Building intelligent networks that connect multidisciplinary expertise, computational models, and experimental capabilities. Our system integrates dynamic discovery flows, continuous learning loops, and targeted deployment to accelerate therapeutic development.
TAP is a focal point for collaboration in the life sciences industry. We attract and orchestrate multi-disciplinary expertise, computational power, and experimental capabilities through intelligent networks that traditional siloed approaches cannot achieve. By leading and originating collaborative initiatives, we unlock latent capabilities across the field to generate beneficial outcomes for patients and all partners involved. Our dynamic approach accelerates therapeutic discovery while creating value for everyone in our network.
Our system is built from the ground up as an AI-native architecture, creating intelligent networks that connect multidisciplinary expertise, computational models, and experimental capabilities. This reveals optimal collaborations and breakthrough opportunities that siloed approaches cannot identify.
Each collaboration teaches the network how to form better connections, transforming drug discovery into a continuously improving, distributed intelligence. The system doesn't just learn about molecules—it learns how to optimize the innovation process itself.
The network-based approach unlocks powerful effects. The network grows smarter with every interaction.
The system leverages state-of-the-art AI architectures:
Built on modern architectural principles:
Comprehensive integration across:
Distributed innovation represents a fundamental shift to collaborative networks that unlock collective intelligence. This approach connects people, their expertise, and the knowledge they generate alongside machine intelligence and learnings across institutions and computational models. Information is retrieved from the edges rather than centralized aggregation, enabling dynamic risk distribution and exponential learning.
A distributed network of talent, cutting-edge technologies, and leading institutions is coordinated. In-house capabilities are amplified through strategic partnerships with:
Built from the ground up with AI/ML at the core. The computational infrastructure spans across the network, enabling distributed processing, model deployment, and collaboration.
Seamless coordination of distributed capabilities through the orchestration platform, ensuring efficient resource allocation and communication across all network nodes.
We operate dynamic portfolios across multiple therapeutic targets, continuously optimizing candidate selection through data-driven processes. Our system maintains active portfolios that are dynamically managed with real-time decisions to pause, purge, or promote candidates based on emerging data and predictive models. This enables continuous risk mapping and early false positive detection through strategic "killing experiments" that validate or eliminate candidates quickly, allowing rapid reallocation of resources to the most promising candidates while systematically eliminating dead ends.
Parallel processing across our network accelerates discovery timelines. Our learn-fast/kill-fast approach enables rapid decision-making and program advancement, with continuous flow from target discovery through preclinical and clinical development guided by empirical loops and computational predictions at each stage.
Portfolios are pursued that are driven by partnerships and disease indications through focused "Answer Projects" that are spun out. These are formed to concentrate efforts around specific initiatives. New "Answer Projects" are dynamically created as opportunities emerge, enabling rapid deployment across multiple therapeutic areas.
Every experimental result feeds back into AI models, creating a continuous learning loop that improves predictive accuracy across the entire network.
Rapid empirical validation of computational predictions, with results immediately informing model refinement and next-round predictions.
Iterative refinement of both computational models and experimental approaches, continuously improving the accuracy and efficiency of the discovery process.
Our collaborative networks enable multiple paths to commercialization. Strategic optionality is achieved through a range of partnerships. Stakeholders across the field are engaged to accelerate development programs through active risk mapping. Alternative commercialization routes are pursued through various industry partnerships. This approach ensures seamless transition from discovery to clinical development and strategic market access. The probability of successful therapeutic deployment is maximized while creating value across the entire network of collaborators.
Special Assistant to the President, Biological Threats • Managing Director/Partner, BCG, PwC • Operation Warp Speed architect
Corporate and Technology Strategy • Entrepreneur, Co-Founder ValueAI Institute • Investor, Venture Partner
Senior Pharma Leadership • AI-driven Drug Discovery, Portfolio • Platform Technology and Science, GSK
Machine Learning, Deep Learning • AI Researcher/Instructor, Berkeley, NASA • Founder, Silicon Valley Bank AI Lab
Head of Operations, SaponiQx • Novavax Vaccine Lead, US Government Operation Warp Speed • Technology Selection and Clinical Evaluation, Department of Defense
Medicinal Chemist • Director, Exelixis • Principal Scientist, Merck
Machine Learning, Computational Biology, Cancer Genomics • CSO / CTO, Cancer IQ
Medical Strategy • CMO, ADC Therapeutics • SVP, Celgene, Pfizer, Wyeth
Chief Security Officer, Cloudflare • CISO, McAfee, HSBC, Silicon Valley Bank
DNA Encoded Libraries • Informatics & Molecular Biology, Dice Therapeutics
Management Systems • High Performance Organization • Senior Lecturer, MIT Sloan
Life Sciences Strategy & Business Operations • Supply Chain, Project Management • Boston Consulting Group
Senior Pharma Leadership • Collaborative Drug Discovery, InnoCentive • R&D Executive, Eli Lilly
Founder • Distributed Innovation • Entrepreneur, Impact Investor
TAP engages with partners by referral.