SARS-CoV-2 variants with spike (S)-protein D614G mutations now predominate globally and increase infectivity by assembling more functional S protein into the virion. In this paper, I combine topology geometric methods for the generation of novel drug designs by using generalized k - nearest neighbors within a quantum computing chemical context targeting in a atomistic level the S proteins with aspartic acid (SD614) and glycine (SG614) at residue 614 protein apparatus. In this effort, I propose powerful enough computer - aided rational drug design strategies to achieve very high accuracy levels for the generation of AI - Quantum designed molecules of GisitorviffirnaTM, Roccustyrna_ gs1_TM, and Roccustyrna_fr1_TM ligands targeting the SARS - COV - 2 SPIKE D614G mutation by unifying Eigenvalue Statements into Shannon entropy quantities as composed on Tipping–Ogilvie driven Machine Learning potentials for nonzero Christoffel symbols. For this model, I find analytic black hole solutions relevant to address a vast variety of small molecule modeling problems essential to describe pharmacophore merging phenomena in the presence of chemical potentials among others at the locally AdS5 spacetime. A boundary solution in five-dimensional Chern-Simons supergravity is described in the form of a Quantum Circuit which can carry U(1) charge provided the spacetime torsion is non-vanishing. Thus, I analyze the most general configuration consistent with the local AdS5 generated D614G Binding Site isometries in Riemann-Cartan space. I also arrived at a new Zmatter derived finite ‐ dimensional state integral and a Schwarzschild (DFT) ℓneuron (ι) : = φ∘D∘r2∘S∘r102 /3[T] Ψ0⋮Ψ0Ψ0e [r] (F ∧ F ∧ F) (1o∑ ∑ ∑ ) improver for a Chern - Simons Topology and Euclidean symplectic ω = (i~)− 1/2 F (ab)J(ab) o1 ℓ T (a)J(a) oF T1 (dx/x) ∧ (dy/y) model by computing the analytically continued “holomorphic blocks” on an appropriate quantum Hilbert space H to put pharmacophoric elements back together.