generative multiomics model. It can reconstruct assay tracks, predict the effects of non-coding variants, and link regulatory elements to target genes. Omnii-1 outperforms leading supervised and specialized models on nearly every benchmark we tested. It is the most accurate at identifying causal QTL variants and at linking enhancers to their target genes. It also predicts DNA methylation levels at single-CpG resolution.
Less than 2% of the human genome codes for protein. Much of the rest encodes the regulatory logic for how and where these genes are expressed. This regulatory genome gives rise to the myriad cell types, tissues, and structures of the human body. A central challenge in biology, and a major bottleneck in therapeutic development, is understanding exactly how genotype impacts phenotype via these complex hierarchies of DNA regulation.
Omnii-1, our multimodal genome language model, is designed to help address these challenges. Omnii-1 is generative, with unprecedented abilities to read, interpret, and write genomic sequences and multiomic assay data. In this post, we highlight the ability of our model to flexibly reconstruct held-out assay data (which we refer to as track reconstruction), identify causal variants associated with differential gene expression, splicing, and chromatin accessibility (referred to as quantitative trait loci; QTLs), and link DNA enhancer elements to the genes that they regulate (Figure 1). Together, these tasks lay the groundwork for future applications that require us to write new information into the genome, rewiring the genotype to phenotype relationship in diverse contexts.
Our team designed the first genome language models (gLMs)123 and earlier this year we subsequently released a new state-of-the-art gLM, Omnii-preview4. This model excelled at specific types of variant effect prediction, especially as it relates to variant pathogenicity. However, gLMs learn from DNA sequence alone; they can score how unusual a variant is but cannot predict what a variant does, such as altering gene expression or splicing in a specific cell type. By contrast, sequence-to-function models (sometimes referred to a sequence-to-omics models) such as AlphaGenome5 and Borzoi6 learn to predict regulatory activity from DNA sequence in a pre-defined set of biosamplesbb A biosample is the biological source of a measurement: a cell line, primary cell type, tissue, or organoid, sometimes under a particular treatment. determined at training time. Experimental assay data (which we also call tracks) are provided only as training targets; at prediction time, their input is DNA sequence alone. This fundamentally limits their ability to respond to new data modalities and generalize to out-of-distribution cellular contexts. Omnii-1 overcomes both of these limitations. We trained Omnii-1 on trillions of tokens of DNA sequence and multiomic assay data, and the model can both accept assay data as an input and predict it. Table 1 compares Omnii-1's capabilities with those of sequence-to-function models and gLMs. As we further discuss in other blog posts, Omnii-1 can also be post-trained on new tasks and new modalities, including assays it has never seen as input.
In this post, we highlight specific aspects of Omnii-1's capabilities on previously published benchmarks for variant effect prediction and track reconstruction. We show that Omnii-1 has state-of-the-art performance compared to leading published models. Through these enhanced modeling capabilities, we hope to greatly improve upon our ability to demystify variation in the regulatory genome, which makes up most of the genetic signal behind both rare and common diseases.
Multimodal reconstruction
Nearly every cell in the human body carries the same genome, yet diverse cell types and structures arise from the many ways cells regulate their gene expression. These regulatory mechanisms leave measurable traces: which stretches of DNA are open or tightly packed in heterochromatin, where transcription factors bind, and what types of chemical tags are deposited on DNA or nearby histones. Whereas the DNA sequence is the same in every cell, these -omics modalities reveal how the genome is packaged and expressed. Over the past several decades, scientists have devised assays that convert these regulatory marks into a DNA signal that can be sequenced, for example by capturing open stretches of chromatin, pulling down DNA bound to a particular protein, or chemically marking which cytosines are methylated. Aligning each assay's sequenced fragments to the genome yields a track, or a signal measured at every position along the same coordinates as the DNA sequence.
Omnii-1 models DNA sequence together with these sequence-aligned multiomic modalities and with evolutionary conservation at each base (Figure 2). Because every track shares the genome's coordinate system, we are able to jointly model interactions between DNA sequence and other modalities. In this section, we evaluate how well Omnii-1 predicts these tracks in a cell-type- and tissue-specific fashion.
Here, we compare Omnii-1 against ChromBPNet, Borzoi, and AlphaGenomeaa Given our status as a commercial entity we are not able to run AlphaGenome. As such, all reported AlphaGenome metrics in this post are derived directly from Avsec, et al. (2026)5. on head-to-head track benchmarks using held-out genomic loci defined by Borzoi. For each track, we compute the Pearson correlation between predicted and observed signal over the held-out intervals and then average across biosamples (Table 2).
Methods
Held-out data
RNA-seq, CAGE, ChIP-seq, and splicing are scored on Borzoi's held-out genome sections (folds 3 and 4 of its sequences_human.bed.gz), which AlphaGenome's fold-1 model also holds out. ATAC-seq and DNase-seq are scored on ChromBPNet's fold-0 test peaks, less any region that overlaps AlphaGenome's training intervals. The metric is Pearson r computed per track over the held-out intervals and averaged across tracks.
Tracks and biosamples
Tracks are Borzoi's human targets: 1,543 RNA-seq tracks from 955 stranded samples, kept where the 1 bp reprocessed data match Borzoi's at r ≥ 0.99; 1,276 CAGE tracks from 638 stranded FANTOM5 samples; and 1,885 TF and 2,001 histone ChIP-seq tracks. DNase-seq covers four ENCODE cell lines (K562, HepG2, GM12878, and IMR-90) and ATAC-seq one (IMR-90). Splicing is per-tissue splice site usage derived from RNA-seq.
Resolution
CAGE and ChIP-seq are scored at 32 bp, Borzoi's output resolution; for this comparison AlphaGenome is fine-tuned with a 32 bp head on Borzoi's tracks.5 RNA-seq is scored at 1 bp on log1p coverage, with Borzoi's 32 bp predictions upsampled to match. ATAC-seq and DNase-seq are scored at 1 bp, and DNA methylation at each CpG.
Baselines
All AlphaGenome numbers are taken directly from the AlphaGenome paper in Nature5, as are the Borzoi and ChromBPNet numbers it reports for RNA-seq, CAGE, splicing, ATAC-seq, and DNase-seq (its Supplementary Table 3: AlphaGenome's fold-1 model against Borzoi replicate 1, and against ChromBPNet on the same peaks).
We show additional results for track reconstruction across 4 modalities in Figure 3. Here, we report performance metrics per functional unit (average coverage over a gene's exons, an accessibility peak, etc.) and show single base pair resolution reconstructions for indivudal loci × biosample combinations. At this level, predicted and measured values agree with a Pearson r of 0.869 for RNA-seq, 0.925 for splicing, 0.960 for ATAC-seq, and 0.957 for DNA methylation.
Reconstructing DNA methylation patterns
DNA methylation adds a methyl group to a cytosine, almost always at a CpG site (a cytosine immediately followed by a guanine on the same strand), and methylated promoters tend to switch their genes off. Methylation is copied through cell division, differs between cell types, shifts with age, and is disrupted early in cancer,8 which makes it one of the most useful signals in cell-free DNA for cancer detection.9 It is measured by whole-genome bisulfite sequencing (WGBS)cc Bisulfite converts unmethylated cytosines to uracil, which is read as thymine, while methylated cytosines are protected. At each CpG, the fraction of reads that still carry a cytosine gives β. A sample pools many cells, each carrying two copies of the genome, so β usually falls between 0 and 1: it is the share of copies methylated at that CpG., which gives the methylation level, or β, at each CpG from 0 (never methylated) to 1 (always methylated). None of the sequence-to-function models we compare against (ChromBPNet, Borzoi, and AlphaGenome) predict DNA methylation. Omnii-1 predicts β at single-CpG resolution, and across our evaluation set predicted and measured β agree with a Pearson r of 0.879.
Omnii leverages local context for accurate track prediction
Omnii-1 predicts a track from DNA together with the measured tracks of the same biosample, so a prediction can draw on local context from both DNA sequence and multiomics context. To see which inputs a reconstruction uses, we attribute each predicted base of RNA-seq back to the 12 kb locus around it (Figure 4). In this vignette, we show the RNA-seq coverage prediction for the gene ORM2 (an acute-phase plasma protein made almost entirely in the liver). In the liver, where ORM2 is highly expressed, the strongest regions are the gene's own promoter, exon 2, and the last exon; conservation, DNA, and Pol II (POLR2A) occupancy carry most of their influence. By contrast, in skeletal muscle, H3K27ac, H3K4me3, and Pol II signals are at least an order of magnitude lower at the ORM2 promoter, and the model correctly predicts almost no RNA-seq coverage.
Variant effect prediction for quantitative trait loci
Most genetic variants associated with human traits and disease fall outside protein-coding regions, where they act through gene regulation rather than protein structure. Predicting what such a variant does means predicting how it changes the molecular readouts above: chromatin accessibility, transcription factor binding, splicing, or gene expression, and in which tissues and cell types. One way to study these effects is through quantitative trait loci (QTLs), which are mapped by statistically associating genetic variation with variation in a molecular trait, such as gene expression (eQTLs). Here, we benchmark Omnii-1 against other models on how accurately they predict whether specific variants are causal QTLs for a given molecular trait. These benchmarks encompass eQTLs, splicing QTLs (sQTLs), chromatin accessibility QTLs (caQTLs), DNase-sensitivity QTLs (dsQTLs), and binding QTLs (bQTLs).
Expression QTLs
We used the AlphaGenome zero-shot eQTL causality panel to test how accurately each model separates variants that cause a change in gene expression from variants that do not. The panel is a set of test cases, each pairing a potentially causal variant with a gene and a GTEx tissue. In a positive case, statistical fine-mappingdd Statistical fine-mapping takes the variants associated with a gene's expression and estimates, for each one, the probability that it causes the association rather than riding along with a causal variant inherited alongside it. This probability is the posterior inclusion probability (PIP). The panel's labels come from SuSiE fine-mapping of GTEx eQTLs: a variant with PIP ≥ 0.9 is a positive, and one with PIP ≤ 0.01 is a negative. These labels are statistical inferences from population genetic data, not variants whose effects have been validated by experiment. confidently identifies the variant as causal for that gene's expression in that tissue. In a negative case, fine-mapping rules the variant out. Negatives are chosen at the same distances from the gene as positives, so distance alone cannot separate them. AlphaGenome reports only overall scores on this panel (0.713 AUROC zero-shot and 0.799 with a supervised random forest, Table 3), so it is absent from the slices below. We scored Borzoi as an ensemble of four replicate models (Methods) and sliced its scores and Omnii-1's by distance from the variant to the target gene's nearest transcription start site (TSS, where transcription of the gene begins), by variant class (Figure 6), and by gene type (Figure 7). Borzoi reaches 0.705 tissue-weighted AUROCee AUROC is the probability that a model scores a randomly chosen positive above a randomly chosen negative: 0.5 is chance and 1 is perfect. Tissue-weighted AUROC computes it within each tissue and averages, weighting each tissue by its number of test cases. overall and stays between 0.663 and 0.714 in every distance bin, with no trend with distance. Omnii-1 reaches 0.810 on the same panel and gains accuracy with distance, from 0.746 under 500 bp to 0.854 beyond 50 kb, so its lead over Borzoi grows from 0.05 to 0.19. By variant classff Variant classes come from the GENCODE gene annotation: exonic (inside an exon), splice-proximal (within 200 bp of an exon edge), promoter (within 2 kb of the TSS), intronic (elsewhere inside the gene), and flank (outside the gene)., its lead over Borzoi is smallest on exonic and splice-proximal variants (0.065 and 0.035) and largest on promoter, intronic, and flank variants (0.13 to 0.20).
The panel mixes two questions: whether a gene carries a causal variant at all, and which of its variants is the causal one. To test each question on its own, we grouped genes by the labels of their variants (Figure 7). A gene's variants are all the variants the panel pairs with it, each labeled causal or not. In single-variant and homogeneous genes, all of a gene's variants share one label, so a model can score well just by recognizing which genes carry a causal variant. These categories test the model's ability to recover gene-level signal. In contrast, mixed genes include both causal and non-causal variants, so the model must recover variant-level signal to tell them apart. Mixed genes with nine or more variants make up a fifth of the panel, and three in four of their rows are non-causal; there Borzoi scores 0.603 and Omnii-1 0.738. Omnii-1's largest margins are on homogeneous genes, where it scores 0.824 to 0.892 against 0.616 to 0.721 for Borzoi. Borzoi is ahead on single-variant genes and on mixed genes with eight or fewer variants.
Methods
Panel
The AlphaGenome zero-shot eQTL causality set: 21,948 variant–gene–tissue triples over 12,532 variants, 3,759 genes and 48 GTEx11 tissues, 50% positives. Labels come from SuSiE fine-mapping of GTEx eQTLs in the eQTL Catalogue12: variant–gene pairs with posterior inclusion probability (PIP) ≥ 0.9 are causal and those with PIP ≤ 0.01 are non-causal. Non-causal triples are downsampled within ten log-distance-to-TSS bins (distance to the gene's median TSS). The metric is AUROC computed per tissue and averaged with weights equal to the rows per tissue.
Slices
Distance is measured from the variant to the nearest transcript TSS of the target gene (GENCODE v47). Variant class is derived from the same annotation: exonic, splice-proximal (within 200 bp of an exon edge), promoter (within 2 kb of the TSS), intronic (inside the gene span), and flank. Gene cells count the distinct variants the panel pairs with a gene, across all tissues and both labels; a gene is mixed when its rows carry both labels.
Scoring Borzoi
Borzoi scores every row with a window-level expression score. For each allele, Borzoi predicts RNA-seq coverage from its 524 kb input over the central 196,608 bp (6,144 bins of 32 bp). For each bin and each GTEx RNA-seq track matched to the row's tissue (two or three per tissue, from the Borzoi paper's GTEx-to-track mapping), we take log₂(alt + 1) − log₂(ref + 1) of the predicted coverage, average over the tissue's tracks, and sum over all output bins. This is the logSUM score from the Borzoi paper's eQTL methods, implemented as logSUM in Calico's baskerville library. Forward and reverse-complement predictions are averaged, and causality uses the magnitude. The score depends on the variant and the tissue but not on the target gene. Four Borzoi replicate models are ensembled at the score level: within each tissue, each replicate's score is log-transformed (log(1 + s − min)) and z-scored, and the four are averaged.
Splicing QTLs
A splicing QTL (sQTL) is a variant that changes how a gene's transcripts are spliced, for instance, how often an exon is kept. The spliceosome finds each intron using short sequence signals: a GT at its 5′ end (the donor site), an AG at its 3′ end (the acceptor site), and a branch point and pyrimidine-rich tract a few dozen bases upstream of the acceptor. Variants in these regions most clearly affect splicing, but sQTLs can also sit deeper in exons and introns, where they alter splicing enhancers and silencers or create new donor or acceptor sites.
We used the AlphaGenome sQTL causality panel on its test chromosomes, which is drawn from Borzoi's GTEx sQTL set: 14,458 test cases, each a variant in one tissue, over 6,815 variants, 2,836 genes and 47 tissues. Each causal variant is paired with a non-causal one in the same tissue, with the same substitution and the same distance to the splice site. We compare against Pangolin10, a splicing model trained on splice-site usage in four tissues, and Borzoi, which predicts RNA-seq coverage and so sees splicing through exon coverage. They score 0.721 and 0.693 tissue-weighted AUROC on this panel; Omnii-1 scores 0.814.
Figure 8 groups variants by their position relative to the nearest annotated splice site. Both models change little between classes: outside the canonical dinucleotides, Pangolin ranges from 0.722 to 0.785 and Borzoi from 0.693 to 0.789. Both are highest in the branch-point window (0.785 and 0.789), the one class where Borzoi edges ahead; Pangolin leads Borzoi in every other class, by 0.016 to 0.038. Near-exonic, near-intronic, and deep-intronic variants (seven in ten test cases) sit at 0.722 to 0.727 for Pangolin and 0.693 to 0.710 for Borzoi. Variants in the GT or AG itself are the smallest class, 119 test cases over 28 variants and 78% causal; Pangolin scores 0.673 there, and Borzoi is at chance (0.487). Omnii-1 leads both models in every class, from 0.759 on deep exonic variants, where its margin over Pangolin is smallest (0.009), to 0.864 in the branch-point window. Its largest gain is on the canonical dinucleotides, 0.820 against Pangolin's 0.673, and on near-intronic variants it scores 0.832 against 0.722.
By distance (Figure 9), Pangolin is most accurate 11 to 200 bp from the splice site (0.757 and 0.755) and less accurate both at the site itself (0.719 within 2 bp) and beyond 1 kb (0.713). Borzoi is the stronger of the two within 2 bp (0.763), trails Pangolin by 0.014 to 0.021 from 3 bp to 1 kb, and falls furthest beyond 1 kb (0.658). The 1/distance baseline stays between 0.43 and 0.54 in every bin, so the panel's matching removes distance as a cue within each bin as well as overall. Omnii-1 leads in every bin and follows the same shape as Pangolin, highest 11 to 50 bp from the site (0.844) and lowest within 2 bp (0.791) and beyond 1 kb (0.785). Beyond 1 kb, it keeps a margin of 0.073 over Pangolin and 0.128 over Borzoi.
Methods
Panel
The AlphaGenome sQTL causality set restricted to its test chromosomes (3, 6, 9, 12, 16, 18, 19, and 21): 14,458 variant–tissue rows over 6,815 variants, 2,836 genes and 47 GTEx tissues, 50.9% causal. The rows come from Borzoi's sQTL benchmark: GTEx v8 sQTLs from the eQTL Catalogue12, quantified as txrevise13 internal-exon events and fine-mapped per tissue. A causal row is a variant with posterior inclusion probability above 0.9 for an event of its gene. Each causal row has one non-causal partner in the same tissue with the same REF→ALT substitution and, to within 2%, the same distance to the event's nearest splice site. The metric is AUROC computed per tissue and averaged with weights equal to the rows per tissue, as for eQTLs.
Slices
Position class and distance are measured to the nearest splice site of the row's gene over all its GENCODE v41 basic transcripts, on the gene's strand. Classes are mutually exclusive and assigned in this order: canonical dinucleotide (intron +1 and +2, or −2 and −1); donor region (the last three exonic bases to intron +6); acceptor region (intron −20 to exon +3); branch-point window (intron −44 to −21); then exonic or intronic by whether the variant falls in an annotated exon, near when within 50 bp (exonic) or 250 bp (intronic) of a splice site and deep beyond. The panel matches distance to the txrevise event's splice site rather than to the nearest annotated one: the 1/distance baseline scores 0.485 overall and 0.43 to 0.54 in every distance bin, but it is not at chance inside every position class, so it is not drawn in Figure 8. Tissues that carry only one label inside a slice are left out of that slice's average. This matters only for the canonical dinucleotides, where 73 of 119 rows enter the metric; with 28 variants, that class should be read with care. All numbers are point estimates.
Scoring Pangolin
We ran the released Pangolin ensemble of 40 checkpoints, five replicates of each of its eight outputs (splice-site probability and usage in heart, liver, brain, and testis). For each tissue the score is the largest gain or loss in predicted splice-site probability within 2 kb of the variant, with strand from GENCODE v41. A row's score is the maximum over the four tissues, so it does not depend on the row's GTEx tissue. Probability rather than usage was chosen on chromosome 22, outside the panel.
Scoring Borzoi
Borzoi is scored with the splicing statistic from the Borzoi paper's splicing variant methods: the largest absolute change between ALT and REF in gene-normalised predicted RNA-seq coverage over the gene body, on the GTEx RNA-seq tracks matched to the row's tissue, with forward and reverse-complement predictions averaged. This is the nDi statistic of Borzoi's borzoi_sed.py, run with --span --rc as in Borzoi's splice-scoring example. Four Borzoi replicate models are averaged in a final ensemble score.
Chromatin Accessibility QTLs
A chromatin accessibility QTL (caQTL) is a variant whose alleles change how open the chromatin is at a nearby regulatory element, measured by ATAC-seq across individuals. We used the AlphaGenome caQTL panels from lymphoblastoid cell lines (LCLs) of African14 and European ancestry: 26,042 and 31,621 variants, of which 8.5% and 8.3% are caQTLs. A variant is a caQTL when its genotype is significantly associated with accessibility of its peak. We compare against Borzoi and ChromBPNet trained on GM12878 ATAC-seq. On the African panel they score 0.794 and 0.792 AUROC and Omnii-1 scores 0.898; on the European panel 0.710, 0.680, and 0.802. On AUPRC, Omnii-1 reaches 0.587 and 0.394 against AlphaGenome's 0.564 and 0.364 (Table 3).
A variant changes accessibility mostly by changing how well a transcription factor binds there, and the factors that open chromatin bind near the centre of an accessible region, where they push nucleosomes aside. Figure 10 sorts variants by where they sit relative to the nearest GM12878 accessible peak. Omnii-1 leads both public models in every class on both panels. Where these factors bind, it leads by 0.084 AUROC at the summit on the African panel (0.896 against Borzoi's 0.812) and 0.064 on the European (0.828 against 0.764), and by 0.112 and 0.111 in the peak body. On the African panel caQTLs are most frequent outside GM12878 peaks (17%), plausibly because some regions open in African LCLs are closed in the European GM12878 line; there the public models fall to 0.735 and 0.755 and Omnii-1 holds 0.866. On the European flanks Borzoi and ChromBPNet are close to chance (0.577 and 0.545) and Omnii-1 scores 0.696.
Methods
Panels
The AlphaGenome caQTL panels on its test chromosomes (3, 6, 9, 12, 16, 18, 19, and 21). caQTL African: 26,042 total variants, 2,219 positive caQTLs, from the ChromBPNet paper's benchmark of caQTLs mapped in 100 LCLs of the Esan, Gambian, Luhya, Mende, and Yoruba 1000 Genomes populations and HapMap Maasai. caQTL European: 31,621 total variants, 2,618 positive caQTLs.
Slices
Position is measured to the nearest ENCODE GM12878 ATAC-seq summit and its peak: summit (inside the peak, within 50 bp of the summit), peak body (inside the peak, further from the summit), flank (outside any peak, within 1 kb of a summit), and outside (more than 1 kb from any summit).
Scoring Borzoi
Borzoi is scored with a single replicate model: the absolute log2 fold change between ALT and REF of predicted GM12878 DNase signal summed over 501 bp (the logSED statistic of Borzoi's borzoi_sed.py), with forward and reverse-complement predictions averaged.
Scoring ChromBPNet
ChromBPNet scores were computed with the official ChromBPNet variant scorer (kundajelab/variant-scorer) using the ENCODE GM12878 ATAC-seq ChromBPNet models (bias-corrected, all 5 folds). Each variant is scored as the absolute log fold-change in predicted counts between alleles, multiplied by the Jensen–Shannon distance between the two alleles' predicted profiles. That product is multiplied again by the active-allele quantile: the percentile of the stronger allele's predicted accessibility among the model's ENCODE training peaks. Predictions are averaged over forward and reverse-complement strands and then over the 5 folds. Variants are scored on hg19 (matching the panel's coordinates).
Modeling long-range regulatory interactions
Enhancer-to-gene interactions
Enhancers are stretches of DNA that bind transcription factors and increase a gene's expression, often from tens or hundreds of kilobases away, by looping into contact with the gene's promoter. An enhancer does not always act on the nearest gene. It can skip over neighbors to reach a gene farther away, and one enhancer can regulate several genes (Figure 11). Enhancer-to-gene (E2G) prediction takes a candidate enhancer and a gene and asks whether the enhancer regulates that gene. Solving such a task has broad implications for genetics research, especially for genome-wide association studies (GWAS). Most variants that GWAS link to disease lie outside gene bodies, often in enhancers, so the association alone does not say which gene a variant affects. Identifying that gene is a major bottleneck in turning genetic associations into drug targets.
We evaluate Omnii-1 on this task using a previously published benchmark of CRISPR interference (CRISPRi) experiments in K562 cells, curated for the ENCODE-rE2G project.15 CRISPRi guides a catalytically inactive Cas9 protein to a chosen stretch of DNA, where it recruits a repressor that silences that stretch without cutting it. Silencing each candidate enhancer in turn and measuring the expression of nearby genes reveals which enhancers regulate which genes. A pair is positive when silencing the enhancer significantly lowers the gene's expression. Only 471 of the 10,353 tested pairs are true positives so we report AUPRC, where chance performance is 0.045.
Table 4 shows performance of various models on this benchmark. The distance baseline ranks pairs by how close the enhancer is to the TSS. Borzoi scores a pair by the input × gradient of the gene's predicted expression over the enhancer. ENCODE-rE2G and its extended version ("rE2G extended") are logistic regression models trained on a curated set of features for each pair, including chromatin accessibility, 3D contact, and activity-by-contact16. Omnii-1 + rE2G extended is a trained model: it adds Omnii-1's K562 predictions to the ENCODE-rE2G extended features and is trained on the same pairs, with each chromosome predicted by a model fit on the others (leave one chromosome out cross validation). We then froze it and scored it once on a separate cohort of 1,709 K562 CRISPRi pairs that none of the models were fit on, as an external check that its gain does not come from fitting the main benchmark.
Long-range pairs are the hard part of this task. Most tested pairs sit 100 kb or more from the target TSS (8,550 of 10,353), but only 91 of them are positive (about 1%). Over these distal pairs, Omnii-1 reaches an AUPRC of 0.491 vs. 0.439 for rE2G extended (Figure 12a), and 0.567 vs. 0.464 for ENCODE-rE2G on the external validation cohort. Omnii-1 leads rE2G extended at every distance (Figure 12a), but the gain is not evenly distributed across distal pairs. When no other gene sits between the enhancer and its target, the two models are tied (0.80 each). When the enhancer has to skip over other genes to reach its target, Omnii-1 pulls ahead, and with six or more genes in between it has three times the AUPRC (0.110 vs. 0.037).
The gene MYC shows an example of what this E2G task looks like in practice (Figure 12b). Of the 105 candidate enhancers tested against MYC, 9 regulate it, from 163 kb to nearly 2 Mb away. We let each model call a link wherever its score clears the cutoff at which it reaches 50% precision over the whole benchmark. Omnii-1 links 7 of the 9, including four of the five in a cluster about 1.9 Mb downstream; rE2G extended links 3 and none of that cluster. Omnii-1 also makes more false links, 10 against 3, most of them closer to the gene.
Future directions
The results in this post are about reading, reconstructing, and interpreting the regulatory genome. Our next goal is to write it: to design changes to DNA sequence that produce a chosen regulatory outcome in a chosen cell type. For example, the model could propose an edit to an enhancer that lowers its target gene's expression in one tissue while leaving the gene unchanged in others, as in the gene editing panel of Figure 1. This kind of control would make gene and cell therapies more precise, and could counteract disease-causing variants in the regulatory genome itself. Accurate variant effect prediction is what makes this possible, because a model that can score the effect of a change can also search for the change that has the effect we want.
We also built Omnii-1 to take on new tasks and data types after pretraining. Our posts on cancer diagnostics and cancer vaccines describe two cases where we have extended Omnii-1 to perform new tasks.
Closing
In this post, we evaluated Omnii-1 on three problems in reading and interpreting the regulatory genome. In track reconstruction, the model predicts held-out assay data in a cell-type-specific way, including DNA methylation, which none of the sequence-to-function models we compare against predict. In variant effect prediction, Omnii-1 identifies the variants that alter gene expression, splicing, and chromatin accessibility more accurately than the leading published models on nearly every benchmark. In enhancer-to-gene linking, the model's largest gains come from long-range interactions, where an enhancer skips over other genes to reach its target.
Most of the genetic signal behind rare and common disease lies in the regulatory genome. Our disease genetics post applies Omnii-1 to variants in both rare and complex disease.
Partner with us
We're interested in partnerships involving large-scale multiomic datasets, novel biological assays, and experimental validation. Together, we can use Omnii-1 to predict biological function across cell types, interpret genetic variation, and explore the design of new genomic functions.
If you're looking to help build general biological intelligence, we'd like to hear from you.
Citation
@misc{omnii_genome_2026,
title = {A unified model for generative multiomics with Omnii-1},
author = {Carter, Matthew and Meinardus, Boris and Neiswanger, Willie and Poli, Michael and Thomas, Armin},
year = {2026},
month = {Oct},
url = {https://www.radicalnumerics.ai/blog/omnii-genome},
organization = {Radical Numerics}
}References
1.Nguyen, E., Poli, M., et al. "HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution." Advances in Neural Information Processing Systems (NeurIPS) 36 (2023).
2.Nguyen, E., Poli, M., Durrant, M.G., et al. "Sequence modeling and design from molecular to genome scale with Evo." Science 386, eado9336 (2024).
3.Brixi, G., Durrant, M.G., Ku, J., et al. "Genome modelling and design across all domains of life with Evo 2." Nature (2026).
4.Radical Numerics. "A new frontier in generative genomics with Omnii." Radical Numerics blog (2026).
5.Avsec, Ž., Latysheva, N., Cheng, J., et al. "Advancing regulatory variant effect prediction with AlphaGenome." Nature 649, 1206–1218 (2026).
6.Linder, J., Srivastava, D., Yuan, H., et al. "Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation." Nature Genetics 57, 949–961 (2025).
7.Pampari, A., Shcherbina, A., Kvon, E.Z., et al. "ChromBPNet: bias factorized, base-resolution deep learning models of chromatin accessibility reveal cis-regulatory sequence syntax, transcription factor footprints and regulatory variants." bioRxiv (2024).
8.Greenberg, M.V.C. and Bourc'his, D. "The diverse roles of DNA methylation in mammalian development and disease." Nature Reviews Molecular Cell Biology 20(10), 590–607 (2019).
9.Liu, M.C., Oxnard, G.R., Klein, E.A., et al. "Sensitive and specific multi-cancer detection and localization using methylation signatures in cell-free DNA." Annals of Oncology 31(6), 745–759 (2020).
10.Zeng, T. & Li, Y.I. "Predicting RNA splicing from DNA sequence using Pangolin." Genome Biology 23, 103 (2022).
11.The GTEx Consortium. "The GTEx Consortium atlas of genetic regulatory effects across human tissues." Science 369(6509), 1318–1330 (2020).
12.Kerimov, N., Hayhurst, J.D., Peikova, K., et al. "A compendium of uniformly processed human gene expression and splicing quantitative trait loci." Nature Genetics 53, 1290–1299 (2021).
13.Alasoo, K., Rodrigues, J., Danesh, J., Freitag, D.F., Paul, D.S., Gaffney, D.J. "Genetic effects on promoter usage are highly context-specific and contribute to complex traits." eLife 8, e41673 (2019).
14.DeGorter, M.K., et al. "Transcriptomics and chromatin accessibility in multiple African population samples." bioRxiv (2023).
15.Gschwind, A.R., Mualim, K.S., Karbalayghareh, A., et al. "An encyclopedia of enhancer-gene regulatory interactions in the human genome." bioRxiv (2023).
16.Fulco, C.P., Nasser, J., Jones, T.R., et al. "Activity-by-contact model of enhancer–promoter regulation from thousands of CRISPR perturbations." Nature Genetics 51, 1664–1669 (2019).
