Dell Medical School at The University of Texas at Austin’s Post

With the increase in the size of chemical libraries, new challenges arise in using structure-based virtual screening to select hit candidates for a protein of interest. Matthieu Schapira's team reviews machine learning-accelerated and synthon-based library screening approaches summarizing the results from seminal proof-of-concept studies, the latest developments, limitations and future directions. Read the review: https://lnkd.in/gCs9XAnc #MachineLearning #DrugDiscovery #ChemicalLibrary #VirtualScreening #HitFinding

Inside every plant, animal and human cell are billions of molecular machines. They’re made up of proteins, DNA and other molecules, but no single piece works on its own. Only by seeing how they interact together, across millions of types of combinations, can we start to truly understand life’s processes. In a paper published in Nature, AlphaFold 3 is introduced by Google, a revolutionary model that can predict the structure and interactions of all life’s molecules with unprecedented accuracy. https://lnkd.in/dZw94hHJ

Part bioscience, part engineering wizardry... #Resipher is driven by sophisticanted signal processing algorithms, which convert concentration readings into real-time cellular #OxygenConsumption data. Learn more about the magic on the inside: https://bit.ly/44vPHJS

COMING SOON -- turn your complex neural data into clear results with Axion Bio's powerful new neural analysis software   See what's possible with our upcoming software: ✅ Automatically import all experimental recordings to accelerate your workflow ✅ Simultaneously analyze & compare multiple files for in-depth evaluation ✅ Easily visualize complex data at a glance with new plot options  Sign up to get the latest updates on the neural analysis software via 🔗 https://bit.ly/3ZLmEBG #AxionBio #BioTech

I have excited to share that Successfully completed the Course Signal Processing Onramp.. Signal processing involves converting or transforming data in a way that allows us to see things in it that are not possible via direct observation. Signal processing allows engineers and scientists to analyze, optimize, and correct signals, including scientific data, audio streams, images, and video. Nothing is Impossible the word itself says I'm Possible !!! #bio medical #kpriet #matlab #math works

[2024, Nature Comm] Bidirectional generation of structure and properties through a single molecular foundation model Site: https://lnkd.in/g4jSRV-M Abstract: Recent successes of foundation models in artificial intelligence have prompted the emergence of large-scale chemical pre-trained models. Despite the growing interest in large molecular pre-trained models that provide informative representations for downstream tasks, attempts for multimodal pre-training approaches on the molecule domain were limited. To address this, here we present a multimodal molecular pre-trained model that incorporates the modalities of structure and biochemical properties, drawing inspiration from recent advances in multimodal learning techniques. Our proposed model pipeline of data handling and training objectives aligns the structure/property features in a common embedding space, which enables the model to regard bidirectional information between the molecules’ structure and properties. These contributions emerge synergistic knowledge, allowing us to tackle both multimodal and unimodal downstream tasks through a single model. Through extensive experiments, we demonstrate that our model has the capabilities to solve various meaningful chemical challenges, including conditional molecule generation, property prediction, molecule classification, and reaction prediction.

Visual Question and Answer models AIMER Society - Artificial Intelligence Medical and Engineering Researchers Society #AIMER #VisualQuestionandAnswermodels

Alerting the IP community to Alexander Reben's All Prior Art Project: "All Prior Art is a project attempting to algorithmically create and publicly publish all possible new prior art, thereby making the published concepts not patent-able. The concept is to democratize ideas, provide an impetus for change in the patent system, and to preempt patent trolls. The system works by pulling text from the entire database of US issued and published (un-approved) patents and creating prior art from the patent language. While most inventions generated will be nonsensical, the cost to computationally create and publish millions of ideas is nearly zero – which allows for a higher probability of possible valid prior art.   Further, a large institution could dedicate many servers to this task, along with developing more advanced techniques such as deep learning, to flood the prior art space. It is not unforeseeable with current technology (along with sufficient cash for fees) to flood the actual patent application process itself with sufficiently advanced patent applications based on this concept." Here is an example of AI generate prior art: 1461187615-ce36a947-f6e1-440b-8e57-b76bf06f5fed Devices and methods for therapeutic photodynamic modulation of neural function in a human. Product gas in the vapor phase is drawn from the head space above the liquid level and condensed to form the product fuel. The adapter segment is positioned at the first end and is configured to be coupled to another component. https://lnkd.in/gm36HYUw From the FAQs: "Doesn’t the USA’s transition to first-to-file make this not work? -Even with the change to the first-to-file system in the USA, the patent applicant still needs to prove they are the original inventor, which would not be true for any inventions published here. -The intent is not to prevent actual creative and innovative patents from being filed, it is to take the obvious and easily automated ideas out-of-play. If an idea is truly creative and innovative, a computer should have difficulty coming up with it." I'd ask, don't patent examiners already have a hard enough time finding and correctly applying the closest prior art? #USPTO, #IP, #AI, #IT, #patent, #invention, #innovation

From patient-centered precision healthcare to computationally intense molecular research, AI is reshaping medicine—but it’s also led to new intellectual property challenges. After the U.S. Patent and Trade Office announced it would only protect AI-assisted inventions with significant human contribution, Fenwick partners Robert Hulse, Stuart Meyer, and associate Michael Saffron broke down what that means for experimentation and chemical research. It’s all part of our laser focus on the forefront of life sciences. Uncover more insights here: https://bit.ly/48OTXoe #FenwickForLifeSciences #ArtificialIntelligence #Patents

💡 Dive into the Future with MolDrug AI Systems! 💊🔬 Ever wondered how we accelerate drug discovery? 🚀 We're the trailblazers in computational chemistry and molecular modeling, pioneering technologies to optimize chemical compound properties. 💻✨ #MolDrugAI #FutureForward #DrugDiscovery #ComputationalChemistry #Innovation #Science #TechRevolution 🌟