News and Trends on TechBio ⚗️
Aging Intervention Foundation, Longevity and TechBio, and Two Sigma Ventures
“To an extent that has surprised us and the rest of the scientific community, telomeres do not simply carry out the commands issued by your genetic code.
Your telomeres, it turns out, are listening to you. 🎧
They absorb the instructions you give them. The way you live can, in effect, tell your telomeres to speed up the process of cellular aging. But it can also do the opposite.”
Longevity 🤸♂️
⏺️ Aging Intervention Foundation
Aging Intervention Foundation has a mission to increase Healthspan and Lifespan, and to slow and ultimately reverse biological aging and age-related decline for more years of healthy living, utilizing the following modalities:
Gene therapy and AI for drug design and biomarker analysis
Plasma Therapies, therapeutic plasma exchange/removal of pro-aging factors and adding youth enhancing factors
Mitochondrial therapies
Yamanaka/OSK systemic therapy, reset the epigenome toward youth/cellular reprogramming
Personalized Microbiome therapies
NAD and NAD enhancement supplements, AlphaKetoglutarate (AKG), nutritional supplements and Kaufmann protocol, cognitive and life enhancement
Senolytics, Peptides, Exosomes, Engineered Reprogramming Extracellular Vesicles (VSELs) and Protein profile control. For more
The Aging Intervention Foundation is run by Johnny Adams, that he is actively looking right now for exceptional people to create aging solutions, money to make it happen, grants for exceptional researchers, as well as to fund companies for equity and to partner with labs in the US and offshore working on TechBio Longevity. His supporters will get early access to longevity therapies, valuable information and money if they desire.
In his Scientific Advisory Board you can find “great minds” 🧠 like:
Alexander Zhavoronkov, PhD CEO and founder of Insilico Medicine (Insilico Medicine 10 Years of AI Drug Discovery Innovation)
“To sustain longevity, you have to evolve.”
Aries Spears
🔶 Longevity and TechBio
Headquartered in Toronto, Deep Genomics uses AI and ML to develop life saving drugs by combining DNA, biomarkers and cell machinery. Since its founding in 2015, Deep Genomics has built several predictive systems known as the AI Workbench, and has made billions of predictions across the entire human genome, for millions of genetic variants, and hundreds of millions of novel compounds. So far, the company has used its computational system to develop a database that provides predictions for more than 300 million genetic variations that could affect the genetic code.
Its proprietary AI platform, BigRNA, which is the world’s first RNA foundation model for RNA therapeutics, can predict tissue-specific RNA expression, splicing, microRNA sites and RNA binding protein specificity. BigRNA can uniquely discover a wide range of new biological mechanisms and RNA therapeutic candidates that would not be found using traditional approaches that measure only overall gene expression levels. In contrast, BigRNA is trained to predict RNA expression at sub-gene resolution, such as polyadenylation, exon skipping and intron retention (An RNA foundation model enables discovery of disease mechanisms and candidate therapeutics).
Deep Genomics made headlines back in 2019 with discovering a novel target and a novel RNA therapeutics candidate, DG12P1, for the rare Wilson disease using its platform BigRNA, all within 18 months of initiating target discovery efforts (Deep Genomics Nominates Industry’s First AI-Discovered Therapeutic Candidate). In particular,
Deep Genomics’ AI system scanned over 2,400 diseases and over 100,000 pathogenic mutations while searching for good drug development opportunities and was able to predict and confirm the precise disease-causing mechanism of the mutation Met645Arg. One of several genetic mutations that leads to loss of function of the ATP7B copper-binding protein, a genetic mutation that impairs the body’s ability to remove copper, and thereby identify a clear therapeutic target. The AI system was then used to identify 12 lead candidates out of thousands of potential compounds, taking into account in vitro efficacy and toxicity. In particular, TDG12P1 was designed to correct the exon skipping mechanism of Met645Arg and after tolerability experiments Deep Genomics declared it the ideal candidate to advance toward IND.
On June 12, 2024, Deep Genomics announced the opening of its new office and lab facility in Cambridge, Massachusetts (the expansion of its Toronto office) and several key leadership hires. Deep Genomics raised so far a total of $180M to automate drug discovery.
Off course, it's not only Deep Genomics studying genetic variability or genomic instability (the high frequency of mutations), namely the first hallmark of aging. On July 11, 2024, the “Targeting chromosomal instability (CIN) in patients with cancer” review was published, describing advances regarding our understanding of CIN from a translational perspective, highlighting both challenges and opportunities in the development of therapeutic interventions for patients with chromosomally unstable cancers:
CIN has long been recognized as a hallmark of aggressive human malignancies.
CIN drives cancer progression by generating genomic alterations such as chromosomal gains, losses and complex rearrangements. CIN can also drive the development of epigenetic abnormalities and chronic inflammation that facilitate both metastatic dissemination and immune evasion. And
Several novel treatment approaches include KIF18A inhibitors, p53-reactivating agents and PLK4 inhibitors, all of which are currently being tested in clinical trials.
On September 28, 2021, Genomic Vision announced the launch of TeloSizer, for precise detection and quantitative measurement of telomere length (the 2nd hallmark of aging). The new TeloSizer service was built on Genomic Vision’s proprietary technology FiberSmart, of AI automation analysis, to automatically detect, grab images and quantify telomere length on single DNA molecules.
Unfortunately, on November 17, 2023 Genomic Vision—a biotechnology company that develops products and services for the highly accurate characterization of genome modifications—announced that it decided to open a receivership procedure to protect the company and avoid bankruptcy.
Alzheimer’s disease (AD) is influenced by both genetic and brain epigenomic alterations and “Multiple array-based Epigenome-Wide Association Studies - EWASs" have identified robust brain methylation changes in AD. For this reason, a group of researchers developed EWASplus—a computational method that uses a supervised ML strategy to extend EWAS coverage to the entire genome—finding genes near top EWASplus loci enriched for kinases and genes with evidence for physical interactions with known AD genes (A machine learning approach to brain epigenetic analysis reveals kinases associated with Alzheimer’s disease). The epigenetic alterations—genes are turned on or off by changing the chemical structure (methylation) of DNA but not changing the DNA coding sequence—have been shown to be correlated with many aging diseases, including autoimmune disorders, neurological disorders as well as Huntington, Alzheimer’s, Parkinson’s diseases and schizophrenia, and is considered the 3rd hallmark of aging (The Hallmarks of Aging).
The US health data firm TruDiagnostic is building out its epigenetic platform and testing services, which aim to provide the most accurate and insightful longevity analysis using information found in the epigenome. Its flagship testing product, TruAge, measures biological age using DNA methylation data, but the company also provides a wide range of aging-related metrics, from telomere length and immune cell measurements to current rate of aging, intrinsic and extrinsic age calculations and more (TruDiagnostic: a new level of epigenetic testing in longevity).
The company went from zero to $80M within three and a half years in terms of revenue, and from one employee to hundreds within three-and-a-half years. In 2020, TruDiagnostic built its 20,000 square foot CLIA-certified and HIPAA-compliant lab in Lexington, Kentucky, with the aim of helping drive the fields of epigenetics and longevity-focused personalized medicine.
They are involved in the following clinical trials:
Doterra is conducting multiple studies to evaluate the impact of their essential oils. Their first study is with a product called On Guard, which is an essential oil blend to support the immune system.
A prospective, non-randomized 4 month study, containing 50-100 patients to evaluate Semaglutide’s Impact on epigenetic aging.
A prospective non-randomized study of 20-25 patients over age 40 to evaluate the effects Quercetin and Dasatinib have on healthy individuals over a 6-month period.
A study to compare multiple DNA methylation age indicators between a group of participants following the standard American diet to a group of participants who have followed the Nutritarian diet for at least five years
And many more.
In 2020, Astellas acquired the UK based Nanna Therapeutics for €80M to boost the development of anti-aging drugs. Through this deal, Astellas gained access to Nanna’s drug discovery technology—which focuses on drugs that target the mitochondria (the 4th hallmark of aging)—developing a treatment for a genetic syndrome called "mitochondrial encephalopathy, lactic acidosis and stroke-like episodes", or MELAS (caused by a change in one of several genes that help build mitochondria, cell structures that convert food into energy). Nanna’s microfluidics-based drug discovery technology was a big attraction for Astellas. Since with its high-throughput platform, Nanna can generate, screen and acquire data on billions of small molecules in parallel, producing drug candidates in a matter of months rather than the years it typically takes.
In a study that was published in 2022, a group of researchers screened 60 herbs derived from a book on Chinese traditional medicine, and have identified hesperetin (a structural analog of the sophricoside and genistein found in Sophora japonica), as a uniquely powerful Cisd2 activator (pro-longevity gene Cisd2). In fact, previous research has shown that Cisd2 expression is associated with longevity in mice (by aiding mitochondrial function) and that Cisd2 deficiency is associated with premature aging in mice (Hesperetin Upregulates Metabolism and Longevity in Mice) .
In particular, Cisd2’s effects on mitochondria are due to its effects on calcium homeostasis and its deficiency causes problems in multiple organs, as mitochondria become overloaded with calcium ions. Hopefully, hesperetin clearly influences mitochondrial function in a way that leads to significant and positive effects on metabolism and longevity in mice. But of course, this is still only a mouse study.
Always, regarding nutraceuticals—food or elements of food obtained from plant or animal origin with significant medical or health benefits—an AI-powered drug discovery project will be trained on natural ingredients to create novel longevity-focused nutraceuticals after Insilico Meicine and SRW partnered to advance longevity science through the power of AI.
The professor Shinsuke Yuasa from Tokyo has been focusing on AI drug development in Longevity for many years, by utilizing convolutional neural networks (CNN)—deep neural networks commonly applied for visual imagery analysis that expresses how one shape is modified by another. One of it's most recent breakthrough is the development of DeepSeSMo, a CNN based scoring system that was trained to quantify the number of senescent cells on biological microscopy slides, since they have distinct morphologies with enlarged and flat cell bodies and distinct aggregation heterochromatin, a tightly-packed form of DNA (5th hallmark).
This algorithm was tested on tissue treated with various drugs in an attempt to find senolytic or senotherapeutic drugs and four targets were identified: terreic acid, PD-98059, daidzein and Y-27632·2HCl (via Longevity Technology).
In particular,
the terreic acid (a metabolite with antibiotic properties produced by the fungus Aspergillus terreus) extends yeast’s lifespan,
the PD-98059 (an inhibitor of mitogen-activated protein kinase kinase) and daizein (a naturally occurring compound found exclusively in soybeans and other legumes and structurally belongs to a class of compounds known as isoflavones) suppresses cellular senescence and associated phenotypes, and
Y-27632·2HCl (a selective p160ROCK inhibitor) regulates the cell cycle more generally.
Moreover, investigators at Stanford University School of Medicine and the Buck Institute for Research on Aging, published their findings in a paper titled “An inflammatory aging clock (iAge) based on deep learning tracks multimorbidity, immunosenescence, frailty and cardiovascular aging”, claiming that by using AI they can build an inflammatory-aging clock, the iAge, predicting how strong or not our immune system is (immune-senescence). Since standard immune metrics used to identify individuals most at risk for developing single or even multiple chronic diseases of aging are lacking.
So, while the immune system is important for fighting diseases, it was only in the past few decades that it has become apparent that inflammatory components of the immune system are often chronically elevated in aged individuals and associated with an increased incidence of cancer, cardiovascular disease, neurodegenerative disorders, and this have led to the concept that inflammation plays a critical role in regulating physiological aging.
Regarding aging clocks, ExplaiNAble BioLogical Age (ENABL Age) is an AI framework for interpretable biological age. ENABL Age is a computational framework that combines ML models with explainable artificial intelligence (XAI) methods to accurately estimate biological age with individualized explanations. ENABL Age clock was significantly correlated with chronological age.
On August 24, 2020, Yumanity Therapeutics (a clinical-stage biopharmaceutical company that is accelerating the revolution in the treatment of neurodegenerative diseases) and Proteostasis Therapeutics (a clinical stage biopharmaceutical company developing small molecule therapeutics to treat diseases caused by dysfunctional protein processing) announced that they have entered into a merger agreement, to leverage their common scientific expertise in protein misfolding (Source) (6th hallmark). Yumanity’s drug discovery platform was designed to enable a rapid screening for potential disease-modifying therapies by overcoming toxicity of misfolded proteins in neurogegenerative diseases.
On June 6, 2022, Yumanity sold its most advanced experimental drug—which is being tested as a treatment for Parkinson's disease, among other conditions—as well as its unpartnered, discovery-stage product candidates to Johnson & Johnson's Janssen division for $26M in cash.
Gero (2015), working in the field of longevity, is a pre-clinical stage company aiming to create therapeutics through the use of its GERO.AI platform, that utilizes whole-exome sequencing data for in-human AI Drug Discovery.
Gero also has a platform called GeroSense, which creates digital biomarkers to measure health changes via smartphone with a precision blood test. GeroSense is a health app on our smartphone that provides digital biomarkers of health and resilience (the recovery rate after stress such as having a cold, exhausting physical activity etc). But instead of simply counting the total number of steps taken each day, GeroSense predicts biological age acceleration in years of life gained or lost, due to healthy or unhealthy lifestyle and nutrition choices. Nutrient sensing—cells ability to recognise and respond to fuel substrates such as glucose—is also gradually declining as we age. Current evidence indicates that increased nutrient signaling accelerates aging. While decreased nutrient signaling—achieved with caloric restricted diets—is promoting healthspan and longevity (7th hallmark).
In January 2023, Gero announced that it had entered a research collaboration with Pfizer to discover potential targets for fibrotic diseases, using large-scale human-based data.
On October 18, 2023, Gero closed $6M in a Series A extension round (for a total of $13.5M). The round was led by Melnichek Investments (a Cyprus-based VC firm that seeks to improve the quality of human lives by funding and supporting promising, potentially high-impact, ML startups) with the participation of VitaDAO and Leonid Lozner.
Twin Health is a revolutionary Precision Health platform combining IoT Sensors, ML and Medical Science to reverse chronic diseases like diabetes and improve human metabolic health. Twin Health announced in 2022 that it has conducted a randomized controlled trial to develop India’s first AI-powered technological therapy, called Whole Body Digital Twin, for the remission of type 2 diabetes.
On December 13, 2023, the Digital twin company Twin Health secured $50M.
On May 22, 2024, Twin Health announced it is extending its whole body digital twin AI platform, already proven to help members achieve remission of type 2 diabetes and eliminate medications, also to address the challenge of obesity and weight loss. Twin's Healthy Weight solution combines digital twin AI and compassionate clinical care to help members achieve a healthy weight that they can sustain without medication (Twin Health Announces Digital Twin AI for Sustainable Weight Loss with GLP-1 Elimination).
Traf2- and Nck-interacting kinase (TNIK) has emerged as a key regulator of pathological metabolic signaling in several diseases and is a promising drug target. Originally studied for its role in cell migration and proliferation, TNIK possesses several newly identified functions that drive the pathogenesis of multiple diseases. Specifically, researchers have evaluated TNIK's newfound roles in cancer, metabolic disorders, and neuronal function. TNIK signaling appears to converge on four critical hallmarks of aging: cellular senescence, deregulated nutrient sensing, chronic inflammation, and altered intercellular communication. TNIK's contribution to these processes implicate it as a possible contributor to aging-related pathology, particularly by promoting conditions like cancer and metabolic dysregulation (TNIK as a Potential Target for Age-Slowing Therapeutics).
Cellino Biotech founded in 2017 by Nabiha Saklayen is using AI and ML to automate stem cell production, for stem cell-derived regenerative medicines (8th hallmark) for Parkinson’s, diabetes, heart disease and many more. Cellino’s platform combines label-free imaging and high-speed laser editing with ML to automate cell reprogramming, expansion and differentiation in a closed cassette format, enabling thousands of patient samples to be processed in parallel in a single facility, combining biology, laser physics, gene editing tools and ML.
Cellino, a closed loop cell therapy manufacturing company, has raised so far $96M by Leaps by Bayer, 8VC, Humboldt Fund, Felicis Ventures and Khosla Ventures. Khosla Ventures apart Cellino, has invested also in
CellFE, that has developed a scalable, high throughput microfluidic technology for the efficient delivery of gene-editing molecules into cells,
Bionaut, developing microscale robots to deliver biologics or small molecule therapies locally to targeted disease areas and
Liberate Bio, using automation, in vivo high-throughput screening and ML to accelerate discovery of novel extrahepatic delivery vehicles.
For example, Cellino Biotech is using a unique blend of lasers and ML to transform the manufacturing process of stem cells. They are the only company using this approach, and that convergence lets them produce stem cells in a scalable way for the first time. Cellino uses image-guided ML to characterize the highest quality stem cells. They want to live in a world where it’s possible to make therapies derived from our own stem cells and tissues (because they don’t require immunosuppression), so in order to achieve their goal, they are pursuing collaborations with cell therapy developers to move programs through the clinic very quickly (Source).
On October 4, 2021, a review on GlyNAC (a combination of Glycine and N-Acetylcysteine) supplementation as a novel nutritional approach to improving declines associated with aging was published, analyzing published research on the effects of GlyNAC supplementation on various components of aging, and concluded that emerging evidence supports that GlyNAC could play a role in the overall health of humans as they age (Source).
In particular, emerging evidence from human studies showed that GlyNAC influences five of the nine hallmarks of aging, including mitochondrial dysfunction, altered intercellular communication, dysregulated nutrient sensing, genomic toxicity and cellular senescence. Altered intercellular communication is another of the integrative hallmarks of aging (the 9th in particular), but is mainly caused by other hallmarks, particularly cellular senescence and inflammation.
On June 15, 2013, it was announced that algorithms have led to the discovery of three drugs that have the potential to delay the effects of aging (AI and anti-aging research: Unveiling the latest drug discovery). In particular, a group of researchers from the University of Edinburgh developed an innovative method that employs AI to identify senolytic drugs, by leveraging data from over 2,500 chemical structures extracted from past studies, and training a ML model to recognize the essential characteristics associated with chemicals possessing senolytic activity.
For more:
Albert Einstein, the famous mathematician and scientist, once said:
“There is something essential about the ‘now’ which is outside the realm of science”.
What he probably meant was:
“If the past is t=10 years ago from “now” and the future is t=10 years ahead from “now” in a symmetrical reality, what is then “now” in terms of time? Zero? A state of zero time?”.
Longevity 🦿🦾 and Big Data (2022)
Latest News
Lantern Pharma Achieves Key Milestone Towards Development of Molecular Diagnostic for use in Oncology Clinical Trials for Patient Selection and Stratification with Drug Candidate LP-184
France’s Bioptimus Releases AI Model for Disease Diagnosis
IMGAIA: Insilico Medicine Generative AI Action. Event by Insilico Medicine
Exscientia extends AWS partnership to boost AI drug discovery platform
Two Sigma Ventures
Two Sigma Ventures invests in early-stage companies across many industries spanning enterprise SaaS, fintech, techbio, consumer tech, crypto and more. Two Sigma is proud to be an equal opportunity workplace and does not discriminate based upon race, religion, color, national origin, sex, sexual orientation, gender identity/expression, age, status as a protected veteran, status as an individual with a disability, or any other applicable legally protected characteristics.
On September 14, 2022, Two Sigma Announced $400M in New Funds to Fuel Data Science and Software-Driven Innovation in Early and Growth Stage Startups. This brings their assets under management to over $1.8B, and celebrates their 10th year of backing founders at the leading-edge of data and computing. Regarding TechBio they invest into:
➡️ Cajal Neuroscience is a drug discovery company built for one purpose: to deliver new medicines that give life back to patients suffering from neurodegenerative disease.
On May 1, 2024, Cajal Neuroscience and Creyon Bio, Inc. ("Creyon"), a drug development company that engineers Oligonucleotide-Based Medicines (OBMs) with industry leading efficiency creating novel best-in-class gene-centric medicines to treat rare and common diseases, announced a partnership to develop novel OBMs for neurodegenerative diseases.
Cajal is responsible for nominating targets and mechanisms of action based on therapeutic insights from their discovery platform. And Creyon is responsible for engineering oligonucleotide therapeutic candidates leveraging the powerful Creyon™ Platform, the first and only OBM platform, creating lead compounds with optimal pharmacological properties designed to minimize side effects.
➡️ Enveda Bioscience is a drug discovery company focused on identifying new therapeutics derived from the natural world, beginning with the plant kingdom. Enveda has built an advanced “search engine” using metabolomics and advanced ML to catalog and map new drugs that can be derived from the plant kingdom.
Enveda Biosciences is building the Google search for drug discovery in dark chemical space. By using ML, metabolomics and robotics their platform indexes nature’s untapped chemical space for new drug discovery, since over 95% of the natural world is a chemical mystery. They have created a map of the world’s chemistry by profiling thousands of complex samples through tandem mass-spectrometry (LC-MS/MS). Subsequently, they build generative DL models to predict chemical properties and structure directly with high accuracy from MS2 spectra, allowing scientists to characterize novel chemical space orders of magnitude faster than previously possible. By proprietary high-throughput screening methods they link each compound to laboratory-tested biological activities, finding not one, but hundreds of active compounds at once. And they have invented methods to obtain organ distribution data in vivo for thousands of compounds at once with high-confidence.
On June 14, 2024, Enveda raised $55M to accelerate drug discovery with AI (for a total over $230M).
➡️ Exai is a next generation AI-powered liquid biopsy company. Exai Bio’s next-generation RNA-based platform delivers actionable insight into cancer biology from a simple blood draw.
On April 8, 2024, Exai announced that its liquid biopsy platform detects early stage disease with high accuracy and uniquely distinguishes invasive breast cancer from low grade ductal carcinoma in situ.
➡️ Hexagon Bio is a data-driven biotech developing targeted small molecule therapeutics. Their proprietary platform combines data science and synthetic biology to discover and engineer drugs from DNA sequences. They are mining fungal genomes for inspiration for the next generation of targeted therapies for diseases with unmet needs. Since 99% of microbial genomes have yet to be sequenced vast troves of new medicines are waiting to be surfaced using DNA sequencing, ML and synthetic biology. Their TICker algorithm computationally predicts microbial secondary metabolites that inhibit human disease proteins and prioritizes them among thousands of candidates. While their HEx platform produces novel compounds using heterologous expression, an approach that allows forced expression of the secondary metabolites of interest. The result is new chemical entities based on novel chemical scaffolds, potential medicines that may offer entirely new ways to treat disease.
Hexagon Bio announced in 2023 that it has raised a $77.3M Series B financing, for a total of $270.9M in funding over 5 rounds.
➡️ Insitro (2018, South San Francisco, California) is a drug discovery company that operates an automated lab equipment running on algorithms and its own in vitro disease models. In particular, Insitro’s predictive models are grounded in human data (genetic, phenotypic and clinical data) using ML. Moreover, they combine patient-derived induced pluripotent stem cells (iPSCs), genome editing, high content cellular phenotyping and ML to build in vitro models of disease. The outcome is an integrated model of disease spanning in vitro cellular systems and in silico ML models—namely an insitro model that allows them to differentiate between cell states at much finer granularity and predict disease-relevant clinical traits.
So far they have found: 🏓 ML-derived imaging and transcriptional phenotypes in genetic epilepsies; 🏓 have revealed distinct phenotypes from the world’s largest collection of familial, sporadic and isogenically engineered cell lines derived from patients with ALS; 🏓 they have built an ML-native datastore containing significant amounts of multimodal high-content human primary data from a wide variety of solid tumors and discovered un/underexplored pathways that are active in a variety of solid tumors; 🏓 and their ML-driven genetic analysis has enabled the identification of multiple genes with strong human evidence of causality for MASLD that are potentially independent of overall adiposity.
On April 30, 2024, Insitro announced the appointment of Emily Fox, Ph.D., as senior vice president of AI/ML, to oversee those areas as well as data science and computational biology, inclusive of data modalities that span genetics, omics, imaging, clinical data and molecular design. Dr. Fox, a professor in the Department of Statistics and Department of Computer Science at Stanford University, has made groundbreaking contributions in the application of ML in healthcare.
On April 1, 2024, the company signed a six-year lease extension with Alexandria Real Estate Equities (ARE) for 143,188 square feet at Alexandria’s life sciences center in South San Francisco.
➡️ The New York-based Kallyope has taken the impossible task of mapping out the bidirectional communication between the central and the enteric nervous system and the microbiota influencing these interactions (the gut-brain axis) linked to metabolic and gastrointestinal diseases as well as central nervous systems disorders (autism and Parkinson’s disease). In 2022, the company closed a Series D financing worth $236M and right now has three compounds into phase 1 clinical trials (for type 2 diabetes, obesity and diseases of the gastrointestinal barrier) and many more in preclinical phase.
On September 27th, 2023, Kallyope announced the initiation of their Phase 2 trial evaluating K-757 and K-833, new oral nutrient receptor agonists being studied for obesity and Type 2 diabetes. The trial aims to demonstrate the weight-loss efficacy, safety and tolerability of these novel agents for patients with obesity, a growing epidemic in the United States.
➡️ Osmo, founded in 2023 in Cambridge, Massachusetts as a spinout from Google Research by Alex Wiltschko, uses ML and has created a map of odor giving computers a sense of smell to improve the health and wellbeing of human life. They are now embarking on end-to-end reproduction of a captured scent and they call this an Osmograph, and believe that like a photo or a song an Osmograph has the power to activate treasured memories and evoke profound emotions.
More specifically, in order to find out if a computer could predict smells based on molecular structure they built a ML model using graph neural networks and trained the models using a dataset of 5,000 known compounds that were paired with the smell labels they evoked, such as "fruity," "floral," “cheesy,” or "minty."
Then they froze the model in place and selected and tested it with 400 compounds. The idea was to see how the model predicted the scents of truly new molecules compared to 15 human panelists. Facing this maximally difficult challenge, their model made perceptual predictions that matched the empirical data 50% of the time, vs <20% of the time for the baseline model.
On June 5, 2024, Osmo CEO predicts we'll be sending smells via online messages someday.
Osmo raised a total of $63.5M and investors include Bill & Melinda Gates Foundation, Lux Capital, Google Ventures, Google Research, Moore Strategic Ventures and 12 more.
➡️ Xilis, is a pioneering biotechnology company developing its MicroOrganoSphere (MOS) technology—a new standard in patient-derived micro-tumor production—to guide precision therapy for cancer patients. For that reason, Xilis is using MOS and AI-driven algorithms, to develop a Xilis Response Score™ for the clinic, and in 2023 closed an extension of over $19M to its Series A financing round, bringing the total amount raised to over $89M.
On February 15, 2023, Xilis and The University of Texas MD Anderson Cancer Center announced a strategic collaboration to deploy Xilis's proprietary MOS technology in support of preclinical research to accelerate the development of novel cancer therapies.
➡️ Funa the well known Recursion Pharmaceuticals, Terray Therapeutics and Verge Genomics.