Zechen Wang

Protein-protein binding affinity is important for understanding protein interactions within a protein complex and for identifying strong drug-peptide binders to a target protein. Many structure-based models were built previously with reasonable performance. However, such models require protein complex structure as input, which is usually unavailable due to high cost and experimental constraints. To tackle such an issue, the sequence-based CrossAffinity model was constructed in this study, using the cross-attention module to extract contextual information of interacting protein components while separating the protein complex into two distinct parts to predict the protein-protein binding affinity. CrossAffinity managed to outperform all structure-based models and sequence-based models in an S34 test set containing newer protein complex structures and binding affinity values in a timeline while being trained on an older dataset, showing generalisability to new data points. In other test sets, namely S90, S90 subset and S79*, CrossAffinity also managed to outperform all other sequence-based models while maintaining comparable performance to many recently published structure-based models. The acceptable performance and quick inference of CrossAffinity enable it to be deployed in situations requiring the prediction of the binding affinity of many protein complexes that lack structural information.

The rapid development of machine learning (ML) and deep learning (DL) methods provides new opportunities for innovative drug discovery. While these techniques are widely used in docking organic molecules (drugs) with protein, an evaluation of the performance of ML and DL in treating nanostructures remains lacking. This situation becomes the main hindrance for the development of nanostructure-based medicine and medical materials. In this study, we have compared the performance of a recently developed DL model, named DeepRMSD + Vina, with the traditional molecular dynamic (MD) simulations in treating the docking problem of a carbon nanotube, the most representative nanomaterial, and the main proteinase (M^pro) of SARS-CoV-2 as the representative case. Our results indicate that most of the DL-generated structures are in good agreement with the structures optimized by MD. However, minor discrepancies were indeed observed where structural alterations happened for the flexible loops near the binding pocket of M^pro, which were not addressed in the DL-generated structures. Further analyses demonstrated that the DL-generated binding pose is a metastable conformation at a local minimum on the energy surface. The transition from such a local minimum structure to a global minimum structure has to overcome an energy barrier that is accompanied by a flip of the flexible loops. In brief, we demonstrate that the DL method has considerably high efficacy in treating nanobiosystems, with potential implications for the design of nanomedicine materials. This study also shed new light on the future development direction of the DL method for enhanced docking accuracy.

Accurate prediction of enzyme kinetic parameters is crucial for enzyme exploration and modification. Existing models face the problem of either low accuracy or poor generalization ability due to overfitting. In this work, we first developed unbiased datasets to evaluate the actual performance of these methods and proposed a deep learning model, CataPro, based on pre-trained models and molecular fingerprints to predict turnover number (k _{c a t} ), Michaelis constant (K _m ), and catalytic efficiency (k _{c a t} /K _m ). Compared with previous baseline models, CataPro demonstrates clearly enhanced accuracy and generalization ability on the unbiased datasets. In a representational enzyme mining project, by combining CataPro with traditional methods, we identified an enzyme (SsCSO) with 19.53 times increased activity compared to the initial enzyme (CSO2) and then successfully engineered it to improve its activity by 3.34 times. This reveals the high potential of CataPro as an effective tool for future enzyme discovery and modification.

In recent years, the deep learning (DL) technique has rapidly developed and shown great success in scoring the protein-ligand binding affinities. The protein-ligand conformation optimization based on DL-derived scoring functions holds broad application prospects, for instance, drug design and enzyme engineering. In this study, we evaluated the robustness of a DL-based ligand conformation optimization protocol (DeepRMSD+Vina) for optimizing structures with input perturbations by examining the predicted ligand binding poses and scoring. Our results clearly indicated that compared to traditional optimization algorithms (such as Prime MM-GBSA and Vina optimization), DeepRMSD+Vina exhibits higher performance when treating diverse protein-ligand cases. The DeepRMSD+Vina is robust and can always generate the correct binding structures even if perturbations (up to 3 Å) are introduced to the input structure. The success rate is 62% for perturbation with a RMSD within 2-3 Å. However, the success rate dramatically drops to 11% for large perturbations, with RMSD extending to 3-4 Å. Furthermore, compared to the widely used optimization protocol of AutoDock Vina, the DL-generated conformation shows a balanced performance for all of the systems under examination. Overall, the DL-based DeepRMSD+Vina is unarguably more reliable than the traditional methods, which is attributed to the physically inspired design of the neural networks in DeepRMSD+Vina where the distance-transformed features describing the atomic interactions between the protein and the ligand have been explicitly considered and modeled. The outstanding robustness of the DL-based ligand conformational optimization algorithm further validates its superiority in the field of conformational optimization.

The success of AlphaFold in protein structure prediction highlights the power of data-driven approaches in scientific research. However, developing machine learning models to design and engineer proteins with desirable functions is hampered by limited access to high-quality data sets and experimental feedback. The Critical Assessment of Protein Engineering (CAPE) challenge addresses these issues through a student-focused competition, utilizing cloud computing and biofoundries to lower barriers to entry. CAPE serves as an open platform for community learning, where mutant data sets and design algorithms from past contestants help improve overall performance in subsequent rounds. Through two competition rounds, student participants collectively designed >1500 new mutant sequences, with the best-performing variants exhibiting catalytic activity up to 5-fold higher than the wild-type parent. We envision CAPE as a collaborative platform to engage young researchers and promote computational protein engineering.

Motivation: Molecular docking is an invaluable computational tool with broad applications in computer-aided drug design and enzyme engineering. However, current molecular docking tools are typically implemented in languages such as C++ for calculation speed, which lack flexibility and user-friendliness for further development. Moreover, validating the effectiveness of external scoring functions for molecular docking and screening within these frameworks is challenging, and implementing more efficient sampling strategies is not straightforward. Results: To address these limitations, we have developed an open-source molecular docking framework, OpenDock, based on Python and PyTorch. This framework supports the integration of multiple scoring functions; some can be utilized during molecular docking and pose optimization, while others can be used for post-processing scoring. In terms of sampling, the current version of this framework supports simulated annealing and Monte Carlo optimization. Additionally, it can be extended to include methods such as genetic algorithms and particle swarm optimization for sampling docking poses and protein side chain orientations. Distance constraints are also implemented to enable covalent docking, restricted docking or distance map constraints guided pose sampling. Overall, this framework serves as a valuable tool in drug design and enzyme engineering, offering significant flexibility for most protein–ligand modelling tasks. Availability and implementation: OpenDock is publicly available at: https://github.com/guyuehuo/opendock.

Accurate protein-ligand binding poses are the prerequisites of structure-based binding affinity prediction and provide the structural basis for in-depth lead optimization in small molecule drug design. However, it is challenging to provide reasonable predictions of binding poses for different molecules due to the complexity and diversity of the chemical space of small molecules. Similarity-based molecular alignment techniques can effectively narrow the search range, as structurally similar molecules are likely to have similar binding modes, with higher similarity usually correlated to higher success rates. However, molecular similarity is not consistently high because molecules often require changes to achieve specific purposes, leading to reduced alignment precision. To address this issue, we propose a new alignment method─Z-align. This method uses topological structural information as a criterion for evaluating similarity, reducing the reliance on molecular fingerprint similarity. Our method has achieved success rates significantly higher than those of other methods at moderate levels of similarity. Additionally, our approach can comprehensively and flexibly optimize bond lengths and angles of molecules, maintaining a high accuracy even when dealing with larger molecules. Consequently, our proposed solution helps in achieving more accurate binding poses in protein-ligand docking problems, facilitating the development of small molecule drugs. Z-align is freely available as a web server at https://cloud.zelixir.com/zalign/home.

The recently reported machine learning- or deep learning-based scoring functions (SFs) have shown exciting performance in predicting protein–ligand binding affinities with fruitful application prospects. However, the differentiation between highly similar ligand conformations, including the native binding pose (the global energy minimum state), remains challenging that could greatly enhance the docking. In this work, we propose a fully differentiable, end-to-end framework for ligand pose optimization based on a hybrid SF called DeepRMSD+Vina combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF. The DeepRMSD+Vina, which combines (1) the root mean square deviation (RMSD) of the docking pose with respect to the native pose and (2) the AutoDock Vina score, is fully differentiable; thus is capable of optimizing the ligand binding pose to the energy-lowest conformation. Evaluated by the CASF-2016 docking power dataset, the DeepRMSD+Vina reaches a success rate of 94.4%, which outperforms most reported SFs to date. We evaluated the ligand conformation optimization framework in practical molecular docking scenarios (redocking and cross-docking tasks), revealing the high potentialities of this framework in drug design and discovery. Structural analysis shows that this framework has the ability to identify key physical interactions in protein–ligand binding, such as hydrogen-bonding. Our work provides a paradigm for optimizing ligand conformations based on deep learning algorithms. The DeepRMSD+Vina model and the optimization framework are available at GitHub repository https://github.com/zchwang/DeepRMSD-Vina_Optimization.

Scoring functions are important components in molecular docking for structure-based drug discovery. Traditional scoring functions, generally empirical- or force field-based, are robust and have proven to be useful for identifying hits and lead optimizations. Although multiple highly accurate deep learning- or machine learning-based scoring functions have been developed, their direct applications for docking and screening are limited. We describe a novel strategy to develop a reliable protein–ligand scoring function by augmenting the traditional scoring function Vina score using a correction term (OnionNet-SFCT). The correction term is developed based on an AdaBoost random forest model, utilizing multiple layers of contacts formed between protein residues and ligand atoms. In addition to the Vina score, the model considerably enhances the AutoDock Vina prediction abilities for docking and screening tasks based on different benchmarks (such as cross-docking dataset, CASF-2016, DUD-E and DUD-AD). Furthermore, our model could be combined with multiple docking applications to increase pose selection accuracies and screening abilities, indicating its wide usage for structure-based drug discoveries. Furthermore, in a reverse practice, the combined scoring strategy successfully identified multiple known receptors of a plant hormone. To summarize, the results show that the combination of data-driven model (OnionNet-SFCT) and empirical scoring function (Vina score) is a good scoring strategy that could be useful for structure-based drug discoveries and potentially target fishing in future.