mirror of
https://github.com/allaunthefox/SilverSight.git
synced 2026-07-31 01:25:21 +00:00
allaun
1794299a6c
Systematic native_decide → dec_trivial/rfl migration across all Lean modules to comply with AGENTS.md rule 5 (no native_decide unless only option): - CoreFormalism: BraidEigensolid, BraidField, ChentsovFinite, HachimojiBase, HachimojiBridging, HachimojiCodec, HachimojiLUT, HachimojiManifoldAxiom, Q16_16Numerics - BindingSite: BindingSiteCodec, BindingSiteEntropy, BindingSiteHachimoji - SilverSight: ProductSchema, ProductWireFormat, PolyFactorIdentity, Schema, WireFormat - PVGS_DQ_Bridge: all three files (native_decide->dec_trivial) - UniversalEncoding/ChiralitySpace Additional changes: - gemma4_mcp.py: upgraded to two-tier routing (local Gemma4 + FreeLLMAPI proxy) - ChentsovFinite: added traceability map and Chentsov (1972) citation - HachimojiBase: renamed Σ→Sig, Π→Pi to avoid non-ASCII issues - Import path fixes for Mathlib 4.30.0-rc2 compatibility - Doc updates: PURE_FORMULAS, SOS_CERTIFICATE, fundamental math derivations - Build log: 2026-06-26 session findings - BRKGLASS_NR_BRACKET_PROPOSAL: updated to REAL-DATA VALIDATED status - New docs: FOUNDATIONAL_GUIDANCE, PURE_EQUATION_MAP, CHENTSOV_FINITE_MATH, BREAKGLASS_FUSION_REVIEW_SPEC, COLD_REVIEWER_FORMULA - New python: phi pipeline (equation_dna_encoder, ast_parse, charclass, consistency, embed, output), nr_bracket_validation with receipt Build: lake build SilverSightRRC — passes on all committed modules. Excluded: HachimojiN8Bridge, HachimojiCharClass (missing CoreFormalism.HachimojiManifoldAxiom olean — WIP)
227 lines
14 KiB
Text
227 lines
14 KiB
Text
/-
|
||
BindingSite.BindingSiteEntropy — Information entropy for protein binding sites.
|
||
|
||
§1-§4: computable, Q16_16, no Float, no Real.
|
||
§5: noncomputable theorems using Real — legitimate math, not IO compute path.
|
||
fisher_implies_similar_druggability is BLOCKED on entropy_lipschitz axiom
|
||
(research-level Pinsker-type inequality; see inline documentation).
|
||
|
||
References:
|
||
- Yang, Yuan, Chou 2025 (Void-X): Eq. 3 (information entropy)
|
||
- Giani, Win, Conti 2025: quantum discrimination via PVGS
|
||
-/
|
||
import BindingSite.BindingSiteHachimoji
|
||
import Mathlib.Data.Real.Basic
|
||
import Mathlib.Topology.Basic
|
||
import Mathlib.Analysis.SpecialFunctions.Log.Basic
|
||
import Mathlib.Analysis.Complex.ExponentialBounds
|
||
|
||
namespace BindingSite
|
||
|
||
open SilverSight.FixedPoint
|
||
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- §1 Information entropy over a probability distribution (noncomputable/math)
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
|
||
/-- Shannon entropy of a probability distribution over 50 atom types.
|
||
Void-X Eq. 3: S_i = -∑_j p(a_j|context) log p(a_j|context).
|
||
Noncomputable: uses ℝ and Real.log; for math section only. -/
|
||
noncomputable def siteEntropy (p : AminoAcidDistribution) : ℝ :=
|
||
-∑ i : Fin 50, if p.val i > 0 then p.val i * Real.log (p.val i) else 0
|
||
|
||
/-- Maximum possible entropy for 50 states (uniform distribution).
|
||
S_max = log(50) ≈ 3.912. -/
|
||
noncomputable def maxEntropy50 : ℝ := Real.log 50
|
||
|
||
/-- Normalized entropy: S* = S / S_max ∈ [0, 1]. -/
|
||
noncomputable def normalizedEntropy (p : AminoAcidDistribution) : ℝ :=
|
||
siteEntropy p / maxEntropy50
|
||
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- §2 B-factor → entropy (computable, Q16_16)
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- Re-exported from BindingSiteTypes; provided here for namespace convenience.
|
||
|
||
/-- Compute average entropy for a residue from its B-factor and neighbors.
|
||
Uses the linear proxy entropy = clamp(avg_bFactor, 0, 100) / 100.
|
||
Monotone, deterministic, Q16_16. -/
|
||
def siteEntropyQ (bFactor : Nat) (neighborBFactors : List Nat) : Q16_16 :=
|
||
entropyFromBFactor bFactor neighborBFactors
|
||
|
||
/-- Entropy from sequence cluster membership.
|
||
Higher cluster diversity → higher entropy; higher conservation → lower entropy.
|
||
Q16_16 arithmetic: diversity in [0,1], conservation in [0,1]. -/
|
||
def entropyFromCluster (clusterSize : Nat) (sequenceIdentityQ : Q16_16) : Q16_16 :=
|
||
-- diversity = clusterSize / maxClusterSize, clamp to [0,1]
|
||
let maxCluster : Nat := 10000
|
||
let diversityQ := Q16_16.ofRawInt ((min clusterSize maxCluster : Int) * 65536 / (maxCluster : Int))
|
||
-- conservation term: (1 - sequenceIdentity)
|
||
let oneMinusConserv := Q16_16.sub Q16_16.one sequenceIdentityQ
|
||
Q16_16.mul diversityQ oneMinusConserv
|
||
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- §3 Binding site entropy profile (computable, Q16_16)
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
|
||
/-- Compute the full entropy profile of a binding site from raw PDB residue data.
|
||
Input: (residue_type, modification, b_factor_nat, neighbor_b_factors_nat)
|
||
Output: (AminoAcidToken × Q16_16 × BindingSiteState) list -/
|
||
def bindingSiteEntropyProfile
|
||
(residues : List (String × String × Nat × List Nat))
|
||
: List (AminoAcidToken × Q16_16 × BindingSiteState) :=
|
||
residues.map fun (resType, mod, bFactor, neighborBFs) =>
|
||
let token := residueToToken resType mod
|
||
let entropy := entropyFromBFactor bFactor neighborBFs
|
||
let state := entropyToHachimoji entropy false (mod == "ZN" || mod == "CA")
|
||
(token, entropy, state)
|
||
|
||
/-- Average entropy of a classified site profile (Q16_16). -/
|
||
def averageSiteEntropyQ (profile : List (AminoAcidToken × Q16_16 × BindingSiteState)) : Q16_16 :=
|
||
q16Mean (profile.map (·.2.1))
|
||
|
||
/-- Bindability score B* ∈ [0, 100] in Q16_16.
|
||
B* = 100 × (1 - (avgEntropy - globalMin) / (globalMax - globalMin)).
|
||
High B* ↔ low entropy relative to protein surface ↔ ordered pocket. -/
|
||
def bindabilityScore
|
||
(profile : List (AminoAcidToken × Q16_16 × BindingSiteState))
|
||
(globalMin globalMax : Q16_16)
|
||
: Q16_16 :=
|
||
let avg := averageSiteEntropyQ profile
|
||
let range := Q16_16.sub globalMax globalMin
|
||
if range.val ≤ 0 then Q16_16.ofNat 50 -- degenerate: return mid-score
|
||
else
|
||
let normalized := Q16_16.div (Q16_16.sub avg globalMin) range
|
||
Q16_16.mul (Q16_16.ofNat 100) (Q16_16.sub Q16_16.one normalized)
|
||
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- §4 Sidon address from entropy profile (computable, Q16_16/Nat)
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
|
||
/-- Map a BindingSiteState to its Sidon index ∈ {0,…,7}. -/
|
||
def stateToSidonIdx : BindingSiteState → Nat
|
||
| .Phi => 0 | .Lambda => 1 | .Rho => 2 | .Kappa => 3
|
||
| .Omega => 4 | .Sigma => 5 | .Pi => 6 | .Zeta => 7
|
||
|
||
/-- Compute the Sidon address of a binding site from its entropy profile.
|
||
The 8 dominant entropy values map to Sidon powers {2⁰,…,2⁷},
|
||
weighted by entropy magnitude (clamped to [0,16]). -/
|
||
def entropyToSidonAddress
|
||
(profile : List (AminoAcidToken × Q16_16 × BindingSiteState))
|
||
: List Nat :=
|
||
profile.filterMap fun (_, entropy, state) =>
|
||
let idx := stateToSidonIdx state
|
||
-- entropy.val ∈ [0, 65536]; scale to [0, 16]
|
||
let scale := (entropy.val * 16 / 65536).toNat
|
||
some (Nat.pow 2 idx * scale)
|
||
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
-- §5 Fisher metric on binding site manifold (noncomputable math)
|
||
-- ═══════════════════════════════════════════════════════════════════════════
|
||
|
||
/-- Approximate Fisher-Rao distance via Bhattacharyya coefficient.
|
||
d_FR(p,q) ≈ sqrt(2 * log(1 / Σ_i sqrt(p_i * q_i))).
|
||
Noncomputable: uses Real arithmetic. -/
|
||
noncomputable def fisherRaoApprox (p q : AminoAcidDistribution) : ℝ :=
|
||
Real.sqrt (2 * Real.log (1 / ∑ i : Fin 50, Real.sqrt (p.val i * q.val i)))
|
||
|
||
/-- The binding site manifold: probability distributions over residue tokens
|
||
with the Fisher metric. Geodesics are evolutionarily optimal paths. -/
|
||
structure BindingSiteManifold where
|
||
distribution : AminoAcidDistribution
|
||
metric : Fin 50 → Fin 50 → ℝ := fisherMetric50 distribution
|
||
entropy : ℝ := siteEntropy distribution
|
||
|
||
-- ─────────────────────────────────────────────────────────────────────────
|
||
-- §5.1 Entropy Lipschitz axiom (research-level; unblocks §5.2)
|
||
-- ─────────────────────────────────────────────────────────────────────────
|
||
|
||
/-- Shannon entropy is Lipschitz w.r.t. Fisher-Rao distance, constant L = sqrt(2·log 50).
|
||
Pinsker-type inequality; research-level analytical result.
|
||
Informally: nearby distributions on the statistical manifold have nearby entropies. -/
|
||
axiom entropy_lipschitz (p q : AminoAcidDistribution) :
|
||
|siteEntropy p - siteEntropy q| ≤ Real.sqrt (2 * maxEntropy50) * fisherRaoApprox p q
|
||
|
||
-- ─────────────────────────────────────────────────────────────────────────
|
||
-- §5.2 Classification stability theorem
|
||
-- ─────────────────────────────────────────────────────────────────────────
|
||
|
||
/-- Nearby binding sites (Fisher-Rao distance < 0.1) have compatible druggability.
|
||
|
||
Uses NORMALIZED entropy N = S/S_max ∈ [0,1] so Q16_16-derived thresholds apply:
|
||
T₁ = 39321/65536 ≈ 0.600 (druggable-pocket boundary)
|
||
T₂ = 26214/65536 ≈ 0.400 (moderate-entropy floor)
|
||
|
||
Proof sketch:
|
||
1. log(50) > 2 (since exp(2) < 9 < 50)
|
||
2. sqrt(2/M) < 1 (since M > 2)
|
||
3. |N(p) - N(q)| ≤ sqrt(2/M)·d_FR < 1·0.1 = 0.1
|
||
4. threshold gap T₁ - T₂ = 13107/65536 ≈ 0.200 > 0.1
|
||
5. If sites straddle T₁, the lower one is still > T₁ - 0.1 > T₂ -/
|
||
theorem fisher_implies_similar_druggability (p q : AminoAcidDistribution)
|
||
(h : fisherRaoApprox p q < 0.1)
|
||
: let s1 := if normalizedEntropy p ≥ 39321 / 65536 then true else false
|
||
let s2 := if normalizedEntropy q ≥ 39321 / 65536 then true else false
|
||
s1 = s2 ∨ (normalizedEntropy p > 26214 / 65536 ∧ normalizedEntropy q > 26214 / 65536) := by
|
||
-- 1. log(50) > 2 ← exp(2) < 9 < 50
|
||
have hM2 : (2 : ℝ) < maxEntropy50 := by
|
||
show (2 : ℝ) < Real.log 50
|
||
have h1 : Real.exp 1 < 3 := Real.exp_one_lt_three
|
||
have h2 : Real.exp 2 = Real.exp 1 * Real.exp 1 := by
|
||
rw [show (2 : ℝ) = 1 + 1 from by norm_num, Real.exp_add]
|
||
have hexp2 : Real.exp 2 < 50 := by nlinarith [Real.exp_pos (1 : ℝ)]
|
||
calc (2 : ℝ) = Real.log (Real.exp 2) := (Real.log_exp 2).symm
|
||
_ < Real.log 50 := Real.log_lt_log (Real.exp_pos 2) hexp2
|
||
have hM : (0 : ℝ) < maxEntropy50 := by linarith
|
||
-- 2. sqrt(2·M) ≤ M ← 2·M ≤ M² ← M ≥ 2
|
||
have hsqrt_le : Real.sqrt (2 * maxEntropy50) ≤ maxEntropy50 := by
|
||
calc Real.sqrt (2 * maxEntropy50)
|
||
≤ Real.sqrt (maxEntropy50 ^ 2) := Real.sqrt_le_sqrt (by nlinarith)
|
||
_ = maxEntropy50 := Real.sqrt_sq hM.le
|
||
-- 3. |N(p) - N(q)| < 1/10
|
||
have hNL := entropy_lipschitz p q
|
||
have hbound : |siteEntropy p - siteEntropy q| < 1 / 10 * maxEntropy50 :=
|
||
calc |siteEntropy p - siteEntropy q|
|
||
≤ Real.sqrt (2 * maxEntropy50) * fisherRaoApprox p q := hNL
|
||
_ ≤ maxEntropy50 * fisherRaoApprox p q :=
|
||
mul_le_mul_of_nonneg_right hsqrt_le (Real.sqrt_nonneg _)
|
||
_ < maxEntropy50 * (1 / 10) := mul_lt_mul_of_pos_left (by linarith) hM
|
||
_ = 1 / 10 * maxEntropy50 := by ring
|
||
have hNdiff : |normalizedEntropy p - normalizedEntropy q| < 1 / 10 := by
|
||
have heq : normalizedEntropy p - normalizedEntropy q =
|
||
(siteEntropy p - siteEntropy q) / maxEntropy50 := by
|
||
simp [normalizedEntropy, sub_div]
|
||
-- |N|·M = |S| (by dividing), then nlinarith from |S| < (1/10)·M
|
||
have hmul : |normalizedEntropy p - normalizedEntropy q| * maxEntropy50 =
|
||
|siteEntropy p - siteEntropy q| := by
|
||
rw [heq, abs_div, abs_of_pos hM]; field_simp [hM.ne']
|
||
nlinarith [abs_nonneg (normalizedEntropy p - normalizedEntropy q)]
|
||
-- 4. Case analysis
|
||
show (if normalizedEntropy p ≥ 39321 / 65536 then true else false) =
|
||
(if normalizedEntropy q ≥ 39321 / 65536 then true else false) ∨
|
||
(normalizedEntropy p > 26214 / 65536 ∧ normalizedEntropy q > 26214 / 65536)
|
||
split_ifs with h1 h2
|
||
· left; rfl
|
||
· -- p ≥ T₁, q < T₁ → N(q) > N(p) - 0.1 ≥ T₁ - 0.1 > T₂
|
||
right
|
||
have h2' : normalizedEntropy q < 39321 / 65536 := not_le.mp h2
|
||
have hnn : (0 : ℝ) ≤ normalizedEntropy p - normalizedEntropy q := by linarith
|
||
have hd : normalizedEntropy p - normalizedEntropy q < 1 / 10 := by
|
||
rwa [abs_of_nonneg hnn] at hNdiff
|
||
constructor
|
||
· linarith [show (39321 : ℝ) / 65536 > 26214 / 65536 from by norm_num]
|
||
· linarith [show (39321 : ℝ) / 65536 - 1 / 10 > 26214 / 65536 from by norm_num]
|
||
· -- p < T₁, q ≥ T₁ → N(p) > N(q) - 0.1 ≥ T₁ - 0.1 > T₂
|
||
right
|
||
have h1' : normalizedEntropy p < 39321 / 65536 := not_le.mp h1
|
||
have hneg : normalizedEntropy p - normalizedEntropy q ≤ 0 := by linarith
|
||
have habsform : |normalizedEntropy p - normalizedEntropy q| =
|
||
normalizedEntropy q - normalizedEntropy p := by
|
||
rw [abs_of_nonpos hneg]; ring
|
||
have hd : normalizedEntropy q - normalizedEntropy p < 1 / 10 := habsform ▸ hNdiff
|
||
constructor
|
||
· linarith [show (39321 : ℝ) / 65536 - 1 / 10 > 26214 / 65536 from by norm_num]
|
||
· linarith [show (39321 : ℝ) / 65536 > 26214 / 65536 from by norm_num]
|
||
· left; rfl
|
||
|
||
end BindingSite
|