Skip to main content
Premium Trial:

Request an Annual Quote

With Moon Software Launch, Diploid Aims to Accelerate Diagnosis of Rare Genetic Diseases

Premium

NEW YORK (GenomeWeb) – Diploid, a Leuven, Belgium-based genomics company, recently introduced a new software offering that it claims can reduce the time necessary for genome interpretation for inherited disease diagnostics from days to minutes.

Diploid is marketing the tool, called Moon, to large genomics centers and national programs, among other clients, to expedite the diagnosis of rare genetic diseases with the aim of lightening the workload of clinical geneticists drowning in next-generation sequencing data.

According to CEO Peter Schols, Diploid originally entered the market three years ago with a service for diagnosing rare genetic diseases, where clients sent the company their patients' human genome data and phenotypic information, and Diploid provided a clinical diagnosis back.

Companies such as Sengenics, Otogenetics, and Macrogen have since adopted Diploid's clinical genome interpretation service.

As it refined its services, the privately held,  Leuven-based company's team developed Moon to speed up that process. Diploid currently employees seven people, most of whom have been affiliated with the University of Leuven, Schols said.

"Instead of requiring our geneticist to spend hours working with the software to come up with causal variants, the software should be able to do it itself," said Schols. "It should work fully autonomously. That was our aim with Moon."

While Moon has been used by a number of early access partners since the end of last year, the tool only became available commercially a few weeks ago. Clients input patient symptoms, age, gender, and their whole-exome sequencing or whole-genome sequencing data. Using the tool's artificial intelligence algorithms, a diagnosis is generated within three minutes.

According to Diploid, its product operates without supervision, and updates itself with the latest genetic discoveries, enabling customers to reanalyze data from undiagnosed patients on an ongoing basis. These twin ideas, of paring down the time to diagnosis and lessening the workload of clinical geneticists, while allowing them to automatically resolve old cases, comprise Diploid's main propositions to the clinical genetics community.

"In some cases, especially with infants, it is very important to come up with fast genome analysis," said Schols. "If you have to spend 20 to 40 hours on average to do the interpretation in order to keep up with faster sequencing, faster exome sequencing, it is important that there is software available that can do the interpretation really fast."

In terms of resolving unsolved cases, Schols noted that patients with rare diseases often visit hospitals at a certain point in time. "If they do exome analysis, it might be positive or it might be negative," he said "If it's negative, all the data is archived, but rarely used again. ,As most centers are overbooked, it's hard for them to solve older cases," Schols added, "but this entire equation changes when you have fully autonomous data interpretation."

Given a patient's genomic information, plus phenotypic data, Schols suggested that it would be possible to redo the analysis of thousands of cases on a weekly basis, given Moon's three-minute turnaround time. And since the tool operates autonomously, users in hospitals and centers would only be notified in the case that a diagnosis has been made. Since Moon automatically scans the literature for new information on rare disease-causing variants, it means that more cases could be solved over time with little manual input from geneticists.

"These are the two driving forces: making the analysis more efficient and faster, and making it possible to do it in the background and being notified if something in an older case comes up," said Schols.

Moon was beta-tested and validated by partners at the University of Antwerp in Belgium and the National Institutes of Health in Bethesda, Maryland. To validate the software, they assessed 100 previously solved patient cases using Moon and were able to match previous diagnoses with an accuracy of 90 percent. In all of the cases, Moon provided the disease-causing variant in its list of top 10 candidate variants. Diploid claims it was also able to reach a diagnosis in cases where manual interpretation had failed.

Geert Mortier, a medical geneticist at the University of Antwerp who was one of Moon's beta testers, said that the system is "quite good" at getting the right answer in a short amount of time.

"I think it is important to have this kind of software and firms that are developing bioinformatic algorithms," because the challenge lies in the data interpretation, said Mortier, who works primarily with patients suffering from short stature.

"The challenge is to have a good system, a good bioinformatic pipeline, so that when [clinicians] do exome sequencing, they can get the variants in a short amount of time," said Mortier. "That is what Diploid has done by developing Moon." While he said that his lab's experience with Moon was "quite positive," he noted that the software has just been launched and will no doubt be revised over time. As such, his lab has not yet brought the system in house.

"Any genetic group dealing with whole-exome or whole-genome sequencing data could benefit from using this, unless they have a perfect system themselves," said Mortier. "They will save time going from the raw sequencing data to the variant report. Any system that can be built where you shorten the time, increase quality of data interpretation, is helpful."

Joris Veltman, the new director of the Institute of Genetic Medicine at Newcastle University in the UK, welcomed Diploid's market entry for that very reason, even though he has not used the software himself.

"It's great to see more and more innovative companies entering this important field of rare disease diagnostics," said Veltman. "Clearly, the software needs good patient phenotyping as well as exome or genome sequencing data as input, and therefore their tool still is highly dependent on clinical and genomics expertise," he said, "but it may help diagnostics personnel in prioritizing the causal genetic variant and assist in reducing diagnostic turnaround time."

While Moon could benefit users like Mortier or Veltman, Diploid is also marketing the tool at companies and institutes that develop variant analysis software, as well as national genome programs, such as Genomics England, and high-volume genome centers, Schols said. Vendors, such as Illumina or Agilent Technologies, might also be interested in integrating Moon into their products, he said.

"We are definitely selling Moon to individual hospitals and genetic centers, but realistically, it would make sense to partner with another company that offers interpretation software that would imbed Moon into their pipeline," Schols said. "That would allow us to focus on developing the product, which we would prefer to do." The company is specifically looking to work with a software provider or tool vendor that would add Moon to its offering.

While it looks to expand the availability of Moon, Diploid is also enhancing the software. Schols said that by launching Moon as a product, it will gain more customer feedback that will enable it to improve its algorithms. The company would also like to better integrate copy number analysis into Moon, said he added. Last year, Diploid introduced InHelix, a copy number analysis service, where users provide the firm with genomic data and phenotypic information and are provided back with a list of ranked relevant CNVs. That service is currently carried out manually, but Diploid envisions automating the process of copy number analysis from sequencing data, and reporting the information back in the same manner it reports SNP data in Moon.

Schols acknowledged that Moon has competitors, some offered by companies like Tute Genomics, Euformatics, and Cartagenia, and others publicly available. The Wellcome Trust Sanger Institute, for instance, offers Exomiser, a Java program that enables users to identify disease-causing variants from whole-exome or whole-genome sequencing data.

According to Schols, Diploid will soon release a white paper comparing Moon with Exomiser.

"The results are quite spectacular, nothing else comes close," he claimed. "In a way, it's strange we came up with [Moon] given our size, but I think the main reason is, most of our competitors are software companies," he said. "We aren't just software developers; our team has lots of experience coming up with the causal variant and knowing what to do to solve a case," he said. "This expertise has been the key factor for us in being able to develop this."

The Scan

Long COVID-19 Susceptibility Clues Contained in Blood Plasma Proteome

A longitudinal study in eBioMedicine found weeks-long blood plasma proteome shifts after SARS-CoV-2 infection, along with proteomic signatures that appeared to coincide with long Covid risk.

Tibetan Study Finds Adaptive Variant Influencing Skin Pigmentation

With a combination of phenotyping and genetic data, researchers document at PNAS a Tibetan-enriched enhancer variant influencing melanin synthesis and ultraviolet light response.

Domestication Linked to Nervous System Genes in Inbred Mouse Strains

Researchers highlighted more than 300 positively selected genes in domesticated mice, including genes linked to nervous system function or behavior in Genome Biology.

ALS Genetic Testing May Be Informative Across Age Ranges, Study Finds

Researchers in the journal Brain identified clinically actionable variants in a significant subset of older ALS patients, prompting them to point to the potential benefits of broader test use.