Binding Affinity Prediction Research Articles

TwoFold: Highly accurate structure and affinity prediction for protein-ligand complexes from sequences

We describe our development of ab initio protein-ligand binding pose prediction models based on transformers and binding affinity prediction models based on the neural tangent kernel (NTK). Folding both protein and ligand, the TwoFold models achieve efficient and quality predictions matching state-of-the-art implementations while additionally reconstructing protein structures. Solving NTK models points to a new use case for highly optimized linear solver benchmarking codes on HPC.

TAG-DTA: Binding-region-guided strategy to predict drug-target affinity using transformers

The proper assessment of target-specific compound selectivity is paramount in the drug discovery context, promoting the identification of drug-target interactions (DTIs) and the discovery of potential leads. On that account, the accurate prediction of an unbiased drug-target binding affinity (DTA) metric is pivotal to understanding the binding process. Most in silico computational approaches, however, neglect the inter-dependency of the proteomics, chemical, and pharmacological spaces and the explainability during the model construction. Furthermore, these methods have yet to actively include information associated with binding pockets during the learning process, which is essential to DTA prediction performance and model explainability. In this study, we propose an end-to-end binding-region-guided Transformer-based architecture that simultaneously predicts the 1D binding pocket and the binding affinity of DTI pairs, where the prediction of the 1D binding pocket guides and conditions the prediction of DTA. This architecture uses 1D raw sequential and structural data to represent the proteins and compounds, respectively, and combines multiple Transformer-Encoder blocks to capture and learn the proteomics, chemical, and pharmacological contexts. The predicted 1D binding pocket conditions the attention mechanism of the Transformer-Encoder used to learn the pharmacological space in order to model the inter-dependency amongst binding-related positions. The results show that the proposed architecture, TAG-DTA, achieved the best performance in DTA prediction compared to state-of-the-art benchmarks, including in unknown subsets of the proteomics and chemical representation spaces. Moreover, the 1D binding pocket prediction increases the discriminative power and robustness of the aggregate representation of the pharmacological space and improves the DTA prediction performance. Overall, this research study validates the applicability of an end-to-end Transformer-based architecture in the context of drug discovery, and that combining computationally different yet contextually related tasks is critical to new findings in the DTI domain. Additionally, it shows that TAG-DTA is capable of providing increasing DTI and prediction understanding due to the nature of the attention blocks and prediction of the 1D binding pocket. The data and source code used in this study are available at: https://github.com/larngroup/TAG-DTA.

Binding affinity predictions with hybrid quantum-classical convolutional neural networks

Central in drug design is the identification of biomolecules that uniquely and robustly bind to a target protein, while minimizing their interactions with others. Accordingly, precise binding affinity prediction, enabling the accurate selection of suitable candidates from an extensive pool of potential compounds, can greatly reduce the expenses associated to practical experimental protocols. In this respect, recent advances revealed that deep learning methods show superior performance compared to other traditional computational methods, especially with the advent of large datasets. These methods, however, are complex and very time-intensive, thus representing an important clear bottleneck for their development and practical application. In this context, the emerging realm of quantum machine learning holds promise for enhancing numerous classical machine learning algorithms. In this work, we take one step forward and present a hybrid quantum-classical convolutional neural network, which is able to reduce by 20% the complexity of the classical counterpart while still maintaining optimal performance in the predictions. Additionally, this results in a significant cost and time savings of up to 40% in the training stage, which means a substantial speed-up of the drug design process.

Ensemble of local and global information for Protein–Ligand Binding Affinity Prediction

Accurately predicting protein–ligand binding affinities is crucial for determining molecular properties and understanding their physical effects. Neural networks and transformers are the predominant methods for sequence modeling, and both have been successfully applied independently for protein–ligand binding affinity prediction. As local and global information of molecules are vital for protein–ligand binding affinity prediction, we aim to combine bi-directional gated recurrent unit (BiGRU) and convolutional neural network (CNN) to effectively capture both local and global molecular information. Additionally, attention mechanisms can be incorporated to automatically learn and adjust the level of attention given to local and global information, thereby enhancing the performance of the model. To achieve this, we propose the PLAsformer approach, which encodes local and global information of molecules using 3DCNN and BiGRU with attention mechanism, respectively. This approach enhances the model’s ability to encode comprehensive local and global molecular information.PLAsformer achieved a Pearson’s correlation coefficient of 0.812 and a Root Mean Square Error (RMSE) of 1.284 when comparing experimental and predicted affinity on the PDBBind-2016 dataset. These results surpass the current state-of-the-art methods for binding affinity prediction. The high accuracy of PLAsformer’s predictive performance, along with its excellent generalization ability, is clearly demonstrated by these findings.

Efficient prediction of relative ligand binding affinity in drug discovery.

Efficient prediction of relative ligand binding affinity in drug discovery.

Neo-intline: integrated pipeline enables neoantigen design through the in-silico presentation of T-cell epitope

Neoantigen vaccines are one of the most effective immunotherapies for personalized tumour treatment. The current immunogen design of neoantigen vaccines is usually based on whole-genome sequencing (WGS) and bioinformatics prediction that focuses on the prediction of binding affinity between peptide and MHC molecules, ignoring other peptide-presenting related steps. This may result in a gap between high prediction accuracy and relatively low clinical effectiveness. In this study, we designed an integrated in-silico pipeline, Neo-intline, which started from the SNPs and indels of the tumour samples to simulate the presentation process of peptides in-vivo through an integrated calculation model. Validation on the benchmark dataset of TESLA and clinically validated neoantigens illustrated that neo-intline could outperform current state-of-the-art tools on both sample level and melanoma level. Furthermore, by taking the mouse melanoma model as an example, we verified the effectiveness of 20 neoantigens, including 10 MHC-I and 10 MHC-II peptides. The in-vitro and in-vivo experiments showed that both peptides predicted by Neo-intline could recruit corresponding CD4+ T cells and CD8+ T cells to induce a T-cell-mediated cellular immune response. Moreover, although the therapeutic effect of neoantigen vaccines alone is not sufficient, combinations with other specific therapies, such as broad-spectrum immune-enhanced adjuvants of granulocyte-macrophage colony-stimulating factor (GM-CSF) and polyinosinic-polycytidylic acid (poly(I:C)), or immune checkpoint inhibitors, such as PD-1/PD-L1 antibodies, can illustrate significant anticancer effects on melanoma. Neo-intline can be used as a benchmark process for the design and screening of immunogenic targets for neoantigen vaccines.

Artificial intelligence for prediction of biological activities and generation of molecular hits using stereochemical information

In this work, we develop a method for generating targeted hit compounds by applying deep reinforcement learning and attention mechanisms to predict binding affinity against a biological target while considering stereochemical information. The novelty of this work is a deep model Predictor that can establish the relationship between chemical structures and their corresponding pIC_{50} values. We thoroughly study the effect of different molecular descriptors such as ECFP4, ECFP6, SMILES and RDKFingerprint. Also, we demonstrated the importance of attention mechanisms to capture long-range dependencies in molecular sequences. Due to the importance of stereochemical information for the binding mechanism, this information was employed both in the prediction and generation processes. To identify the most promising hits, we apply the self-adaptive multi-objective optimization strategy. Moreover, to ensure the existence of stereochemical information, we consider all the possible enumerated stereoisomers to provide the most appropriate 3D structures. We evaluated this approach against the Ubiquitin-Specific Protease 7 (USP7) by generating putative inhibitors for this target. The predictor with SMILES notations as descriptor plus bidirectional recurrent neural network using attention mechanism has the best performance. Additionally, our methodology identify the regions of the generated molecules that are important for the interaction with the receptor’s active site. Also, the obtained results demonstrate that it is possible to discover synthesizable molecules with high biological affinity for the target, containing the indication of their optimal stereochemical conformation.

Iterative Knowledge-Based Scoring Function for Protein-Ligand Interactions by Considering Binding Affinity Information.

Scoring functions for protein-ligand interactions play a critical role in structure-based drug design. Owing to the good balance between general applicability and computational efficiency, knowledge-based scoring functions have obtained significant advancements and achieved many successes. Nevertheless, knowledge-based scoring functions face a challenge in utilizing the experimental affinity data and thus may not perform well in binding affinity prediction. Addressing the challenge, we have proposed an improved version of the iterative knowledge-based scoring function ITScore by considering binding affinity information, which is referred to as ITScoreAff, based on a large training set of 6216 protein-ligand complexes with both structures and affinity data. ITScoreAff was extensively evaluated and compared with ITScore, 33 traditional, and 6 machine learning scoring functions in terms of docking power, ranking power, and screening power on the independent CASF-2016 benchmark. It was shown that ITScoreAff obtained an overall better performance than the other 40 scoring functions and gave an average success rate of 85.3% in docking power, a correlation coefficient of 0.723 in scoring power, and an average rank correlation coefficient of 0.668 in ranking power. In addition, ITScoreAff also achieved the overall best screening power when the top 10% of the ranked database were considered. These results demonstrated the robustness of ITScoreAff and its improvement over existing scoring functions.

ResBiGAAT: Residual Bi-GRU with attention for protein-ligand binding affinity prediction

Protein-ligand interaction plays a crucial role in drug discovery, facilitating efficient drug development and enabling drug repurposing. Several computational algorithms, such as Graph Neural Networks and Convolutional Neural Networks, have been proposed to predict the binding affinity using the three-dimensional structure of ligands and proteins. However, there are limitations due to the need for experimental characterization of the three-dimensional structure of protein sequences, which is still lacking for some proteins. Moreover, these models often suffer from unnecessary complexity, resulting in extraneous computations. This study presents ResBiGAAT, a novel deep learning model that combines a deep Residual Bidirectional Gated Recurrent Unit with two-sided self-attention mechanisms. ResBiGAAT leverages protein and ligand sequence-level features and their physicochemical properties to efficiently predict protein-ligand binding affinity. Through rigorous evaluation using 5-fold cross-validation, we demonstrate the performance of our proposed approach. The model exhibits competitive performance on an external dataset, highlighting its generalizability. Our publicly available web interface, located at resbigaat.streamlit.app, allows users to conveniently input protein and ligand sequences to estimate binding affinity.

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design

In the prediction of protein-ligand affinity, the traditional methods require a large amount of computing resources, and have certain limitations in predicting and simulating the structural changes. Although employing data-driven approaches can yield favorable outcomes in deep learning, it entails a lack of interpretability. Some methods may require additional structural information or domain knowledge to support the interpretation, which may limit their applicability. This paper proposes an affinity variational autoencoder (AffinityVAE) using interaction feature mapping and a variational autoencoder, which consists of a multi-objective model capable of end-to-end affinity prediction and drug discovery. In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high efficiency of the proposed model. The experimental results show that AffinityVAE has very high prediction performance, and it has the potential to enhance the diversity and the amount of protein-ligand binding data, which promotes the drug development.

Designing peptides predicted to bind to the omicron variant better than ACE2 via computational protein design and molecular dynamics.

Brought about by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), coronavirus disease (COVID-19) pandemic has resulted in large numbers of worldwide deaths and cases. Several SARS-CoV-2 variants have evolved, and Omicron (B.1.1.529) was one of the important variants of concern. It gets inside human cells by using its S1 subunit's receptor-binding domain (SARS-CoV-2-RBD) to bind to Angiotensin-converting enzyme 2 receptor's peptidase domain (ACE2-PD). Using peptides to inhibit binding interactions (BIs) between ACE2-PD and SARS-CoV-2-RBD is one of promising COVID-19 therapies. Employing computational protein design (CPD) as well as molecular dynamics (MD), this study used ACE2-PD's α1 helix to generate novel 25-mer peptide binders (SPB25) of Omicron RBD that have predicted binding affinities (ΔGbind (MM‑GBSA)) better than ACE2 by increasing favorable BIs between SPB25 and the conserved residues of RBD. Results from MD and the MM-GBSA method identified two best designed peptides (SPB25T7L/K11A and SPB25T7L/K11L with ΔGbind (MM‑GBSA) of -92.4 ± 0.4 and -95.7 ± 0.5 kcal/mol, respectively) that have better ΔGbind (MM‑GBSA) to Omicron RBD than ACE2 (-87.9 ± 0.5 kcal/mol) and SPB25 (-71.6 ± 0.5 kcal/mol). Additionally, they were predicted to have slightly higher stabilities, based on their percent helicities in water, than SBP1 (the experimentally proven inhibitor of SARS-CoV-2-RBD). Our two best designed SPB25s are promising candidates as omicron variant inhibitors.

Experimental Uncertainty in Training Data for Protein-Ligand Binding Affinity Prediction Models

The accuracy of machine learning models for protein-ligand binding affinity prediction depends on the quality of the experimental data they are trained on. Most of these models are trained and tested on different subsets of the PDBbind database, which is the main source of protein-ligand complexes with annotated binding affinity in the public domain. However, estimating its experimental uncertainty is not straightforward because just a few protein-ligand complexes have more than one measurement associated. In this work, we analyze bioactivity data from ChEMBL to estimate the experimental uncertainty associated with the three binding affinity measures included in the PDBbind (Ki, Kd, and IC50), as well as the effect of combining them. The experimental uncertainty of combining these three affinity measures was characterized by a mean absolute error of 0.78 logarithmic units, a root mean square error of 1.04 and a Pearson correlation coefficient of 0.76. These estimations were contrasted with the performances obtained by state-of-the-art machine learning models for binding affinity prediction, showing that these models tend to be overoptimistic when evaluated on the core set from PDBbind.

Ligand Based Virtual Screening Testing and Analysis for Plasmodium Falciparum

Malaria, caused by the parasite Plasmodium falciparum, continues to pose a significant global health challenge, with drug resistance and limited treatment options exacerbating the problem. Ligand-Based Virtual Screening (LBVS) has emerged as a promising computational tool for identifying potential drug candidates. This research focuses on the application of LBVS to target essential proteins within Plasmodium falciparum and identify small molecules with inhibitory potential. A diverse dataset of ligands and advanced computational algorithms were employed to predict binding affinities and screen compounds for potential antimalarial activity. LBVS is a computational method used to identify potential drug candidates by screening large databases of molecules for those that have a high similarity to known active molecules. This is done by calculating the shape and chemical properties of the molecules and comparing them to the known active molecules. Malaria is a mosquito-borne disease caused by the parasite Plasmodium falciparum. It isa major public health problem, especially in tropical and subtropical regions. LBVS can be used to accelerate the drug discovery process by identifying potential drug candidatesmore quickly and efficiently. Keywords: LBVS, Plasmodium Falciparum, DHFR, Anti-malarial compound, Protein target.

Computing the relative binding affinity of ligands based on a pairwise binding comparison network

Structure-based lead optimization is an open challenge in drug discovery, which is still largely driven by hypotheses and depends on the experience of medicinal chemists. Here we propose a pairwise binding comparison network (PBCNet) based on a physics-informed graph attention mechanism, specifically tailored for ranking the relative binding affinity among congeneric ligands. Benchmarking on two held-out sets (provided by Schrödinger and Merck) containing over 460 ligands and 16 targets, PBCNet demonstrated substantial advantages in terms of both prediction accuracy and computational efficiency. Equipped with a fine-tuning operation, the performance of PBCNet reaches that of Schrödinger’s FEP+, which is much more computationally intensive and requires substantial expert intervention. A further simulation-based experiment showed that active learning-optimized PBCNet may accelerate lead optimization campaigns by 473%. Finally, for the convenience of users, a web service for PBCNet is established to facilitate complex relative binding affinity prediction through an easy-to-operate graphical interface.

TeM-DTBA: time-efficient drug target binding affinity prediction using multiple modalities with Lasso feature selection.

Drug discovery, especially virtual screening and drug repositioning, can be accelerated through deeper understanding and prediction of Drug Target Interactions (DTIs). The advancement of deep learning as well as the time and financial costs associated with conventional wet-lab experiments have made computational methods for DTI prediction more popular. However, the majority of these computational methods handle the DTI problem as a binary classification task, ignoring the quantitative binding affinity that determines the drug efficacy to their target proteins. Moreover, computational space as well as execution time of the model is often ignored over accuracy. To address these challenges, we introduce a novel method, called Time-efficient Multimodal Drug Target Binding Affinity (TeM-DTBA), which predicts the binding affinity between drugs and targets by fusing different modalities based on compound structures and target sequences. We employ the Lasso feature selection method, which lowers the dimensionality of feature vectors and speeds up the proposed model training time by more than 50%. The results from two benchmark datasets demonstrate that our method outperforms state-of-the-art methods in terms of performance. The mean squared errors of 18.8% and 23.19%, achieved on the KIBA and Davis datasets, respectively, suggest that our method is more accurate in predicting drug-target binding affinity.

Improving the accuracy of the FMO binding affinity prediction of ligand-receptor complexes containing metals.

Polarization and charge transfer strongly characterize the ligand-receptor interaction when metal atoms are present, as for the Au(I)-biscarbene/DNA G-quadruplex complexes. In a previous work (J Comput Aided Mol Des2022, 36, 851-866) we used the ab initio FMO2 method at the RI-MP2/6-31G* level of theory with the PCM [1] solvation approach to calculate the binding energy (ΔEFMO) of two Au(I)-biscarbene derivatives, [Au(9-methylcaffein-8-ylidene)2]+ and [Au(1,3-dimethylbenzimidazole-2-ylidene)2]+, able to interact with DNA G-quadruplex motif. We found that ΔEFMO and ligand-receptor pair interaction energies (EINT) show very large negative values making the direct comparison with experimental data difficult and related this issue to the overestimation of the embedded charge transfer energy between fragments containing metal atoms. In this work, to improve the accuracy of the FMO method for predicting the binding affinity of metal-based ligands interacting with DNA G-quadruplex (Gq), we assess the effect of the following computational features: (i) the electron correlation, considering the Hartree-Fock (HF) and a post-HF method, namely RI-MP2; (ii) the two (FMO2) and three-body (FMO3) approaches; (iii) the basis set size (polarization functions and double-ζ vs. triple-ζ) and (iv) the embedding electrostatic potential (ESP). Moreover, the partial screening method was systematically adopted to simulate the solvent screening effect for each calculation. We found that the use of the ESP computed using the screened point charges for all atoms (ESP-SPTC) has a critical impact on the accuracy of both ΔEFMO and EINT, eliminating the overestimation of charge transfer energy and leading to energy values with magnitude comparable with typical experimental binding energies. With this computational approach, EINT values describe the binding efficiency of metal-based binders to DNA Gq more accurately than ΔEFMO. Therefore, to study the binding process of metal containing systems with the FMO method, the adoption of partial screening solvent method combined with ESP-SPCT should be considered. This computational protocol is suggested for FMO calculations on biological systems containing metals, especially when the adoption of the default ESP treatment leads to questionable results.

Selective modifications of lactose and N-acetyllactosamine with sulfate and aromatic bulky groups unveil unique structural insights in galectin-1-ligand recognition

Galectins, a family of endogenous glycan-binding proteins, play crucial roles in a broad range of physiological and pathological processes. Galectin-1 (Gal-1), a proto-type member of this family, is overexpressed in several cancers and plays critical roles in tumor-immune escape, angiogenesis and metastasis. Thus, generation of high-affinity Gal-1 inhibitors emerges as an attractive therapeutic approach for a wide range of neoplastic conditions. Small-molecule carbohydrate inhibitors based on lactose (Lac) and N-acetyllactosamine (LacNAc) structures have been tested showing different results. In this study, we evaluated Lac- and LacNAc-based compounds with specific chemical modifications at key positions as Gal-1 ligands by competitive solid-phase assays (SPA) and isothermal titration calorimetry (ITC). Both assays showed excellent correlation, highlighting that lactosides bearing bulky aromatic groups at the anomeric carbon and sulfate groups at the O3′ position exhibited the highest binding affinities. To dissect the atomistic determinants for preferential affinity of the different tested Gal-1 ligands, molecular docking simulations were conducted and PRODIGY-LIG structure-based method was employed to predict binding affinity in protein–ligand complexes. Notably, calculated binding free energies derived from the molecular docking were in accordance with experimental values determined by SPA and ITC, showing excellent correlation between theoretical and experimental approaches. Moreover, this analysis showed that 3′-O-sulfate groups interact with residues of the Gal-1 subsite B, mainly with Asn33, while the ester groups of the aromatic anomeric group interact with Gly69 and Thr70 at Gal-1 subsite E, extending deeper into the pocket, which could account for the enhanced binding affinity. This study contributes to the rational design of highly optimized Gal-1 inhibitors to be further studied in cancer models and other pathologic conditions.

Drug-target binding affinity prediction using message passing neural network and self supervised learning

BackgroundDrug-target binding affinity (DTA) prediction is important for the rapid development of drug discovery. Compared to traditional methods, deep learning methods provide a new way for DTA prediction to achieve good performance without much knowledge of the biochemical background. However, there are still room for improvement in DTA prediction: (1) only focusing on the information of the atom leads to an incomplete representation of the molecular graph; (2) the self-supervised learning method could be introduced for protein representation.ResultsIn this paper, a DTA prediction model using the deep learning method is proposed, which uses an undirected-CMPNN for molecular embedding and combines CPCProt and MLM models for protein embedding. An attention mechanism is introduced to discover the important part of the protein sequence. The proposed method is evaluated on the datasets Ki and Davis, and the model outperformed other deep learning methods.ConclusionsThe proposed model improves the performance of the DTA prediction, which provides a novel strategy for deep learning-based virtual screening methods.

GPCNDTA: Prediction of drug-target binding affinity through cross-attention networks augmented with graph features and pharmacophores

Drug-target affinity prediction is a challenging task in drug discovery. The latest computational models have limitations in mining edge information in molecule graphs, accessing to knowledge in pharmacophores, integrating multimodal data of the same biomolecule and realizing effective interactions between two different biomolecules. To solve these problems, we proposed a method called Graph features and Pharmacophores augmented Cross-attention Networks based Drug-Target binding Affinity prediction (GPCNDTA). First, we utilized the GNN module, the linear projection unit and self-attention layer to correspondingly extract features of drugs and proteins. Second, we devised intramolecular and intermolecular cross-attention to respectively fuse and interact features of drugs and proteins. Finally, the linear projection unit was applied to gain final features of drugs and proteins, and the Multi-Layer Perceptron was employed to predict drug-target binding affinity. Three major innovations of GPCNDTA are as follows: (i) developing the residual CensNet and the residual EW-GCN to correspondingly extract features of drug and protein graphs, (ii) regarding pharmacophores as a new type of priors to heighten drug-target affinity prediction performance, and (iii) devising intramolecular and intermolecular cross-attention, in which the intramolecular cross-attention realizes the effective fusion of different modal data related to the same biomolecule, and the intermolecular cross-attention fulfills the information interaction between two different biomolecules in attention space. The test results on five benchmark datasets imply that GPCNDTA achieves the best performance compared with state-of-the-art computational models. Besides, relying on ablation experiments, we proved effectiveness of GNN modules, pharmacophores and two cross-attention strategies in improving the prediction accuracy, stability and reliability of GPCNDA. In case studies, we applied GPCNDTA to predict binding affinities between 3C-like proteinase and 185 drugs, and observed that most binding affinities predicted by GPCNDTA are close to corresponding experimental measurements.

Novel multi-objective affinity approach allows to identify pH-specific μ-opioid receptor agonists

Opioids are essential pharmaceuticals due to their analgesic properties, however, lethal side effects, addiction, and opioid tolerance are extremely challenging. The development of novel molecules targeting the mu-opioid receptor (MOR) in inflamed, but not in healthy tissue, could significantly reduce these unwanted effects. Finding such novel molecules can be achieved by maximizing the binding affinity to the MOR at acidic pH while minimizing it at neutral pH, thus combining two conflicting objectives. Here, this multi-objective optimal affinity approach is presented, together with a virtual drug discovery pipeline for its practical implementation. When applied to finding pH-specific drug candidates, it combines protonation state-dependent structure and ligand preparation with high-throughput virtual screening. We employ this pipeline to characterize a set of MOR agonists identifying a morphine-like opioid derivative with higher predicted binding affinities to the MOR at low pH compared to neutral pH. Our results also confirm existing experimental evidence that NFEPP, a previously described fentanyl derivative with reduced side effects, and recently reported beta-fluorofentanyls and -morphines show an increased specificity for the MOR at acidic pH when compared to fentanyl and morphine. We further applied our approach to screen a >50K ligand library identifying novel molecules with pH-specific predicted binding affinities to the MOR. The presented differential docking pipeline can be applied to perform multi-objective affinity optimization to identify safer and more specific drug candidates at large scale.