Wednesday, December 30, 2020

Insilico partners with APRINOIA on AI-powered neurodegenerative drug discovery

Insilico enters into a collaboration with APRINOIA to apply novel generative AI-powered system to discover novel compounds for neurodegenerative diseases


Wednesday, 30th of December, 2020 (9:00AM, Taipei) - Insilico Medicine is pleased to announce that it has entered into a research collaboration with APRINOIA Therapeutics to utilize Insilico's novel generative artificial intelligence (AI) technology to accelerate the discovery of next generation compounds targeting abnormal proteins in brain associated with neurodegenerative diseases.

"We are excited to initiate the collaboration with Insilico to enrich APRINOIA's proprietary collection of compounds for neurodegeneration," said Dr. Ming-Kuei Jang, CEO of APRINOIA.

"Early diagnosis is critical for disease management. Our initial focus is to discover novel imaging PET tracers to quantify and visualize pathologies of abnormal proteins in the brain. With Insilico's AI-powered platform, we are hoping to shorten the time from lab to clinics to benefit patients and in the medical communities."

With a mission to accelerate drug discovery and development, Insilico Medicine has been breaking new grounds with its next-generation AI technologies and expanding international partnerships in the US, Europe and Asia Pacific Region.

"APRINOIA discovers and develops first-in-class diagnostics and therapeutics that can be broadly applied as PET tracers in the field of neurodegenerative diseases. We are glad to collaborate with APRINOIA, where we will apply our Chemistry42 suite to design a new generation of PET tracers with desired properties. Through this collaboration, we will further demonstrate the universality of our AI-powered generative chemistry platform," said Jimmy Yen-Chu Lin, PhD, CEO of Insilico Medicine Taiwan.

By leveraging an integrated AI-driven drug discovery approach, Insilico Medicine provides APRINOIA Therapeutics with an effective, rational, external auxiliary solution for driving programs forward. The partnership between APRINOIA and Insilico will include an upfront fee and performance-based milestones.

###

About APRINOIA Therapeutics

APRINOIA Therapeutics is currently advancing a pipeline featuring diagnostic and therapeutic programs, collectively targeting brain disorders associated with abnormal accumulation of pathological proteins, including tau and alpha-synuclein, from its proprietary small molecule and antibody discovery platforms. APRINOIA is committed to building a pipeline of innovative products, as well as developing partnership with global and regional pharmaceutical companies to accelerate its programs. The company currently has operations in Taipei, Suzhou, Shanghai, Tokyo, and Boston.
Website: http://www.aprinoia.com

About Insilico Medicine

Since 2014 Insilico Medicine is focusing on generative models, reinforcement learning (RL), and other modern machine learning techniques for the generation of new molecular structures with the specified parameters, generation of synthetic biological data, target identification, and prediction of clinical trials outcomes. Recently, Insilico Medicine secured $37 million in series B funding. Since its inception, Insilico Medicine raised over $52 million, published over 100 peer-reviewed papers, applied for over 25 patents, and received multiple industry awards.
Website: http://insilico.com/

Media Contact
For further information, images or interviews, please contact:
ai@insilico.com

Wednesday, December 16, 2020

Scientists publish the first human psychological aging clock using artificial intelligence


 

Scientists at Deep Longevity published the first set of psychomarkers of aging developed using deep learning to track the changes in human psychology; the new PsychoAge and SubjAge aging clocks were linked to mortality risk

Today, Deep Longevity, a company developing artificial intelligence to track human aging and extend productive longevity, released the first AI-powered psychological aging clocks to analyze and interpret psychosocial factors in the context of aging. Deep Longevity researchers, joined by Dr. Peter Diamandis, the visionary physician, engineer, and entrepreneur, the founder of the XPRIZE Foundation and Singularity University published their study titled "PsychoAge and SubjAge: Development of Deep Markers of Psychological and Subjective Age Using Artificial Intelligence" in Aging.

Like other species following the classical evolutionary paradigm, humans are born, develop, reproduce, take care of their young, and then gradually decline and die. However, humans are conscious intelligent species and change their behavior, priorities, beliefs, and attitude, during life. Prior works on Socioemotional Selectivity Theory (SST) demonstrated that human life horizons can be manipulated and affect their behavior. To better understand the features that affect psychological age, and perceived age, and the mind-body connection in the context of aging, scientists at Deep Longevity decided to apply their skills in the development of deep biomarkers of aging to human psychology.

Biomarkers of aging that can accurately quantify the human aging process using various biological data types, commonly referred to as the "aging clocks", are among the most important recent advances in the field of longevity research. For example, in November, Deep Longevity scientists published one such aging clock based on DNA methylation, which showed superior performance to all other comparable solutions.

Despite massive progress in aging clock technology, the psychological aspect of aging has been severely understudied. However, the new study on deep psychomarkers of aging is expected to substantially accelerate the progress in the psychology of aging. The recently published study aims to fill this gap by demonstrating two AI-based age predictors: PsychoAge (which predicts chronological age) and SubjAge (which describes personal aging rate perception). These models were trained on a collection of >10,000 questionnaires completed by people aged 25-75 years as a part of the MacArthur Foundation's "Midlife in the United States (MIDUS)" study. The models presented in the publication were reworked into 15-question long surveys available at Young.AI to enable people to find out estimates of their psychological and subjective age.

The authors of the study verified the SubjAge on large independent datasets to discover that higher SubjAge is very predictive of all-cause mortality. More specifically, a person whose SubjAge is five years greater than the chronological age he or she reported is twice as likely to die as a person with normal age perception.

The authors also point out how SubjAge can be manipulated therapeutically to make patients feel younger and thus reduce their mortality risk. For example, developing openness to new experiences can reduce SubjAge prediction by seven years. Keeping the bar high, being productive and not backing away from difficult-to-reach goals will take another four years off of a person's psychological aging clock.

"For the first time, AI can predict human psychological and subjective age and help identify the possible interventions that can be applied in order to help people feel and behave younger" said Alex Zhavoronkov, PhD, founder and CLO of Deep Longevity and co-author of the study. "One's mindset may determine the decisions that ultimately affect their overall health. By identifying the psychosocial variables that underpin particular mindsets and behaviors, deep psychological clocks can serve as a powerful tool in promoting personal improvement, mental health, wellness, and a wide range of other health and therapeutic applications."

In follow-up studies of psychological aging, Deep Longevity plans to explore differences in the perception of aging between men and women, examine psychosocial markers connected to mental health, and build an integrated model of mental-physical health crosstalk.

About Young.AI: Young.AI is an AI-powered longevity web platform & iOS app created by the product of Deep Longevity. Young.AI users can access a variety of aging analysis tools, including psychological and subjective age estimation, to reach productive longevity.

###

About Deep Longevity: Originally incubated by Insilico Medicine, Deep Longevity was acquired on 14 December 2020 by Regent Pacific Group Limited (SEHK:0575.HK), a specialist healthcare, wellness and life sciences investment group. Deep Longevity is developing explainable artificial intelligence systems to track the rate of aging at the molecular, cellular, tissue, organ, system, physiological, and psychological levels. It is also developing systems for the emerging field of longevity medicine, enabling physicians to make better decisions on the interventions that may slow down or reverse the aging processes. Deep Longevity developed the Longevity as a Service (LaaS) solution to integrate multiple deep biomarkers of aging dubbed "deep aging clocks" to provide a universal multifactorial measure of human biological age. http://longevity.ai

Saturday, December 12, 2020

Longenesis announces Curator platform for privacy-preserving data use for COVID-19 research


 Longenesis announces the first deployment of its flagship product Curator for real-time, privacy-preserving biomedical data identification, with National Research Programme in Latvia for COVID-19 research acceleration and Federated Learning pipeline

Longenesis - a digital health startup aiming towards acceleration of the biomedical research pipeline worldwide, announced a release of its product Curator. It is a platform where clinical institutions and patient organizations are connected in consortiums with potential collaboration partners and study sponsors to initiate further cooperation. Main difference between existing solutions - ability to showcase available personalized datasets without compromising privacy.

Curator provides an opportunity to search for specific biomedical data by different combinations of descriptive characteristics without revealing personal data. It means that actual data sets are left within the institution. However, Curator notifies the data custodian that researchers or institutions are interested in contacting patients or using a particular dataset. This approach provides data controlling mechanisms to the data publishing institutions and the patients. Thus, Curator provides an opportunity for clinical investigators, patient organisations, registries, biobanks and other institutions to showcase the scope of data that could be used for research without compromising the privacy of patients and data protection regulations.

"The majority of solutions aimed to address the similar challenges are providing a centralized approach towards data storing and structuring, powered by the ingestion of data from multiple centers. Such approaches limit the ability to utilize the hidden value of personalized data for scientific breakthroughs, while preserving privacy and ethical aspects in the first place. Pandemic just amplified previously described problems and highlighted the necessity to find solutions for fragmented data as well as initiate collaboration. SARS-CoV-2 accelerated the need for data changing pace from monthly to daily. Moreover, to quickly act and find the treatment, data has to be in-sync not only in one institution, but also providing real-time identification among multiple centers in various geographies. Thus, with a centralised approach for metadata curation, Longenesis becomes an essential tool at the forefront of biomedical international research," says Emil Syundyukov, Longenesis Chief Technical Officer.

Currently the company Longenesis has already initiated a collaboration with 20+ clinical institutions, as well as patient organizations, biobanks, genomic sequencers, and digital health startups in the U.S., South Korea, Northern and Central European region and the Middle East, utilizing the platform for COVID-19, metabolic disorder and oncology research.

One of the strategic projects to mention is collaboration with the Latvian Biomedical Research and Study Centre (BMC), University of Latvia, Riga Stradins University and Riga Technical University. The aim of the cooperation is to use a solution to accelerate COVID-19 research and engagement with international scientific groups. Within the framework of National Research program to Mitigate Consequences of COVID-19, National Biobank of Latvia - Genome Database of Latvia maintained by BMC has established cohort of over 500 COVID-19 patients. Latvian COVID-19 cohort includes various types of samples (blood, serum, plasma, oropharyngeal swabs, PBMC, feces, urine, isolated DNA, RNA), molecular data (blood biochemistry, cytokine panel, genome wide genotyping, viral genome data, metagenome, metabolome, and transcriptome data) as well as excessive characterization of each clinical case. Being also engaged in utilization of COVIDomic platform, developed by Insilico Medicine, providing multi-omics analysis and patient stratification and severity prognosis, such approach would dramatically accelerate the process of international collaborations and new discoveries in COVID-19 space.

"The platform will significantly impact infrastructure development and acquire many new competencies in Latvia that reaches far outside the COVID-19 research frame. The COVID-19 data set is the most evaluated and data-rich disease cohort in Latvia. The development of such an integrated platform is a large step towards implementing personalized preventive medicine in the nearest future," says prof. Janis Klovins, director of Latvian Biomedical Research and Study Centre (BMC).

The Curator platform has enabled safe sharing of this significant research resource to wider scientific audience. The platform has opened collaboration across distributed COVID-19 datasets keeping the link to biological samples that is crucial factor for management of world-wide COVID-19 pandemics.

###

For press and other inquiries:
+371 20201964
Emil Syundyukov
es@longenesis.com

About Longenesis:

Longenesis, co-founded by Insilico Medicine and other top-tier biotech players, is a medical technology startup company working towards providing a technological bridge between Healthcare institutions and the BioTech industry with an aim to help identify and unlock the hidden value of biomedical data to accelerate the novel drug and treatment discovery and provide better help to those of need. Our team has experience working with the biomedical organizations and unlocking the potential for accelerating the R&D process around the globe, including National level projects in the Middle East, U.S., EU and APAC regions.

About the National Research Programme of Latvia to Mitigate Consequences of COVID-19
(Project No. VPP-COVID-2020/1-0016)

The main goal of this project is to create a well-managed, secure and centralized biobank and data exchange resource to support the activities that would limit the spread of the virus, search for novel biomarkers and treatment strategies, facilitate the establishment of new international collaborations. Project will be an important part of the overarching objective of the National Research Program for mitigation of the impact of COVID-19. The main concept behind this approach is to provide centralized service for scientific groups involved in COVID-19 research limiting the unnecessary overlapping of activities related to patient recruitment, data gathering, analytical tests.

About Insilico Medicine

Insilico Medicine develops software that leverages generative models, reinforcement learning (RL), and other modern machine learning techniques for the generation of new molecular structures with specific properties. Insilico Medicine also develops software for the generation of synthetic biological data, target identification, and the prediction of clinical trials outcomes. The company integrates two business models; providing AI-powered drug discovery services and software through its Pharma.AI platform and developing its own pipeline of preclinical programs. The preclinical program is the result of pursuing novel drug targets and novel molecules discovered through its platforms. Since its inception in 2014, Insilico Medicine has raised over $52 million and received multiple industry awards. Insilico Medicine has also published over 100 peer-reviewed papers and has applied for over 25 patents.

Tuesday, December 1, 2020

Imagining perfect molecules using AI - a benchmarking system for generative chemistry

 


 

Insilico Medicine together with collaborators announces the publication of Molecular Sets (MOSES), a benchmarking system for generative chemistry models


November 30, 2020 - Insilico Medicine, a leading company in AI-powered drug discovery, today announced that the paper titled "Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models" was published in Frontiers in Pharmacology. In addition to the authors from Insilico Medicine and Neuromation, the author list includes Simon Johansson and Hongming Chen from AstraZeneca, Benjamin Sanchez Lengeling from Harvard University, and Alan Aspuru-Guzik from Vector Institute, Department of Computer Science, University of Toronto, and Canadian Institute for Advanced Research (CIFAR).

"With the rapid development of new generative chemistry, it is crucial to compare machine learning models in a unified way; with MOSES, we can easily compare new models with existing approaches without reimplementing all the baselines. MOSES is a result of tight collaboration between multiple generative chemistry labs; together we polished the platform over the last two years and made it as simple and intuitive as possible. We are glad to help researchers obtain interpretable, reproducible results with our platform.", said Daniil Polikovskiy, senior author of the paper.

In 2018, Insilico Medicine presented Molecular Sets (MOSES) benchmarking platform that was employed by multiple research groups since then. MOSES contains a carefully curated dataset, a set of metrics, and a wide variety of baselines for comparing generative models for chemistry. Over the last two years, we extended the repository with new baselines, enhanced evaluation protocols, and implemented simple routines for using MOSES out of the box. Today, Insilico Medicine announces that the manuscript describing the platform has been accepted for publication in Frontiers in Pharmacology, "Artificial intelligence for Drug Discovery and Development" special issue. The paper will soon be available here: https://www.frontiersin.org/articles/10.3389/fphar.2020.565644. For more information on MOSES, please visit the GitHub repository https://github.com/molecularsets/moses.

To cite the paper: https://www.frontiersin.org/articles/10.3389/fphar.2020.565644

###

Media Contact

For further information, images, or interviews, please contact: ai@insilico.com

About Insilico Medicine

Insilico Medicine develops software that leverages generative models, reinforcement learning (RL), and other modern machine learning techniques for the generation of new molecular structures with specific properties. Insilico Medicine also develops software for the generation of synthetic biological data, target identification, and the prediction of clinical trials outcomes. The company integrates two business models; providing AI-powered drug discovery services and software through its Pharma.AI platform (http://www.insilico.com/platform/) and developing its own pipeline of preclinical programs. The preclinical program is the result of pursuing novel drug targets and novel molecules discovered through its platforms. Since its inception in 2014, Insilico Medicine has raised over $52 million and received multiple industry awards. Insilico Medicine has also published over 100 peer-reviewed papers and has applied for over 25 patents. Website insilico.com