L1 ⚛ L1-521 ⊙ Testnet

Drug-Target Binding Affinity Classification (PWDR)

Computational Chemistry · Quantum-chemistry binding-energy estimation with affinity-class categorical readout

⬇ Download bundle 🚀 Submit to mainnet — earn 5% royalty

🎁 Contribute & earn PWM

Improve L1-521 — submit with or without uploading. Accepted submissions earn the 1/16 modify share of A(t).

✨ Submit without uploading free check · 1×

One click — no files, no typing. We submit a check of L1-521 for you; it goes through review and earns the 1/16 share once. One free no-upload Principle per account.

You'll be asked to log in first — then it's one click, no files.

⬆ Or submit by uploading your files

Upload your .md + .json as a modification of L1-521. Unlimited.

🛠 Helper: build your files in ChatGPT / Gemini / Claude

Layer template

⬇ principle.md ⬇ principle.json

Fork L1-521

⬇ L1-521.md ⬇ L1-521.json

Prompt — copy into your LLM

You are helping me submit a MODIFICATION of L1-521 (Drug-Target Binding Affinity Classification (PWDR)) to the PWM Protocol — a Principle (L1) artifact.

I will paste a Markdown template (or the current L1-521.md).
1. Rewrite the Markdown so the science is correct and clearly explained for my change.
2. Regenerate the sibling L1-521.json so EVERY field matches the Markdown.
3. Keep the schema in the "File Mapping" footer at the bottom of the MD.
4. Keep the parent reference unchanged unless I ask otherwise.
Rules: the Markdown is the source of truth; use SI units; do NOT invent benchmark scores.
Output each file in its own fenced code block tagged with the filename.

Here is my template:
[PASTE THE .md HERE]

⚙ Forward Model

y = `int.ensemble` `L.affinity_threshold_classifier` `L.binding_free_energy` `L.fep_thermodynamic_cycle` `L.molecular_dynamics` `L.force_field_parameterization` `L.dft_charge_calculation` `L.molecular_topology` x

world state x (1D affinity class)

→

L · molecular topology `L.molecular_topology`

→

L · dft charge calculation `L.dft_charge_calculation`

→

L · force field parameterization `L.force_field_parameterization`

→

L · molecular dynamics `L.molecular_dynamics`

→

L · fep thermodynamic cycle `L.fep_thermodynamic_cycle`

→

L · binding free energy `L.binding_free_energy`

→

L · affinity threshold classifier `L.affinity_threshold_classifier`

→

int · ensemble `int.ensemble`

→

observation y (atomic potential detector)

Noise: ensemble variance

Markdown — human-readable source of truth

⚙ auto-generated

⬇ L1-521.md

# ⚛ L1 Principle — Drug-Target Binding Affinity Classification (PWDR) **ID:** `L1-521` · **Status:** ⊙ Testnet (genesis catalog) > **🌐 Domain:** Computational Chemistry — *Quantum-chemistry binding-energy estimation with affinity-class categorical readout* > **🎯 Problem class:** nonlinear inverse with categorical readout · **🧮 Solution space:** 1D affinity class > **📡 Carrier:** atomic_potential · **🌫 Noise:** ensemble variance > **⚖ Difficulty (δ):** 5 · **⛓ Block:** 41554143 --- ## 🧠 1. Introduction **Drug-Target Binding Affinity Classification (PWDR)** is a **nonlinear inverse with categorical readout** whose unknown lives in **1D affinity class** space, within the **Quantum-chemistry binding-energy estimation with affinity-class categorical readout** sub-domain of **Computational Chemistry**. Measurements consist of atomic potential via a **fep with affinity threshold** sensing mechanism. The forward operator applies, in order: L · molecular topology operator; L · dft charge calculation operator; L · force field parameterization operator; L · molecular dynamics operator; L · fep thermodynamic cycle operator; L · binding free energy operator; L · affinity threshold classifier operator; int · ensemble operator. Observations are corrupted by ensemble variance. Existence guaranteed within Omega bounds. Uniqueness conditional on adequate sampling (typically ≥100 ns of FEP for druglike ligands) and convergent thermodynamic cycle. Stability dominated by force_field_uncertainty (~1-2 kcal/mol systematic error) and sampling_convergence_error. Joint Hadamard well-posedness for the coupled DFT + MD + FEP + threshold forward established by Wang 2015 (FEP+ benchmark), Mey 2020 (best practices for FEP), Cournia 2020 (relative binding free energy review), Lipinski 1997 (Rule of 5), Veber 2002 (drug-likeness rules), Hopkins 2004 (ligand efficiency). ## ⚙ 2. Forward Model Physical chain: **x** → L · molecular topology → L · dft charge calculation → L · force field parameterization → L · molecular dynamics → L · fep thermodynamic cycle → L · binding free energy → L · affinity threshold classifier → int · ensemble → **y** (detector). ``` y = `int.ensemble` `L.affinity_threshold_classifier` `L.binding_free_energy` `L.fep_thermodynamic_cycle` `L.molecular_dynamics` `L.force_field_parameterization` `L.dft_charge_calculation` `L.molecular_topology` x ``` **Measurement DAG:** | Primitive | What it does | |---|---| | `L.molecular_topology` | L · molecular topology operator | | `L.dft_charge_calculation` | L · dft charge calculation operator | | `L.force_field_parameterization` | L · force field parameterization operator | | `L.molecular_dynamics` | L · molecular dynamics operator | | `L.fep_thermodynamic_cycle` | L · fep thermodynamic cycle operator | | `L.binding_free_energy` | L · binding free energy operator | | `L.affinity_threshold_classifier` | L · affinity threshold classifier operator | | `int.ensemble` | Int · ensemble operator | ## 🔬 3. Physics Fingerprint | Property | Value | |---|---| | Domain | Computational Chemistry | | Sub domain | Quantum-chemistry binding-energy estimation with affinity-class categorical readout | | Carrier | atomic_potential | | Problem class | nonlinear_inverse_with_categorical_readout | | Solution space | 1D_affinity_class | | Noise model | ensemble_variance | | Integration axis | ensemble | | Difficulty delta | 5 | | L dag | 7 | ## 📡 4. Measurement Model Existence guaranteed within Omega bounds. Uniqueness conditional on adequate sampling (typically ≥100 ns of FEP for druglike ligands) and convergent thermodynamic cycle. Stability dominated by force_field_uncertainty (~1-2 kcal/mol systematic error) and sampling_convergence_error. Joint Hadamard well-posedness for the coupled DFT + MD + FEP + threshold forward established by Wang 2015 (FEP+ benchmark), Mey 2020 (best practices for FEP), Cournia 2020 (relative binding free energy review), Lipinski 1997 (Rule of 5), Veber 2002 (drug-likeness rules), Hopkins 2004 (ligand efficiency). | Metric | Value | |---|---| | Metric | categorical_accuracy | | Secondary | RMSE_log10_Kd | ## 📏 5. Operating Range (Ω) **Center problem class:** `drug_target_affinity_pwdr` · **Forward operator:** `fep_affinity_pwdr_forward` **Center point:** | Parameter | Unit | Value | |---|---|---| | Force field | — | AMBER_FF14SB | | Water model | — | TIP3P | | N atoms drug | — | 50 | | Temperature k | — | 298 | | N atoms target | — | 5000 | | Simulation time ns | ns | 100 | | Salt concentration m | m | 0.15 | | Drug protonation state | — | 0 | | Force field uncertainty | — | 0 | | Water model uncertainty | — | 0 | | Sampling convergence error | — | 0 | | Protein flexibility truncation | — | 0 | | Conformational search incompleteness | — | 0 | **Allowed bounds:** | Parameter | Unit | Range | |---|---|---| | N atoms drug | — | 10 – 200 | | Temperature k | — | 273 – 320 | | N atoms target | — | 500 – 50000 | | Simulation time ns | ns | 1 – 10000 | ## 🎯 6. Tolerance (ε) **Center tolerance:** 0.70_accuracy | Metric | Range | |---|---| | Categorical accuracy | 0.3 – 0.95 | ## ⚖ 7. Hardness Function Hardness scales as **`epsilon_fn`** on **categorical_accuracy**, with κ = `100` and δ = `5`. ## 💾 8. Reference Dataset - **primary** · weight 1.0 · IPFS _(not pinned yet)_ ## 9. On-chain Registration - **Chain hash:** `0x361fddfc11128102f96777208aa7734516caaa5086b4f3878351ed4f1fd3073a` - **Chain tx hash:** `0x5ff82741bdf6b9f8b5e4db2a02645c615150199e7bc19e96ee2f2beb96d2233f` - **Chain block:** `41554143` --- ## File Mapping This bundle consists of: `L1-521.md`, `L1-521.json`. | File | Role | How to regenerate | |------|------|-------------------| | `L1-521.md` | Source of truth — edit this | Human or LLM | | `L1-521.json` | Structured metadata for the registry | LLM regenerates from the sections above | **Prompt for your LLM after editing this Markdown:** > Read the attached Markdown. Regenerate the sibling `.json` so every field matches. > Preserve the schema documented in the rows above. > Output each file in its own fenced code block tagged with the filename. > Output only the JSON object. _This Markdown was auto-synthesized from the catalog row for `L1-521`._ _Edit it, regenerate the JSON, and submit at [/submit](/submit) to claim the artifact._

💬

Ask the PWM AI agent AI

Ask about this Drug-Target Binding Affinity Classification (PWDR) — or how to improve it & earn PWM

Free to search; log in to chat with the agent & earn PWM. How it works ↗

⌥ Hierarchy

Upstream lineage and downstream children

↓ L2 Digital Twin 1 child ▾

L2-521-001 Drug-Target Binding Affinity Classification (PWDR) — Spec Skeleton

⬇ Download bundle

2 files · click to download

📋 JSON metadata

{
  "artifact_id": "L1-521",
  "chain_block": 41554143,
  "chain_hash": "0x361fddfc11128102f96777208aa7734516caaa5086b4f3878351ed4f1fd3073a",
  "chain_tx_hash": "0x5ff82741bdf6b9f8b5e4db2a02645c615150199e7bc19e96ee2f2beb96d2233f",
  "domain": "Computational Chemistry",
  "hardness_fn": {
    "delta": 5,
    "kappa": 100,
    "metric": "categorical_accuracy",
    "type": "epsilon_fn"
  },
  "initiator_dataset": [
    {
      "ipfs_cid": null,
      "license_hash": null,
      "name": "primary",
      "weight": 1.0
    }
  ],
  "layer": "L1",
  "observable_profile": {
    "metric": "categorical_accuracy",
    "regime": "Existence guaranteed within Omega bounds. Uniqueness conditional on adequate sampling (typically \u2265100 ns of FEP for druglike ligands) and convergent thermodynamic cycle. Stability dominated by force_field_uncertainty (~1-2 kcal/mol systematic error) and sampling_convergence_error. Joint Hadamard well-posedness for the coupled DFT + MD + FEP + threshold forward established by Wang 2015 (FEP+ benchmark), Mey 2020 (best practices for FEP), Cournia 2020 (relative binding free energy review), Lipinski 1997 (Rule of 5), Veber 2002 (drug-likeness rules), Hopkins 2004 (ligand efficiency).",
    "secondary": "RMSE_log10_Kd"
  },
  "physics_fingerprint": {
    "L_DAG": 7.0,
    "carrier": "atomic_potential",
    "difficulty_delta": 5,
    "domain": "Computational Chemistry",
    "integration_axis": "ensemble",
    "noise_model": "ensemble_variance",
    "primitives": [
      "L.molecular_topology",
      "L.dft_charge_calculation",
      "L.force_field_parameterization",
      "L.molecular_dynamics",
      "L.fep_thermodynamic_cycle",
      "L.binding_free_energy",
      "L.affinity_threshold_classifier",
      "int.ensemble"
    ],
    "problem_class": "nonlinear_inverse_with_categorical_readout",
    "sensing_mechanism": "fep_with_affinity_threshold",
    "solution_space": "1D_affinity_class",
    "sub_domain": "Quantum-chemistry binding-energy estimation with affinity-class categorical readout",
    "title": "Drug-Target Binding Affinity Classification (PWDR)"
  },
  "size_tiers": {
    "allowed_forward_operators": [
      "fep_affinity_pwdr_forward",
      "ti_affinity_pwdr_forward",
      "mmpbsa_affinity_pwdr_forward",
      "dft_corrected_docking_pwdr_forward"
    ],
    "allowed_omega_dimensions": [
      "N_atoms_drug",
      "N_atoms_target",
      "simulation_time_ns",
      "force_field",
      "water_model",
      "temperature_K",
      "salt_concentration_M",
      "force_field_uncertainty",
      "sampling_convergence_error",
      "water_model_uncertainty",
      "protein_flexibility_truncation",
      "drug_protonation_state",
      "conformational_search_incompleteness"
    ],
    "allowed_problem_classes": [
      "drug_target_affinity_pwdr",
      "drug_likeness_pwdr",
      "selectivity_pwdr",
      "fragment_screening_pwdr"
    ],
    "center_spec": {
      "epsilon_fn_center": "0.70_accuracy",
      "forward_operator": "fep_affinity_pwdr_forward",
      "input_format": "drug_target_complex_with_affinity_label",
      "omega": {
        "N_atoms_drug": 50,
        "N_atoms_target": 5000,
        "conformational_search_incompleteness": 0.0,
        "drug_protonation_state": 0.0,
        "force_field": "AMBER_FF14SB",
        "force_field_uncertainty": 0.0,
        "protein_flexibility_truncation": 0.0,
        "salt_concentration_M": 0.15,
        "sampling_convergence_error": 0.0,
        "simulation_time_ns": 100,
        "temperature_K": 298,
        "water_model": "TIP3P",
        "water_model_uncertainty": 0.0
      },
      "problem_class": "drug_target_affinity_pwdr"
    },
    "epsilon_bounds": {
      "categorical_accuracy": [
        0.3,
        0.95
      ]
    },
    "omega_bounds": {
      "N_atoms_drug": [
        10,
        200
      ],
      "N_atoms_target": [
        500,
        50000
      ],
      "simulation_time_ns": [
        1,
        10000
      ],
      "temperature_K": [
        273,
        320
      ]
    }
  },
  "staked_pwm": 0.0,
  "status": "testnet",
  "sub_domain": "Quantum-chemistry binding-energy estimation with affinity-class categorical readout",
  "title": "Drug-Target Binding Affinity Classification (PWDR)"
}

🎁

Earn PWM by promoting this to mainnet

• PWM emission on accept — your share of A(t) (1/16 modify · 3/16 new)
• 5% upstream royalty on every downstream L4 mining event, forever
• Your wallet is enrolled the moment the founder accepts

🚀 Go to submit ↑

How: use the “Contribute & earn PWM” panel at the top — either Submit without uploading (one click) or upload your files. Then the review runs and, on accept, it’s promoted to mainnet.