Nova
Nova
Nova
[ ABOUT NOVA ]
NOVA merges decentralized computing, ML-driven active learning, agent development, and domain-specific heuristics to tackle drug discovery at scale. Our approach transforms the quest for new therapeutics into a competitive, transparent, and efficient search process. NOVA functions as a back to back hackathon, running 24/7. Miners are encouraged to continuously develop and refine ai-driven approaches that make drug hunting in a vast chemical universe more efficient.
NOVA merges decentralized computing, ML-driven active learning, agent development, and domain-specific heuristics to tackle drug discovery at scale. Our approach transforms the quest for new therapeutics into a competitive, transparent, and efficient search process. NOVA functions as a back to back hackathon, running 24/7. Miners are encouraged to continuously develop and refine ai-driven approaches that make drug hunting in a vast chemical universe more efficient.
PHARMA
CRISIS
DRUG DISCOVERY COST
$1 billion USD
10% Chance
SUCCESS RATE TO DEVELOP ONE DRUG
Time to Market
10+ YEARS
90%
OF DRUG SCAFFOLD REUSED
PHARMA
CRISIS
DRUG DISCOVERY COST
$1 billion USD
SUCCESS RATE TO DEVELOP ONE DRUG
10% Chance
Time to Market
10+ YEARS
OF DRUG SCAFFOLD REUSED
90%
PHARMA
CRISIS
DRUG DISCOVERY COST
$1 billion USD
SUCCESS RATE TO DEVELOP ONE DRUG
10% Chance
Time to Market
10+ YEARS
OF DRUG SCAFFOLD REUSED
90%
Advanced virtual
screening can help, but
accuracy is dependent on:
datasets
Large, diverse datasets
Prevent brute force approaches
COMPUTATIONALLY INTENSIVE
datasets
Large, diverse datasets
Prevent brute force approaches
COMPUTATIONALLY INTENSIVE
VALIDATION
Wet lab validation
LARGELY UNAVAILABLE
SILOED BY CLOSED LABS
MOTIVATED TO KEEP SECRET
VALIDATION
Wet lab validation
LARGELY UNAVAILABLE
SILOED BY CLOSED LABS
MOTIVATED TO KEEP SECRET
Properties
Multiple properties
rarely included in predictive models
NO cross optimization
Properties
Multiple properties
rarely included in predictive models
NO cross optimization
Decentralized
merit-based competition
is necessary to deliver
the promise of ai
PROCESSING SUBMISSIONS
EVALUATING SUBMISSIONS
102.932 / 3.232.943.203 Molecules
Centralized AI drug discovery platforms reward secrecy over scientific progress—models and data are locked behind NDAs to protect valuations, teams duplicate each other’s efforts, and exploration is confined to well‑trodden chemical scaffolds. This siloed approach breeds redundancy, stifles collaboration, and makes it very difficult to scale to truly novel regions of the chemical universe. Without open data‑sharing or adversarial stress‑testing, AI models overfit to narrow datasets and falter when faced with unprecedented targets.
NOVA flips the script. By harnessing a decentralized, tokenized incentive system, we align rewards with transparency and merit. Miners compete to submit diverse, high‑affinity molecules and then stress‑test open source models across billions of compounds. Dynamic target–antitarget challenges and a Shannon‑diversity bonus ensure broad chemical mapping and early toxicity filtering. In doing so, NOVA exposes blind spots in the models, areas of high variance, so that we can iteratively refine predictive models and accelerate the discovery of breakthrough small molecules in ways no closed lab does.
Decentralized
merit-based competition
is necessary to deliver
the promise of ai
PROCESSING SUBMISSIONS
EVALUATING SUBMISSIONS
102.932 / 3.232.943.203 Molecules
Centralized AI drug discovery platforms reward secrecy over scientific progress—models and data are locked behind NDAs to protect valuations, teams duplicate each other’s efforts, and exploration is confined to well‑trodden chemical scaffolds. This siloed approach breeds redundancy, stifles collaboration, and makes it very difficult to scale to truly novel regions of the chemical universe. Without open data‑sharing or adversarial stress‑testing, AI models overfit to narrow datasets and falter when faced with unprecedented targets.
NOVA flips the script. By harnessing a decentralized, tokenized incentive system, we align rewards with transparency and merit. Miners compete to submit diverse, high‑affinity molecules and then stress‑test open source models across billions of compounds. Dynamic target–antitarget challenges and a Shannon‑diversity bonus ensure broad chemical mapping and early toxicity filtering. In doing so, NOVA exposes blind spots in the models, areas of high variance, so that we can iteratively refine predictive models and accelerate the discovery of breakthrough small molecules in ways no closed lab does.
Decentralized
merit-based competition is
necessary to deliver
the promise of ai
PROCESSING SUBMISSIONS
EVALUATING SUBMISSIONS
102.932 / 3.232.943.203 Molecules
Centralized AI drug discovery platforms reward secrecy over scientific progress—models and data are locked behind NDAs to protect valuations, teams duplicate each other’s efforts, and exploration is confined to well‑trodden chemical scaffolds. This siloed approach breeds redundancy, stifles collaboration, and makes it very difficult to scale to truly novel regions of the chemical universe. Without open data‑sharing or adversarial stress‑testing, AI models overfit to narrow datasets and falter when faced with unprecedented targets.
NOVA flips the script. By harnessing a decentralized, tokenized incentive system, we align rewards with transparency and merit. Miners compete to submit diverse, high‑affinity molecules and then stress‑test open source models across billions of compounds. Dynamic target–antitarget challenges and a Shannon‑diversity bonus ensure broad chemical mapping and early toxicity filtering. In doing so, NOVA exposes blind spots in the models, areas of high variance, so that we can iteratively refine predictive models and accelerate the discovery of breakthrough small molecules in ways no closed lab does.
What makes
Nova Different
What makes
Nova Different
What makes
Nova Different
1
Massive libraries
Miners tap into an ultra-large virtual database of 1+ billion synthesizable compounds.This ensures that every “hit” is ready for further development.
1
Massive libraries
Miners tap into an ultra-large virtual database of 1+ billion synthesizable compounds.This ensures that every “hit” is ready for further development.
1
Massive libraries
Miners tap into an ultra-large virtual database of 1+ billion synthesizable compounds.This ensures that every “hit” is ready for further development.
2
Heuristic innovation
Miners iteratively refine their search strategies, from brute force to advanced ML-based active learning. The duration of the challenges encourage miners to develop innovative heuristics to select top compounds at top speed.
2
Heuristic innovation
Miners iteratively refine their search strategies, from brute force to advanced ML-based active learning. The duration of the challenges encourage miners to develop innovative heuristics to select top compounds at top speed.
2
Heuristic innovation
Miners iteratively refine their search strategies, from brute force to advanced ML-based active learning. The duration of the challenges encourage miners to develop innovative heuristics to select top compounds at top speed.
3
hyper competitive
“Winner-takes-all” challenges incentivize continuous improvement and reveal areas of low confidence in SOTA models at lightning speed that are used to fine-tune more robust models.
3
hyper competitive
“Winner-takes-all” challenges incentivize continuous improvement and reveal areas of low confidence in SOTA models at lightning speed that are used to fine-tune more robust models.
3
hyper competitive
“Winner-takes-all” challenges incentivize continuous improvement and reveal areas of low confidence in SOTA models at lightning speed that are used to fine-tune more robust models.
4
low barrier of entry
Our subnet design encourages high miner registration given low hardware requirements and that there is no need for domain-specific expertise to participate. Challenge is reduced to a search problem that rewards heuristic innovation.
4
low barrier of entry
Our subnet design encourages high miner registration given low hardware requirements and that there is no need for domain-specific expertise to participate. Challenge is reduced to a search problem that rewards heuristic innovation.
4
low barrier of entry
Our subnet design encourages high miner registration given low hardware requirements and that there is no need for domain-specific expertise to participate. Challenge is reduced to a search problem that rewards heuristic innovation.
5
high value service + outputs
We are developing a series of assets that can power drug r+d in-house and for partners. These include chemical space navigators to identify best entry points, libraries of the most promising compounds, fine-tuned models, wet lab datasets, and drug candidates. We combine the recurring revenue of a subnet with the possibility of outsize payments from licensing .
5
high value service + outputs
We are developing a series of assets that can power drug r+d in-house and for partners. These include chemical space navigators to identify best entry points, libraries of the most promising compounds, fine-tuned models, wet lab datasets, and drug candidates. We combine the recurring revenue of a subnet with the possibility of outsize payments from licensing .
5
high value service + outputs
We are developing a series of assets that can power drug r+d in-house and for partners. These include chemical space navigators to identify best entry points, libraries of the most promising compounds, fine-tuned models, wet lab datasets, and drug candidates. We combine the recurring revenue of a subnet with the possibility of outsize payments from licensing .
6
multiple parameters
As more miners join, the collective knowledge and power expand. We will move beyond activity predictions to include other key parameters for drug development. Our plan is to integrate ADME/TOX metrics and wet lab validations to create first-in-class libraries.
6
multiple parameters
As more miners join, the collective knowledge and power expand. We will move beyond activity predictions to include other key parameters for drug development. Our plan is to integrate ADME/TOX metrics and wet lab validations to create first-in-class libraries.
6
multiple parameters
As more miners join, the collective knowledge and power expand. We will move beyond activity predictions to include other key parameters for drug development. Our plan is to integrate ADME/TOX metrics and wet lab validations to create first-in-class libraries.
NOVA
EVALUATING SUBMISSIONS
102.932
/
3.232.943.203
Molecules
How does it
work?
How does it
work?
How does it
work?
STEP
1
Library
Provide billion size dataset of synthesizable molecules
By
METANOVA
STEP
1
Library
Provide billion size dataset of synthesizable molecules
By
METANOVA
STEP
1
Library
Provide billion size dataset of synthesizable molecules
By
METANOVA
STEP
2
Miners
id top compounds with highest affinity to key targets + ideal physicochemical properties
By
Miners
STEP
2
Miners
id top compounds with highest affinity to key targets + ideal physicochemical properties
By
Miners
STEP
2
Miners
id top compounds with highest affinity to key targets + ideal physicochemical properties
By
Miners
STEP
3
Validators
score submissions using SOTA prediction model
By
Validators
STEP
3
Validators
score submissions using SOTA prediction model
By
Validators
STEP
3
Validators
score submissions using SOTA prediction model
By
Validators
STEP
6
Repeat
integrate ground truth data to improve miner predictions
By
METANOVA
STEP
6
Repeat
integrate ground truth data to improve miner predictions
By
METANOVA
STEP
6
Repeat
integrate ground truth data to improve miner predictions
By
METANOVA
STEP
5
Synthesize
synthesize molecules + run wet lab validation
By
CRO
STEP
5
Synthesize
synthesize molecules + run wet lab validation
By
CRO
STEP
5
Synthesize
synthesize molecules + run wet lab validation
By
CRO
STEP
4
Select
score submissions using SOTA prediction model
By
METANOVA
STEP
4
Select
score submissions using SOTA prediction model
By
METANOVA
STEP
4
Select
score submissions using SOTA prediction model
By
METANOVA
STEP
Licensing
licensing deal opportunitites
STEP
Licensing
licensing deal opportunitites
STEP
Licensing
licensing deal opportunitites
NOVA is the starting
point of a flywheel of
digital and real world
value creation
NOVA is the starting
point of a flywheel of
digital and real world
value creation
NOVA is the starting
point of a flywheel of
digital and real world
value creation
NOVA
NOVA
chemical space navigator
chemical space navigator
Libraries
of top Compounds
Libraries
of top Compounds
DRUG R&D
DRUG R&D
RETRAINED + FINE-TUNED MODELS
REAL WORLD DATA
REAL WORLD DATA
RETRAINED + FINE-TUNED MODELS
NOVA
Virtual drug
Screening at
Lightning speed
Virtual drug
Screening at
Lightning speed
Virtual drug
Screening at
Lightning speed
FAQ
NOVA is a decentralized drug discovery subnet on the bittensor network, designed to rapidly screen billions of synthesizable compounds for potential therapeutic applications. Traditional pipelines often take over a decade and cost billions per drug—our approach leverages global compute power, cutting-edge ai, and a dynamic incentive model to reduce both time and expense, accelerating the path to new treatments.
What is NOVA and why does it matter?
NOVA is a decentralized drug discovery subnet on the bittensor network, designed to rapidly screen billions of synthesizable compounds for potential therapeutic applications. Traditional pipelines often take over a decade and cost billions per drug—our approach leverages global compute power, cutting-edge ai, and a dynamic incentive model to reduce both time and expense, accelerating the path to new treatments.
What is NOVA and why does it matter?
NOVA is a decentralized drug discovery subnet on the bittensor network, designed to rapidly screen billions of synthesizable compounds for potential therapeutic applications. Traditional pipelines often take over a decade and cost billions per drug—our approach leverages global compute power, cutting-edge ai, and a dynamic incentive model to reduce both time and expense, accelerating the path to new treatments.
What is NOVA and why does it matter?
Each “challenge” is tied to a particular protein target or family. Miners submit candidate molecules from massive databases of synthesizable molecules, with only one active submission allowed at a time. Validator score these submission with our deterministic oracle. The highest-scoring miner receives alpha tao rewards. This winner-takes-all approach rewards genuine innovation and continually improves the quality of submissions.
What does the “competition model” look like and how are winners determined?
Each “challenge” is tied to a particular protein target or family. Miners submit candidate molecules from massive databases of synthesizable molecules, with only one active submission allowed at a time. Validator score these submission with our deterministic oracle. The highest-scoring miner receives alpha tao rewards. This winner-takes-all approach rewards genuine innovation and continually improves the quality of submissions.
What does the “competition model” look like and how are winners determined?
Each “challenge” is tied to a particular protein target or family. Miners submit candidate molecules from massive databases of synthesizable molecules, with only one active submission allowed at a time. Validator score these submission with our deterministic oracle. The highest-scoring miner receives alpha tao rewards. This winner-takes-all approach rewards genuine innovation and continually improves the quality of submissions.
What does the “competition model” look like and how are winners determined?
Most AI platforms for drug discovery are centralized, limited by their own compute capacity and proprietary data. NOVA, on the other hand, distributes the workload across a global network of participants—miners, validators, and data scientists—who compete in real time. This collective intelligence, combined with on-chain transparency, transforms drug discovery into an open, merit-based process rather than a black-box service.
How does NOVA differ from traditional AI-driven drug discovery?
Most AI platforms for drug discovery are centralized, limited by their own compute capacity and proprietary data. NOVA, on the other hand, distributes the workload across a global network of participants—miners, validators, and data scientists—who compete in real time. This collective intelligence, combined with on-chain transparency, transforms drug discovery into an open, merit-based process rather than a black-box service.
How does NOVA differ from traditional AI-driven drug discovery?
Most AI platforms for drug discovery are centralized, limited by their own compute capacity and proprietary data. NOVA, on the other hand, distributes the workload across a global network of participants—miners, validators, and data scientists—who compete in real time. This collective intelligence, combined with on-chain transparency, transforms drug discovery into an open, merit-based process rather than a black-box service.
How does NOVA differ from traditional AI-driven drug discovery?
Yes. NOVA focuses on the savi 2020 database, which exclusively contains synthesizable compounds—meaning each predicted molecule comes with a viable route to lab production. This direct link between virtual hits and real-world validation greatly accelerates the journey from in silico discovery to experimental testing, enhancing both scientific impact and commercial potential.
Are these predicted molecules actually usable in the real world?
Yes. NOVA focuses on the savi 2020 database, which exclusively contains synthesizable compounds—meaning each predicted molecule comes with a viable route to lab production. This direct link between virtual hits and real-world validation greatly accelerates the journey from in silico discovery to experimental testing, enhancing both scientific impact and commercial potential.
Are these predicted molecules actually usable in the real world?
Yes. NOVA focuses on the savi 2020 database, which exclusively contains synthesizable compounds—meaning each predicted molecule comes with a viable route to lab production. This direct link between virtual hits and real-world validation greatly accelerates the journey from in silico discovery to experimental testing, enhancing both scientific impact and commercial potential.
Are these predicted molecules actually usable in the real world?