Boris Fain | Predictive Molecular Simulation

Apply to join Foresight Molecular Machines program: foresight.org/molecular-machi...
A group of scientists, entrepreneurs, and institutional allies who cooperate to advance molecular machines, applications in energy, medicine, and material science, and long-term progress toward Richard Feynman’s vision of nanotechnology.
Boris Fain | Predictive Molecular Simulation
'Boris Fain started his scientific career by writing the equations that governed the shapes of DNA. He then worked with Michael Levitt to bring the methods of Physics and Mathematics into computational biology, where and his colleagues, using knot theory, designed the very first fingerprint of protein structure. Following that he led an international team of brilliant misfits to transform biology and chemistry into Physics: getting the correct answers for the right reasons. Boris is a CEO of Freecurve Labs , a company dedicated to commercializing the molecular modeling breakthroughs.
A team of brilliant scientists, including 2 Nobel Laureates, spent a decade creating a way to replace experiments with simulation in biology, energy storage, and many other fields. The team combined Physics from 1600 - 1970s with recently exploding methods of AI to make a breakthrough in molecular simulation. The in-silico microscope they created will revolutionize the way many industries and researchers work
www.freecurve.com/
══════════════════════════════════════
About The Foresight Institute
The Foresight Institute is a research organization and non-profit that supports the beneficial development of high-impact technologies. Since our founding in 1986 on a vision of guiding powerful technologies, we have continued to evolve into a many-armed organization that focuses on several fields of science and technology that are too ambitious for legacy institutions to support. From molecular nanotechnology, to brain-computer interfaces, space exploration, cryptocommerce, and AI, Foresight gathers leading minds to advance research and accelerate progress toward flourishing futures.
We are entirely funded by your donations. If you enjoy what we do please consider donating through our donation page: foresight.org/donate/
Visit foresight.org, subscribe to our channel for more videos or join us here:
• Twitter: / foresightinst
• Facebook: / foresightinst
• LinkedIn: / foresight-institute

[@sebek12345]

🎯 Key points for quick navigation:
00:00 *🧬 Introduction and welcome to Boris Fain, discussing his work in molecular simulations.*
00:14 *🌟 Highlighting Boris's progress and new organizational structure in molecular simulations.*
00:43 *💡 Importance of simulations in predicting and building real-world applications using physics laws.*
01:25 *🧪 Challenges in modeling molecular behaviors due to the complexity of quantum mechanics.*
02:03 *☕ State-of-the-art tools struggle with simple predictions like dissolving sugar in coffee.*
02:43 *📉 Ligand-protein drug design simulations often yield random results.*
03:11 *🧬 AI tools like AlphaFold extract structural information but lack predictive abilities for energies.*
03:38 *🧩 Biological complexity makes accurate predictions difficult in drug design.*
04:18 *⚖️ Achieving necessary precision is a major hurdle in molecular simulations.*
05:08 *💻 Quantum computing's potential in molecular simulations, despite current limitations.*
05:36 *📈 Market value of simulation companies and their economic impact.*
06:16 *🧮 Achievements in predictive molecular simulation, claiming significant advancement.*
07:00 *🔍 Discussion on the limitations of AlphaFold and RosettaFold in energy predictions.*
08:11 *🔄 Revisiting predictions on the future of molecular modeling, suggesting progress is ahead of schedule.*
09:30 *🧠 Introduction of the Monte Carlo method in molecular simulations.*
10:09 *🔬 Challenges and techniques in molecular simulation, including AI and neural networks.*
11:49 *🧪 Importance of high precision and the role of physics in enhancing simulation accuracy.*
12:29 *🧠 Combination of physics and neural networks to achieve near-zero error in quantum mechanical energy predictions.*
13:55 *🌌 Achievements in accurately simulating protein-ligand interactions and ionic systems.*
15:05 *🧬 Overview of the company’s background and commercialization efforts.*
16:27 *🚀 Future plans for incremental development and enabling molecular interactions for chemical groups.*
24:39 *💼 Boris discusses the company's core team, advisors, and investors, highlighting their expertise.*
25:19 *🌱 Announcement of a planned seed round for September 2024 and an invitation for potential investors.*
25:33 *💡 Addressing the time and cost efficiency of verifying AI outputs, stating that the AI component is manageable.*
26:15 *🔄 Discussion on the efficiency and speed of polarizable force fields in simulations.*
27:12 *⏱️ Highlighting the importance of sampling techniques in condensed phase systems for accurate simulations.*
27:40 *⚡ Explaining the potential to simulate dynamic processes like ATP hydrolysis with current techniques.*
28:48 *🔬 Describing the computation of intermediate states in enzyme reactions, emphasizing the need for high accuracy.*
30:23 *🧠 Clarification on the computational cost and time required for simulating complex molecular interactions.*
31:05 *📊 Explanation of functional group interactions to reduce computational complexity.*
32:14 *🏗️ Projecting the company's progress in three to five years, aiming to refine protein structures and simulate various systems.*
33:40 *🛠️ Seeking collaboration on specific technical challenges like quantum mechanical computational descriptions.*
34:58 *💰 Clarifying funding goals and the plan for a $10 million seed round to enable predictive molecular computing products.*
36:20 *🔍 Reiterating the significant interest from smaller companies in their simulation technology.*
37:13 *🤝 Introducing team members and acknowledging the collaborative effort behind their progress.*
37:55 *🌍 Expressing excitement about their progress and the future potential of their work, with plans to publish on UA-cam.*
Made with HARPA AI

[@comradecapybara]

so if understood this right instead of training the ai on limited experimental data they are instead using ai to extrapolate quantum mechanics to larger systems?