Colossal Introduces GenoMorph AI to Identify Dodo Genetic Editing Targets

Colossal Biosciences on October 14, 2026 unveiled GenoMorph, an artificial intelligence platform developed to identify gene editing targets for species with limited genomic data, and reported that the system identified approximately 2,300 candidate regulatory DNA elements associated with beak size and shape of birds in the company’s dodo de-extinction program.

The Dallas-based company announced the platform alongside a number of advances in its avian pipeline: a substantially improved dodo genome assembly built with technology from its Dire Wolf project, an expanded Nicobar pigeon colony, newly derived Nicobar pigeon primordial germ cells, the first chimeras of chick embryonic stem cells born, and a lipid nanoparticle system to deliver gene-editing tools in bird embryos. Colossal said the capabilities together provide the genomic, cellular and reproductive foundations needed to translate predicted dodo traits into experimentally validated modifications. The announcement builds on the company’s reported progress in 2025 on pigeon primordial germ cells, genetically engineered chicken surrogates and comparative bird genomes. Colossal, founded by entrepreneur Ben Lamm and geneticist George Church, describes itself as the first company to apply CRISPR technology to the de-extinction of species.

The GenoMorph platform

GenoMorph combines comparative genomics, developmental biology, and high-resolution 3D morphology to predict which regulatory elements might be active during development and identify those most strongly associated with differences in fitness. Unlike protein-coding genes, which carry instructions for building an animal, regulatory DNA controls when, where and how strongly those instructions are activated, shaping traits such as the size and structure of a bird’s skull and beak.

To build the platform, Colossal’s avian team created what it calls an avian regulatory atlas from hundreds of samples collected from chickens, quail, ducks and pigeons, covering six stages of embryonic development and three regions of the developing face. The team combined this data with genomes and CT-derived skull measurements of more than 70 bird species, including the Nicobar pigeon, the dodo’s closest living relative, mapped using 541 anatomical landmarks.

Applied to the dodo program, the analysis identified 653 candidate regulatory elements associated with beak size and 1,698 associated with beak thickness and width. Colossal said the findings do not establish that the elements cause such traits, but instead provide priority targets for experimental testing. Elements shown to influence craniofacial development could therefore be considered for precision genome editing in the Nicobar pigeon.

“De-extinction is as much a data problem as it is a biology problem,” said Ben Lamm, CEO and co-founder of Colossal. He said that because so few dodo genomes survive, the company cannot rely on the population-level comparisons available for many living species, and that GenoMorph instead learns how regulatory DNA shapes living birds before identifying genetic switches that may have contributed to the dodo’s distinctive anatomy. Lamm described the platform as a repeatable approach for extinct species whose genomic records are similarly limited.

From prediction to experimental validation

Candidate elements are entering functional validation studies, and those confirmed to affect craniofacial development may be prioritized for precision editing in the Nicobar pigeon genome, the company said. Chief Science Officer Beth Shapiro said the dodo’s defining anatomy emerged from networks of regulatory instructions that are difficult to interpret from ancient DNA alone, and that using the breadth of diversity of living birds combined with artificial intelligence allows GenoMorph to prioritize the regulatory changes that most likely shaped the dodo and move them into functional validation.

“It is not possible to train AI to answer a precise developmental question using only generic data,” said Anna Keyte, director of avian species at Colossal. He said the team needed to capture how regulatory activity changes across species, developmental stages and regions of the face, and that building the dataset took more than a year of focused experimental work.

Preliminary findings were presented at the Craniofacial Gordon Research Conference and the 2026 annual meeting of the Society for Molecular Biology and Evolution. A conference poster, created by researchers and academic collaborators at Colossal, details the underlying method: a convolutional neural network trained on chromatin accessibility data from craniofacial dissections of pigeon, chicken, quail and duck embryos at six developmental stages, then used to predict accessibility across an array of 363 bird species. The poster reports an average prediction accuracy, measured as area under the receiver operating curve, of 0.863 within species and 0.848 between species. A phylogenetic regression between predicted accessibility and beak length measurements taken from VertNet across the 363 species found that 210 of the 293,686 open chromatin regions tested were significantly associated with beak length with a false discovery rate of less than 0.2, with the CACHD1 gene highlighted as the best candidate. The poster also reports that CACHD1 expression was elevated in long-beaked species during frontonasal process development, and that a separate transcriptomic analysis identified 356 genes with divergent expression dynamics between long-beaked and short-beaked species.

A more complete Dodo genome

Colossal also reported progress on the dodo genome itself. Ancient DNA survives in short, damaged fragments, and conventional assembly methods map these fragments against a living reference genome, in this case the Nicobar pigeon, which may discard fragments that are too divergent to align. This can leave gaps in the assembly and skew the reconstructed genome in favor of living species.

The company’s published iterative assembly method, developed through its Dire Wolf program, uses newly mapped dodo DNA to progressively update the reference genome, allowing previously unmatched fragments to fill in gaps with each subsequent cycle until the number of newly recovered sequences reaches a plateau. Colossal reported that its dodo genome now has 95% of bases covered at least 5x, with an average coverage of 65x. Shapiro said the team is in the final stages of analyzing the dodo genome, with more to follow after the genome paper is peer-reviewed.

Colony growth, stem cells and embryo editing

Colossal has expanded its Texas colony of Nicobar pigeons to 36 birds after successfully breeding between established pairs. Eggs collected during the most recent breeding season were used to derive the Nicobar pigeon’s primordial germ cells, the cells that eventually develop into sperm and eggs. Colossal said the creation of these cells is essential to create heritable genome modifications and produce future generations of birds carrying selected dodo traits. The company is also developing a telomere-to-telomere Nicobar pigeon genome to improve the current assembly at the chromosomal level and plans to remap newly available sequence data from the Rodrigues solitaire, an extinct relative of the dodo, against the improved reference to increase its coverage and completeness.

The company’s scientists also hatched the first chimeric chickens produced through a new platform built on avian embryonic stem cells, which Colossal says confirms that cultured cells retain the developmental potential to integrate into a host embryo and contribute to its tissues. The culture system is expanding to pigeons so that modified stem cells can be tested in chimeric pigeons for their predicted effects on phenotype before any changes are made to primordial germ cells, establishing a phenotype screening platform.

Finally, Colossal reported that it has developed a lipid nanoparticle delivery platform that introduces DNA, RNA, and CRISPR gene editing tools into developing avian embryos, while improving embryo viability compared to traditional delivery methods. In the company’s experiments, modification of the bone development regulator Runx2 produced a clear craniofacial phenotype, and the system was used in turtle dove and duck embryos. Colossal said its scientists are using the platform to validate regulatory elements identified by GenoMorph in near real time, that the strongest candidates are being engineered into Nicobar pigeon primordial germ cells for further precision editing studies, and that a manuscript describing the platform has been submitted to the bioRxiv preprint server.