# SelfDecode

AI platform that provides personalised health recommendations based on DNA, labs and environment. 

## Elevator pitch
SelfDecode is an integrated AI platform that provides personalized health recommendations based on a combination of your DNA, labs, microbiome, and environmental factors.

- Canonical URL: https://wefunder.com/selfdecode
- Entity ID: wefunder:company:79286
- Last updated: 2026-06-15T05:00:34Z
- Generated at: 2026-06-15T22:40:02Z

## Quick facts
- $8M raised (mid 2021). ~$2.5M in revenue in 2022.
- Recurring Revenue: Predictable revenue stream from subscription sales model. Est$447 Lifetime Value of a Customer (LTV).
- Large Margins & Scalable: High Avg Order Value of $254 - Low Cost of Goods Sold of ~$20 = $234 Gross Profit/Customer.
- Highly Rated: 4.8 Trustpilot score, 98% retention rate, 75 Net Promoter Score (Q4 2021).
- Growth Potential: Digital health market will be worth $639B by 2026 & medical apps market size is growing at 23%/yr.
- Professional Experience: Team of 88 is composed of highly skilled scientists, MDs, PhDs, NDs and software engineers.
- Operational Excellence: Bootstrapped to multimillion dollar revenue with only small seed investments (totaling $450K).
- Accumulated Intellectual Property over 5 years. Proven B2C & B2B business models.

## Active fundraises
- wefunder:fundraise:65637: 4(a)(6) successful (USD)
- wefunder:fundraise:65636: 4(a)(6) successful (USD)
- wefunder:fundraise:42686: 4(a)(6) successful (USD)
- wefunder:fundraise:42687: 4(a)(6) successful (USD)

## Story
SelfDecode provides users with an integrated AI platform that provides personalized health recommendations based on a combination of your DNA, labs, and environmental factors.In addition to providing a direct-to-consumer service, SelfDecode has signed 26+ business contracts licensing its technology to a variety of health companies as of January 2023.Founded in 2016 with a mission to make precision medicine standard in the healthcare industry, the SelfDecode platform provides all the tools an individual or practitioner needs to understand risk factors and build a personalized action plan for optimal wellness.With SelfDecode's new Health Score feature, users will have a tangible representation of how their genes, lifestyle and biomarkers are impacting their health. Through targeted diet, lifestyle and supplement changes, individuals will be able to improve their overall health score. Within the app, users are provided with comprehensive genetic reports about their health predispositions, lab test analysis and tracking tools and lifestyle assessments to get the fullest picture of their health. Based on these results, SelfDecode provides personalized diet, supplement and lifestyle recommendations.This includes comprehensive reports such as the Diet & Nutrition report, which provides a personalized meal plan with recipes and shopping lists. This is in major contrast to the one-size-fits-all approach to health in traditional medicine, in which healthcare strategies are developed for the average person, with much less consideration for our unique characteristics and risk factors. The problem with conventional medicine & consumer health habitsTypically, when a person has a health problem, they immediately visit Google looking for answers. However, the information they find is generic and they can’t really understand what will, or won’t, actually work for them.The fact of the matter is that it’s not possible to find out the root cause of health issues, or identify optimal solutions, without utilizing personal health data, such as genetics, labs, or environmental data. Even when a sick person visits a doctor, very little of this data is actually used to treat the issues. Doctors don’t have the time to analyze millions of data points, so they typically rely on treating symptoms.Each issue is treated separately and people often end up on dozens of medications, none of which treat the root cause of their issues.The SelfDecode differenceSelfDecode provides a solution that is different from both conventional medicine and other direct-to-consumer health services.Unlike doctors, SelfDecode is able to analyze billions of pieces of information with artificial intelligence and machine learning to produce polygenic risk scores and personalized recommendations. That way, we can help consumers uncover the underlying cause of their health issues and give them a comprehensive plan to address their problems with specific supplements, diets, and lifestyle changes.SelfDecode is the only company in the world as of January 2023 that provides cutting-edge ancestry-adjusted polygenic risk scoring direct to the consumer.We are also the only company that offers truly personalized health recommendations based on a person's genes and other personal health data. While other companies provide risk analysis, their recommendations are generic and they do not use an integrative approach that takes all relevant health data points into consideration.In fact, we’ve been setting ourselves apart from the competition for quite a while.When you sign up for a membership with SelfDecode, you get:More than 83 million genetic variants analyzed through a process called genetic imputation using AI and machine learning to provide the most accurate risk and recommendations analysis.Natural supplement, diet and lifestyle suggestions based on your genes, labs and environment that you can implement right away.Prioritized recommendations based on our analysis of all the relevant genes instead of one gene at a time.Explanations about why we make each recommendation so that you can understand the science behind the suggestion (everything is supported with peer-reviewed scientific studies with references linked!).Privacy and security - we never give away or sell your data. The science behind SelfDecode: Integrative & data-drivenThe human genome consists of about 7 billion pieces of information. On top of that, there are thousands of lab tests, diets and other environmental factors that impact your health and what works best for you.In order to make the best health decisions, you must take all of these factors into account. Otherwise, you end up addressing individual problems or symptoms without looking at the whole picture. The problem is that there is just too much information for any human to analyze.That’s why SelfDecode is solving this problem with artificial intelligence and machine learning.We use the latest techniques in AI including Deep Learning, Bayesian Machine learning, and Hyperdimensional Computing for imputation and our genetic models.That's why we're able to analyze 83 million SNPs (versus a typical 23andme kit that analyzes 650K SNPs) so that we get the most complete picture of your DNA.In addition to genetics, we’re using advanced algorithms that will allow us to consider all relevant health data points, such as your labs and lifestyle factors, to make better predictions and recommendations so that you can become the best and healthiest version of yourself.Who built SelfDecode? A highly qualified team of professionalsIn order to build SelfDecode, we brought together a diverse team of 88 trained scientists, engineers, MDs, PhDs and skilled professionals to create something that’s never existed before.The team consisted of 41 software architects and engineers, and 38 scientists with PhDs, MDs and Masters degrees. In addition, we have highly skilled professionals in product development, design, marketing, finance, operations, customer support, and human resources.The process wasn’t easy, but in the end we were able to select the best people out of 53,000 applicants to bring together the world-class team responsible for building SelfDecode.Scientific Innovations: Improved Models = Better AccuracyOur team has successfully built genetic ancestry and imputation models that consistently outperform today’s state-of-the-art models. These are critical components in providing cutting edge polygenic risk scoring. In addition, our core algorithm for these polygenic scores significantly outperforms others, which will be released in a paper that we are working on publishing with the prestigious Scripps Institute.Two of these reasons that genetics is not in mainstream medicine today is because of ancestry and imputation. When you have a diverse population like the US, the same variants will not be accurate for a person of Chinese, Nigerian, Spanish and Norwegian descent. You can't create a test and say that it only works for northern Europeans, etc.To solve this problem, as a first step, you need to accurately compute ancestry. There are currently 3 companies that have reasonable Ancestry based on our research - 23andme, Ancestry and MyHeritage.All of these are multi billion dollar companies, and one reason is because ancestry is not easy to predict well.Our algorithm outperforms their algorithms, and we plan on licensing our ancestry to our B2B partners and others who want cutting edge ancestry.As far as imputation, whole‐genome sequencing fully captures genetic variation but remains prohibitively expensive and commercially unviable for larger datasets. Instead, the overwhelming majority rely on cost-effective genotyping arrays which capture a sparser set of variants. However, looking at 700k variants can't give you even close to a full picture. Genotype imputation then fills in the gaps, using the array variants as a scaffold, by inferring missing variants from a relevant reference panel. The accuracy of imputation, therefore, is crucial for all downstream applications.Below, you can see the results from the tests that compare our models (Orchestra and Selphi) to the leading industry standards. It's important to note that most other consumer companies don't use ancestry and imputation in their prediction models at all, or they use methods that are inferior to what is being tested here. Fig.1: Orchestra vs. state of the art LAI methods. (a) Percent recall and precision for ancestry deconvolution by FLARE (navy), Gnomix (light blue), RFmix (green) and Orchestra (red) across 6 generations of admixture. Each generation is represented with a star shape. The number of points on the star corresponds to the number of generations (0 - 6). Orchestra outperforms other methods in the 1000 Genomes Project (1KGP) dataset with 16 populations (left) and our larger custom data panel with 35 populations (right). Accuracy (%) per population for the 16 populations in the 1KGP dataset (b) and the 35 populations in the larger custom dataset (c). Populations are ordered by mean accuracy across all methods (cross). Overall accuracy for each reference panel is shown on the right.As seen above, Orchestra markedly outperforms other leading ancestry methods in both non-admixed (generation 0) and admixed samples (generations 1-6). It has ~15% better overall recall and ~14% better overall precision than the next best model. It also retains high accuracy across all tested populations, with a remarkable ability to distinguish between closely related ancestries. Orchestra achieves an accuracy of over 75% for 100% populations within the 1KGP dataset and for 75% of populations within the custom data panel. The other models struggle with about a third of the populations, where their accuracy falls below 50%.Fig. 2: Accuracy of Selphi vs. state of the art Imputation methods. Imputation errors across chromosomes 1-22 for Beagle 5.4 (blue), Impute 5 (magenta), Minimac 4 (Yellow) and Selphi (Green) for different minor allele frequencies (MAFs) (a) and in different superpopulations (b). Target and reference samples are obtained from the 1000 Genomes Project (1KGP) 30x reference panel. Errors are shown as deviations from the average number of errors across all 4 methods. Selphi outperforms all other methods for all minor allele frequencies and all four super populations. Selphi is in particular better at imputing rare variants (MAF < 1%).As seen above, Selfie outperforms leading imputation methods across all allele frequencies, performing exceedingly well for rare variants, where all other models struggle. This is of importance because rare variants are more likely to be of medical significance. Selphi also performs better in all tested super populations: Africans, East and South Asians, and Europeans.B2B Growth & High Return on Marketing SpendIn 2022, SelfDecode averaged a 13:1 return on every dollar spent on marketing.However, we looked at the landscape and saw that there are quite a few direct-to-consumer companies in genetics, but none of them were using up-to-date methods because of the difficulty in building the core technology.We could have just continued with our V1 technology and had a profitable business without improving it, but then it would never make it into mainstream healthcare. It takes longer to do something correctly to begin with, but the results are much better in the long run. That is why we raised and why we are raising again.For the past two years, we have utilized the additional funds from revenue and our previous raise to improve our core technology, which allowed us to create the best genetic analysis models currently available, as evidenced above. Additionally, we:Optimized our AI and machine learning technology to provide clinical-grade Polygenic Risk ScoresCombined genetics with conventional labs and self-assessments within SelfDecode health reportsImplemented Ancestry-Informed Polygenic Risk Scoring ModelsImprove our genetic file analysis to impute over 83 million SNPs with 99.7% accuracy, outperforming academic and commercial models by 22%Because of our advancements in our technology and valuable consumer-ready software, SelfDecode has massive B2B potential. Already in the last year, we were able to secure 26+ B2B partnerships with an estimated value of $69M over the next 5 years.Throughout the year, we also worked on improving the product, dialing in our subscription offers, and introducing targeted and relevant upsells to our customers, nearly doubling the average lifetime value from $247 to $447. Since 2021, we’ve grown our active subscribers by more than 150%. Additionally, SelfDecode was named a winner in Similarweb’s #Digital100 for 2023. With a website growth rate of 120.5%, we’ve been included in the company’s annual ranking of the fastest-growing digital companies.A look inside SelfDecodeWhat’s next for SelfDecode? Goals for 2023 & beyondSelfDecode will continue adding features and product offerings for their B2C and B2B subscription products.B2B BusinessAs of Q4 2022, we have signed 25+ partners to license our technology out to other companies in the personalized health space.Including:Direct to consumer genetics companiesDirect to consumer lab testing companiesSupplement companies that want to integrate precision healthHealth apps or devices that want to integrate precision healthB2B Subscription Product for integrative Health PractitionersClient management system (2023)Integrative client reports & health recommendations (2023)B2C Product ExpansionComprehensive health reports that combine multiple PRS into one report (current)Expansion of our recommendations feature (2023)Precision Health Forum - connects patients with similar conditions, genetics and labs (2023)Long-term goals (2023-2025) Utilize our large user database to dramatically improve predictions and recommendationsConduct health economic studyPartner with corporations to reduce healthcare costs via preventative treatments.Provide clinical decision support system to medical providers - tools that allow doctors to make better decisionsCreate a laboratory developed test so that doctors can start ordering the tests in hospitalsConduct clinical trials for FDA approval for patented diagnostic testsMarket Growth PotentialSelfDecode has entered the health industry at just the right time. It's quite clear that polygenic risk scoring will be part of the clinical healthcare market. What isn't clear is how soon it's going to happen - but we believe in the next 1-2 years.Since we are the industry leader in this space, we think we are poised to get a big share of the market and grow with the market.Consumers are looking for digital solutions for their healthcare now more than ever before. In fact, the Accenture 2020 Digital Health Consumer Survey showed that 62% of consumers are open to using digital health services.With 6 in 10 adults having at least one chronic disease that can be impacted by lifestyle choices, the consumer need for personalized and data-driven health recommendations is apparent. GMI Insights reported that the digital health market is expected to grow to over $639 billion by 2026.People aren’t just looking for ways to solve their current health problems. They are looking for strategies to effectively prevent diseases and conditions. Grand View Research predicts that the preventive healthcare technologies and services market will be worth $432 billion by 2024. Combined with the fact that the mobile medical apps market size is growing at a compound rate of 23% per year (Emergen Research), and SelfDecode is poised to provide a growing market with just the right product at exactly the right time.We also believe that consumers don't just want generic solutations, but they are starting to demand real personalization when making health decisions.SelfDecode is poised to not only market its own consumer platform, but to be a provider for other consumer platforms and functional healthcare providers who want to integrate genomics into their practice. Meet the founder: Joe Cohen's StoryOur customers are happier, healthier & they love us

## FAQ
1. **How can UK customers invest? All the bank accounts to invest are US only.**
   - I also have in a support ticket with WeFunder, as it appears that the international investor guide may be out of date, as people are not seeing the options shown on that page. We'll update as soon as we have an answer. Thank you!
2. **Can you comment on the number of active subscribers and the distribution of revenue per subscriber. Does this follow a power law distribution or is it more uniformly distributed amongst paying subscribers?**
   - There are around 12,000 active paying subscribers. All our subscribers are paying.
3. **Is this investment in all Genius properties (lab, selfhacked, etc), or just selfdecode?**
   - Yes, it's in all of Genius Labs - SelfDecode, SelfHacked, and the LabTestAnalyzer. It also includes our new ventures into lab sales that we released and supplement sales that we aim to come out in 1 month. We provided a roadmap of all the products we'd like to release in 2021 and 2022.
4. **whats the current MRR**
   - Around 75k USD/month
5. **Is there a way for UK investors to invest?**
   - Hi John - https://help.wefunder.com/154992-linked/international-investor-guide. This page explains how international investors can invest, but if you visit https://wefunder.com/selfdecode/invest as indicated by the guide you will need to have a WeFunder account and be logged in to see the page.

## Team
- Joseph Cohen (Founder, CEO)
- Puya Yazdi (Chief Scientific Officer (CSO))
- Edward K (Chief Technology Officer (CTO))
- Ralph Kenney (Chief Operating Officer (COO))
- Manfred Grabherr (VP of Bioinformatics and AI)
- Charles Manson (AI/Machine Learning Engineer & Statistician)
-  Brett DeColyse (Chief Financial Officer (CFO))
- Anibal Jimenez (Director of Business Development)
- Adriano De Marino (Senior Bioinformatics scientist & Team Lead)
- Jon Lerga Jaso (Bioinformatics Scientist)
- [deleted user] (Software Architect & Team Lead)
- Eliana Ferdman (Chief of Product)
- Laurent Dufloux (Big Data Engineer)
- Umar Khan (Big Data Engineering Team Lead)
- Biljana Novkovic (Senior Precision Medicine Scientist)

## Q&A
- Q: Thank you very much Joseph for the corporate structure/IP ownership clarification.
  - A: In the beginning for the first day, we were testing a small early bird discount, but that disappeared after it quickly got surpassed. Since then, we've done a deal with a single investor who is also a user of ours for 4M dollars. To build the all encompassing AI health platform that we are working on will require a lot of capital. So as we raise more capital, the valuations will always increase. Once we file the Form C with the SEC, you will view the final set of terms and sign off before the investment is complete. That way, you know exactly what you're getting.
- Q: How can UK customers invest? All the bank accounts to invest are US only.
  - A: I also have in a support ticket with WeFunder, as it appears that the international investor guide may be out of date, as people are not seeing the options shown on that page. We'll update as soon as we have an answer. Thank you!
  - A: Hi Elektra - https://help.wefunder.com/154992-linked/international-investor-guide. This page explains how international investors can invest, but if you visit https://wefunder.com/selfdecode/invest as indicated by the guide you will need to have a WeFunder account and be logged in to see the page.
- Q: I see there are currently more pledged investments than the money you asked for. If actual investments that you receive via this Wefunder campaign go over the total of money you asked for, will you accept them at the same conditions? That is, you raise the total limit here on Wefunder? Thanks for clearifying! And, is there a deadline until when funds must be received by Wefunder? Thet is, when will you close this investment opportunity?
  - A: Hi, the round is closing by April 30th for sure, but we assume it will fill up before then. There's some money pledged (70k) but people have not transferred yet, so there's still an opportunity to invest before then, but it's anyone's guess when it closes between now and April 30th.
- Q: Can you update revenue for October, November and December? Also, I see you're oversubscribed. Are you going to raise the limit or close? Any indication of interest for an institutional round? Thanks
  - A: 856k in Q4 We are going to close it after the limit is reached. For now, there's some people that have pledged and still haven't been able to send the money for one reason or another, but it will be closing soon and the valuation raised.
- Q: Hi, amazing business you have here. A few quick questions. 1. What was total revenue in 2018, 2019, and 2020? I'd like to see a better picture of the growth pattern. 2. What is the current run rate based on March 2021 revenue? 3. What is the current monthly burn rate? 4. Is the biggest differentiator between your company and companies like Invitae the fact that patients don't need a doctor for your services? Please clarify if or if not. Thank you
  - A: Hi LaFoy, Sorry for the delay. We just closed funding of 4M off of Wefunder as we are waiting for the financial review to be complete (any day now!). There's 3 operating LLCs under a holding company called Genius Labs. Genius Labs Co is where people are investing. SelfDecode is our main product, and we don't want to mix that with say selling lab tests or supplements, or the SelfHacked health content website, which are in different categories. 2017 - 678k 2018 - 887k 2019 - 1.264M - Genius Labs is formed to operate as an investment company 2020 - 1.933M 2021 - 2.7M Our burn rates from 2017 to 2020 was close to zero, because we didn't raise much money, so we had to make sure that we are not operating at a loss. This also limited growth of course. SelfDecode revenue however has been growing quite fast. The important thing to note is that we haven't been spending money on paid ads, and recently we did an analysis to find out they are highly profitable. So we are in the process of scaling paid ads. We do not have an exact figures for March yet, but every month so far this year, revenue has been growing for SelfDecode.
- Q: What is the current ownership structure of genius lab? Joe Cohen, Eliana Ferdman, Igor Lychagov, Dan Magnuszewski, Michael Levy, Bay Wharf Capital, Knockout Capital, .... Could you please specify the complete list and what percentage of the Enterprise they own?
  - A: Hey Leila, I'm sorry but that is information that I would like to be kept private.
- Q: Are there other platforms available to invest in Selfdecode? Because at this moment I've been trying fervently for over a month to get money into my Wefunder cash account. All transfers simply say "pending" yet my bank has no record of an ACH transfer being initiated by Wefunders bank. After 6 support emails throughout the month I still have yet to recieve any response. Wefunders "support" seems to be nonexistent. Wefunder may not be a scam site but it seems to be operating so poorly I dont trust them to handle my money. Are there any other options?
  - A: It could be related to that we are not 'official' yet. We are at the finish line to complete this, so hopefully we are looking at 2 weeks from this date. Or it might be some other problem. If you're having a problem once we become official, do let us know and we will contact them as well.
- Q: I’ve been reading SelfHacked and using the various tools of the platform for years. Pleasantly surprised that you’re doing some crowdfunding. What’s the plan in the future? Will you take more funding at a later date from venture capitalists? Would there be a future exit event on the table? What’s your plan in that regard?
  - A: We plan to grow as fast as possible. Ideally, we'd like to IPO rather than be bought out, but we are open to the right partners who match our ideals and goals.
- Q: Hi there, given that DNA and genomic data is touchy subject, how do you anticipate handling DNA data? Does your company currently or anticipates sharing and selling DNA data to third-parties or providing it for law enforcement purposes?
  - A: We take privacy and data security very seriously. We hope to use some of the investment to hire a security engineer. We do not anticipate selling or sharing data, and certainly not without explicit approval from customers. Selling data is not part our business model.
- Q: Is there a way for UK investors to invest?
  - A: Hi John - https://help.wefunder.com/154992-linked/international-investor-guide. This page explains how international investors can invest, but if you visit https://wefunder.com/selfdecode/invest as indicated by the guide you will need to have a WeFunder account and be logged in to see the page.
- Q: Hi I have a high level of confidence in the company to deliver in this niche. My concern is that It is not clear what my investment means/translate to as a value/stake in the company. I invested in a previous round and would love to invest more but I have reservations from the first round. The communication was very poor. Other than a payment receipt there was NO formal documentation of the investment or statement of the value from SelfDecode or Genius Labs Corp. When do we expect these to be issued?
  - A: Hi Lara, You can go to your portfolio - wefunder.com/portfolio. On that page, you will see all your investments and be able to download all pertinent contracts.
- Q: Can you post some recent financial metrics? What was revenue in July, August and September? How many new customers did you sign up during those months?
  - A: Yes! July: $194,067.05 Aug: $198,343.18 Sept: $262,471.78
- Q: What exactly do you do with machine learning? What do you use as training data? Do you hold or plan to hold proprietary data that is not easy to access or re-create for other similar companies?
  - A: We use machine learning for a lot of stuff. To name some off the top of my head: 1) To make our polygenic risk scores more accurate 2) Imputations pipeline more accurate 3) Genome simulation and genome compression projects 4) Recommendations and many other projects in the future We use both public datasets and our own data to train.
- Q: Do you intend to pay a dividend?
  - A: No. We plan on going public as soon as it makes sense for us. Companies in cutting-edge technologies generally don't pay dividends, even companies as big as Amazon, because it's better spent on investing in technology and gaining intellectual property or growth than dividends.
- Q: I am trying to do my early bird investment and I keep getting denied because I have not completed the form, but I do not see how I can do that. EDIT: I realized it was because wefunder would only let me invest a fraction of what I wanted to invest, only 200 which I don't understand, even after updating my financial information. EDIT: changing my investment amount after investing the first time seemed to work, hope this helps anyone else having wefunder issues.
  - A: Great!