TechBio News: 2nd part 👾
TechBio News: 2nd part 👾
Revolutionizing Drug Development
Bio Japan 2024 in Yokohama and Medical Japan 2024 in Tokyo
Japan will host two of the most anticipated events in the biotechnology and healthcare industries: Bio Japan 2024 in Yokohama and Medical Japan 2024 in Tokyo, both running concurrently from October 9th to 11th (Bio Japan 2024 and Medical Japan 2024 Unleashing Innovation in Biopharmaceuticals and Healthcare Technologies).
🔶 At Bio Japan 2024, held at the Pacifico Yokohama Convention Center, attendees can expect a strong focus on next-generation biopharmaceuticals, regenerative medicine (stem cell research and gene therapies), sustainability in biotech and AI in drug discovery. The conference will bring together over 20,000 attendees from 35 countries, including leading biotech companies, research institutions and government representatives. For example, Takeda Pharmaceutical Industries Ltd is making significant progress in gene therapy development, including TAK-755 for treating rare blood disorders like congenital thrombotic thrombocytopenic purpura, currently in advanced clinical trials. As for Chugai Pharmaceutical Co Ltd, continues to make significant progress in oncology, particularly with its immunotherapy Tecentriq (targets multiple cancers such as lung and bladder cancer) and is also advancing its next-generation antibody therapies, focusing on personalized medicine to enhance treatment efficacy and improve patient outcomes in cancer care.
🔶 Meanwhile, Medical Japan 2024, taking place at Makuhari Messe Exhibition Center, will focus on the rapidly evolving landscape of medical devices, healthcare IT and hospital services. This event will feature over 1,000 exhibitors showcasing the latest technologies in medical diagnostics, telemedicine, smart hospitals and elderly care solutions. For example, Astellas Pharma Inc recently announced the FDA listing of DIGITIVA, a non-invasive digital health solution for managing heart failure. This innovative platform empowers patients to take an active role in their care through at-home monitoring and data triage by a dedicated clinical review team, aiming to improve clinical outcomes and reduce hospitalizations. Astellas is expected to share more about its pipeline developments at the upcoming events.
ArtiDock 2.5, is a significantly upgraded version of the molecular docking model developed by Receptor.AI and released on October 07, 2024. This version provides enhanced capabilities for predicting the binding poses of small molecule ligands in different pocket representations, accounting for non-standard residues, ions and co-factors, surpassing classic docking techniques. Now seamlessly integrated into their Drug Design Ecosystem, ArtiDock 2.5 is ready to multiply R&D throughput.
The main advancement of ArtiDock 2.5 is the employment of augmented pocket representations during training. In a real-world scenario, researchers don’t know the true ligand pose in the protein pocket; otherwise, there would be no need to perform docking. Therefore, a significant variability of potential pocket representations may be selected before the docking.
Their solution to this issue is the introduction of random binding pocket extraction in the training process. This method simulates possible variations of the binding sites that researchers might use as input. This approach allowed them to increase the percentage of correct predictions up to 2-fold in the pockets of different sizes.
Another upgrade in ArtiDock 2.5 is accounting for modified or non-standard residues, ions, and cofactors. They modified the training set to include all possible non-protein entities except water, which led to improved model performance in a variety of cases. Researchers may now include any molecular structures in the binding pocket, and ArtiDock will handle them.
Learn more about ArtiDock: link
Learn more about ArtiDock’s integration into Nvidia BioNeMo here: link
Ainnocence
On October 07, 2024, Ainnocence, a next-generation biotech company, announced the launch of its cutting-edge AAV (Adeno-Associated Virus) design services, powered by the SentinusAI platform (Ainnocence Unveils Advanced AAV Design Services to Revolutionize Gene Therapy).
Ainnocence (2021, US) is a next-generation biotech company with a fast, self-evolving AI drug design platform consisting of:
✳️ SentinusAI is a de novo antibody and fusion protein engineering engine that performs antibody design and optimization based solely on sequences, delivering computational results in just a week and an optimized drug candidate within a month.
✳️ The CarbonAI is a de novo small-molecule and PROTAC design engine that holds the power to screen billions of compounds in mere days, optimizing multiple pharmacological properties simultaneously for lead generation and lead optimization.
✳️ And CellulaAI represents a cutting-edge AI system that leverages the power of AI to transform CAR-T therapy. By optimizing every aspect of the CAR-T design and production process, this engine aims to bring safer, more effective and personalized cancer treatments to patients worldwide (AINNOCENCE LAUNCHES CellulaAI™: A Pioneering AI Engine to Revolutionize CAR-T Therapy).
Cleveland Clinic
On October 6, 2024, Researchers at Cleveland Clinic's Genome Center used AI to find Non-Opioid Pain relief options. In particular, Feixiong Cheng, Ph.D., Director of Cleveland Clinic's Genome Center, and IBM are using AI for drug discovery in advanced pain management, and have identified so far multiple gut microbiome-derived metabolites and FDA-approved drugs that can be repurposed to select non-addictive, non-opioid options to treat chronic pain.
In their paper just published A deep learning framework combining molecular image and protein structural representations identifies candidate drugs for pain they present an interpretable DL-based ligand image- and receptor’s three-dimensional (3D)-structure-aware framework to predict compound-protein interactions called LISACPI. LISA-CPI integrates an unsupervised DL-based molecular image representation (ImageMol) of ligands and an advanced AlphaFold2-based algorithm (Evoformer).
They demonstrated that LISA-CPI achieved 20% improvement in the average mean absolute error compared to state-of-the-art models on experimental CPIs connecting 104,969 ligands and 33 G-protein-coupled receptors (GPCRs). Using LISACPI, they prioritized potential repurposable drugs (e.g., methylergometrine) and identified candidate gut-microbiota-derived metabolites (e.g., citicoline) for potential treatment of pain via specifically targeting human GPCRs.