TechBio September 🍃 News (part II)
TechBio September 🍃 News (part II)
✴️ Virtual Screening Tools & Companies and 🔷 Amplify Partners
For the first part of this week’s update:
Albert Einstein, the famous mathematician and scientist, once said:
“There is something essential about the ‘now’ which is outside the realm of science”.
September News 🏃♀️
Tencent-Backed AI Drug Researcher Xtalpi’s Shares Double On Revenue Rise
Insilico Medicine partners with Inimmune
Altris AI and Heidelberg Engineering announced a new partnership: now AltrisAI platform is available on AppWay, and all HEYEX 2 users can create AI-powered OCT reports.
Barlow Twins Deep Neural Network for Advanced 1D Drug-Target Interaction Prediction
A Novel Rational PROTACs Design and Validation via AI-Driven Drug Design Approach
Automating open source: How Ersilia distributes AI models to advance global health equity
AlphaProteo generates novel proteins for biology and health research
TechBio Transformers (a global community for techbio nerds — both online and in-person created by
) are meeting in London at the Big Chill near King's Cross on Sept 24th starting at 5:30pmPepper Bio is launching a collaboration to increase understanding of healthy muscle growth with Novo Nordisk’s Bio Innovation Hub through its Co-Creation Greenhouse Program
How DeepCure taps reinforcement learning for first-in-class therapies
Gilead inks $35M collab with AI drug discovery outfit Genesis
Virtual Screening
RosettaVS: Structure-Based Virtual Screen
Just this month, a new highly accurate structure-based virtual screen method was presented, the RosettaVS, for predicting docking poses and binding affinities (An artificial intelligence accelerated virtual screening platform for drug discovery), and was developed to outperform other state-of-the-art methods on a wide range of benchmarks, partially due to its ability to model receptor flexibility.
This new platform was developed by improving a prior physics-based Rosetta general force field, RosettaGenFF, yielding an improved forcefield named RosettaGenFF-VS. Based on this new force field, a state-of-the-art virtual screening protocol was developed using Rosetta GALigandDock, hereafter referred to as RosettaVS. RosettaVS implements two high-speed ligand docking modes: virtual screening express (VSX) designed for rapid initial screening, while the virtual screening high-precision (VSH) is a more accurate method used for final ranking of the top hits from the initial screen.
In particular, the modeling of receptors flexibility was incorporated into a new open-source AI accelerated virtual screening platform, used to screen multi-billion compound libraries against two unrelated targets, a ubiquitin ligase target KLHDC2 and the human voltage-gated sodium channel NaV1.7.
For both targets, hit compounds were discovered, including seven hits (14% hit rate) to KLHDC2 and four hits (44% hit rate) to NaV1.7, all with single digit micromolar binding affinities, and screening in both cases was completed in less than seven days. Finally, a high resolution X-ray crystallographic structure validated the predicted docking pose for the KLHDC2 ligand complex, demonstrating the effectiveness of RosettaVS.
You can find here the Major types of virtual screening algorithms that are available right now for drug screening (2023).
Chemical Space: Known and Virtual
Searching for a new drug candidate, means searching and wandering around in a vast chemical space, comprising >10^60 molecules (…keep in mind that there are something like 10^22 to 10^24 stars in our Universe). In particular, the known chemical space—that includes public databases and corporate collections—probably contains something like 10^8 molecules (100 million), but the virtual chemical space might contain 10^60 compounds when considering only basic structural rules, or a more modest 10^20 – 10^24 molecules if combination of known fragments are considered.
Since the chemical space is far too large for an exhaustive "exploration", one is therefore left only with a partial, targeted "exploration" inside smaller virtual libraries and smaller chemical libraries. So, numerous in silico methods are used to virtual screen compounds from virtual chemical spaces along with in vitro high-throughput screening experiments of chemical libraries, in order to identify drug candidates. Nowadays, several chemical spaces are open access, including PubChem, ChemBank, DrugBank, ChemDB and more. While some solutions for virtual libraries are:
A partnership with Enamine and Cresset will enable screening of ultra-large chemical spaces as part of the virtual screening process in drug discovery.
Discover eXplore: the largest virtual accessible and actionable Chemical Space providing over 7 trillion compounds for your novel drug discovery research by eMolecules.
PolarisQB announced integration of Virtual Libraries and Fragmentation schemes from chemical innovator Liverpool ChiroChem into Quantum-Aided Drug Design.
The logic behind the design of both types of libraries is often similar, and the two methods—experimental for real compound libraries and computational for virtual compound libraries—often complement each other in drug discovery. In the end, both types of libraries are commonly run in parallel, and the results of one are compared to the other aiming at discovering promising new drug leads.
Virtual Screening with NVIDIA: NIM Agent Blueprint
Aiming at making the virtual screening faster and smarter, NVIDIA (NASDAQ: NVDA) released on August 27, 2024 the NIM Agent Blueprint for generative AI-based virtual screening (Better Molecules, Faster: NVIDIA NIM Agent Blueprint Redefines Hit Identification With Generative AI-Based Virtual Screening), that identifies and improves virtual hits in a smarter and more efficient way and has at its core three essential AI models:
AlphaFold2,
MolMIM, a novel model developed by NVIDIA that generates molecules while simultaneously optimizing for multiple properties, such as high solubility and low toxicity, and
DiffDock, an advanced tool for quickly modeling the binding of small molecules to their protein targets.
These three models work in concert to improve the hit-to-lead process, making it more efficient and faster. Benchling, Dotmatics, Terray, TetraScience and Cadence Molecular Sciences (OpenEye), are all using NIM Agent Blueprints in their computer-aided drug discovery platforms.
AI-Driven Virtual Screening Approaches: Structure-based, Ligand-based and Chemogenomic
In general, the AI-Driven Virtual Screening for lead compound identification during drug discovery consists of:
Structure-based approaches: molecular docking simulations (a computational technique that predicts the binding affinity of ligands to receptor proteins) that involve a two-step process of conformational space search and scoring.
The Deep Docking (DD) platform enables up to 100-fold acceleration of structure-based virtual screening by docking only a subset of a chemical library, synchronized with a ligand-based prediction of the remaining docking scores. This AI method results in hundreds- to thousands-fold virtual hit enrichment (without significant loss of potential drug candidates) and hence enables the screening of billion molecule–sized chemical libraries without using extraordinary computational resources.
Traditional scoring functions, as well as data-driven machine learning (MLSF) and deep learning-based scoring functions (DLSF), such as 3D convolutional neural networks (3D-CNN) and graph convolutional networks (GCN), prioritize ligand poses and estimate binding affinity.
DUD-E is for benchmarking molecular docking by providing challenging decoy.
In general, the Structure-Based Drug Designing (SBDD) is the current mainstream mode for the rational drug design of small molecules, based on molecular recognition of the 3D structure of molecules and respective target proteins (the rational drug design is based on knowledge to distinguish it from the traditional drug design that is based exclusively on screening). Usually, SBDD includes structure determination of the target protein, cavity identification, ligand database construction, ligand docking and lead discovery, combined with a computational-based virtual screening of large chemical libraries. The softwares used for SBDD are: SWISS-MODEL, MODELER, Phyre and Phyre2, CASTp, Active site prediction tool, AutoDockVina and Schrodinger.
Maestro is Schrödinger’s streamlined portal for access to state-of-the-art predictive computational modeling and ML workflows for molecular discovery.