Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions.

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

Dirigent isoflavene-forming PsPTS2: 3D structure, stereochemical, and kinetic characterization comparison with pterocarpan-forming PsPTS1 homolog in pea.

Pea phytoalexins (-)-maackiain and (+)-pisatin have opposite C6a/C11a configurations, but biosynthetically how this occurs is unknown. Pea dirigent-protein (DP) PsPTS2 generates 7,2'-dihydroxy-4',5'-methylenedioxyisoflav-3-ene (DMDIF), and stereoselectivity toward four possible 7,2'-dihydroxy-4',5'-methylenedioxyisoflavan-4-ol (DMDI) stereoisomers was investigated. Stereoisomer configurations were determined using NMR spectroscopy, electronic circular dichroism, and molecular orbital analyses. PsPTS2 efficiently converted cis-(3R,4R)-DMDI into DMDIF 20-fold faster than the trans-(3R,4S)-isomer. The 4R-configured substrate's near ß-axial OH orientation significantly enhanced its leaving group abilities in generating A-ring mono-quinone methide (QM), whereas 4S-isomer's α-equatorial-OH was a poorer leaving group. Docking simulations indicated that the 4R-configured ß-axial OH was closest to Asp51, whereas 4S-isomer's α-equatorial OH was further away. Neither cis-(3S,4S)- nor trans-(3S,4R)-DMDIs were substrates, even with the former having C3/C4 stereochemistry as in (+)-pisatin. PsPTS2 used cis-(3R,4R)-7,2'-dihydroxy-4'-methoxyisoflavan-4-ol [cis-(3R,4R)-DMI] and C3/C4 stereoisomers to give 2',7-dihydroxy-4'-methoxyisoflav-3-ene (DMIF). DP homologs may exist in licorice (Glycyrrhiza pallidiflora) and tree legume Bolusanthus speciosus, as DMIF occurs in both species. PsPTS1 utilized cis-(3R,4R)-DMDI to give (-)-maackiain 2200-fold more efficiently than with cis-(3R,4R)-DMI to give (-)-medicarpin. PsPTS1 also slowly converted trans-(3S,4R)-DMDI into (+)-maackiain, reflecting the better 4R configured OH leaving group. PsPTS2 and PsPTS1 provisionally provide the means to enable differing C6a and C11a configurations in (+)-pisatin and (-)-maackiain, via identical DP-engendered mono-QM bound intermediate generation, which PsPTS2 either re-aromatizes to give DMDIF or PsPTS1 intramolecularly cyclizes to afford (-)-maackiain. Substrate docking simulations using PsPTS2 and PsPTS1 indicate cis-(3R,4R)-DMDI binds in the anti-configuration in PsPTS2 to afford DMDIF, and the syn-configuration in PsPTS1 to give maackiain.

Shaping Nanobodies and Intrabodies against Proteoforms.

Proteoforms expand genomic diversity and direct developmental processes. While high-resolution mass spectrometry has accelerated characterization of proteoforms, molecular techniques working to bind and disrupt the function of specific proteoforms have lagged behind. In this study, we worked to develop intrabodies capable of binding specific proteoforms. We employed a synthetic camelid nanobody library expressed in yeast to identify nanobody binders of different SARS-CoV-2 receptor binding domain (RBD) proteoforms. Importantly, employment of the positive and negative selection mechanisms inherent to the synthetic system allowed for amplification of nanobody-expressing yeast that bind to the original (Wuhan strain RBD) but not the E484 K (Beta variant) mutation. Nanobodies raised against specific RBD proteoforms were validated by yeast-2-hybrid analysis and sequence comparisons. These results provide a framework for development of nanobodies and intrabodies that target proteoforms.

The Superfund Research Program Analytics Portal: linking environmental chemical exposure to biological phenotypes.

The OSU/PNNL Superfund Research Program (SRP) represents a longstanding collaboration to quantify Polycyclic Aromatic Hydrocarbons (PAHs) at various superfund sites in the Pacific Northwest and assess their potential impact on human health. To link the chemical measurements to biological activity, we describe the use of the zebrafish as a high-throughput developmental toxicity model that provides quantitative measurements of the exposure to chemicals. Toward this end, we have linked over 150 PAHs found at Superfund sites to the effect of these same chemicals in zebrafish, creating a rich dataset that links environmental exposure to biological response. To quantify this response, we have implemented a dose-response modelling pipeline to calculate benchmark dose parameters which enable potency comparison across over 500 chemicals and 12 of the phenotypes measured in zebrafish. We provide a rich dataset for download and analysis as well as a web portal that provides public access to this dataset via an interactive web site designed to support exploration and re-use of these data by the scientific community at http://srp.pnnl.gov .

Graph identification of proteins in tomograms (GRIP-Tomo).

In this study, we present a method of pattern mining based on network theory that enables the identification of protein structures or complexes from synthetic volume densities, without the knowledge of predefined templates or human biases for refinement. We hypothesized that the topological connectivity of protein structures is invariant, and they are distinctive for the purpose of protein identification from distorted data presented in volume densities. Three-dimensional densities of a protein or a complex from simulated tomographic volumes were transformed into mathematical graphs as observables. We systematically introduced data distortion or defects such as missing fullness of data, the tumbling effect, and the missing wedge effect into the simulated volumes, and varied the distance cutoffs in pixels to capture the varying connectivity between the density cluster centroids in the presence of defects. A similarity score between the graphs from the simulated volumes and the graphs transformed from the physical protein structures in point data was calculated by comparing their network theory order parameters including node degrees, betweenness centrality, and graph densities. By capturing the essential topological features defining the heterogeneous morphologies of a network, we were able to accurately identify proteins and homo-multimeric complexes from 10 topologically distinctive samples without realistic noise added. Our approach empowers future developments of tomogram processing by providing pattern mining with interpretability, to enable the classification of single-domain protein native topologies as well as distinct single-domain proteins from multimeric complexes within noisy volumes.

CPUE standardization for southern bluefin tuna (Thunnus maccoyii) in the Korean tuna longline fishery, accounting for spatiotemporal variation in targeting through data exploration and clustering.

Accounting for spatial and temporal variation in targeting is a concern in many catch per unit effort (CPUE) standardization exercises. In this study we standardized southern bluefin tuna (Thunnus maccoyii, SBT) CPUE from the Korean tuna longline fishery (1996-2018) using generalized linear models (GLMs) with operational set by set data. Data were first explored to investigate the operational characteristics of Korean tuna longline vessels fishing for SBT, such as the spatial and temporal distributions of effort, and changes in the nominal catch rates among major species and species composition. Then we estimated SBT CPUE by area used for the stock assessment in the CCSBT (Commission for the Conservation of Southern Bluefin Tuna) and identified two separate areas in which Korean tuna longline vessels have targeted SBT and albacore tuna (T. alalunga), with targeting patterns varying spatially, seasonally and longer term. We applied two approaches, data selection and cluster analysis of species composition, and compared their ability to address concerns about the changing patterns of targeting through time. Explanatory variables for the GLM analyses were year, month, vessel identifier, fishing location (5° cell), number of hooks, moon phase, and cluster. GLM results for each area suggested that location, year, targeting, and month effects were the principal factors affecting the nominal CPUE. The standardized CPUEs for both areas decreased until the mid-2000s and have shown an increasing trend since that time.

A Comparative Multi-System Approach to Characterizing Bioactivity of Commonly Occurring Chemicals.

A 2019 retrospective study analyzed wristband personal samplers from fourteen different communities across three different continents for over 1530 organic chemicals. Investigators identified fourteen chemicals (G14) detected in over 50% of personal samplers. The G14 represent a group of chemicals that individuals are commonly exposed to, and are mainly associated with consumer products including plasticizers, fragrances, flame retardants, and pesticides. The high frequency of exposure to these chemicals raises questions of their potential adverse human health effects. Additionally, the possibility of exposure to mixtures of these chemicals is likely due to their co-occurrence; thus, the potential for mixtures to induce differential bioactivity warrants further investigation. This study describes a novel approach to broadly evaluate the hazards of personal chemical exposures by coupling data from personal sampling devices with high-throughput bioactivity screenings using in vitro and non-mammalian in vivo models. To account for species and sensitivity differences, screening was conducted using primary normal human bronchial epithelial (NHBE) cells and early life-stage zebrafish. Mixtures of the G14 and most potent G14 chemicals were created to assess potential mixture effects. Chemical bioactivity was dependent on the model system, with five and eleven chemicals deemed bioactive in NHBE and zebrafish, respectively, supporting the use of a multi-system approach for bioactivity testing and highlighting sensitivity differences between the models. In both NHBE and zebrafish, mixture effects were observed when screening mixtures of the most potent chemicals. Observations of BMC-based mixtures in NHBE (NHBE BMC Mix) and zebrafish (ZF BMC Mix) suggested antagonistic effects. In this study, consumer product-related chemicals were prioritized for bioactivity screening using personal exposure data. High-throughput high-content screening was utilized to assess the chemical bioactivity and mixture effects of the most potent chemicals.

Tunable Heteroassembly of a Plant Pseudoenzyme-Enzyme Complex.

Pseudoenzymes have emerged as key regulatory elements in all kingdoms of life despite being catalytically nonactive. Yet many factors defining why one protein is active while its homologue is inactive remain uncertain. For pseudoenzyme-enzyme pairs, the similarity of both subunits can often hinder conventional characterization approaches. In plants, a pseudoenzyme, PDX1.2, positively regulates vitamin B6 production by association with its active catalytic homologues such as PDX1.3 through an unknown assembly mechanism. Here we used an integrative experimental approach to learn that such pseudoenzyme-enzyme pair associations result in heterocomplexes of variable stoichiometry, which are unexpectedly tunable. We also present the atomic structure of the PDX1.2 pseudoenzyme as well as the population averaged PDX1.2-PDX1.3 pseudoenzyme-enzyme pair. Finally, we dissected hetero-dodecamers of each stoichiometry to understand the arrangement of monomers in the heterocomplexes and identified symmetry-imposed preferences in PDX1.2-PDX1.3 interactions. Our results provide a new model of pseudoenzyme-enzyme interactions and their native heterogeneity.

Shallow population structure of southern bluefin tuna, Thunnus maccoyii (Castelnau, 1872) between Indian and Atlantic Oceans inferred from mitochondrial DNA sequences.

Southern bluefin tuna (Thunnus maccoyii Castelnau, 1872) is distributed across most of the southern temperate ocean and migrates extensively between 30°S and 50°S. Since T. maccoyii has been continually and heavily exploited, it is necessary to investigate the genetic diversity, population structure and demographic history of T. maccoyii for effective management and conservation. Thirty-seven gonad tissues of T. maccoyii were sampled from two locations, which were in the eastern Indian Ocean and the eastern Atlantic Ocean, by scientific observers onboard Korean T. maccoyii longline vessels in 2015. We compared 1240-bp sequences of combined mitochondrial DNA (mtDNA) from the cytochrome c oxidase subunit I (COI, 504-bp) and control region (CR, 736-bp) sequences. The pairwise fixation index (F ST) and maximum-likelihood tree showed that two clades (A and B) were formed regardless of locations. Clade A occurred more commonly than clade B in both localities: the occurrence ratio of clade A was 69% in the Indian Ocean, and 79% in the Atlantic Ocean, respectively. Our findings suggest that a historic differentiation event may have occurred in T. maccoyii, but recently the connectivity between the two oceans may be possible in T. maccoyii populations.

Practical Considerations for Atomistic Structure Modeling with Cryo-EM Maps.

We describe common approaches to atomistic structure modeling with single particle analysis derived cryo-EM maps. Several strategies for atomistic model building and atomistic model fitting methods are discussed, including selection criteria and implementation procedures. In covering basic concepts and caveats, this short perspective aims to help facilitate active discussion between scientists at different levels with diverse backgrounds.

Zinc-finger protein CNBP alters the 3-D structure of lncRNA Braveheart in solution.

Long non-coding RNAs (lncRNAs) constitute a significant fraction of the transcriptome, playing important roles in development and disease. However, our understanding of structure-function relationships for this emerging class of RNAs has been limited to secondary structures. Here, we report the 3-D atomistic structural study of epigenetic lncRNA, Braveheart (Bvht), and its complex with CNBP (Cellular Nucleic acid Binding Protein). Using small angle X-ray scattering (SAXS), we elucidate the ensemble of Bvht RNA conformations in solution, revealing that Bvht lncRNA has a well-defined, albeit flexible 3-D structure that is remodeled upon CNBP binding. Our study suggests that CNBP binding requires multiple domains of Bvht and the RHT/AGIL RNA motif. We show that RHT/AGIL, previously shown to interact with CNBP, contains a highly flexible loop surrounded by more ordered helices. As one of the largest RNA-only 3-D studies, the work lays the foundation for future structural studies of lncRNA-protein complexes.

Cryo_fit: Democratization of flexible fitting for cryo-EM.

Cryo-electron microscopy (cryo-EM) is becoming a method of choice for describing native conformations of biomolecular complexes at high resolution. The rapid growth of cryo-EM in recent years has created a high demand for automated solutions, both in hardware and software. Flexible fitting of atomic models to three-dimensional (3D) cryo-EM reconstructions by molecular dynamics (MD) simulation is a popular technique but often requires technical expertise in computer simulation. This work introduces cryo_fit, a package for the automatic flexible fitting of atomic models in cryo-EM maps using MD simulation. The package is integrated with the Phenix software suite. The module was designed to automate the multiple steps of MD simulation in a reproducible manner, as well as facilitate refinement and validation through Phenix. Through the use of cryo_fit, scientists with little experience in MD simulation can produce high quality atomic models automatically and better exploit the potential of cryo-EM.

Tools for the cryo-EM gold rush: going from the cryo-EM map to the atomistic model.

As cryo-electron microscopy (cryo-EM) enters mainstream structural biology, the demand for fitting methods is high. Here, we review existing flexible fitting methods for cryo-EM. We discuss their importance, potential concerns and assessment strategies. We aim to give readers concrete descriptions of cryo-EM flexible fitting methods with corresponding examples.

Molecular characterization of an adiponectin receptor homolog in the white leg shrimp, Litopenaeus vannamei.

Adiponectin (AdipoQ) and its receptors (AdipoRs) are strongly related to growth and development of skeletal muscle, as well as glucose and lipid metabolism in vertebrates. Herein we report the identification of the first full-length cDNA encoding an AdipoR homolog (Liv-AdipoR) from the decapod crustacean Litopenaeus vannamei using a combination of next generation sequencing (NGS) technology and bioinformatics analysis. The full-length Liv-AdipoR (1,245 bp) encoded a protein that exhibited the canonical seven transmembrane domains (7TMs) and the inversed topology that characterize members of the progestin and adipoQ receptor (PAQR) family. Based on the obtained sequence information, only a single orthologous AdipoR gene appears to exist in arthropods, whereas two paralogs, AdipoR1 and AdipoR2, have evolved in vertebrates. Transcriptional analysis suggested that the single Liv-AdipoR gene appears to serve the functions of two mammalian AdipoRs. At 72 h after injection of 50 pmol Liv-AdipoR dsRNA (340 bp) into L. vannamei thoracic muscle and deep abdominal muscle, transcription levels of Liv-AdipoR decreased by 93% and 97%, respectively. This confirmed optimal conditions for RNAi of Liv-AdipoR. Knockdown of Liv-AdipoR resulted in significant changes in the plasma levels of ammonia, 3-methylhistine, and ornithine, but not plasma glucose, suggesting that that Liv-AdipoR is important for maintaining muscle fibers. The chronic effect of Liv-AdipoR dsRNA injection was increased mortality. Transcriptomic analysis showed that 804 contigs were upregulated and 212 contigs were downregulated by the knockdown of Liv-AdipoR in deep abdominal muscle. The significantly upregulated genes were categorized as four main functional groups: RNA-editing and transcriptional regulators, molecular chaperones, metabolic regulators, and channel proteins.

Boosting protein stability with the computational design of ß-sheet surfaces.

ß-sheets often have one face packed against the core of the protein and the other facing solvent. Mutational studies have indicated that the solvent-facing residues can contribute significantly to protein stability, and that the preferred amino acid at each sequence position is dependent on the precise structure of the protein backbone and the identity of the neighboring amino acids. This suggests that the most advantageous methods for designing ß-sheet surfaces will be approaches that take into account the multiple energetic factors at play including side chain rotamer preferences, van der Waals forces, electrostatics, and desolvation effects. Here, we show that the protein design software Rosetta, which models these energetic factors, can be used to dramatically increase protein stability by optimizing interactions on the surfaces of small ß-sheet proteins. Two design variants of the ß-sandwich protein from tenascin were made with 7 and 14 mutations respectively on its ß-sheet surfaces. These changes raised the thermal midpoint for unfolding from 45°C to 64°C and 74°C. Additionally, we tested an empirical approach based on increasing the number of potential salt bridges on the surfaces of the ß-sheets. This was not a robust strategy for increasing stability, as three of the four variants tested were unfolded.

A new species of Anchistrotos Brian, 1906 (Copepoda: Cyclopoida: Taeniacanthidae) from the filamentous shrimpgoby Myersina filifer (Valenciennes) (Perciformes: Gobiidae) in Korean waters.

A new species of Anchistrotos Brian, 1906 (Copepoda: Cyclopoida: Taeniacanthidae), parasitic in the branchial cavities of the filamentous shrimpgoby Myersina filifer (Valenciennes) (Perciformes: Gobiidae) from Korea is described. The new species is most closely related to A. tangi Venmathi Maran, Moon & Adday, 2014, but differs from it by the following combination of characters in the adult female: the U-shaped rostrum, the distal margin of the anal somite lacks patches of spinules, the proximal segment of the maxilliped is without seta, and the maxilliped claw is armed with long and small naked setae. This is the tenth species of the genus and a key is provided to distinguish all nominal species.

Amphritea ceti sp. nov., isolated from faeces of Beluga whale (Delphinapterus leucas).

A Gram-stain-negative, aerobic, non-spore-forming, non-flagellated and rod-shaped or ovoid bacterial strain, designated RA1(T), was isolated from faeces collected from Beluga whale (Delphinapterus leucas) in Yeosu aquarium, South Korea. Strain RA1(T) grew optimally at 25 °C, at pH 7.0-8.0 and in the presence of 2.0 % (w/v) NaCl. Neighbour-joining, maximum-likelihood and maximum-parsimony phylogenetic trees based on 16S rRNA gene sequences revealed that strain RA1(T) joins the cluster comprising the type strains of three species of the genus Amphritea, with which it exhibited 95.8-96.0 % sequence similarity. Sequence similarities to the type strains of other recognized species were less than 94.3 %. Strain RA1(T) contained Q-8 as the predominant ubiquinone and summed feature 3 (C16 : 1ω7c and/or C16 : 1ω6c), C18 : 1ω7c and C16 : 0 as the major fatty acids. The major polar lipids of strain RA1(T) were phosphatidylethanolamine, phosphatidylglycerol, two unidentified lipids and one unidentified aminolipid. The DNA G+C content of strain RA1(T) was 47.4 mol%. The differential phenotypic properties, together with the phylogenetic distinctiveness, revealed that strain RA1(T) is separated from other species of the genus Amphritea. On the basis of the data presented, strain RA1(T) is considered to represent a novel species of the genus Amphritea, for which the name Amphritea ceti sp. nov. is proposed. The type strain is RA1(T) ( = KCTC 42154(T) = NBRC 110551(T)).

Computational approaches to understanding protein aggregation in neurodegeneration.

The generation of toxic non-native protein conformers has emerged as a unifying thread among disorders such as Alzheimer's disease, Parkinson's disease, and amyotrophic lateral sclerosis. Atomic-level detail regarding dynamical changes that facilitate protein aggregation, as well as the structural features of large-scale ordered aggregates and soluble non-native oligomers, would contribute significantly to current understanding of these complex phenomena and offer potential strategies for inhibiting formation of cytotoxic species. However, experimental limitations often preclude the acquisition of high-resolution structural and mechanistic information for aggregating systems. Computational methods, particularly those combine both all-atom and coarse-grained simulations to cover a wide range of time and length scales, have thus emerged as crucial tools for investigating protein aggregation. Here we review the current state of computational methodology for the study of protein self-assembly, with a focus on the application of these methods toward understanding of protein aggregates in human neurodegenerative disorders.

Shewanella upenei sp. nov., a lipolytic bacterium isolated from bensasi goatfish Upeneus bensasi.

A Gram-staining-negative, motile, non-spore-forming and rod-shaped bacterial strain, 20-23R(T), was isolated from intestine of bensasi goatfish, Upeneus bensasi, and its taxonomic position was investigated by using a polyphasic study. Phylogenetic analyses based on 16S rRNA gene sequences revealed that strain 20-23R(T) belonged to the genus Shewanella. Strain 20-23R(T) exhibited 16S rRNA gene sequence similarity values of 99.5, 99.2, and 97.5% to Shewanella algae ATCC 51192(T), Shewanella haliotis DW01(T), and Shewanella chilikensis JC5(T), respectively. Strain 20-23R(T) exhibited 93.1-96.0% 16S rRNA gene sequence similarity to the other Shewanella species. It also exhibited 98.3-98.4% gyrB sequence similarity to the type strains of S. algae and S. haliotis. Strain 20-23R(T) contained simultaneously both menaquinones and ubiquinones; the predominant menaquinone was MK-7 and the predominant ubiquinones were Q-8 and Q-7. The fatty acid profiles of strain 20-23R(T), S. algae KCTC 22552(T) and S. haliotis KCTC 12896(T) were similar; major components were iso-C(15:0), C(16:0), C(16:1) ω7c and/or iso-C(15:0) 2-OH and C(17:1) ω8c. The DNA G+C content of strain 20-23R(T) was 53.9 mol%. Differential phenotypic properties and genetic distinctiveness of strain 20-23R(T), together with the phylogenetic distinctiveness, revealed that this strain is distinguishable from recognized Shewanella species. On the basis of the data presented, strain 20-23R(T) represents a novel species of the genus Shewanella, for which the name Shewanella upenei sp. nov. is proposed. The type strain is 20-23R(T) (=KCTC 22806(T) =CCUG 58400(T)).

EaMEAD: Activation energy prediction of cytochrome P450 mediated metabolism with effective atomic descriptors.

In an effort to improve drug design and predictions for pharmacokinetics (PK), an empirical model was developed to predict the activation energies (Ea) of cytochrome P450 (CYP450) mediated metabolism. The model, EaMEAD (Activation energy of Metabolism reactions with Effective Atomic Descriptors), predicts the Ea of four major metabolic reactions of the CYP450 enzyme: aliphatic hydroxylation, N-dealkylation, O-dealkylation, and aromatic hydroxylation. To build and validate the empirical model, the E(a) values of the substrates with diverse chemical structures (394 metabolic sites for aliphatic hydroxylation, 27 metabolic sites for N-dealkylation, 9 metabolic sites for O-dealkylation, and 85 metabolic sites for aromatic hydroxylation) were calculated by AM1 molecular orbital (MO). Empirical equations, Quantitative Structure Activity Relationship (QSAR) models, were derived using effective atomic charge, effective atomic polarizability, and bond dipole moments of the substrates as descriptors. EaMEAD is shown to accurately predict Ea with a correlation coefficient (R) of 0.94 and root-mean-square error (RMSE, unit is kcal/mol) of 0.70 for aliphatic hydroxylation, N-dealkylation, and O-dealkylation, and R of 0.83 and RMSE of 0.80 for aromatic hydroxylation, respectively. Physical origin and the role of the effective atomic descriptors of the models are presented in detail. With this model, the Ea of the metabolism can be rapidly predicted without any experimental parameters or time-consuming QM calculation. Regioselectivity prediction with our model is presented in the case of CYP3A4 metabolism. The reliability and ease of use of this model will greatly facilitate early stage PK predictions and rational drug design. Moreover, the model can be applied to develop the Ea prediction model of various types of chemical reactions.