Molecular Modification Strategies of Nitrilase for Its Potential Application in Agriculture.

Some feed source plants will produce secondary metabolites such as cyanogenic glycosides during metabolism, which will produce some poisonous nitrile compounds after hydrolysis and remain in plant tissues. The consumption of feed-source plants without proper treatment affect the health of the animals' bodies. Nitrilases can convert nitriles and have been used in industry as green biocatalysts. However, due to their bottleneck problems, their application in agriculture is still facing challenges. Acid-resistant nitrilase preparations, high-temperature resistance, antiprotease activity, strong activity, and strict reaction specificity urgently need to be developed. In this paper, the application potential of nitrilase in agriculture, especially in feed processing industry was explored, the source properties and catalytic mechanism of nitrilase were reviewed, and modification strategies for nitrilase application in agriculture were proposed to provide references for future research and application of nitrilase in agricultural and especially in the biological feed scene.

Maximizing the potential of nitrilase: Unveiling their diversity, catalytic proficiency, and versatile applications.

Nitrilases represent a distinct class of enzymes that play a pivotal role in catalyzing the hydrolysis of nitrile compounds, leading to the formation of corresponding carboxylic acids. These enzymatic entities have garnered significant attention across a spectrum of industries, encompassing pharmaceuticals, agrochemicals, and fine chemicals. Moreover, their significance has been accentuated by mounting environmental pressures, propelling them into the forefront of biodegradation and bioremediation endeavors. Nevertheless, the natural nitrilases exhibit intrinsic limitations such as low thermal stability, narrow substrate selectivity, and inadaptability to varying environmental conditions. In the past decade, substantial efforts have been made in elucidating the structural underpinnings and catalytic mechanisms of nitrilase, providing basis for engineering of nitrilases. Significant breakthroughs have been made in the regulation of nitrilases with ideal catalytic properties and application of the enzymes for industrial productions. This review endeavors to provide a comprehensive discourse and summary of recent research advancements related to nitrilases, with a particular emphasis on the elucidation of the structural attributes, catalytic mechanisms, catalytic characteristics, and strategies for improving catalytic performance of nitrilases. Moreover, the exploration extends to the domain of process engineering and the multifarious applications of nitrilases. Furthermore, the future development trend of nitrilases is prospected, providing important guidance for research and application in the related fields.

Cryo-EM structure of bacterial nitrilase reveals insight into oligomerization, substrate recognition, and catalysis.

Many enzymes can self-assemble into higher-order structures with helical symmetry. A particularly noteworthy example is that of nitrilases, enzymes in which oligomerization of dimers into spiral homo-oligomers is a requirement for their enzymatic function. Nitrilases are widespread in nature where they catalyze the hydrolysis of nitriles into the corresponding carboxylic acid and ammonia. Here, we present the Cryo-EM structure, at 3 Å resolution, of a C-terminal truncate nitrilase from Rhodococcus sp. V51B that assembles in helical filaments. The model comprises a complete turn of the helical arrangement with a substrate-intermediate bound to the catalytic cysteine. The structure was solved having added the substrate to the protein. The length and stability of filaments was made more substantial in the presence of the aromatic substrate, benzonitrile, but not for aliphatic nitriles or dinitriles. The overall structure maintains the topology of the nitrilase family, and the filament is formed by the association of dimers in a chain-like mechanism that stabilizes the spiral. The active site is completely buried inside each monomer, while the substrate binding pocket was observed within the oligomerization interfaces. The present structure is in a closed configuration, judging by the position of the lid, suggesting that the intermediate is one of the covalent adducts. The proximity of the active site to the dimerization and oligomerization interfaces, allows the dimer to sense structural changes once the benzonitrile was bound, and translated to the rest of the filament, stabilizing the helical structure.

Modification of nitrilase based on computer screening and efficient biosynthesis of 4-cyanobenzoic acid.

4-cyanobenzoic acid serves as a crucial intermediate for the synthesis of various high-value organic compounds. The enzymatic hydrolysis of terephthalonitrile to produce 4-cyanobenzoic acid using nitrilase offers the advantages of a simple reaction pathway, environmental friendliness, and easy product separation. In order to efficiently develop nitrilases that meet industrial production requirements, the virtual screening method used in the study is established and mature. From a total of 371 amino acids in the nitrilase AfNIT, which exhibits activity in terephthalonitrile hydrolysis, three candidate sites (F168, S192, and T201) were identified, and a "small and accurate" mutant library was constructed. The triple mutant F168V/T201N/S192F was screened from this small mutant library with a specific activity of 227.3 U mg-1 , which was 3.8 times higher than that of the wild-type AfNIT. Using the whole-cell biocatalyst containing the mutant F168V/T201N/S192F, terephthalonitrile was successfully hydrolyzed at a concentration of 150 g L-1 to produce 4-cyanobenzoic acid with a final yield of 170.3 g L-1 and a conversion rate of 98.7%. The obtained nitrilase mutant F168V/T201N/S192F in this study can be effectively applied in the biomanufacturing of 4-cyanobenzoic acid using terephthalonitrile as a substrate. Furthermore, the results also demonstrate the significant improvement in predictive accuracy achieved through the latest AI-assisted computer simulation methods. This approach represents a promising and feasible new technological pathway for assisting enzyme engineering research, laying a theoretical foundation for other related studies.

Identification and evolution of non-traditional nitrilase from Spirosoma linguale DSM 74 with high hydration activity.

Hydration, a secondary activity mediated by nitrilase, is a promising new pathway for amide production. However, low hydration activity of nitrilase or trade-off between hydration and catalytic activity hinders its application in the production of amides. Here, natural C-terminal-truncated wild-type nitrilase, mined from a public database, obtained a high-hydration activity nitrilase as a novel evolutionary starting point for further protein engineering. The nitrilase Nit-74 from Spirosoma linguale DSM 74 was successfully obtained and exhibited the highest hydration activity level, performing 50.7 % nicotinamide formation and 87.6 % conversion to 2 mM substrate 3-cyanopyridine. Steric hindrance of the catalytic activity center and the N-terminus of the catalytic cysteine residue helped us identify three key residues: I166, W168, and T191. Saturation mutations resulted in three single mutants that further improved the hydration activity of N-heterocyclic nitriles. Among them, the mutant T191S performed 72.7 % nicotinamide formation, which was much higher than the previously reported highest level of 18.7 %. Additionally, mutants I166N and W168Y exhibited a 97.5 % 2-picolinamide ratio and 97.7 % isonicotinamide ratio without any loss of catalytic activity, which did not indicate a trade-off effect. Our results expand the screening and evolution library of promiscuous nitrilases with high hydration activity for amide formation.

Construing recombinant ZFP160 from Aspergillus terreus as pterin deaminase enzyme.

Pterin deaminase stands as a metalloenzyme and exhibits both antitumor and anticancer activities. Therefore, this study aimed to explore the molecular function of zinc finger protein-160 (zfp160) from Aspergillus terreus with its enzyme mechanism in detail. Subsequently, preliminary molecular docking studies on zfp160 from A. terreus were done. Next, the cloning and expression of zfp160 protein were carried out. Following, protein expression was induced and purified through nickel NTA column with imidazole gradient elution. Through the Mascot search engine tool, the expressed protein of MALDI-TOF was confirmed by 32 kDa bands of SDS-PAGE. Furthermore, its enzymatic characterization and biochemical categorization were also explored. The optimum conditions for enzyme were determined to be pH 8, temperature 35°C, km 50 µm with folic acid as substrate, and Vmax of 24.16 (IU/mL). Further, in silico analysis tried to explore the interactions and binding affinity of various substrates to the modeled pterin deaminase from A. terreus. Our results revealed the binding mode of different substrate molecules with pterin deaminase using the approximate scoring functions that possibly correlate with actual experimental binding affinities. Following this, molecular dynamic simulations provided the in-depth knowledge on deciphering functional mechanisms of pterin deaminase over other drugs.

Identification and structural prediction of the unrevealed amidohydrolase enzyme: Pterin deaminase from Agrobacterium tumefaciens LBA4404.

Microbes make a remarkable contribution to the health and well-being of living beings all over the world. Interestingly, pterin deaminase is an amidohydrolase enzyme that exhibits antitumor, anticancer activities and antioxidant properties. With the existing evidence of the presence of pterin deaminase from microbial sources, an attempt was made to reveal the existence of this enzyme in the unexplored bacterium Agrobacterium tumefaciens LBA4404. After, the cells were harvested and characterized as intracellular enzymes and then partially purified through acetone precipitation. Subsequently, further purification step was carried out with an ion-exchange chromatogram (HiTrap Q FF) using the Fast-Protein Liquid Chromatography technique (FPLC). Henceforward, the approximate molecular weight of the purified pterin deaminase was determined through SDS-PAGE. Furthermore, the purified protein was identified accurately by MALDI-TOF, and the sequence was explored through a Mascot search engine. Additionally, the three-dimensional structure was predicted and then validated, as well as ligand-binding sites, and the stability of this enzyme was confirmed for the first time. Thus, the present study revealed the selected parameters showing a considerable impact on the identification and purification of pterin deaminase from A. tumefaciens LBA4404 for the first time. The enzyme specificity makes it a favorable choice as a potent anticancer agent.

Biotransformation of 3-cyanopyridine to nicotinic acid using whole-cell nitrilase of Gordonia terrae mutant MN12.

In the present study, the Gordonia terrae was subjected to chemical mutagenesis using ethyl methane sulfonate (EMS) and methyl methane sulfonate (MMS), N-methyl-N-nitro-N-nitrosoguanidine (MNNG), 5-bromouracil (5-BU) and hydroxylamine with the aim of improving the catalytic efficiency of its nitrilase for conversion of 3-cyanopyridine to nicotinic acid. A mutant MN12 generated with MNNG exhibited increase in nitrilase activity from 0.5 U/mg dcw (dry cell weight) (in the wild G. terrae) to 1.33 U/mg dcw. Further optimizations of culture conditions using response surface methodology enhanced the enzyme production to 1.2-fold. Whole-cell catalysis was adopted for bench-scale synthesis of nicotinic acid, and 100% conversion of 100 mM 3-cyanopyridine was achieved in potassium phosphate buffer (0.1 M, pH 8.0) at 40 °C in 15 min. The whole-cell nitrilase of the mutant MN12 exhibited higher rate of product formation and volumetric productivity, i.e., 24.56 g/h/g dcw and 221 g/L as compared to 8.95 g/h/g dcw and 196.8 g/L of the wild G. terrae. The recovered product was confirmed by HPLC, FTIR and NMR analysis with high purity (> 99.9%). These results indicated that the mutant MN12 of G. terrae as whole-cell nitrilase is a very promising biocatalyst for the large-scale synthesis of nicotinic acid.

Phylogenetic and Structural Analysis of Bacterial Nitrilases for the Biodegradation of Nitrile Compounds.

BACKGROUND: Microbial nitrilases play a vital role in the biodegradation of nitrilecontaining pollutants, effluent treatments in chemical and textile industries, and the biosynthesis of Indole-3-acetic acid (IAA) from tryptophan in plants. However, the lack of structural information limits the correlation between its activity and substrate specificity. METHODS: The present study involves the genome mining of bacteria for the distribution and diversity of nitrilases, their phylogenetic analysis and structural characterization for motifs/ domains, followed by interaction with substrates. RESULTS: Here, we mined the bacterial genomes for nitrilases and correlated their functions to hypothetical, uncharacterized, or putative ones. The comparative genomics revealed four AcNit, As7Nit, Cn5Nit and Cn9Nit predicted nitrilases encoding genes as uncharacterized subgroups of the nitrilase superfamily. The annotation of these nitrilases encoding genes revealed relatedness with nitrilase hydratases and cyanoalanine hydratases. At the proteomics level, the motif analysis of these protein sequences predicted a single motif of 20-28 aa, with glutamate (E), lysine (K) and cysteine (C) residues as a part of catalytic triad along with several other residues at the active site. The structural analysis of the nitrilases revealed geometrical and close conformation in the form of α-helices and ß-sheets arranged in a sandwich structure. The catalytic residues constituted the substrate binding pocket and exhibited the broad nitrile substrate spectra for aromatic and aliphatic nitriles-containing compounds. The aromatic amino acid residues Y159 in the active site were predicted to be responsible for substrate specificity. The substitution of non-aromatic alanine residue in place of Y159 completely disrupted the catalytic activity for indole-3-acetonitrile (IAN). CONCLUSION: The present study reports genome mining and simulation of structure-function relationship for uncharacterized bacterial nitrilases and their role in the biodegradation of pollutants and xenobiotics, which could be of applications in different industrial sectors.

Improvement of multicatalytic properties of nitrilase from Paraburkholderia graminis for efficient biosynthesis of 2-chloronicotinic acid.

Nitrilases are promising biocatalysts to produce high-value-added carboxylic acids through hydrolysis of nitriles. However, since the enzymes always show low activity and sometimes with poor reaction specificity toward 2-chloronicotinonitrile (2-CN), very few robust nitrilases have been reported for efficient production of 2-chloronicotinic acid (2-CA) from 2-CN. Herein, a nitrilase from Paraburkholderia graminis (PgNIT) was engineered to improve its catalytic properties. We identified the beneficial residues via computational analysis and constructed the mutant library. The positive mutants were obtained and the activity of the "best" mutant F164G/I130L/N167Y/A55S/Q260C/T133I/R199Q toward 2-CN was increased from 0.14 × 10-3  to 4.22 U/mg. Its reaction specificity was improved with elimination of hydration activity. Molecular docking and molecular dynamics simulation revealed that the conformational flexibility, the nucleophilic attack distance, as well as the interaction forces between the enzyme and substrate were the main reason alternating the catalytic properties of PgNIT. With the best mutant as biocatalyst, 150 g/L 2-CN was completely converted, resulting in 2-CA accumulated to 169.7 g/L. When the substrate concentration was increased to 200 g/L, 203.1 g/L 2-CA was obtained with yield of 85.7%. The results laid the foundation for industrial production of 2-CA with the nitrilase-catalyzed route.

The catalytic mechanism of the mitochondrial methylenetetrahydrofolate dehydrogenase/cyclohydrolase (MTHFD2).

Methylenetetrahydrofolate dehydrogenase/cyclohydrolase (MTHFD2) is a new drug target that is expressed in cancer cells but not in normal adult cells, which provides an Achilles heel to selectively kill cancer cells. Despite the availability of crystal structures of MTHFD2 in the inhibitor- and cofactor-bound forms, key information is missing due to technical limitations, including (a) the location of absolutely required Mg2+ ion, and (b) the substrate-bound form of MTHFD2. Using computational modeling and simulations, we propose that two magnesium ions are present at the active site whereby (i) Arg233, Asp225, and two water molecules coordinate [Formula: see text], while [Formula: see text] together with Arg233 stabilize the inorganic phosphate (Pi); (ii) Asp168 and three water molecules coordinate [Formula: see text], and [Formula: see text] further stabilizes Pi by forming a hydrogen bond with two oxygens of Pi; (iii) Arg201 directly coordinates the Pi; and (iv) through three water-mediated interactions, Asp168 contributes to the positioning and stabilization of [Formula: see text], [Formula: see text] and Pi. Our computational study at the empirical valence bond level allowed us also to elucidate the detailed reaction mechanisms. We found that the dehydrogenase activity features a proton-coupled electron transfer with charge redistribution connected to the reorganization of the surrounding water molecules which further facilitates the subsequent cyclohydrolase activity. The cyclohydrolase activity then drives the hydration of the imidazoline ring and the ring opening in a concerted way. Furthermore, we have uncovered that two key residues, Ser197/Arg233, are important factors in determining the cofactor (NADP+/NAD+) preference of the dehydrogenase activity. Our work sheds new light on the structural and kinetic framework of MTHFD2, which will be helpful to design small molecule inhibitors that can be used for cancer treatment.

Time Evolution of the Millisecond Allosteric Activation of Imidazole Glycerol Phosphate Synthase.

Deciphering the molecular mechanisms of enzymatic allosteric regulation requires the structural characterization of functional states and also their time evolution toward the formation of the allosterically activated ternary complex. The transient nature and usually slow millisecond time scale interconversion between these functional states hamper their experimental and computational characterization. Here, we combine extensive molecular dynamics simulations, enhanced sampling techniques, and dynamical networks to describe the allosteric activation of imidazole glycerol phosphate synthase (IGPS) from the substrate-free form to the active ternary complex. IGPS is a heterodimeric bienzyme complex whose HisH subunit is responsible for hydrolyzing glutamine and delivering ammonia for the cyclase activity in HisF. Despite significant advances in understanding the underlying allosteric mechanism, essential molecular details of the long-range millisecond allosteric activation of IGPS remain hidden. Without using a priori information of the active state, our simulations uncover how IGPS, with the allosteric effector bound in HisF, spontaneously captures glutamine in a catalytically inactive HisH conformation, subsequently attains a closed HisF:HisH interface, and finally forms the oxyanion hole in HisH for efficient glutamine hydrolysis. We show that the combined effector and substrate binding dramatically decreases the conformational barrier associated with oxyanion hole formation, in line with the experimentally observed 4500-fold activity increase in glutamine hydrolysis. The allosteric activation is controlled by correlated time-evolving dynamic networks connecting the effector and substrate binding sites. This computational strategy tailored to describe millisecond events can be used to rationalize the effect of mutations on the allosteric regulation and guide IGPS engineering efforts.

Distinct allosteric pathways in imidazole glycerol phosphate synthase from yeast and bacteria.

Understanding the relationship between protein structures and their function is still an open question that becomes very challenging when allostery plays an important functional role. Allosteric proteins, in fact, exploit different ranges of motions (from sidechain local fluctuations to long-range collective motions) to effectively couple distant binding sites, and of particular interest is whether allosteric proteins of the same families with similar functions and structures also necessarily share the same allosteric mechanisms. Here, we compared the early dynamics initiating the allosteric communication of a prototypical allosteric enzyme from two different organisms, i.e., the imidazole glycerol phosphate synthase (IGPS) enzymes from the thermophilic bacteria and the yeast, working at high and room temperatures, respectively. By combining molecular dynamics simulations and network models derived from graph theory, we found rather distinct early allosteric dynamics in the IGPS from the two organisms, involving significatively different allosteric pathways in terms of both local and collective motions. Given the successful prediction of key allosteric residues in the bacterial IGPS, whose mutation disrupts its allosteric communication, the outcome of this study paves the way for future experimental studies on the yeast IGPS that could foster therapeutic applications by exploiting the control of IGPS enzyme allostery.

A novel efficient producer of human ω-amidase (Nit2) in Escherichia coli.

Nit2/ω-amidase catalyzes the hydrolysis of α-ketoglutaramate (KGM, the α-keto acid analogue of glutamine) to α-ketoglutarate and ammonia. The enzyme also catalyzes the amide hydrolysis of monoamides of 4- and 5-C-dicarboxylates, including α-ketosuccinamate (KSM, the α-keto acid analogue of asparagine) and succinamate (SM). Here we describe an inexpensive procedure for high-yield expression of human Nit2 (hNit2) in Escherichia coli and purification of the expressed protein. This work includes: 1) the design of a genetic construct (pQE-Nit22) obtained from the previously described construct (pQE-Nit2) by replacing rare codons within an 81 bp-long DNA fragment "preferred" by E. coli near the translation initiation site; 2) methods for producing and maintaining the pQE-Nit22 construct; 3) purification of recombinant hNit2; and 4) activity measurements of the purified enzyme with KGM and SM. Important features of the hNit2 gene within the pQE-Nit22 construct are: 1) optimized codon composition, 2) the presence of an N-terminus His6 tag immediately after the initiating codon ATG (Met) that permits efficient purification of the end-product on a Ni-NTA-agarose column. We anticipate that the availability of high yield hNit2/ω-amidase will be helpful in elucidating the normal and pathological roles of this enzyme and in the design of specific inhibitors.

Molecular basis for the allosteric activation mechanism of the heterodimeric imidazole glycerol phosphate synthase complex.

Imidazole glycerol phosphate synthase (HisFH) is a heterodimeric bienzyme complex operating at a central branch point of metabolism. HisFH is responsible for the HisH-catalyzed hydrolysis of glutamine to glutamate and ammonia, which is then used for a cyclase reaction by HisF. The HisFH complex is allosterically regulated but the underlying mechanism is not well understood. Here, we elucidate the molecular basis of the long range, allosteric activation of HisFH. We establish that the catalytically active HisFH conformation is only formed when the substrates of both HisH and HisF are bound. We show that in this conformation an oxyanion hole in the HisH active site is established, which rationalizes the observed 4500-fold allosteric activation compared to the inactive conformation. In solution, the inactive and active conformations are in a dynamic equilibrium and the HisFH turnover rates correlate with the population of the active conformation, which is in accordance with the ensemble model of allostery.

Switching the secondary and natural activity of Nitrilase from Acidovorax facilis 72 W for the efficient production of 2-picolinamide.

OBJECTIVES: Catalytic promiscuity, or the ability to catalyze a secondary reaction, provides new opportunities for industrial biocatalysis by expanding the range of biocatalytic reactions. Some nitrilases converting nitriles to amides, referred to as the secondary activity, show great potential for amides production. And our goal was exploiting the amide-forming potential of nitrilases. RESULTS: In this study, we characterized and altered the secondary activity of nitrilase from Acidovorax facilis 72 W (Nit72W) towards different substrates. We increased the secondary activity of Nit72W towards 2-cyanopyridine by 196-fold and created activity toward benzonitrile and p-nitrophenylacetonitrile by modifying the active pocket. Surprisingly, the best mutant, W188M, completely converted 250 mM 2-cyanopyridine to more than 98% 2-picolinamide in 12 h with a specific activity of 90 U/mg and showed potential for industrial applications. CONCLUSIONS: Nit72W was modified to increase its secondary activity for the amides production, especially 2-picolinamide.

Structural and mechanistic insights into the bifunctional HISN2 enzyme catalyzing the second and third steps of histidine biosynthesis in plants.

The second and third steps of the histidine biosynthetic pathway (HBP) in plants are catalyzed by a bifunctional enzyme-HISN2. The enzyme consists of two distinct domains, active respectively as a phosphoribosyl-AMP cyclohydrolase (PRA-CH) and phosphoribosyl-ATP pyrophosphatase (PRA-PH). The domains are analogous to single-domain enzymes encoded by bacterial hisI and hisE genes, respectively. The calculated sequence similarity networks between HISN2 analogs from prokaryotes and eukaryotes suggest that the plant enzymes are closest relatives of those in the class of Deltaproteobacteria. In this work, we obtained crystal structures of HISN2 enzyme from Medicago truncatula (MtHISN2) and described its architecture and interactions with AMP. The AMP molecule bound to the PRA-PH domain shows positioning of the N1-phosphoribosyl relevant to catalysis. AMP bound to the PRA-CH domain mimics a part of the substrate, giving insights into the reaction mechanism. The latter interaction also arises as a possible second-tier regulatory mechanism of the HBP flux, as indicated by inhibition assays and isothermal titration calorimetry.

An Unsual Cys-Glu-Lys Catalytic Triad is Responsible for the Catalytic Mechanism of the Nitrilase Superfamily: A QM/MM Study on Nit2.

Nitrilase 2 (Nit2) is a representative member of the nitrilase superfamily that catalyzes the hydrolysis of α-ketosuccinamate into oxaloacetate. It has been associated with the metabolism of rapidly dividing cells like cancer cells. The catalytic mechanism of Nit2 employs a catalytic triad formed by Cys191, Glu81 and Lys150. The Cys191 and Glu81 play an active role during the catalytic process while the Lys150 is shown to play only a secondary role. The results demonstrate that the catalytic mechanism of Nit2 involves four steps. The nucleophilic attack of Cys191 to the α-ketosuccinamate, the formation of two tetrahedral enzyme adducts and the hydrolysis of a thioacyl-enzyme intermediate, from which results the formation of oxaloacetate and enzymatic turnover. The rate limiting step of the catalytic process is the formation of the first tetrahedral intermediate with a calculated activation free energy of 18.4 kcal/mol, which agrees very well with the experimental kcat (17.67 kcal/mol).

Community Network Analysis of Allosteric Proteins.

Community network analysis (CNA) of correlated protein motions allows modeling of signals propagation in allosteric proteic systems. From standard classical molecular dynamics (MD) simulations, protein motions can be analysed by means of mutual information between pairs of amino acid residues, providing dynamical weighted networks that contains fundamental information of the communication among amino acids. The CNA method has been successfully applied to a variety of allosteric systems including an enzyme, a nuclear receptor and a bacterial adaptive immune system, providing characterization of the allosteric pathways. This method is complementary to network analyses based on different metrics and it is particularly powerful for studying large proteic systems, as it provides a coarse-grained view of the communication flows within large and complex networks.

Machine learning-based prediction of enzyme substrate scope: Application to bacterial nitrilases.

Predicting the range of substrates accepted by an enzyme from its amino acid sequence is challenging. Although sequence- and structure-based annotation approaches are often accurate for predicting broad categories of substrate specificity, they generally cannot predict which specific molecules will be accepted as substrates for a given enzyme, particularly within a class of closely related molecules. Combining targeted experimental activity data with structural modeling, ligand docking, and physicochemical properties of proteins and ligands with various machine learning models provides complementary information that can lead to accurate predictions of substrate scope for related enzymes. Here we describe such an approach that can predict the substrate scope of bacterial nitrilases, which catalyze the hydrolysis of nitrile compounds to the corresponding carboxylic acids and ammonia. Each of the four machine learning models (logistic regression, random forest, gradient-boosted decision trees, and support vector machines) performed similarly (average ROC = 0.9, average accuracy = ~82%) for predicting substrate scope for this dataset, although random forest offers some advantages. This approach is intended to be highly modular with respect to physicochemical property calculations and software used for structural modeling and docking.