Establishment of Age Specific Reference Interval for Aminoacids and Acylcarnitine in Dried Blood Spot by Tandem Mass Spectrometry.

The Extended Screening for Inborn Errors of Metabolism is done for aminoacidopathies, fatty acid oxidation disorders and organic acid disorders. In a single dried blood spot, the tandem mass spectrometry is capable of measuring multiple analytes like amino acids, acylcarnitines, nucleosides, succinylacetone and lysophosphatidylcholines. This study was proposed to establish age specific reference internal for aminoacids and acylcartinitine in dried blood spot by tandem mass spectrometry. A total of 480 apparently healthy children were enrolled for the study and sub classified into four groups as follows: Group A: 0-1 month, Group B: 1 month-1 year, Group C: 1-5 year and Group D: 5-12 years each having 120 participants. Sample size were calculated as per CLSI approved guidelines. Tables 1 and 2 presents the age-specific percentile distribution of aminoacids and acylcarnitines established from healthy subjects as per rank-based method recommended by the IFCC and CLSI. Tables 3, 4 and 5 presents the cut-off values of primary and secondary marker/ratios for screening of aminoacidopathies, fatty acid oxidation disorders and organic acid disorders respectively. As a general principle, the interpretation of extended newborn screening results should be based on age specific cut-off established by the laboratory for primary analyte concentration and secondary analyte concentration/ ratios. This study was useful in establishing age specific cut-off values for various amino acids and acylcarnitines in South Indian population. [Table: see text] [Table: see text] [Table: see text] [Table: see text] [Table: see text].

Reformulation of All ONIOM-Type Molecular Fragmentation Approaches and Many-Body Theories Using Graph-Theory-Based Projection Operators: Applications to Dynamics, Molecular Potential Surfaces, Machine Learning, and Quantum Computing.

We present a graph-theory-based reformulation of all ONIOM-based molecular fragmentation methods. We discuss applications to (a) accurate post-Hartree-Fock AIMD that can be conducted at DFT cost for medium-sized systems, (b) hybrid DFT condensed-phase studies at the cost of pure density functionals, (c) reduced cost on-the-fly large basis gas-phase AIMD and condensed-phase studies, (d) post-Hartree-Fock-level potential surfaces at DFT cost to obtain quantum nuclear effects, and (e) novel transfer machine learning protocols derived from these measures. Additionally, in previous work, the unifying strategy discussed here has been used to construct new quantum computing algorithms. Thus, we conclude that this reformulation is robust and accurate.

Human navicular bone: a morphometric and morphological evaluation.

BACKGROUND: The composition of navicular joint complex is crucial to perform surgical interventions for multiple pathological foot aetiologies. The data on human navicular bone and its facets from Indian population remain scarce in literature. AIMS AND OBJECTIVES: To evaluate the morphometry and morphology of navicular bone. METHODOLOGY: A total of 77 (right: 40; left: 37) dried human navicular bones were used. The collected data were entered and analysed in SPSS software. RESULTS: The anteroposterior diameter of navicular bone on right side was 15.19 mm (13.92, 16.77) and on left side was 15.87 mm (13.83, 17.27). The transverse diameter on right and left sides were 34.21 mm (31.74, 36.6) and 33.59 mm (30.23, 35.43), respectively. The vertical diameter measured on the right was 22.31 mm (21.19, 23.94) and on left 22.53 mm (20.8, 24.24). Morphometric evaluation showed no significant difference between right and left navicular bones. The commonest shape for posterior facet was quadrilateral, on the right (62.5%) and left (40.5%). The most common shape of anterior facet for medial cuneiform is quadrilateral, on the right (85%) and left (89.1%). For intermediate cuneiform, triangular facet was common on the right side (72.5%) and on the left (59.5%). The lateral cuneiform facet was bean shaped on right side (72.5%) and quadrilateral on the left side (32.5%). There was a significant difference in shape distribution between right and left (P < 0.05). The median length of the groove for tibialis posterior tendon was 18.01 mm and 16.19 mm on right and left side, respectively. Cuboid facet was observed in 28 (70%) and 26 (65.9%) navicular bones on right and left sides, respectively. CONCLUSION: There is no significant difference between right and left bones with regards to morphometric parameters. Morphological evaluation revealed significant difference in the distribution of shape between right and left bones.

Capturing Weak Interactions in Surface Adsorbate Systems at Coupled Cluster Accuracy: A Graph-Theoretic Molecular Fragmentation Approach Improved through Machine Learning.

The accurate and efficient study of the interactions of organic matter with the surface of water is critical to a wide range of applications. For example, environmental studies have found that acidic polyfluorinated alkyl substances, especially perfluorooctanoic acid (PFOA), have spread throughout the environment and bioaccumulate into human populations residing near contaminated watersheds, leading to many systemic maladies. Thus, the study of the interactions of PFOA with water surfaces became important for the mitigation of their activity as pollutants and threats to public health. However, theoretical study of the interactions of such organic adsorbates on the surface of water, and their bulk concerted properties, often necessitates the use of ab initio methods to properly incorporate the long-range electronic properties that govern these extended systems. Notable theoretical treatments of "on-water" reactions thus far have employed hybrid DFT and semilocal DFT, but the interactions involved are weak interactions that may be best described using post-Hartree-Fock theory. Here, we aim to demonstrate the utility of a graph-theoretic approach to molecular fragmentation that accurately captures the critical "weak" interactions while maintaining an efficient ab initio treatment of the long-range periodic interactions that underpin the physics of extended systems. We apply this graph-theoretical treatment to study PFOA on the surface of water as a model system for the study of weak interactions seen in the wide range of surface interactions and reactions. The approach divides a system into a set of vertices, that are then connected through edges, faces, and higher order graph theoretic objects known as simplexes, to represent a collection of locally interacting subsystems. These subsystems are then used to construct ab initio molecular dynamics simulations and for computing multidimensional potential energy surfaces. To further improve the computational efficiency of our graph theoretic fragmentation method, we use a recently developed transfer learning protocol to construct the full system potential energy from a family of neural networks each designed to accurately model the behavior of individual simplexes. We use a unique multidimensional clustering algorithm, based on the k-means clustering methodology, to define our training space for each separate simplex. These models are used to extrapolate the energies for molecular dynamics trajectories at PFOA water interfaces, at less than one-tenth the cost as compared to a regular molecular fragmentation-based dynamics calculation with excellent agreement with couple cluster level of full system potential energies.

Graph-|Q⟩⟨C|: A Quantum Algorithm with Reduced Quantum Circuit Depth for Electronic Structure.

The accurate determination of chemical properties is known to have a critical impact on multiple fundamental chemical problems but is deeply hindered by the steep algebraic scaling of electron correlation calculations and the exponential scaling of quantum nuclear dynamics. With the advent of new quantum computing hardware and associated developments in creating new paradigms for quantum software, this avenue has been recognized as perhaps one way to address exponentially complex challenges in quantum chemistry and molecular dynamics. In this paper, we discuss a new approach to drastically reduce the quantum circuit depth (by several orders of magnitude) and help improve the accuracy in the quantum computation of electron correlation energies for large molecular systems. The method is derived from a graph-theoretic approach to molecular fragmentation and enables us to create a family of projection operators that decompose quantum circuits into separate unitary processes. Some of these processes can be treated on quantum hardware and others on classical hardware in a completely asynchronous and parallel fashion. Numerical benchmarks are provided through the computation of unitary coupled-cluster singles and doubles (UCCSD) energies for medium-sized protonated and neutral water clusters using the new quantum algorithms presented here.

Quantum Computing with Dartboards.

We present a physically appealing and elegant picture for quantum computing, using rules constructed for a game of darts. A dartboard is used to represent the state space in quantum mechanics, and the act of throwing the dart is shown to have close similarities to the concept of measurement or collapse of the wave function in quantum mechanics. The analogy is constructed in arbitrary dimensional spaces, that is, using arbitrary dimensional dartboards, and for such arbitrary spaces this also provides us a "visual" description of uncertainty. Finally, connections between qubits and quantum computing algorithms are also made, opening the possibility to construct analogies between quantum algorithms and coupled dart throws.

Synthesis of Hidden Subgroup Quantum Algorithms and Quantum Chemical Dynamics.

We describe a general formalism for quantum dynamics and show how this formalism subsumes several quantum algorithms, including the Deutsch, Deutsch-Jozsa, Bernstein-Vazirani, Simon, and Shor algorithms as well as the conventional approach to quantum dynamics based on tensor networks. The common framework exposes similarities among quantum algorithms and natural quantum phenomena: we illustrate this connection by showing how the correlated behavior of protons in water wire systems that are common in many biological and materials systems parallels the structure of Shor's algorithm.

Computer-Aided Multi-Epitope Based Vaccine Design Against Monkeypox Virus Surface Protein A30L: An Immunoinformatics Approach.

Monkeypox, a viral zoonotic disease resembling smallpox, has emerged as a significant national epidemic primarily in Africa. Nevertheless, the recent global dissemination of this pathogen has engendered apprehension regarding its capacity to metamorphose into a sweeping pandemic. To effectively combat this menace, a multi-epitope vaccine has been meticulously engineered with the specific aim of targeting the cell envelope protein of Monkeypox virus (MPXV), thereby stimulating a potent immunological response while mitigating untoward effects. This new vaccine uses T-cell and B-cell epitopes from a highly antigenic, non-allergenic, non-toxic, conserved, and non-homologous A30L protein to provide protection against the virus. In order to ascertain the vaccine design with the utmost efficacy, protein-protein docking methodologies were employed to anticipate the intricate interactions with Toll-like receptors (TLR) 2, 3, 4, 6, and 8. This meticulous approach led the researchers to discern an optimal vaccine architecture, bolstered by affirmative prognostications derived from both molecular dynamics (MD) simulations and immune simulations. The current research findings indicate that the peptides ATHAAFEYSK, FFIVVATAAV, and MNSLSIFFV exhibited antigenic properties and were determined to be non-allergenic and non-toxic. Through the utilization of codon optimization and in-silico cloning techniques, our investigation revealed that the prospective vaccine exhibited a remarkable expression level within Escherichia coli. Moreover, upon conducting immune simulations, we observed the induction of a robust immune response characterized by elevated levels of both B-cell and T-cell mediated immunity. Moreover, as the initial prediction with in-silico techniques has yielded promising results these epitope-based vaccines can be recommended to in vitro and in silico studies to validate their immunogenic properties.

Quantum Computation of Hydrogen Bond Dynamics and Vibrational Spectra.

Calculating observable properties of chemical systems is often classically intractable and widely viewed as a promising application of quantum information processing. Here, we introduce a new framework for solving generic quantum chemical dynamics problems using quantum logic. We experimentally demonstrate a proof-of-principle instance of our method using the QSCOUT ion-trap quantum computer, where we experimentally drive the ion-trap system to emulate the quantum wavepacket dynamics corresponding to the shared-proton within an anharmonic hydrogen bonded system. Following the experimental creation and propagation of the shared-proton wavepacket on the ion-trap, we extract measurement observables such as its time-dependent spatial projection and its characteristic vibrational frequencies to spectroscopic accuracy (3.3 cm-1 wavenumbers, corresponding to >99.9% fidelity). Our approach introduces a new paradigm for studying the chemical dynamics and vibrational spectra of molecules and opens the possibility to describe the behavior of complex molecular processes with unprecedented accuracy.

Analogy between Boltzmann Machines and Feynman Path Integrals.

Machine learning has had a significant impact on multiple areas of science, technology, health, and computer and information sciences. Through the advent of quantum computing, quantum machine learning has developed as a new and important avenue for the study of complex learning problems. Yet there is substantial debate and uncertainty in regard to the foundations of machine learning. Here, we provide a detailed exposition of the mathematical connections between a general machine learning approach called Boltzmann machines and Feynman's description of quantum and statistical mechanics. In Feynman's description, quantum phenomena arise from an elegant, weighted sum over (or superposition of) paths. Our analysis shows that Boltzmann machines and neural networks have a similar mathematical structure. This allows the interpretation that the hidden layers in Boltzmann machines and neural networks are discrete versions of path elements and allows a path integral interpretation of machine learning similar to that in quantum and statistical mechanics. Since Feynman paths are a natural and elegant depiction of interference phenomena and the superposition principle germane to quantum mechanics, this analysis allows us to interpret the goal in machine learning as finding an appropriate combination of paths, and accumulated path-weights, through a network, that cumulatively captures the correct properties of an x-to-y map for a given mathematical problem. We are forced to conclude that neural networks are naturally related to Feynman path-integrals and hence may present one avenue to be considered as quantum problems. Consequently, we provide general quantum circuit models applicable to both Boltzmann machines and Feynman path integrals.

The vaccine mandates judgment: Some reflections.

This paper scrutinises the Supreme Court Judgment of May 2, 2022, in a vaccine mandate-related petition. The Hon'ble Court's Order reasserts the primacy of right to privacy and Articles 14 and 21 of the Constitution of India. However, in the interest of protection of communitarian health, the Court felt that the Government is entitled to regulate issues of public health concern by imposing certain limitations on individual rights, which are open to scrutiny by constitutional Courts. However, such mandatory vaccination directives with preconditions cannot invade an individual's right to personal autonomy and right to access means of livelihood, and must meet the threefold criteria laid down in K.S.Puttaswamy, a landmark judgment of 2017. This paper examines the validity of the arguments adopted in the Order and suggests certain infirmities therein. Nevertheless, the Order is a balancing act, and worth celebrating. The paper concludes, as a cup that is "a quarter full", as a victory for human rights and as a safeguard against unreasonableness and arbitrariness in medico-scientific decision-making that takes the citizen's compliance and consent for granted. If the State runs amok by way of mandatory health directives, this Order may come to the rescue of the hapless citizen.

Intrathecal pain pumps in pain relief.

Chronic pain is a significant global health issue, described as a bio-psychosocial phenomenon that hampers the integration of body, mind, and social functions. To relieve chronic intractable pain, intrathecal drug-delivery devices (IDDDs) are the last resort after conventional treatment options have been exhausted. This article outlines the indications, pharmacological agents, types, techniques, preparation of the patient, and complications of IDDDs for the management of challenging chronic pain (non-neoplastic and cancer-related pain) conditions in patients who have not responded well to a commonly used conventional line of treatment.

Pragmatic Treatment Strategies for Polyaromatic Hydrocarbon Remediation and Anti-biofouling from Surfaces Using Nano-enzymes: a Review.

In this review, two important environmental pollutants have been considered for its potential remediation using microbial-derived nano-enzymes. Firstly, polyaromatic hydrocarbons (PAHs) are one of the major industrial contaminants in the environment due to their ubiquitous occurrence, toxicity, and proclivity for bioaccumulation. Secondly, biofouling due to biofilm-forming organisms that impact tremendous economic and environmental consequences in many industries, especially marine vessels where it causes an increase in hydrodynamic drag, which results in a loss of ship speed at constant power or a power increase to maintain the same speed with higher fuel consumption and emissions into the atmosphere, particularly Green House Gases (GHGs). Among the remediation strategies, biological routes are found to be promising, efficient, and sustainable. Natural ligninolytic enzymes such as MnP, LiP, laccase, peroxidases, and polysaccharide and protein degradative enzymes are found to be highly efficient for PAH degradation and antifouling respectively. However, large-scale usage of these enzymes is difficult due to various reasons like their poor stability, adaptation, and high-cost production of these enzymes. In recent years, the use of nanoparticles, particularly nano-enzymes, is found to be an innovative and synergistic approach to detoxify contaminated areas with concomitant maintenance of enzyme stability.

Synchronous COD removal and nitrogen recovery from high concentrated pharmaceutical wastewater by an integrated chemo-biocatalytic reactor systems.

Present report, an investigation of highly concentrated and low bio-degradable pharmaceutical wastewater (HCPWW) treatment; simultaneously ammoniacal nitrogen recovery for struvite fertilizer. The use of multiple solvents and many formulation processes in HCPWW, resulting highly refractory chemicals. Here, in this study focused on evaluation of chemo-biocatalysts for the removal of refractory organics, nitrogen recovery from HCPWW. The initial organics, and nitrogen content in HCPWW was 20,753 ± 4606 mg/L; BOD, 6550 ± 1500 mg/L and NH4+-N, 1057.9 ± 185.8 mg/L. Initially, the biodegradability (BOD5: COD ratio from 0.32 to 0.45) of HCPWW, which was improved by heterogeneous Fenton oxidation (HFO) processes, and porous carbon (PCC, 30 g/L), along with FeSO4.7H2O, 200 mg/L and H2O2 (30% v/v), 0.4 ml/L were used as a catalyst in a weakly acidic medium. For the biocatalytic processes, the microbial culture cultivated from sewage and incorporated into a Fluidized Immobilized Carbon Catalytic Oxidation reactor (FICCO), and dominant species are Pseudomonas Putida sp., Pseudomonas Kilionesis sp., and Pseudomonas Japonica sp., which is identified by using 16 S rDNA sequencing analysis. The COD and BOD5 removal efficiency of 65-93% and 70-82%, and follow the pseudo-second-order kinetic model with the rate constants of 1.0 × 10-4 L COD-1 h-1, 1.5 × 10-3 L COD-1 h-1 and 3.0 × 10-3 L COD-1 h-1 in the HFO-FICCO-CAACO catalytic processes. The optimized hydraulic retention time (HRT) of FICCO reactor was 24 h, and 1 h for the Chemo-Autotrophic Activated Carbon Oxidation (CAACO) reactor for maximum organics removal. MAP (Magnesium Ammonium Phosphate precipitation) process showed 90% of NH4+-N elimination and recovered it as a struvite fertilizer at an optimum molar ratio of 1:1.3:1.3 (NH4+-N: Na2HPO4.2H2O: MgO). FT-IR, UV-visible, and UV-fluorescence data confirm the effective elimination of organics. Hence, this integrated treatment system is appropriate for the management of pharmaceutical wastewater especially elimination of complex organic molecules and the recovery of nitrogen in the wastewater.

Development of AI classification model for angiosome-wise interpretive substantiation of plantar feet thermal asymmetry in type 2 diabetic subjects using infrared thermograms.

Diabetic Foot Syndrome (DFS) is the prime impetus for most of the lower extremity complications among the diabetic subjects. DFS is characterized by aberrant variations in plantar foot temperature distribution while healthy subjects exhibit a symmetric thermal pattern between the contralateral and ipsilateral plantar feet. Thus, "asymmetry analysis" of foot thermal distribution is contributory in assessment of overall foot health of diabetic subjects. The study, aims to classify symmetric and asymmetric foot regions angiosome-wise, by comparing minimal number of color image features - color moments and Dissimilarity Index. Further, the asymmetric foot regions are assessed for identifying the hotspots within such angiosomes of the patients that characterize the possibility of onset of diabetic foot ulcer. The color feature based machine learning model developed, achieved an accuracy of 98% for a 10-fold cross validation, test accuracy of 96.07% and 0.96 F1-score thereby convincing that the chosen features are amplest and conducive in the asymmetry analysis. The developed model was validated for generalization by testing on a public benchmark dataset, in which the model achieved 92.5% accuracy and 0.91 F1 score.

Graph-Theoretic Molecular Fragmentation for Potential Surfaces Leads Naturally to a Tensor Network Form and Allows Accurate and Efficient Quantum Nuclear Dynamics.

Molecular fragmentation methods have revolutionized quantum chemistry. Here, we use a graph-theoretically generated molecular fragmentation method, to obtain accurate and efficient representations for multidimensional potential energy surfaces and the quantum time-evolution operator, which plays a critical role in quantum chemical dynamics. In doing so, we find that the graph-theoretic fragmentation approach naturally reduces the potential portion of the time-evolution operator into a tensor network that contains a stream of coupled lower-dimensional propagation steps to potentially achieve quantum dynamics with reduced complexity. Furthermore, the fragmentation approach used here has previously been shown to allow accurate and efficient computation of post-Hartree-Fock electronic potential energy surfaces, which in many cases has been shown to be at density functional theory cost. Thus, by combining the advantages of molecular fragmentation with the tensor network formalism, the approach yields an on-the-fly quantum dynamics scheme where both the electronic potential calculation and nuclear propagation portion are enormously simplified through a single stroke. The method is demonstrated by computing approximations to the propagator and to potential surfaces for a set of coupled nuclear dimensions within a protonated water wire problem exhibiting the Grotthuss mechanism of proton transport. In all cases, our approach has been shown to reduce the complexity of representing the quantum propagator, and by extension action of the propagator on an initial wavepacket, by several orders, with minimal loss in accuracy.

A review on biological methodologies in municipal solid waste management and landfilling: Resource and energy recovery.

Rapid industrialization and urbanization growth combined with increased population has aggravated the issue of municipal solid waste generation. MSW has been accounted for contributing tremendously to the improvement of sustainable sources and safe environment. Biological processing of MSW followed by biogas and biomethane generation is one of the innumerable sustainable energy source choices. In the treatment of MSW, biological treatment has some attractive benefits such as reduced volume in the waste material, adjustment of the waste, economic aspects, obliteration of microorganisms in the waste material, and creation of biogas for energy use. In the anaerobic process the utilizable product is energy recovery. The current review discusses about the system for approaching conversion of MSW to energy and waste derived circular bioeconomy to address the zero waste society and sustainable development goals. Biological treatment process adopted with aerobic and anaerobic processes. In the aerobic process the utilizable product is compost. These techniques are used to convert MSW into a reasonable hotspot for resource and energy recovery that produces biogas, biofuel and bioelectricity and different results in without risk and harmless to the ecosystem. This review examines the suitability of biological treatment technologies for energy production, giving modern data about it. It likewise covers difficulties and points of view in this field of exploration.

Effect of Ball-Milled Steatite Powder on the Latent Heat Energy Storage Properties and Heat Charging-Discharging Periods of Paraffin Wax as Phase Change Material.

Phase change materials (PCMs) serve as an advantage in thermal energy storage systems utilizing the available sensible and latent heat. The PCMs absorb the thermal energy during the charging process and release it into the environment during the discharging process. Steatite is low cost and eco-friendly, with a thermal stability up to 1000 °C, and it is abundantly available in nature. This study investigates the steatite-paraffin wax-based PCM and the effect on the cyclic loads using a horizontal triplex-tube latent heat energy storage system. The thermal conductivity value of the milled steatite-based PCM composite was 7.7% higher than pure PCM. The PCM with the ball-milled steatite-fabricated composite exhibited better discharging characteristics, increasing the discharge time by 50% more than that of the pure paraffin wax. Moreover, the milled steatite-based PCM outperformed that incorporated with non-milled steatite with paraffin.

Hamiltonian Engineering with Multicolor Drives for Fast Entangling Gates and Quantum Crosstalk Cancellation.

Quantum computers built with superconducting artificial atoms already stretch the limits of their classical counterparts. While the lowest energy states of these artificial atoms serve as the qubit basis, the higher levels are responsible for both a host of attractive gate schemes as well as generating undesired interactions. In particular, when coupling these atoms to generate entanglement, the higher levels cause shifts in the computational levels that lead to unwanted ZZ quantum crosstalk. Here, we present a novel technique to manipulate the energy levels and mitigate this crosstalk with simultaneous off-resonant drives on coupled qubits. This breaks a fundamental deadlock between qubit-qubit coupling and crosstalk. In a fixed-frequency transmon architecture with strong coupling and crosstalk cancellation, additional cross-resonance drives enable a 90 ns CNOT with a gate error of (0.19±0.02)%, while a second set of off-resonant drives enables a novel CZ gate. Furthermore, we show a definitive improvement in circuit performance with crosstalk cancellation over seven qubits, demonstrating the scalability of the technique. This Letter paves the way for superconducting hardware with faster gates and greatly improved multiqubit circuit fidelities.

Graph Theoretic Molecular Fragmentation for Multidimensional Potential Energy Surfaces Yield an Adaptive and General Transfer Machine Learning Protocol.

Over a series of publications we have introduced a graph-theoretic description for molecular fragmentation. Here, a system is divided into a set of nodes, or vertices, that are then connected through edges, faces, and higher-order simplexes to represent a collection of spatially overlapping and locally interacting subsystems. Each such subsystem is treated at two levels of electronic structure theory, and the result is used to construct many-body expansions that are then embedded within an ONIOM-scheme. These expansions converge rapidly with many-body order (or graphical rank) of subsystems and have been previously used for ab initio molecular dynamics (AIMD) calculations and for computing multidimensional potential energy surfaces. Specifically, in all these cases we have shown that CCSD and MP2 level AIMD trajectories and potential surfaces may be obtained at density functional theory cost. The approach has been demonstrated for gas-phase studies, for condensed phase electronic structure, and also for basis set extrapolation-based AIMD. Recently, this approach has also been used to derive new quantum-computing algorithms that enormously reduce the quantum circuit depth in a circuit-based computation of correlated electronic structure. In this publication, we introduce (a) a family of neural networks that act in parallel to represent, efficiently, the post-Hartree-Fock electronic structure energy contributions for all simplexes (fragments), and (b) a new k-means-based tessellation strategy to glean training data for high-dimensional molecular spaces and minimize the extent of training needed to construct this family of neural networks. The approach is particularly useful when coupled cluster accuracy is desired and when fragment sizes grow in order to capture nonlocal interactions accurately. The unique multidimensional k-means tessellation/clustering algorithm used to determine our training data for all fragments is shown to be extremely efficient and reduces the needed training to only 10% of data for all fragments to obtain accurate neural networks for each fragment. These fully connected dense neural networks are then used to extrapolate the potential energy surface for all molecular fragments, and these are then combined as per our graph-theoretic procedure to transfer the learning process to a full system energy for the entire AIMD trajectory at less than one-tenth the cost as compared to a regular fragmentation-based AIMD calculation.