Biointron的动态

Explore the transformative impact of AI on therapeutic antibody development in a recent review! ?? Breakthroughs in Artificial Intelligence (AI) are revolutionizing how we approach antibody design. By creating sophisticated in silico models, researchers can now accurately predict antibody structures from their sequences and generate innovative antibodies tailored for optimal performance. This review delves into significant AI tools, including Antibody Language Models (ALMs) and advanced folding algorithms, highlighting their role in streamlining antibody discovery. It also touches on practical aspects, such as licensing considerations for industrial use. Despite these advancements, challenges like solubility and viscosity still pose hurdles, stemming from limited experimental data. Nonetheless, AI’s potential in drug development offers exciting prospects for quicker and more cost-efficient therapeutic solutions. ?#TsingkeInsights #Antibodies #AI #DrugDevelopment #DrugDiscovery

?? Dive into our process and discover how we obtain the best antibodies in just 21 days! From target characterization to leads optimization, we've got the step-by-step guide to revolutionize therapeutic antibody discovery. ?? ?? mabsilico.com #Antibody #AI #ML #DrugDesign #DrugDiscovery

In antibody drug development, lead optimization is a crucial phase that often determines whether the therapy is likely to succeed in the clinic. Traditionally a time-consuming and costly process, antibody lead optimization efforts can be greatly enhanced with #AI. In a new blog post, written by our specialists: Maciej Jasinski and Joanna Marczyńska-Grzelak, we summarize the latest developments in AI tools for antibody improvement. Using real-world examples, we highlight three main ways AI can enhance lead optimization efforts based on the type of input data: ? Antibody sequence only. ? Sequence and structure. ? Sequence, structural, and target data. Learn how you can take advantage of the power of AI for antibody improvement and maximize the efficiency of your lead optimization efforts. Read the article: https://lnkd.in/g3fCqD8U #drugdiscovery #antibodies #leadoptimization

tFold: Fast and Accurate Prediction of Structures of Antibodies and Antibody-Antigen Complexes Tencent Scientists Wu et al recently introduced, tFold: A novel method for predicting 3D atomic-resolution structures of antibodies (Abs) and antibody-antigen (Ab-Ag) complexes. It uses a pre-trained protein sequence language model, eliminating the need for time-consuming multiple sequence alignment searches. https://lnkd.in/eTR2hB42 #AI

?????????? ?????? ?????????????? ?????????????? ????????-???????? ???? ???????????????? ?????????????????? ???????????????????? ?????? ?????????????????? ?????????????? ?? Both companies have just announced their collaboration to push boundaries of antibody discovery to a new level. ?? MOLCURE will use its zero-shot AI technology to design antibodies towards so far undruggable and difficult to access targets, and YUMAB will in vitro verify the lead candidates. ?? Zero-shot AI enables the exploration of a large and diverse sequence space, which supports the discovery of new antibodies towards more targets. Together we are advancing antibody development utilize zero-shot AI technology to deliver next-generation antibodies to as many patients as possible. ?? Read YUMAB's and MOLCURE's joint press release: https://lnkd.in/ezUxXsrm #AI, #drugdiscovery, #YUMAB, #MOLCURE, #antibodies

Exciting antibody news! Researchers at the University of Washington have developed a generative AI tool capable of designing thousands of novel antibodies. This technology still has a long way to go, but we will be watching this space for potential breakthroughs. Read the article here: https://lnkd.in/e4qW5_Uf ? A high-throughput recombinant production platform is beneficial for screening antibodies or for conducting pilot studies. Absolute Antibody’s FleXpress? system has been optimized to rapidly express a large number of IgGs in a short amount of time, while maintaining high purity and low endotoxin levels. Click the link below for more information. https://lnkd.in/g3yAiUPi

Did you miss us at Antibody Engineering and Therapeutics last week? Take a look at our poster below!?? Fusion Antibodies expertise, in sequence engineering and supply of pre-clinical material, enables ease of access to AI drug discovery using Fusion’s AI/ML-Ab initiative.? ? We can design a target specific library of Full-length ?IgG in a variety of species, frameworks & formats including VHH, against any number of targets. Due to the nature of the AI model, we do not require crystal structure.? ? You will receive an AI selection plot which is constructed by the model in a 5000-dimensional space. All sequence information such as germ lines selected and CDR mutations can be easily reviewed. We can screen these plots using high-throughput small scale expression to ensure we are only moving forward with a mini library of molecules that match the characteristics you wish to see e.g. expression levels, binding affinity & monodispersity.? ? Developability will also be checked at the time the sequences are generated.? ? At Fusion we foresee the AI movement as a vital shift in the drug discovery landscape and we welcome you to partner with us as we move into this new future of De-Novo Design.? If you have any questions please reach out to us at [email protected] ? #AI #Animal_Free #DrugDiscovery #Antibody #Therapeutics

Did you know that AlphaFold and RubrYc Therapeutics are using #AI to predict protein structure and function and find new #antibodies? Find out how these breakthroughs are accelerating AI research in this article. https://ow.ly/3oQU50Qw2rU

AI-driven antibody design with generative diffusion models: current insights and future directions ABSTRACT Therapeutic antibodies are at the forefront of biotherapeutics, valued for their high target specificity and binding affinity. Despite their potential, optimizing antibodies for superior efficacy presents significant challenges in both monetary and time costs. Recent strides in computational and artificial intelligence (AI), especially generative diffusion models, have begun to address these challenges, offering novel approaches for antibody design. This review delves into specific diffusion-based generative methodologies tailored for antibody design tasks, de novo antibody design, and optimization of complementarity-determining region (CDR) loops, along with their evaluation metrics. We aim to provide an exhaustive overview of this burgeoning field, making it an essential resource for leveraging diffusion-based generative models in antibody design endeavors. PAPER: https://lnkd.in/dW_AEgFc