DNA Phenotyping is the prediction of physical appearance from DNA.
It can be used to generate leads in cases where there are no suspects or database hits, or to help identify unknown remains.

DNA carries the genetic instruction set for an individual’s physical characteristics, producing the wide range of appearances among people. By determining how genetic information translates into physical appearance, it is possible to “reverse-engineer” DNA into a physical profile. Snapshot reads tens of thousands of genetic variants (“genotypes”) from a DNA sample and uses this information to predict what an unknown person looks like.

Over the past four years, using deep data mining and advanced machine learning algorithms in a specialized bioinformatics pipeline, Parabon — with funding support from the US Department of Defense (DoD) — developed the Snapshot Forensic DNA Phenotyping System, which accurately predicts genetic ancestry, eye color, hair color, skin color, freckling, and face shape in individuals from any ethnic background, even individuals with mixed ancestry.

Because some traits are partially determined by environmental factors and not DNA alone, Snapshot trait predictions are presented with a corresponding measure of confidence, which reflects the degree to which such factors influence each particular trait. Traits, such as eye color, that are highly heritable (i.e., are not greatly affected by environmental factors) are predicted with higher accuracy and confidence than those that have lower heritability; these differences are shown in the confidence metrics that accompany each Snapshot trait prediction.

fhid snapshot dna phenotyping

Using genomic data from large populations of subjects with known phenotypes, Parabon’s bioinformaticists have built statistical models for forensic traits, which can be used to predict the physical appearance of unknown individuals.


Snapshot takes advantage of modern SNP technology, translating select biomarkers from a DNA sample into predictions about various physical traits of its source. Using these predictions, Snapshot generates a descriptive profile that contains sex, ancestry, pigmentation (skin color, hair color, eye color, freckling), and even face morphology, as well as excluded phenotypes.

SNP Technology

Recent advances in DNA sequencing technology have made it practical and affordable to read genetic content from DNA, which in turn has allowed the creation of datasets that include both genotypic (genetic content) and phenotypic (trait) data for each of thousands of subjects. With the diligent and repeated application of data mining and machine learning processes to such data, Parabon NanoLabs produces statistical models that translate the presence of specific genetic biomarkers into forensically relevant trait predictions.

Data Mining

Beginning with large datasets comprised of a phenotype (trait) of interest and genotype data for thousands of subjects, our bioinformatics team performs large-scale statistical analysis on millions of individual SNPs and billions of combinations thereof to identify sets of these genetic markers that associate with the given trait. This mining process can take weeks running on hundreds, sometimes thousands, of computers. In the end, those SNPs with the greatest likelihood of contributing to the variation observed in the target trait are culled for potential use in predictive models.

Data Modeling

The modeling phase further refines this set of SNPs to a final set that most accurately predict the target trait under a framework of machine learning algorithms. Models are validated against data held out for such testing and calibrated with all available data before being installed into the Snapshot architecture.
Tested on thousands of out-of-sample genotypes, Snapshot’s trait predictions have been shown to be highly accurate. For example, Snapshot predicts pigmentation traits with an average accuracy of greater than 80%, and its ability to discriminate between pigmentation extremes is considerably higher — often 99% or more.

Even in cases where it is difficult to distinguish between two similar phenotypes — e.g., hazel eyes vs. green eyes — Snapshot can, with high confidence, exclude certain traits (for instance, Snapshot can, with confidence approaching 100%, predict that a particular subject does not have brown or black eyes.

fhid snapshot dna phenotyping

Using genomic data from large populations of subjects with known phenotypes, Parabon’s bioinformaticists have built statistical models for forensic traits, which can be used to predict the physical appearance of unknown individuals.

DNA Phenotyping Use Cases

Snapshot was built for the defense, security, justice, and intelligence communities. The technology has been validated with as little as 50 picograms (0.05 nanograms) of DNA, from which high-quality genotypes of nearly 1 million SNPs have been produced with very high call rates.

The development of Snapshot took four years and was funded by the United States Defense Threat Reduction Agency (DTRA). As part of the development and validation process, Snapshot was tested on thousands of out-of-sample genotypes and was shown to be extremely accurate. In addition, Snapshot has been used by State and local police departments throughout the US, and private citizens seeking ancestry information.

Snapshot can be applied to any case where DNA has been found that does not match a known suspect or CODIS. Snapshot provides a means to determine the physical appearance and other characteristics of the individuals that are the source of such samples.

Instead of being stymied by DNA evidence that fails to produce a database match, investigators can now use Snapshot to generate viable leads in cases that might otherwise go cold.

Request a Sample Report