ML-PLIC: a web platform for characterizing protein-ligand interactions and developing machine learning-based scoring functions.

Cracking the entangling code of protein-ligand interaction (PLI) is of great importance to structure-based drug design and discovery. Different physical and biochemical representations can be used to describe PLI such as energy terms and interaction fingerprints, which can be analyzed by machine learning (ML) algorithms to create ML-based scoring functions (MLSFs). Here, we propose the ML-based PLI capturer (ML-PLIC), a web platform that automatically characterizes PLI and generates MLSFs to identify the potential binders of a specific protein target through virtual screening (VS). ML-PLIC comprises five modules, including Docking for ligand docking, Descriptors for PLI generation, Modeling for MLSF training, Screening for VS and Pipeline for the integration of the aforementioned functions. We validated the MLSFs constructed by ML-PLIC in three benchmark datasets (Directory of Useful Decoys-Enhanced, Active as Decoys and TocoDecoy), demonstrating accuracy outperforming traditional docking tools and competitive performance to the deep learning-based SF, and provided a case study of the Serine/threonine-protein kinase WEE1 in which MLSFs were developed by using the ML-based VS pipeline in ML-PLIC. Underpinning the latest version of ML-PLIC is a powerful platform that incorporates physical and biological knowledge about PLI, leveraging PLI characterization and MLSF generation into the design of structure-based VS pipeline. The ML-PLIC web platform is now freely available at http://cadd.zju.edu.cn/plic/.

Comprehensive assessment of protein loop modeling programs on large-scale datasets: prediction accuracy and efficiency.

Protein loops play a critical role in the dynamics of proteins and are essential for numerous biological functions, and various computational approaches to loop modeling have been proposed over the past decades. However, a comprehensive understanding of the strengths and weaknesses of each method is lacking. In this work, we constructed two high-quality datasets (i.e. the General dataset and the CASP dataset) and systematically evaluated the accuracy and efficiency of 13 commonly used loop modeling approaches from the perspective of loop lengths, protein classes and residue types. The results indicate that the knowledge-based method FREAD generally outperforms the other tested programs in most cases, but encountered challenges when predicting loops longer than 15 and 30 residues on the CASP and General datasets, respectively. The ab initio method Rosetta NGK demonstrated exceptional modeling accuracy for short loops with four to eight residues and achieved the highest success rate on the CASP dataset. The well-known AlphaFold2 and RoseTTAFold require more resources for better performance, but they exhibit promise for predicting loops longer than 16 and 30 residues in the CASP and General datasets. These observations can provide valuable insights for selecting suitable methods for specific loop modeling tasks and contribute to future advancements in the field.

Genetic Algorithm-Based Receptor Ligand: A Genetic Algorithm-Guided Generative Model to Boost the Novelty and Drug-Likeness of Molecules in a Sampling Chemical Space.

Deep learning-based de novo molecular design has recently gained significant attention. While numerous DL-based generative models have been successfully developed for designing novel compounds, the majority of the generated molecules lack sufficiently novel scaffolds or high drug-like profiles. The aforementioned issues may not be fully captured by commonly used metrics for the assessment of molecular generative models, such as novelty, diversity, and quantitative estimation of the drug-likeness score. To address these limitations, we proposed a genetic algorithm-guided generative model called GARel (genetic algorithm-based receptor-ligand interaction generator), a novel framework for training a DL-based generative model to produce drug-like molecules with novel scaffolds. To efficiently train the GARel model, we utilized dense net to update the parameters based on molecules with novel scaffolds and drug-like features. To demonstrate the capability of the GARel model, we used it to design inhibitors for three targets: AA2AR, EGFR, and SARS-Cov2. The results indicate that GARel-generated molecules feature more diverse and novel scaffolds and possess more desirable physicochemical properties and favorable docking scores. Compared with other generative models, GARel makes significant progress in balancing novelty and drug-likeness, providing a promising direction for the further development of DL-based de novo design methodology with potential impacts on drug discovery.

Small-Molecule Conformer Generators: Evaluation of Traditional Methods and AI Models on High-Quality Data Sets.

Small-molecule conformer generation (SMCG) is an extremely important task in both ligand- and structure-based computer-aided drug design, especially during the hit discovery phase. Recently, a multitude of artificial intelligence (AI) models tailored for SMCG have emerged. Despite developers typically furnishing performance evaluation data upon releasing their AI models, a comprehensive and equitable performance comparison between AI models and conventional methods is still lacking. In this study, we curated a new benchmarking data set comprising 3354 high-quality ligand bioactive conformations. Subsequently, we conducted a systematic assessment of the performance of four widely adopted traditional methods (i.e., ConfGenX, Conformator, OMEGA, and RDKit ETKDG) and five AI models (i.e., ConfGF, DMCG, GeoDiff, GeoMol, and torsional diffusion) in the tasks of reproducing bioactive and low-energy conformations of small molecules. In the former task, the AI models have no advantage, particularly with a maximum ensemble size of 1. Even the best-performing AI model GeoMol is still worse than any of the tested traditional methods. Conversely, in the latter task, the torsional diffusion model shows obvious advantages, surpassing the best-performing traditional method ConfGenX by 26.09 and 12.97% on the COV-R and COV-P metrics, respectively. Furthermore, the influence of force field-based fine-tuning on the quality of the generated conformers was also discussed. Finally, a user-friendly Web server called fastSMCG was developed to enable researchers to rapidly and flexibly generate small-molecule conformers using both traditional and AI methods. We anticipate that our work will offer valuable practical assistance to the scientific community in this field.

Discovery of 3,6-diaryl-1H-pyrazolo[3,4-b]pyridines as potent anaplastic lymphoma kinase (ALK) inhibitors.

A new series of 3,6-diaryl-1H-pyrazolo[3,4-b]pyridine compounds have been discovered as potent anaplastic lymphoma kinase (ALK) inhibitors. The 4-hydroxyphenyl in the 6-position of 1H-pyrazolo[3,4-b]pyridine were crucial and a fluorine atom substitution could give promising inhibitory activity. The IC50 of compound 9v against ALK was up to 1.58 nM and a binding mechanism was proposed.

Importance of protein flexibility in molecular recognition: a case study on Type-I1/2 inhibitors of ALK.

Anaplastic lymphoma kinase (ALK) has been regarded as a promising target for the therapy of various cancers. A large number of ALK inhibitors with diverse scaffolds have been discovered, and most of them belong to Type-I inhibitors that only occupy the ATP-binding pocket. Recently, we reported a series of novel and potent Type-I1/2 inhibitors of ALK with the 1-purine-3-piperidinecarboxamide scaffold, which can bind to both the ATP-binding site of ALK and the adjacent hydrophobic allosteric pocket. In this study, the binding mechanisms of these Type-I1/2 ALK inhibitors were elucidated by multiple molecular modeling techniques. The calculation results demonstrate that the ensemble docking based on multiple protein structures and the MM/PB(GB)SA calculations based on molecular dynamics (MD) simulations yield better predictions than conventional rigid receptor docking (Glide, Surflex-Dock, and Autodock Vina), highlighting the importance of incorporating receptor flexibility in the predictions of binding poses and binding affinities of Type-I1/2 ALK inhibitors. Furthermore, the umbrella sampling (US) simulations and MM/GBSA binding free energy decomposition analyses indicate that Leu1122, Leu1198, Gly1202 and Glu1210 in the hinge region and Glu1197, Ile1171, Phe1174, Ile1179, His1247, Ile1268, Asp1270 and Phe1271 in the allosteric pocket of ALK are the key residues for determining the relative binding strength of the studied inhibitors. Besides, we found that the most potent inhibitor (001-017) tends to form stronger transient interactions with residues along the dissociation channel due to the high electronegativity of its bulky 4-(trifluoromethoxy) phenylamine tail. As a whole, both the stronger binding affinity and the higher energetic barrier (which may prolong the drug-target residence time) of 001-017 contribute to its excellent anti-proliferation activity against ALK-positive cancer cells.

Assessing the performance of MM/PBSA and MM/GBSA methods. 7. Entropy effects on the performance of end-point binding free energy calculation approaches.

Entropy effects play an important role in drug-target interactions, but the entropic contribution to ligand-binding affinity is often neglected by end-point binding free energy calculation methods, such as MM/GBSA and MM/PBSA, due to the expensive computational cost of normal mode analysis (NMA). Here, we systematically investigated entropy effects on the prediction power of MM/GBSA and MM/PBSA using >1500 protein-ligand systems and six representative AMBER force fields. Two computationally efficient methods, including NMA based on truncated structures and the interaction entropy approach, were used to estimate the entropic contributions to ligand-target binding free energies. In terms of the overall accuracy, we found that, for the minimized structures, in most cases the inclusion of the conformational entropies predicted by truncated NMA (enthalpynmode_min_9Å) compromises the overall accuracy of MM/GBSA and MM/PBSA compared with the enthalpies calculated based on the minimized structures (enthalpymin). However, for the MD trajectories, the binding free energies can be improved by the inclusion of the conformation entropies predicted by either truncated-NMA for a relatively high dielectric constant (εin = 4) or the interaction entropy method for εin = 1-4. In terms of reproducing the absolute binding free energies, the binding free energies estimated by including the truncated-NMA entropies based on the MD trajectories (ΔGnmode_md_9Å) give the lowest average absolute deviations against the experimental data among all the tested strategies for both MM/GBSA and MM/PBSA. Although the inclusion of the truncated NMA based on the MD trajectories (ΔGnmode_md_9Å) for a relatively high dielectric constant gave the overall best result and the lowest average absolute deviations against the experimental data (for the ff03 force field), it needs too much computational time. Alternatively, considering that the interaction entropy method does not incur any additional computational cost and can give comparable (at high dielectric constant, εin = 4) or even better (at low dielectric constant, εin = 1-2) results than the truncated-NMA entropy (ΔGnmode_md_9Å), the interaction entropy approach is recommended to estimate the entropic component for MM/GBSA and MM/PBSA based on MD trajectories, especially for a diverse dataset. Furthermore, we compared the predictions of MM/GBSA with six different AMBER force fields. The results show that the ff03 force field (ff03 for proteins and gaff with AM1-BCC charges for ligands) performs the best, but the predictions given by the tested force fields are comparable, implying that the MM/GBSA predictions are not very sensitive to force fields.

Assessing the performance of the MM/PBSA and MM/GBSA methods. 6. Capability to predict protein-protein binding free energies and re-rank binding poses generated by protein-protein docking.

Understanding protein-protein interactions (PPIs) is quite important to elucidate crucial biological processes and even design compounds that interfere with PPIs with pharmaceutical significance. Protein-protein docking can afford the atomic structural details of protein-protein complexes, but the accurate prediction of the three-dimensional structures for protein-protein systems is still notoriously difficult due in part to the lack of an ideal scoring function for protein-protein docking. Compared with most scoring functions used in protein-protein docking, the Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) and Molecular Mechanics/Poisson Boltzmann Surface Area (MM/PBSA) methodologies are more theoretically rigorous, but their overall performance for the predictions of binding affinities and binding poses for protein-protein systems has not been systematically evaluated. In this study, we first evaluated the performance of MM/PBSA and MM/GBSA to predict the binding affinities for 46 protein-protein complexes. On the whole, different force fields, solvation models, and interior dielectric constants have obvious impacts on the prediction accuracy of MM/GBSA and MM/PBSA. The MM/GBSA calculations based on the ff02 force field, the GB model developed by Onufriev et al. and a low interior dielectric constant (εin = 1) yield the best correlation between the predicted binding affinities and the experimental data (rp = -0.647), which is better than MM/PBSA (rp = -0.523) and a number of empirical scoring functions used in protein-protein docking (rp = -0.141 to -0.529). Then, we examined the capability of MM/GBSA to identify the possible near-native binding structures from the decoys generated by ZDOCK for 43 protein-protein systems. The results illustrate that the MM/GBSA rescoring has better capability to distinguish the correct binding structures from the decoys than the ZDOCK scoring. Besides, the optimal interior dielectric constant of MM/GBSA for re-ranking docking poses may be determined by analyzing the characteristics of protein-protein binding interfaces. Considering the relatively high prediction accuracy and low computational cost, MM/GBSA may be a good choice for predicting the binding affinities and identifying correct binding structures for protein-protein systems.

Molecular principle of the cyclin-dependent kinase selectivity of 4-(thiazol-5-yl)-2-(phenylamino) pyrimidine-5-carbonitrile derivatives revealed by molecular modeling studies.

Due to the high sequence identity of the binding pockets of cyclin-dependent kinases (CDKs), designing highly selective inhibitors towards a specific CDK member remains a big challenge. 4-(thiazol-5-yl)-2-(phenylamino) pyrimidine derivatives are effective inhibitors of CDKs, among which the most promising inhibitor 12u demonstrates high binding affinity to CDK9 and attenuated binding affinity to other homologous kinases, such as CDK2. In this study, in order to rationalize the principle of the binding preference towards CDK9 over CDK2 and to explore crucial information that may aid the design of selective CDK9 inhibitors, MM/GBSA calculations based on conventional molecular dynamics (MD) simulations and enhanced sampling simulations (umbrella sampling and steered MD simulations) were carried out on two representative derivatives (12u and 4). The calculation results show that the binding specificity of 12u to CDK9 is primarily controlled by conformational change of the G-loop and variation of the van der Waals interactions. Furthermore, the enhanced sampling simulations revealed the different reaction coordinates and transient interactions of inhibitors 12u and 4 as they dissociate from the binding pockets of CDK9 and CDK2. The physical principles obtained from this study may facilitate the discovery and rational design of novel and specific inhibitors of CDK9.

Identification and Preliminary SAR Analysis of Novel Type-I Inhibitors of TIE-2 via Structure-Based Virtual Screening and Biological Evaluation in in vitro Models.

Angiopoietin (ANG) ligands and their downstream TIE receptors have been validated as the second vascular signaling system involving vessel remodeling and maturation. Among them, the ANG/TIE-2 signaling pathway is involved in numerous life-threatening diseases and has become an attractive potential therapeutic target. Several large-molecule inhibitors targeting the ANG/TIE-2 axis have recently entered clinical phase for the therapy of various solid tumors, but selective small-molecule inhibitors of TIE-2 are still quite limited. In the present work, structure-based virtual screening was performed to search for type-I inhibitors of TIE-2. Of the only 41 compounds selected by our strategy, 8 molecules with the concentration of 25 µg/mL exhibit over 50% inhibitory rate against TIE-2 in in vitro enzymatic activity assay, and the IC50 values of 2 hits are lower than 1 µM. Further optimization and SAR analysis based on compound TP-S1-30 and 31 were carried out by using substructure searching strategy, leading to the discovery of several sub-100 nM inhibitors. Among them, the most potent compound, TP-S1-68, showed an inhibitory IC50 of 0.149 µM. These novel inhibitors of TIE-2 discovered in this study and the analogs of the active core scaffolds can serve as the starting points for further drug development.

Importance of protein flexibility in ranking inhibitor affinities: modeling the binding mechanisms of piperidine carboxamides as Type I1/2 ALK inhibitors.

Anaplastic lymphoma kinase (ALK) has gained increased attention as an attractive therapeutic target for the treatment of various cancers, especially non-small-cell lung cancer (NSCLC). Recently, piperidine carboxamides were reported as Type I1/2 inhibitors of ALK, which occupy both the ATP binding site and the back ATP hydrophobic cavity in DFG-in conformation. Due to the dynamic behavior of ALK in the binding of Type I1/2 inhibitors, the accurate predictions of the binding structures and relative binding potencies of these inhibitors are quite challenging. In this study, different modeling techniques, including molecular docking, ensemble docking based on multiple receptor conformations, molecular dynamics simulations and free energy calculations, were utilized to explore the binding mechanisms of piperidine carboxamides. Our predictions show that the conventional docking protocols are not sufficient to predict the relative binding potencies of the studied inhibitors with high accuracy, but incorporating protein flexibility before or after docking is quite effective to improve the prediction accuracy. Notably, the binding free energies predicted by MM/GBSA or MM/PBSA based on the MD simulations for the docked poses give the highest correlation with the experimental data, highlighting the importance of the inclusion of receptor flexibility for the accurate predictions of the binding potencies for Type I1/2 inhibitors of ALK. Furthermore, the comprehensive analysis of several pairs of representative inhibitors demonstrates the importance of hydrophobic interactions in improving the binding affinities of the inhibitors with the hot-spot residues surrounding the binding pocket. This work is expected to provide valuable clues for further rational design of novel and potent Type I1/2 ALK inhibitors.

Pathway-dependent inhibition of paclitaxel hydroxylation by kinase inhibitors and assessment of drug-drug interaction potentials.

Paclitaxel is often used in combination with small molecule kinase inhibitors to enhance antitumor efficacy against various malignancies. Because paclitaxel is metabolized by CYP2C8 and CYP3A4, the possibility of drug-drug interactions mediated by enzyme inhibition may exist between the combining agents. In the present study, a total of 12 kinase inhibitors were evaluated for inhibitory potency in human liver microsomes by monitoring the formation of CYP2C8 and CYP3A4 metabolites simultaneously. For reversible inhibition, nilotinib was found to be the most potent inhibitor against both CYP2C8 and CYP3A4, and the inhibition potency could be explained by strong hydrogen binding based on molecular docking simulations and type II binding based on spectral analysis. Comparison of K(i) values revealed that the CYP2C8 pathway was more sensitive toward some kinase inhibitors (such as axitinib), while the CYP3A4 pathway was preferentially inhibited by others (such as bosutinib). Pathway-dependent inactivation (time-dependent inhibition) was also observed for a number of kinase inhibitors against CYP3A4 but not CYP2C8. Further studies showed that axitinib had a K(I) of 0.93 µM and k(inact) of 0.0137 min(-1), and the observed inactivation toward CYP3A4 was probably due to the formation of reactive intermediate(s). Using a static model, a reasonably accurate prediction of drug-drug interactions was achieved by incorporating parallel pathways and hepatic extraction ratio. The present results suggest that potent and pathway-dependent inhibition of CYP2C8 and/or CYP3A4 pathways by kinase inhibitors may alter the ratio of paclitaxel metabolites in vivo, and that such changes can be clinically relevant as differential metabolism has been linked to paclitaxel-induced neurotoxicity in cancer patients.

Assessing an ensemble docking-based virtual screening strategy for kinase targets by considering protein flexibility.

In this study, to accommodate receptor flexibility, based on multiple receptor conformations, a novel ensemble docking protocol was developed by using the naïve Bayesian classification technique, and it was evaluated in terms of the prediction accuracy of docking-based virtual screening (VS) of three important targets in the kinase family: ALK, CDK2, and VEGFR2. First, for each target, the representative crystal structures were selected by structural clustering, and the capability of molecular docking based on each representative structure to discriminate inhibitors from non-inhibitors was examined. Then, for each target, 50 ns molecular dynamics (MD) simulations were carried out to generate an ensemble of the conformations, and multiple representative structures/snapshots were extracted from each MD trajectory by structural clustering. On average, the representative crystal structures outperform the representative structures extracted from MD simulations in terms of the capabilities to separate inhibitors from non-inhibitors. Finally, by using the naïve Bayesian classification technique, an integrated VS strategy was developed to combine the prediction results of molecular docking based on different representative conformations chosen from crystal structures and MD trajectories. It was encouraging to observe that the integrated VS strategy yields better performance than the docking-based VS based on any single rigid conformation. This novel protocol may provide an improvement over existing strategies to search for more diverse and promising active compounds for a target of interest.

Assessing the performance of MM/PBSA and MM/GBSA methods. 5. Improved docking performance using high solute dielectric constant MM/GBSA and MM/PBSA rescoring.

With the rapid development of computational techniques and hardware, more rigorous and precise theoretical models have been used to predict the binding affinities of a large number of small molecules to biomolecules. By employing continuum solvation models, the MM/GBSA and MM/PBSA methodologies achieve a good balance between low computational cost and reasonable prediction accuracy. In this study, we have thoroughly investigated the effects of interior dielectric constant, molecular dynamics (MD) simulations, and the number of top-scored docking poses on the performance of the MM/GBSA and MM/PBSA rescoring of docking poses for three tyrosine kinases, including ABL, ALK, and BRAF. Overall, the MM/PBSA and MM/GBSA rescoring achieved comparative accuracies based on a relatively higher solute (or interior) dielectric constant (i.e. ε = 2, or 4), and could markedly improve the 'screening power' and 'ranking power' given by Autodock. Moreover, with a relatively higher solute dielectric constant, the MM/PBSA or MM/GBSA rescoring based on the best scored docking poses and the multiple top-scored docking poses gave similar predictions, implying that much computational cost can be saved by considering the best scored docking poses only. Besides, compared with the rescoring based on the minimized structures, the rescoring based on the MD simulations might not be completely necessary due to its negligible impact on the docking performance. Considering the much higher computational demand of MM/PBSA, MM/GBSA with a high solute dielectric constant (ε = 2 or 4) is recommended for the virtual screening of tyrosine kinases.

Comprehensive, Open-Source, and Automated Workflow for Multisite λ-Dynamics in Lead Optimization.

Multisite λ-dynamics (MSLD) is a highly efficient binding free energy calculation method that samples multiple ligands in a single round by assigning different λ values to the alchemical part of each ligand. This method holds great promise for lead optimization (LO) in drug discovery. However, the complex data preparation and simulation process limits its widespread application in diverse protein-ligand systems. To address this challenge, we developed a comprehensive, open-source, and automated workflow for MSLD calculations based on the BLaDE dynamics engine. This workflow incorporates the Ligand Internal and Cartesian coordinate reconstruction-based alignment algorithm (LIC-align) and an optimized maximum common substructure (MCS) search algorithm to accurately generate MSLD multiple topologies with ideal perturbation patterns. Furthermore, our workflow is highly modularized, allowing straightforward integration and extension of various simulation techniques, and is highly accessible to nonexperts. This workflow was validated by calculating the relative binding free energies of large-scale congeneric ligands, many of which have large perturbing groups. The agreement between the calculations and experiments was excellent, with an average unsigned error of 1.08 ± 0.47 kcal/mol. More than 57.1% of the ligands had an error of less than 1.0 kcal/mol, and the perturbations of 6 targets were fully connected via the calculations, while those of 2 targets were connected via both calculations and experimental data. The Pearson correlation coefficient reached 0.88, indicating that the MSLD workflow provides accurate predictions that can guide lead optimization in drug discovery. We also examined the impact of single-site versus multisite perturbations, ligand grouping by perturbing group size, and the position of the anchor atom on the MSLD performance. By integrating our proposed LIC-align and optimized MCS search algorithm along with the coping strategies to handle challenging molecular substructures, our workflow can handle many realistic scenarios more reasonably than all previously published methods. Moreover, we observed that our MSLD workflow achieved similar accuracy to free energy perturbation (FEP) while improving computational efficiency by over 1 order of magnitude in speedup. These findings provide valuable insights and strategies for further MSLD development, making MSLD a competitive tool for lead optimization.

Dissecting the role of ALK double mutations in drug resistance to lorlatinib with in-depth theoretical modeling and analysis.

Anaplastic lymphoma kinase (ALK) is implicated in the genesis of multiple malignant tumors. Lorlatinib stands out as the most advanced and effective inhibitor currently used in the clinic for the treatment of ALK-positive non-small cell lung cancer. However, resistance to lorlatinib has inevitably manifested over time, with double/triple mutations of G1202, L1196, L1198, C1156 and I1171 frequently observed in clinical practice, and tumors regrow within a short time after treatment with lorlatinib. Therefore, elucidating the mechanism of resistance to lorlatinib is paramount in paving the way for innovative therapeutic strategies and the development of next-generation drugs. In this study, we leveraged multiple computational methodologies to delve into the resistance mechanisms of three specific double mutations of ALKG1202R/L1196M, ALKG1202R/L1198F and ALKI1171N/L1198F to lorlatinib. We analyzed these mechanisms through qualitative (PCA, DCCM) and quantitative (MM/GBSA, US) kinetic analyses. The qualitative analysis shows that these mutations exert minimal perturbations on the conformational dynamics of the structural domains of ALK. The energetic and structural assessments show that the van der Waals interactions, formed by the conserved residue Leu1256 within the ATP-binding site and the residues Glu1197 and Met1199 in the hinge domain with lorlatinib, play integral roles in the occurrence of drug resistance. Furthermore, the US simulation results elucidate that the pathways through which lorlatinib dissociates vary across mutant systems, and the distinct environments during the dissociation process culminate in diverse resistance mechanisms. Collectively, these insights provide important clues for the design of novel inhibitors to combat resistance.

A general model for predicting enzyme functions based on enzymatic reactions.

Accurate prediction of the enzyme comission (EC) numbers for chemical reactions is essential for the understanding and manipulation of enzyme functions, biocatalytic processes and biosynthetic planning. A number of machine leanring (ML)-based models have been developed to classify enzymatic reactions, showing great advantages over costly and long-winded experimental verifications. However, the prediction accuracy for most available models trained on the records of chemical reactions without specifying the enzymatic catalysts is rather limited. In this study, we introduced BEC-Pred, a BERT-based multiclassification model, for predicting EC numbers associated with reactions. Leveraging transfer learning, our approach achieves precise forecasting across a wide variety of Enzyme Commission (EC) numbers solely through analysis of the SMILES sequences of substrates and products. BEC-Pred model outperformed other sequence and graph-based ML methods, attaining a higher accuracy of 91.6%, surpassing them by 5.5%, and exhibiting superior F1 scores with improvements of 6.6% and 6.0%, respectively. The enhanced performance highlights the potential of BEC-Pred to serve as a reliable foundational tool to accelerate the cutting-edge research in synthetic biology and drug metabolism. Moreover, we discussed a few examples on how BEC-Pred could accurately predict the enzymatic classification for the Novozym 435-induced hydrolysis and lipase efficient catalytic synthesis. We anticipate that BEC-Pred will have a positive impact on the progression of enzymatic research.

Structure-based virtual screening of novel USP5 inhibitors targeting the zinc finger ubiquitin-binding domain.

The equilibrium of cellular protein levels is pivotal for maintaining normal physiological functions. USP5 belongs to the deubiquitination enzyme (DUBs) family, controlling protein degradation and preserving cellular protein homeostasis. Aberrant expression of USP5 is implicated in a variety of diseases, including cancer, neurodegenerative diseases, and inflammatory diseases. In this paper, a multi-level virtual screening (VS) approach was employed to target the zinc finger ubiquitin-binding domain (ZnF-UBD) of USP5, leading to the identification of a highly promising candidate compound 0456-0049. Molecular dynamics (MD) simulations were then employed to assess the stability of complex binding and predict hotspot residues in interactions. The results indicated that the candidate stably binds to the ZnF-UBD of USP5 through crucial interactions with residues ARG221, TRP209, GLY220, ASN207, TYR261, TYR259, and MET266. Binding free energy calculations, along with umbrella sampling (US) simulations, underscored a superior binding affinity of the candidate relative to known inhibitors. Moreover, US simulations revealed conformational changes of USP5 during ligand dissociation. These insights provide a valuable foundation for the development of novel inhibitors targeting USP5.