If you work in aging and would like help with your projects, sign up.

If you're enthusiastic about ending diseases and aging, sign up.


We are now at a juncture in the aging and longevity field: year over year, there is an exponential increase in data availability, but not necessarily in the availability of data scientists, artificial intelligence practitioners, software engineers, data engineers, machine learning experts, and more. The goal of MoreLife is to bridge this gap between aging research labs and machine learning / engineering expertise. 

Read more

Below is the high-level picture of the type of collaborations that are possible:

Screen Shot 2019-07-20 at 7.20.02 PM.png

Project 1: Large data organization and analysis using software tools freely available in the web

Who: Albert Einstein​ Institute for Aging Research

Type of data

Comparisons of changes in proteins, RNA and metabolites across experimental models of aging or age reversing interventions

  • Proteomics

  • RNase seq

  • Metabolomic

Type of analysis

  • Use of pertinent software for analysis (IPA, STRING, GO)

  • Identification of differences

  • Reporting of differences

Screen Shot 2019-04-29 at 10.50.41 PM.pn

Project 2: Automatic analysis/quantification of image

Who: Albert Einstein​ Institute for Aging Research

Type of data

  • Images from experimental cellular and animal (tissue) models of aging and age-related disorders

  • Immunofluorescence images

  • Histology images

  • Electron micrography images

Type of analysis

  • Number for fluorescent “puncta” per cell

  • Quantification of staining intensities

  • Recognition of changes of patterns in stainings

  • Identification of structures with defined characteristics

Screen Shot 2019-04-29 at 10.55.43 PM.pn

Project 3: Database creation

Who: Albert Einstein​ Institute for Aging Research


Development and input information of animal colony records and link them to the data generated from each mouse model.

[Side Note: This project can be extended to other labs, therefore is not limited to this lab.]

Screen Shot 2019-04-29 at 10.58.25 PM.pn

Project 4: Web lab page development

Who: Albert Einstein​ Institute for Aging Research


  • Provide information about the goals/activities of lab research

  • Keep up to date information on advances, publications

  • Provide contacting information for people interested in this area

  • Provide links for sharing of our protocols

  • Provide links for reagent requests/sharing

[Side Note: This project can be extended to other labs, therefore is not limited to this lab.]

Project 5: Secure collection and storing of biomarkers (test results of volunteers)

Who: LongeCity

Description: The LongeCity biomarker testing database is one of the few open testing initiatives to measure the biological age and track the rejuvenation/anti-aging practices of the participants.


The biomarker testing initiative just completed its first year and will test the same cohort for a second year with plans to keep the testing going on an annual basis, while also adding participants.


Needs: Database engineer to create an application for participants to easily enter data, such as test results, supplement regimens, and other rejuvenation efforts (like diet, fasting, exercise, meditation, etc...)


One LongeCity member created a simple spreadsheet as a beginning for tracking results, but we are hoping for something more structured: https://www.longecit...r-test-results/

Project 6: Wordpress development

Who: Lifespan.io


Combine their two sites (https://www.leafscience.org/ and https://www.lifespan.io/) and add additional features to turn it into a true community hub for aging research information, advocacy, and research support. The plan is to include features such as those similar to change.org, ways to orchestrate crowdsourced clinical trials, and more persistent communication / collaboration options for the users of the site. 

Project 7: Data visualization

Who: Lifespan.io

This would be using technologies such as D3 to make very clear and engaging infographics to clearly showcase current budgetary failings, demographics and economic trends relating to societal aging, etc. that make plain the need for significantly altered priorities at the national and international levels regarding aging research funding and focus. This is currently lacking, and something with the potential to have a profound effect on currently existing dialogues around policies such as medicare-for-all, for example.

Project 8: Algorithmic annotations and groupings of metadata on public databases

Who: Robur Health 


The ability to deepen our understanding of biology and discover new therapeutics benefits from the growth of publicly available data. Most databases, such as those governed by the NIH, contain structured entries of experimental designs. However, much of this metadata is human-generated, thus the information can be inconsistent and incomplete, and limits comparative analyses across experiments. Many experiments are thematically similar, and perhaps amenable to grouping by topic or other shared features. Possible strategies include topical modeling, natural language processing, or neural networks (such as LSTMs).

Significance: Improved annotations and searches within and across open databases is an important step towards maximizing their utility. This project would provide broad benefits in academic, public, and private sectors. Importantly, aging research to date has been largely underrepresented in biomedical research. Effective data aggregation across repositories with studies on aging could increase our power to better understand the aging process. In addition, like any scientific field, improved mechanisms to study aging can yield a positive feedback loop for future funding and research.


Progress to date: Text-parsers have been scripted for public NIH databases, with a small set of curated annotations (these positive controls could be useful for semi-supervised learning techniques).

Project 9: Probabilistic inference of reaction activities

Who: Robur Health

Metabolism is both complex and dynamic, driven largely by the conversion of reactants to products via enzymes. However, our ability to observe the activity of these reactions in living systems is severely limited. Our knowledge on reaction rates largely comes from experiments in either non-living systems, or in bacteria. Even so, there is abundant information on the properties of these enzymes, such as their size, structure, and promiscuity for multiple reactants and products. These variables currently exist across multiple public databases, and is ripe for a data science approach. Possible strategies include scraping, programmatic queries, and advanced statistical learning techniques.


Significance: While we cannot currently observe the true reaction rates in higher organisms, such as humans, a predictive model of rates in non-living or bacterial systems can improve our estimates. While this project has main applications in bioengineering, in the context of aging, research has demonstrated broad changes in metabolism with age. Mitochondrial dysfunction and deregulated nutrient sensing are two hallmarks of aging, which are currently receiving attention in both basic biology and therapeutic applications. However, metabolic approaches to aging and lifespan suffer from weak science and unrealistic interventions, such as extreme feeding/fasting diets. These limitations can be overcome with more accurate models of human metabolism.


Progress to date: Programmatic queries and scrapes have been created for multiple databases to extract the aforementioned predictor variables. Published work on “true” reaction rates in non-living and bacterial systems provides positive controls to build predictive algorithms for non-observable rates. Approaches such as forests and neural networks have been attempted to date, but generally yield poor test accuracy.

About Robur Health: 

Our gains in life expectancy are incurring a cost of years lived in poor health. This cost grows with the prevalence of conditions related to both our metabolism, and to the very process of aging itself. These conditions, categorically considered “chronic and complex”, represent long problems for our collective health. The pharmaceutical industry does not focus on long problems, nor treats these complex conditions with commensurate therapeutic strategies. Robur views therapeutics as a complex objective function, and builds an unconventional computational discovery platform designed to restore youthful and healthy metabolism. Robur taps into the growth potential enabled by unprecedented compute power and data availability, and overlays branches of network theory, machine learning, and bioengineering onto first principles of biology. This unique therapeutic perspective, and this unique blend of disciplines, offers the promise to meet the unique challenges of human health in the 21st century.

More projects coming. Sign up here or email me at morelifetech@gmail.com.

Screen Shot 2019-05-30 at 3.43.41 PM.png