Mission: Empowering a Revolution in AI-Driven Drug Discovery
At SmartDrugDiscovery.org, our mission is rooted in a transformative vision for the future of drug discovery—one that makes the process Personalized, Accelerated, and Economically Feasible (PEACE). We believe that by harnessing the full potential of AI and systems pharmacology, we can drive innovation that not only accelerates drug discovery but also makes it more precise and accessible to those who need it the most.
PEACE
Personalized: We aim to tailor drug discovery processes to individual patient needs by leveraging advanced AI and multi-omics data integration. Our approach recognizes that every patient is unique, and so too should be their treatment. By building network models from comprehensive datasets, including genomic, proteomic, and clinical data, we create a personalized medicine ecosystem that targets the right treatment for the right patient at the right time.
Accelerated: The traditional drug discovery timeline is long and arduous. We seek to disrupt this paradigm by employing hierarchical accurate simulation models and programmable medicine. Our AI-powered platforms are designed to significantly reduce the time from target identification to therapeutic intervention, speeding up the discovery process and delivering life-saving treatments faster.
Economically Feasible: Drug discovery has historically been an expensive venture, often costing billions of dollars and many years of research. Our vision for an AI-ready ecosystem aims to cut these costs through efficient, decentralized networks and data-driven decision-making. By creating a decentralized AI drug discovery ecosystem, we bring together researchers, clinicians, and industry partners in a cost-effective manner, ensuring that innovative treatments are not only developed swiftly but also at a fraction of the traditional cost.
Our Manifesto
​AI-Ready: We are pioneering the integration of AI at every step of the drug discovery process. Our platforms are built to be AI-ready, ensuring that the latest in machine learning, deep learning, and AI technologies are seamlessly integrated into our workflows.
Hierarchical Accurate Simulation Models: We utilize sophisticated simulation models that can accurately replicate biological systems at multiple scales. These models allow us to predict the behavior of potential drugs in silico before they ever reach the lab, saving time and resources.
Programmable Medicine: Our vision includes the development of programmable therapies that can be precisely controlled and adjusted to meet the needs of individual patients. This approach moves beyond the one-size-fits-all mentality, opening the door to a new era of bespoke medicine.
Brand-New AI Race Track: We are creating an environment where AI tools are constantly evolving and improving. This dynamic ecosystem acts as a race track where AI technologies can be tested, validated, and optimized, driving continuous innovation in drug discovery.
Decentralized AI Drug Discovery Ecosystem: We believe in the power of collaboration. Our decentralized network connects researchers, clinicians, and industry partners from around the world, creating a vibrant community focused on advancing AI-driven drug discovery.
AI+ Drug Discovery Researchers: We are building a community of researchers who are not only experts in drug discovery but also fluent in the language of AI. These multidisciplinary professionals are at the forefront of the AI revolution in healthcare, pushing the boundaries of what is possible.
Our Resources
The AI.MED lab uses translational bioinformatics to develop innovative techniques and create new databases and discover novel biomedical information to improve clinical care, diagnosis and treatment. The Bioinformatics Lab provides services to manage and analyze next-generation sequencing data. The team includes individuals with skills in bioinformatics, computer science, and statistics.
U-BRITE (UAB Biomedical Research Information Technology Enhancement) assembles new and existing HIPAA-compliant, high-performance informatics tools to provide researchers with a means to better manage and analyze clinical and genomic data sets and implements a “translational research commons” to facilitate and enable interdisciplinary team science across geographical locations.
i2b2 (Informatics for Integrating Biology and the Bedside) is an NIH-funded National Center for Biomedical Computing based at Partners HealthCare System. i2b2 was developed as a scalable informatics framework designed for translational research. i2b2 was designed primarily for cohort identification, allowing users to perform an enterprise-wide search on a de-identified repository of health information to determine the existence of a set of patients meeting certain inclusion or exclusion criteria.
Our Activities
Connect ICC’s role in coordinating the activities of various stakeholders and facilitating collaboration significantly enhances the CFDE’s potential to revolutionize biomedical research.
The NIH Common Fund’s Bridge to Artificial Intelligence (Bridge2AI) Consortium will propel biomedical research forward by setting the stage for widespread adoption of artificial intelligence (AI) that tackles complex biomedical challenges beyond human intuition.
Every August we organize a data science hackathon, which brings together biomedical researchers, bioinformaticians, scientists, software developers, and computer engineers from around the world.
This initiative aims to strengthen the collaborative development and application of cancer data science tools among UAB biomedical informaticians, IT professionals, cancer researchers, and oncologists.
Our Awards
In 2019, Jake Chen was recognized by Deep Knowledge Analytics as one of the “Top 100 AI Leaders in Drug Discovery and Healthcare” for his entrepreneurial activities in systems biology software.
In 2023, Jake Chen was awarded the Pioneer Award by the Chinese Association of Science and Technology USA Chapter (CAST-USA) for his contributions in AI in drug discovery leadership in academic institutions.
Our Impact
12
AI-based Drug Design Projects
161
Invited Talks
159
Publications
43
Team Projects
189
Users