Loading...
Loading
ظ / τ Price
0.01979 τ
−0.93%24h−2.57%7d
Overview
Registration Activity
Neuron registration trends
This Interval
3
24h: 60 registrations (60 burn · 0 PoW)
Target / Interval
1
Slots Available
Competitive
64/64
Neurons
64
Loading
Neuron registration trends
The alpha price in τ, day by day, and what moved it each way.
Log change over the last 30 days −9.18%: protocol buys +11.47%, root sells −2.09%, users net −15.17%, cross-subnet −3.62%, unattributed +0.24%.
The chart follows the alpha price in τ. Each period starts at its opening price and steps through the mechanisms below, in a fixed order, to its closing price: a step that rises pushed the price up, one that falls pushed it down, and its height is how far it moved the price. A thin line carries each close into the next period’s open; it is dashed where the two differ. The faint candle behind each period is the market’s own open, high, low and close, for context.
With many periods on screen (90 days, or hours), the steps would be too thin to read, so the chart draws the price as a line instead and colours each period by the mechanism that moved it most. Hover a period for the full step-by-step breakdown.
Not here, because they do not move the spot price: the per-block TAO injection into the pool, and burns.
All figures are log changes, not simple percentage changes, so the parts add up exactly to the total; on big moves the two differ (a 10% log fall is a 9.5% price fall).
2026-10-14 UTC, as of ≈05:04 UTC (block 9,279,305)
The day isn’t over yet, so these figures keep changing. They are in no daily total, average or rank.
Holder & total-staked metrics as of (daily close)
Drug discovery requires screening billions of compounds and designing novel biologics to find candidates with strong binding affinity to disease targets. These screening campaigns consume months and millions in computational resources, often run by centralized institutions with limited scale. Current approaches bottleneck on expensive structure prediction and binding affinity scoring—only a fraction of chemical space can be explored in any campaign.
A decentralized network of contributors can parallelize this exploration. Instead of a single lab running one screening campaign, dozens of independent miners globally can simultaneously generate and test molecule and nanobody candidates against the same targets, each bringing different design strategies and compute resources. Miners are incentivized via token rewards based on the quality of their submissions—measured by predicted binding affinity and structural confidence. Validators evaluate submissions objectively using shared ML models (Boltz-2 for molecules, BoltzGen for nanobodies), ensuring reproducibility and eliminating bias.
NOVA (Subnet 68 on Bittensor) implements this model in a continuous 361-block competition cycle. Miners submit encrypted molecular identifiers (drawn from a combinatorial synthesis database) or novel nanobody amino acid sequences. Validators decrypt submissions, check them against chemical and biological validity rules, score them using binding affinity predictions and structural metrics, and set network weights to reward the top performers each epoch. Winners earn NOVA tokens proportional to their submission quality.
Auto-generated from the GitHub repository and may not reflect the latest changes.
NOVA Compound is a Bittensor subnet that incentivizes miners to discover drug-like molecules and design nanobody sequences with high predicted binding affinity to target proteins. Miners submit encrypted submissions competing on two tiers: small molecules (scored via Boltz-2 binding affinity prediction) and nanobodies (scored via BoltzGen metrics including structural confidence, interaction quality, and developability). Validators decrypt, validate, and score submissions using ML models, then set weights to reward the best performers.
NOVA Subnet 68 operates on epoch-based cycles of 361 blocks. Challenge parameters (targets, allowed reactions) are derived from epoch start block hash. Miners generate small molecules (from combinatorial database) or nanobody sequences (de novo design), encrypt submissions using Bittensor Drand Timelock, and upload encrypted payloads to public GitHub repos, committing the GitHub path on-chain.
Validators retrieve commitments, fetch and decrypt submissions from GitHub, validate format and chemical/biological constraints (Layer 1: format, SMILES, length, composition; Layer 2: diversity, nativeness, developability), run scoring via Boltz-2 or BoltzGen models, aggregate scores across targets/items, rank submissions, retrieve scores from other validators via score-sharing API, and set weights on-chain accordingly (73.7% burn, rest to winners). Molecules and nanobodies are evaluated in parallel on separate GPUs if available. Timeout enforcement: submissions within last 10 blocks of epoch are rejected.
Scoring is two-tiered: validity (all-or-nothing per submission type) and scoring (only valid submissions scored). For small molecules, Boltz-2 predicts binding affinity scores per target, averaged across targets and summed across molecules for final score; mode is max or min per config. For nanobodies, BoltzGen produces 10 metrics per sequence (confidence, interaction quality, developability), all miners ranked per metric independently, then ranks summed for final score (lower is better in rank-sum).
Multi-target submissions average scores per item first, then aggregate. Validators also share scores via external API for robustness. Winners determined by best final score with tie-breaking by earliest block_submitted, then push_time, then UID.
The sections above were auto-generated from the GitHub repository and may not reflect the latest changes. View repository (github.com, opens in a new tab, external site)
Accelerating drug discovery.
This information was auto-extracted from the GitHub repository and may be incomplete or out of date. Always refer to the subnet's GitHub repository (github.com, opens in a new tab, external site) for the latest instructions.
Not yet verified: GPU, VRAM, Notes
Not yet verified: VRAM, Notes
Machine-extracted from the subnet's repository docs; may be wrong or out of date. Check the repository before buying or renting hardware. Open the repository (github.com, opens in a new tab, external site) · Extracted 28 Sep 2026
Clone the NOVA repository with submodules
git clone --recurse-submodules https://github.com/metanova-labs/nova.git && cd nova
Copy example environment file
cp example.env .env
Configure environment variables in .env file (GitHub credentials, network settings, GPU allocation)
# Edit .env with your configuration: SUBTENSOR_NETWORK, GITHUB_TOKEN, GITHUB_REPO_NAME, GITHUB_REPO_OWNER, GITHUB_REPO_PATH, NOVA_BOLTZ_SHARDS, NOVA_BOLTZ_GPUS, NOVA_BOLTZGEN_GPUS, etc.
Install dependencies (CUDA version optional, default 12.6)
./install_deps.sh [--cuda <version>] && source "$HOME/.local/bin/env"
Activate virtual environment
source .venv/bin/activate
Run miner with Bittensor wallet and logging
python3 neurons/miner.py --wallet.name <your_wallet> --wallet.hotkey <your_hotkey> --logging.info
Clone the NOVA repository with submodules
git clone --recurse-submodules https://github.com/metanova-labs/nova.git && cd nova
Copy example environment file
cp example.env .env
Configure environment variables (network, GitHub, validator API, GPU settings)
# Edit .env: SUBTENSOR_NETWORK, GITHUB_TOKEN (for reading miner submissions), VALIDATOR_API_KEY (for monitoring/score sharing), SCORE_SHARE_API_URL, AUTO_UPDATE, NOVA_BOLTZ_SHARDS, NOVA_BOLTZ_GPUS, NOVA_BOLTZGEN_GPUS, NOVA_BOLTZ_THREADS, NOVA_MAX_CONCURRENT_TNP
Install dependencies with CUDA 12.6 support
./install_deps_cu126.sh
Activate virtual environment
source .venv/bin/activate
Run validator with debug logging (production mode with weight setting)
python3 neurons/validator/validator.py --wallet.name <my_wallet> --wallet.hotkey <my_hotkey> --logging.debug
Run validator in test mode (no weight setting, for testing)(optional)
python3 neurons/validator/validator.py --wallet.name <my_wallet> --wallet.hotkey <my_hotkey> --test_mode --logging.debug
Run validator with local input file (for testing without chain)(optional)
python3 neurons/validator/validator.py --wallet.name <my_wallet> --wallet.hotkey <my_hotkey> --local_input_file /path/to/input --test_mode
| Day (UTC) | Share |
|---|---|
| 2026-10-13 | 2.44% |
| 2026-10-12 | 2.44% |
| 2026-10-11 | 2.45% |
| 2026-10-10 | 2.46% |
| 2026-10-09 | 2.47% |
| 2026-10-08 | 2.48% |
| 2026-10-07 | 2.60% |
| 2026-10-06 | 2.75% |
| 2026-10-05 | 2.73% |
| 2026-10-04 | 2.72% |
| 2026-10-03 | 2.79% |
| 2026-10-02 | 2.79% |
| 2026-10-01 | 2.71% |
| 2026-09-30 | 2.80% |
| 2026-09-29 | 2.68% |
| 2026-09-28 | 2.63% |
| 2026-09-27 | 2.64% |
| 2026-09-26 | 2.79% |
| 2026-09-25 | 2.75% |
| 2026-09-24 | 2.69% |
| 2026-09-23 | 2.71% |
| 2026-09-22 | 2.77% |
| 2026-09-21 | 2.85% |
| 2026-09-20 | 2.87% |
| 2026-09-19 | 2.82% |
| 2026-09-18 | 2.76% |
| 2026-09-17 | 2.77% |
| 2026-09-16 | 2.77% |
| 2026-09-15 | 2.82% |
| 2026-09-14 | 2.88% |
| 2026-09-13 | 2.83% |
| 2026-09-12 | 2.83% |
| 2026-09-11 | 2.79% |
| 2026-09-10 | 2.74% |
| 2026-09-09 | 2.96% |
| 2026-09-08 | 3.39% |
| 2026-09-07 | 3.53% |
| 2026-09-06 | 3.48% |
| 2026-09-05 | 3.51% |
| 2026-09-04 | 3.55% |
| 2026-09-03 | 3.62% |
| 2026-09-02 | 3.38% |
| 2026-09-01 | 2.81% |
| 2026-08-31 | 2.81% |
| 2026-08-30 | 2.83% |
| 2026-08-29 | 2.94% |
| 2026-08-28 | 3.09% |
| 2026-08-27 | 2.89% |
| 2026-08-26 | 2.84% |
| 2026-08-25 | 2.87% |
| 2026-08-24 | 2.93% |
| 2026-08-23 | 2.92% |
| 2026-08-22 | 2.93% |
| 2026-08-21 | 2.94% |
| 2026-08-20 | 2.93% |
| 2026-08-19 | 3.00% |
| 2026-08-18 | 3.09% |
| 2026-08-17 | 3.22% |
| 2026-08-16 | 3.28% |
| 2026-08-15 | 3.20% |
| 2026-08-14 | 3.25% |
| 2026-08-13 | 3.27% |
| 2026-08-12 | 3.34% |
| 2026-08-11 | 3.41% |
| 2026-08-10 | 3.49% |
| 2026-08-09 | 3.39% |
| 2026-08-08 | 3.42% |
| 2026-08-07 | 3.30% |
| 2026-08-06 | 3.22% |
| 2026-08-05 | 3.23% |
| 2026-08-04 | 3.48% |
| 2026-08-03 | 3.50% |
| 2026-08-02 | 3.19% |
| 2026-08-01 | 2.91% |
| 2026-07-31 | 2.95% |
| 2026-07-30 | 2.95% |
| 2026-07-29 | 3.08% |
| 2026-07-28 | 3.20% |
| 2026-07-27 | 2.92% |
| 2026-07-26 | 2.64% |
| 2026-07-25 | 2.68% |
| 2026-07-24 | 2.85% |
| 2026-07-23 | 3.10% |
| 2026-07-22 | 3.13% |
| 2026-07-21 | 3.12% |
| 2026-07-20 | 3.10% |
| 2026-07-19 | 3.08% |
| 2026-07-18 | 3.10% |
| 2026-07-17 | 3.17% |
| 2026-07-16 | 2.24% |
