RapidBio Inc.

On International Women's Day????, we reflect with gratitude on the exceptional women colleagues we have known throughout our healthcare, science, and technology career. While we are delighted to see increasing ↗?female representation in these sectors????, significant challenges remain.?? ↗? The data is clear : UNESCO reports women comprise just 35% of STEM graduates, and the National Science Foundation found only 38% of women ????with computer science degrees work in their field, compared to 53% of men. These disparities demand our attention, particularly as AI transforms healthcare. At RapidBio Inc., we're dedicated to advancing women across science, technology, sales, communications, and marketing. We are committed to supporting women and girls, paying forward the mentorship that shaped our own journey. By creating environments where women can fully thrive, and by supporting each other, we drive meaningful change. Here's to the women worldwide who continue breaking barriers, driving innovation, and improving our world! #InternationalWomensDay #AccelerateAction #WomenInSTEM #Pride #Proud

Challenge of Valuing Preclinical Assets: It's extremely difficult to determine the future value of very early-stage compounds. Neither Schering-Plough nor initially Merck seemed to recognize the extraordinary potential of pembrolizumab. It is a fascinating example of how valuable pharmaceutical assets can change hands during early development stages, sometimes with their potential not fully recognized. The Journey of Keytruda Discovery Phase at Organon: Pembrolizumab (later branded as Keytruda) was initially discovered by scientists at Organon. The drug was targeting the PD-1, which was a relatively new and unproven approach to cancer treatment at the time. . First Acquisition - Schering-Plough (2007) When Schering-Plough acquired Organon for $14.4 billion in 2007, pembrolizumab was still in preclinical development. At this stage: The true value of the compound wasn't yet established The PD-1 pathway as a cancer treatment approach was still considered somewhat experimental The compound was likely just one small part of a broader portfolio that Schering-Plough was interested in. Second Acquisition - Just two years later, Merck & Co. acquired Schering-Plough for $41.1 billion. At this point, pembrolizumab still hadn't entered clinical trials. Interestingly, according to the information provided, Merck initially showed little interest in the program. The pembrolizumab asset was probably not a significant factor in Merck's acquisition decision Turning Point (2011) Something changed in Merck's assessment of the asset when they finally advanced pembrolizumab into Phase I clinical trials. This suggests a reevaluation of the compound's potential, possibly due to: New scientific understanding of the PD-1 Competitive development (Bristol-Myers Squibb was developing nivolumab, another PD-1) Portfolio reprioritization Promising preclinical data that began to demonstrate special potential Approval and Commercial Success Keytruda received its first FDA approval in 2014 for melanoma, becoming a blockbuster drug (generating over $1 billion in annual sales) by 2016. Today, it's one of the most successful cancer drugs ever developed, with expanded approvals across numerous cancer types. Why This Case Is Notable: Hidden Gems in Acquisitions: Companies often acquire other firms for strategic assets, but may end up with unexpected treasures in the broader portfolio. Keytruda wasn't the main reason for either acquisition, yet became one of the most valuable outcomes. Timing and Scientific Understanding: The value perception changed as scientific understanding of immune checkpoint inhibitors evolved. This highlights how external scientific progress can dramatically change the perceived value of an asset. Strategic Patience: Importance of periodically reassessing developmental compounds. Transformative Impact: Transformed Merck's business trajectory and helped establish the company as a leader in oncology, an area where it wasn't traditionally dominant.

Drug repurposing for acute myeloid leukaemia: Google AI co-scientist proposed novel repurposing candidates for acute myeloid leukemia (AML). Subsequent experiments validated these proposals, confirming that the suggested drugs inhibit tumor viability at clinically relevant concentrations in multiple AML cell lines. Exciting times ahead! ??????

Revolutionizing Protein Research: Microsoft's BioEmu-1 AI Breakthrough BioEmu is a large-scale deep learning model for efficient prediction of biomolecular equilibrium structure ensembles. The model is being released together with its companion BioEmu Benchmark by Microsoft (License: MIT License) Biomolecular Emulator (BioEmu) is a deep learning model that, given a protein sequence, can sample thousands of statistically independent structures from the protein structure ensemble per hour on a single graphics processing unit. By leveraging novel training methods and vast data of protein structures, over 200 milliseconds of MD simulation, and experimental protein stabilities, BioEmu’s protein ensembles represent equilibrium in a range of challenging and practically relevant metrics. ?? 1?? Qualitatively, BioEmu samples many functionally relevant conformational changes, ranging from formation of cryptic pockets, over unfolding of specific protein regions, to large-scale domain rearrangements. 2?? Quantitatively, BioEmu samples protein conformations with relative free energy errors around 1 kcal/mol, as validated against millisecond-timescale MD simulation and experimentally-measured protein stabilities. ?? By simultaneously emulating structural ensembles and thermodynamic properties, BioEmu reveals mechanistic insights, such as the causes for fold destabilization of mutants, and can efficiently provide experimentally-testable hypotheses. Microsoft made BioEmu-1 open-source following their preprint to empower protein scientists in studying structural ensembles with their model. It provides orders of magnitude greater computational efficiency compared to classical MD simulations, thereby opening the door to insights that have, until now, been out of reach. BioEmu-1 is featured in Azure AI Foundry Labs a hub for developers, startups, and enterprises to explore groundbreaking innovations from research at Microsoft. Funded by: Microsoft AI Research AI for Science Kudos to Sarah Lewis and team. ??For more similar updates follow RapidBio Inc. page. #proteinprediction #artificialintelligence #machinelearning #LLM #drugdiscovery #languagemodels

Today, NVIDIA Healthcare launched Evo 2 -- a powerful foundation model for DNA across all domains of life, developed in collaboration with Arc Institute and Stanford University School of Medicine. NVIDIA announced today the largest publicly available AI model for genomic data, Evo 2 was built using NVIDIA DGX Cloud on Amazon Web Services (AWS) (AWS). It is now accessible to all scientific developers on the BioNemo platform and as an inference microservice. Evo 2 is available to global developers on the NVIDIA BioNeMo platform, including as an NVIDIA NIM microservice for easy, secure AI deployment. Evo 2 represents a major milestone for generative genomics. The NVIDIA NIM microservice for Evo 2 enables users to generate a variety of biological sequences, with settings to adjust model parameters. Developers interested in fine-tuning Evo 2 on their proprietary datasets can download the model through the open-source NVIDIA BioNeMo Framework, a collection of accelerated computing tools for biomolecular research. https://lnkd.in/dRWgy7Ar ??Follow RapidBio Inc. for similar updates. #Nvidia #alphafold #datasets #computingtools #computing #genomics #ai #artificialintelligence #LLMs #LLM

Use of Artificial Intelligence to Support Clinical Trial Activity Yields Time Savings of 18% as per the Tufts Center for the Study of Drug Development. ??Follow RapidBio Inc. page to dive deeper into any specific aspect, such as how operational AI/ML pilots could be used to identify optimal trial sites, boost enrollment by 10 to 20 percent, and predict real-time enrollment performance, which allows for earlier, more proactive interventions. https://lnkd.in/druCyt-g.

Rare diseases are more than you can imagine! But also more than you can imagine is the power of connection and resilience, uniting all who live and work with rare disease…..RapidBio Inc. is leveraging AI to make sure no one is left behind because of the rarity of their condition. #rarediseaseday

What is Molecular Biology? The secret to understanding molecular biology isn't just about the details. It's about the big picture. This field shapes modern medicine in powerful ways. Molecular biology is at the heart of personalized healthcare and drug development. It all starts with the building blocks of life: proteins and nucleic acids. Understanding these structures is crucial. Advancements in imaging technologies, like cryo-electron microscopy and X-ray crystallography, have changed the game. Now, we can visualize complex molecules in ways we never thought possible. This deeper understanding leads to better treatments. Bioinformatics plays a key role too. It helps researchers analyze huge datasets from genomic and proteomic studies. This analysis can reveal new therapeutic targets and biomarkers for diseases. The blend of molecular biology and artificial intelligence is exciting. Machine learning algorithms are used to predict molecular interactions. They help optimize drug design, making the process faster and more efficient. Ethical concerns also come into play. Genetic manipulation and synthetic biology raise important questions. CRISPR technology shows promise in gene editing. But with power comes responsibility. We must consider the benefits and risks of these advancements. Understanding these issues is vital for society. Molecular biology is not just complex; it is beautiful. It offers solutions to some of the biggest healthcare challenges today. By connecting science with real-world impact, we can inspire further research and discussions. This is how we can move forward together. ??Follow RapidBio Inc. page to dive deeper into any specific aspect, such as computational modeling, therapeutic design, or case studies. #Quantumcomputing #OpenAI #NVIDIA #AlphaFold

Yes! Exciting times ahead.

Quantum Learning Machine (QLM) for Drug Discovery provides a powerful simulation environment that bridges current classical computing with the emerging capabilities of quantum computing. In drug discovery it helps build expertise and develop algorithms that will eventually run on fault-tolerant quantum computers, promising even greater breakthroughs in the field. It offers: ?? Enhanced molecular simulation for accurate modeling of drug-target interactions. ?? Optimized synthesis pathways to streamline chemical production. ?? Integration with quantum machine learning for novel molecule generation and data analysis. ?? Here’s how QLM is being applied in drug discovery: 1?? Simulation of Molecular Interactions Accurate Quantum Chemistry: What It Does: QLM simulates the quantum mechanical behavior of molecules, enabling highly accurate modeling of electronic structures and molecular interactions. Impact on Drug Discovery: This precision is crucial for predicting how drug candidates bind to target proteins and for calculating binding energies, which can streamline the identification of promising compounds. E.g.: Researchers use QLM to simulate the behavior of potential drug molecules, evaluating their interaction with specific targets (e.g., enzyme active sites). 2?? Optimization of Chemical Synthesis Enhanced Reaction Pathways: What It Does: QLM can run quantum algorithms designed to optimize chemical reactions, determining the most efficient synthesis pathways. Impact on Drug Discovery: By finding optimal reaction conditions and synthesis routes, researchers can reduce the number of experimental iterations. E.g.: Simulations conducted on QLM have been used to explore various synthesis routes for complex organic molecules, identifying pathways that minimize energy consumption and waste. 3?? Integration with Quantum Machine Learning (QML) Generative Design and Data Analysis: What It Does: QLM serves as a platform to develop and test quantum machine learning models. These models can sift through vast chemical spaces and biological data to identify novel molecular structures with desired therapeutic properties. Impact on Drug Discovery: Combining quantum-enhanced machine learning with QLM accelerates the discovery of candidate molecules by predicting efficacy and potential side effects based on simulated data. 4?? Accelerated Algorithm Development and Benchmarking Prototyping Quantum Algorithms: What It Does: QLM provides a testbed for developing quantum algorithms tailored for complex optimization and simulation tasks common in drug discovery. Impact on Drug Discovery: Researchers can rapidly iterate on quantum algorithms designed to solve intricate problems such as energy minimization in molecular structures or optimization of multi-step synthesis processes. ??Follow RapidBio Inc. page to dive deeper into any specific aspect, such as computational modeling, therapeutic design, or case studies. #Quantumcomputing #OpenAI #NVIDIA #AlphaFold