An integrated, end-to-end technology platform that delivers validated preclinical candidates
Our comprehensive technology platform, Inclusive Digital Drug Discovery and Development (ID4) focuses on hit identification and lead optimization to produce validated preclinical candidates. Our platform is empowered by AI computation, laboratory experiments and research expertise in medicinal chemistry. ID4 includes molecule ideation, drug-like properties evaluation and optimization, ADMET properties prediction, chemical synthesis and biological functional studies. The ID4 platform aims to revolutionize traditional pharmaceutical R&D by delivering candidate compounds with improved speed, scale, novelty and diversity.
We recognize that every project is unique, and we look forward to working with each collaboration partner to provide a custom solution, leveraging parts or the entirety of our ID4 platform, that best suit the project's needs.
AI + Physics-based Model
We utilize AI to process data and generate predictions at scale. Built upon virtually limitless cloud computing resources, we have constructed over 200 proprietary AI models to evaluate key drug-like properties. We also embed AI within our physics-based algorithms to improve calculation efficiency without sacrificing accuracy. We are able to customize AI models as appropriate to improve the performance of our in silico predictions based on each individual project’s unique needs.
Our AI + physics-based models are optimized with a cloud architecture that allows us to benefit from the security, scalability, flexibility and efficiency of cloud computing. The cloud architecture is designed for multi-cloud across geolocations and supported by leading public cloud service providers, and can scale up capacity to millions of cores to accelerate simulations. In addition, we adopt a cloud-native design of our computing architecture, which allows us to quickly update our software in response to the evolving industry requirements.
Synthesis and Biology
The most promising virtual hits are passed off to in-house laboratories for chemical synthesis. Through significant capital investment in state-of-the-art robotics automation, compound ideas rapidly become real chemical matter ready for testing. Our automated workstations can easily handle routine reactions, perform parallel as well as multi-step syntheses. Automation liberates our experienced chemists to focus on interesting new chemistries and unique challenges that come up in trying to synthesize novel compounds. Biology assays and analytical chemistry testing examine properties of all synthesized hits to establish structure-activity relationships (SAR), which are then fed into AI for further ideation to initiate the next design round.
Our multidisciplinary teams of scientists and technologists include computational and synthetic chemists, physicists, biologists, engineers and medicinal chemists, as well as researchers with diverse expertise in computer science and mathematics. Our teams are led by industry experts with years of relevant experience and demonstrated success in their fields. We also recruit young talents from universities to round out our well-staffed teams. Our teams work collaboratively across disciplines to foster cross-functional training and learning.
Validation through Collaboration Pipelines
To date we have engaged in drug discovery projects with partners worldwide, and have delivered promising drug candidate compounds at the successful conclusions of each collaboration, validating our ID4 platform.
Full ID4 Deployment
Firewalled Collaboration TeamsXtalPi assembles an independent delivery team for each collaboration. Each multi-disciplinary team comprises experienced experts in computational, medicinal and synthetic chemistry, as well as biology and artificial intelligence.
First-in-class TargetsThe XtalCryo module integrates cryo-EM structural determination with kinetic simulations and AI technology to explore all possible binding sites of novel targets, including those considered undruggable previously.
Rapid Hit IdentificationThe XcelaHit module includes AI molecular generation to extensively explore chemical space to perform high-throughput virtual screening, based on binding mode and affinity evaluations guided by machine learning strategies, to rapidly identify hit compounds. AI-integrated DEL technology can also be deployed to identify additional hits.
XtalPi is keenly aware that every research partner has unique needs and priorities, and is happy to create a customized solution to optimize your research program