News 🆕 and Trends on TechBio
➡️ Renee Wegrzyn, an ex program manager at DARPA (Defense Advanced Research Projects Agency), ex consultant for Booz Allen Hamilton and ex VP of business development at Ginkgo Bioworks, is now in charge of ARPA-H (Advanced Research Projects Agency for Health). ARPA-H it’s one of the newest government agencies, that was created in March 2022 as part of the PREVENT Pandemics Act with an initial budget of $1 billion in 2022 and a subsequent budget increase to $1.5 billion for 2023.
Her mission at ARPA-H is to accelerate better health outcomes for everyone both by advancing medical research and by improving the health care delivery system, by exploring solutions that scale from the molecular to the societal and by looking for proposals that will touch diverse patient populations, transform communities or attack a broad array of diseases and health conditions, including cancer. ARPA-H is modelled after the DARPA business model, which means they are pursuing some of the high risk, high payoff, really bold research ideas.
On October 19, 2023, ARPA-H announced it will take action to improve the nation’s ability to conduct clinical trials safely, quickly and equitably and to improve clinical trial access for people in communities across the country as the first initiative within the recently launched ARPANET-H Health Innovation Network (to connect people, innovators and institutions). The goal of Advancing Clinical Trial Readiness (ACTR) is to enable 90% of all eligible Americans to take part in a clinical trial within a half hour of their home. To do so, ACTR will leverage the nationwide capabilities and reach of the ARPANET-H Customer Experience Hub by pursuing activities with a diverse array of stakeholders in order to advance, integrate and extend clinical trial capabilities that overcome challenges in evaluating new therapies, technologies and platforms, such as AI, digital health technologies and ML. Moreover,
on October 10, 2023, ARPA-H launched a research program to develop a computational toolkit that helps design vaccines that target many viruses,
on September 29, 2023, they launched a program to develop new technologies that will automatically deliver treatments and monitor for disease from within an individual’s body, and
on September 27, 2023, ARPA-H announced a new project to combat the growing threat of antibiotic-resistant bacteria.
➡️ NewAtlantis is a new promising idea committed for saving our ocean and preserving marine biodiversity. At New Atlantis they think the phylogenetic diversity of the largely un-sequenced marine microbes and planktonic communities could provide a lot of novel potential secondary metabolites that might be of commercial interest. Marine metagenomics, namely the study of the genomes of the marine micro-organisms sampled directly from the ocean environment, it is a new and rapidly expanding area of research and a valuable tool for enzymes and bioactive compounds discovery using new high-throughput DNA sequencing technology and recent bioinformatics tools.
In fact, some of the greatest biological diversity in the world is found in the seas, with only 200,000 species of invertebrates and algae identified so far, and this number being only a small fraction of what is yet to be discovered. This immense biodiversity yields great chemical diversity and in just over 40 years of research over 15,000 chemical compounds have been identified as having biological function for fighting even cancer. But the use of marine chemical resources does not stop with pharmaceuticals, since they can be used in nutritional supplements, cosmetics and more (Ocean bioprospecting).
➡️ On September 29, 2023, researchers at Cambridge University in collaboration with the generative AI-driven drug discovery company Insilico Medicine published the paper Multiomic prediction of therapeutic targets for human diseases associated with protein phase separation describing a new AI-driven method to identify new targets for human disease, including neurodegenerative conditions such as Alzheimer’s disease, based on the protein phase separation (PPS) process (phase separation is a process in which a well-mixed solution of proteins and other macromolecules spontaneously separates into two phases, one phase that is enriched for the macromolecules and a surrounding phase that is depleted of the macromolecules). Their approach is based on the intersection of two components: 1) an analysis of a variety of parameters commonly used to identify therapeutic targets through the multiomic PandaOmics platform of Insilico Medicine (which incorporates multiomic data for ranking genes based on their disease association) and 2) an assessment of the propensity of proteins to undergo PPS through the FuzDrop method (that predicts the probability of proteins to undergo liquid-liquid phase separation and performs a sequence-based identification of both droplet-promoting regions and of aggregation-promoting regions within droplets).
➡️ HeartBeatBio is a drug discovery company dedicated to develop a high-throughput human cardiac organoids (Cardioids) screening platform for cardiac drug discovery, that enables modelling of diseases such as drug-induced and genetic cardiomyopathies as well as myocardial infarction and fibrosis.
Their automated, highly scalable Cardioid generation, acquisition and quality control system is coupled with AI capabilities enabling drug screening with a complex 3D biology at unprecedented throughput and reproducibility, and at a cost comparable with conventional cell-based in vitro models. In particular, their predictive high throughput screening platform for cardiotoxicity testing and cardiac drug discovery combines the innovative hardware solutions of their technology partner Molecular Devices (with a 3D cell culture and image analysis lab), for a complex 3D heart tissue models, relevant functional assays and high-content read-outs as well as AI-based big data analysis software. Other partners include Boehringer Ingelheim, A:HeadBio (a CNS therapeutics company) and IMBA Institute of Molecular Biology at the Austrian Academy of Sciences. You can join them in this virtual panel discussion to identify ways to overcome common challenges during 3D biology research: "How 3D biology is shaping the future of drug discovery.
➡️ Insmed, with research teams based in four laboratories across the US and UK that drives innovation from discovering potential new therapies for hard-to-treat diseases to optimising formulation and delivery design, has just entered in a partnership with Google Cloud to leverage generative AI to transform the discovery, development and marketing of drugs in the life sciences sector. Insmed’s team has an extensive experience in biochemistry/biophysics, biology, drug target identification, protein engineering, computational biology, immunology, microbiology, chemistry, aerosol science, bioanalytics, gene therapy, gene editing, AI, toxicology, and formulation design, and has built a generative AI search capability using Vertex AI Search (formerly Gen App Builder) trained on its internal documentation, as well as separate functionality that enables indexed access to available, external medical publications. With the New Vertex AI Search and Conversation you can:
Help customers and employees quickly get relevant information,
Combine enterprise data with Google search and conversational AI,
Build generative AI experiences with text, voice, images and video, and
Enjoy enterprise grade scalability, data privacy, security and controls.
"Insmed is using Google Cloud infrastructure and AI technology to power this transformation leveraging already available AI modules".
said Mark Pellegrino, chief information officer of Insmed
➡️ Anagenex is a seed stage biotechnology company building a platform for mapping chemical space experimentally and discovering new molecules with ML. They test billions of custom-synthesised compounds to see which ones are likely to modulate a protein “target” and for any target they run dozens of experiments at a billion compound scale, generating rich, high quality datasets. Then those datasets train proprietary neural networks to understand what compounds might help patients and their generative AI shows millions of ideas for new compounds. Finally, their custom chemistry and selection systems allow them to do real experiments on hundreds of millions of compounds, iteratively refining their AI’s predictions. In all this, they combine ML with massively parallel biochemical tools such as DNA Encoded Libraries (DELs) and Affinity Selected Mass Spectrometry (ASMS) to analyse more compounds more efficiently than ever before.
➡️ Front Line Genomics, a genomics focused digital magazine and a website portal, is presenting this week Genomics in Drug Discovery, a series of subsequent webinars where you will be presented with examples of how you can best leverage genomics, big data and AI to propel your drug discovery efforts forward:
Webinar 1: Genomics-Driven Drug Discovery
Thursday 2nd of November at 3 pm GMT / 4 pm CET / 11 am EST
Talk 1: From Target Discovery to Clinical Drug Development with Human Genetics by Katerina Trajanoska, Postdoctoral Research Fellow, McGill University
Talk 2: Leveraging Public Genomic Data to Identify Therapeutic Targets
by Stefanie Morgan, Head of Science, Watershed Bio (Watershed Informatics is an end-to-end bio-IT managed service provider with a cloud data lab for life sciences organisations of any size to perform mission-critical bioinformatics analyses such as bulk, single-cell and spatial transcriptomics, ATAC-Seq, proteomics, etc)
Talk 3: Discovery Forum: National genomic data driving pharmaceutical and biotech R&D by James Duboff, Strategic Partnerships Director, Genomics England
Webinar 2: Infusing Multi-dimensional Data into Drug Discovery
Thursday 9th of November at 3 pm GMT / 4 pm CET / 10 am EST
Talk 1: Integrating Omics into Drug Discovery: from Target ID to Phase 3 and Beyond by Tom Lanz, Senior Director of Multi-Omics and Biomarkers, Pfizer
Talk 2: Advancing Drug Discovery Through Genetics and Genomics
by Nikolina Nakic, Senior Director, Head of V2G2F Computational Biology, GSK
Talk 3: Multi-Omics Approaches to Inform Disease Mechanism and Drug Target Identification by Andrew Jarnuczak, Associate Principal Scientist, AstraZeneca
Webinar 3: Harnessing the Power of Big Data in Drug Discovery with AI
Thursday 16th of November at 3 pm GMT / 4 pm CET / 10 am EST
Talk 1: What To Do and What Not To Do? That is the Question
by Gurpreet Singh, Senior Director and Head of Applied Machine Learning, Bayer
Talk 2: Building AI Models: Lessons Learned by Richard Lewis, Director, Data Science, Computer-Aided Drug Design, Novartis
Talk 3: Proteomics and Single-Cell: Applications to the Drug Discovery Process by Yann Abraham, Associate Scientific Director, Janssen
“The greater part of progress is the desire to progress.” - Seneca the Younger
➡️ Aspect Analytics, is a cloud platform to manage and analyse spatial omics data, and integrate across different platforms. Their platform Nexus is a scalable cloud-based high performance computing platform that can cover the entire digital lifecycle of molecular imaging and Liquid chromatography-mass spectrometry (LC–MS) data, along with all associated metadata. Owing to its scalability, it can efficiently manage petabytes of experimental data and perform complex analyses across large panels of datasets. The Nexus platform is designed to overcome all limitations of isolated desktop applications during traditional data analysis tools for MS and MSI. You can find a list of their highlighted scientific publications here, and a logos next to each entry highlighting a key external collaborator, like for example:
A bilateral development project between Aspect Analytics and Boehringer Ingelheim
A MALDI-imaging based proteomics assay in collaboration with Frontier Diagnostics
➡️ Soley Therapeutics is an AI-accelerated, high-throughput drug development biotech company. The Soley Evaluation Platform decodes the Cellular Language for efficient drug discovery by using AI/ML to augment human intelligence and understand Cellular Language at every stage of the drug discovery and development process (pipeline).
➡️ PostEra is using ML to close the Design-Make-Test cycle of Medicinal Chemistry and bring more cures to patients. ProtonP+, an end-to-end ML platform to close the Design-Make-Test cycle of Medicinal Chemistry, is addressing the key challenges at each stage of the process:
Design: combining proprietary data and low-data ML to design optimised molecules that satisfy the many competing properties that drug candidates must satisfy.
Make: state-of-the-art synthesis and search ensuring that every molecule they design has a reliable synthetic route and that molecules can be made in parallel using shared synthetic intermediates.
Test: novel active learning methodologies to gather the most informative data at each cycle.
So far, they have different collaborations with Pfizer (Oncology, Undisclosed), NIH (Pandemic Preparedness) and the Moonshot project (in March 2020 PostEra helped launch COVID Moonshot, which became the world’s largest open-science initiative to develop a COVID antiviral cure).
➡️ Swift Medical in Canada, a global leader in digital wound care focused on improving clinical and economic outcomes in chronic and acute wound care, was just recognised as McKnight’s Tech Partner of the Year. McKnight’s is a national media brand providing news, perspective and analysis for owners, operators and other leaders of seniors housing, independent living, assisted living, memory care and continuing care retirement and life plan communities
Swift is suitable for all skill levels. It’s as simple as taking a picture of a wound with a smartphone. Then Swift Skin and Wound uses AI to accurately measure the wound circumference, type and progress. Finally, Swift’s AI analyses the wound and provides you and your wound specialists with a comprehensive view of your wound care population.
➡️ Healthy.io, a company that uses computer vision and ML to transform smartphone cameras into clinical grade medical devices, is building systems for taking a short video of a wound—rather than a still image—and then computer algorithms can actually make a 3D measurement, allowing them to automatically measure length, width, surface area and even depth. And this allows to follow patients' wound healing response remotely (Digitise wound management). Moreover, they have the Minuteful Kidney that enables people to conduct the test at home with a smartphone, enabling early detection. The Minuteful Kidney (test app and kit) allow people to test themselves at home for signs of CKD (Chronic Kidney Disease) and receive immediate clinical results. And by using colorimetric analysis, computer vision and AI Healthy.io transforms the smartphone camera into a clinical-grade medical device. Last May, the company raised $50M to expand the smartphone kidney test in US.
➡️ Finally, DeepMind just shared an update on progress towards the next generation of AlphaFold that can now generate predictions for nearly all molecules in the Protein Data Bank, frequently reaching atomic accuracy (A glimpse of the next generation of AlphaFold). Specifically, it unlocks new understanding and significantly improves accuracy in multiple key biomolecule classes, including ligands (small molecules), proteins, nucleic acids (DNA and RNA), and those containing post-translational modifications! Not bad!
Until next time 🪻,
Thank you so much for the shout out for NewAtlantis. I am one of your subscribers and a cofounder of NewAtlantis. I love your newsletter. Truly one of the very best and most informative. Plus it’s fun to read