D3EGFR: a webserver for deep learning-guided drug sensitivity prediction and drug response information retrieval for EGFR mutation-driven lung cancer.

As key oncogenic drivers in non-small-cell lung cancer (NSCLC), various mutations in the epidermal growth factor receptor (EGFR) with variable drug sensitivities have been a major obstacle for precision medicine. To achieve clinical-level drug recommendations, a platform for clinical patient case retrieval and reliable drug sensitivity prediction is highly expected. Therefore, we built a database, D3EGFRdb, with the clinicopathologic characteristics and drug responses of 1339 patients with EGFR mutations via literature mining. On the basis of D3EGFRdb, we developed a deep learning-based prediction model, D3EGFRAI, for drug sensitivity prediction of new EGFR mutation-driven NSCLC. Model validations of D3EGFRAI showed a prediction accuracy of 0.81 and 0.85 for patients from D3EGFRdb and our hospitals, respectively. Furthermore, mutation scanning of the crucial residues inside drug-binding pockets, which may occur in the future, was performed to explore their drug sensitivity changes. D3EGFR is the first platform to achieve clinical-level drug response prediction of all approved small molecule drugs for EGFR mutation-driven lung cancer and is freely accessible at https://www.d3pharma.com/D3EGFR/index.php.

D3AI-CoV: a deep learning platform for predicting drug targets and for virtual screening against COVID-19.

Target prediction and virtual screening are two powerful tools of computer-aided drug design. Target identification is of great significance for hit discovery, lead optimization, drug repurposing and elucidation of the mechanism. Virtual screening can improve the hit rate of drug screening to shorten the cycle of drug discovery and development. Therefore, target prediction and virtual screening are of great importance for developing highly effective drugs against COVID-19. Here we present D3AI-CoV, a platform for target prediction and virtual screening for the discovery of anti-COVID-19 drugs. The platform is composed of three newly developed deep learning-based models i.e., MultiDTI, MPNNs-CNN and MPNNs-CNN-R models. To compare the predictive performance of D3AI-CoV with other methods, an external test set, named Test-78, was prepared, which consists of 39 newly published independent active compounds and 39 inactive compounds from DrugBank. For target prediction, the areas under the receiver operating characteristic curves (AUCs) of MultiDTI and MPNNs-CNN models are 0.93 and 0.91, respectively, whereas the AUCs of the other reported approaches range from 0.51 to 0.74. For virtual screening, the hit rate of D3AI-CoV is also better than other methods. D3AI-CoV is available for free as a web application at http://www.d3pharma.com/D3Targets-2019-nCoV/D3AI-CoV/index.php, which can serve as a rapid online tool for predicting potential targets for active compounds and for identifying active molecules against a specific target protein for COVID-19 treatment.

D3Rings: A Fast and Accurate Method for Ring System Identification and Deep Generation of Drug-Like Cyclic Compounds.

Continuous exploration of the chemical space of molecules to find ligands with high affinity and specificity for specific targets is an important topic in drug discovery. A focus on cyclic compounds, particularly natural compounds with diverse scaffolds, provides important insights into novel molecular structures for drug design. However, the complexity of their ring structures has hindered the applicability of widely accepted methods and software for the systematic identification and classification of cyclic compounds. Herein, we successfully developed a new method, D3Rings, to identify acyclic, monocyclic, spiro ring, fused and bridged ring, and cage ring compounds, as well as macrocyclic compounds. By using D3Rings, we completed the statistics of cyclic compounds in three different databases, e.g., ChEMBL, DrugBank, and COCONUT. The results demonstrated the richness of ring structures in natural products, especially spiro, macrocycles, and fused and bridged rings. Based on this, three deep generative models, namely, VAE, AAE, and CharRNN, were trained and used to construct two data sets similar to DrugBank and COCONUT but 10 times larger than them. The enlarged data sets were then used to explore the molecular chemical space, focusing on complex ring structures, for novel drug discovery and development. Docking experiments with the newly generated COCONUT-like data set against three SARS-CoV-2 target proteins revealed that an expanded compound database improves molecular docking results. Cyclic structures exhibited the best docking scores among the top-ranked docking molecules. These results suggest the importance of exploring the chemical space of structurally novel cyclic compounds and continuous expansion of the library of drug-like compounds to facilitate the discovery of potent ligands with high binding affinity to specific targets. D3Rings is now freely available at http://www.d3pharma.com/D3Rings/.

Ligand-based approach for predicting drug targets and for virtual screening against COVID-19.

Discovering efficient drugs and identifying target proteins are still an unmet but urgent need for curing coronavirus disease 2019 (COVID-19). Protein structure-based docking is a widely applied approach for discovering active compounds against drug targets and for predicting potential targets of active compounds. However, this approach has its inherent deficiency caused by e.g. various different conformations with largely varied binding pockets adopted by proteins, or the lack of true target proteins in the database. This deficiency may result in false negative results. As a complementary approach to the protein structure-based platform for COVID-19, termed as D3Docking in our previous work, we developed in this study a ligand-based method, named D3Similarity, which is based on the molecular similarity evaluation between the submitted molecule(s) and those in an active compound database. The database is constituted by all the reported bioactive molecules against the coronaviruses, viz., severe acute respiratory syndrome coronavirus (SARS), Middle East respiratory syndrome coronavirus (MERS), severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), human betacoronavirus 2c EMC/2012 (HCoV-EMC), human CoV 229E (HCoV-229E) and feline infectious peritonitis virus (FIPV), some of which have target or mechanism information but some do not. Based on the two-dimensional (2D) and three-dimensional (3D) similarity evaluation of molecular structures, virtual screening and target prediction could be performed according to similarity ranking results. With two examples, we demonstrated the reliability and efficiency of D3Similarity by using 2D × 3D value as score for drug discovery and target prediction against COVID-19. The database, which will be updated regularly, is available free of charge at https://www.d3pharma.com/D3Targets-2019-nCoV/D3Similarity/index.php.

D3PM: a comprehensive database for protein motions ranging from residue to domain.

BACKGROUND: Knowledge of protein motions is significant to understand its functions. While currently available databases for protein motions are mostly focused on overall domain motions, little attention is paid on local residue motions. Albeit with relatively small scale, the local residue motions, especially those residues in binding pockets, may play crucial roles in protein functioning and ligands binding. RESULTS: A comprehensive protein motion database, namely D3PM, was constructed in this study to facilitate the analysis of protein motions. The protein motions in the D3PM range from overall structural changes of macromolecule to local flip motions of binding pocket residues. Currently, the D3PM has collected 7679 proteins with overall motions and 3513 proteins with pocket residue motions. The motion patterns are classified into 4 types of overall structural changes and 5 types of pocket residue motions. Impressively, we found that less than 15% of protein pairs have obvious overall conformational adaptations induced by ligand binding, while more than 50% of protein pairs have significant structural changes in ligand binding sites, indicating that ligand-induced conformational changes are drastic and mainly confined around ligand binding sites. Based on the residue preference in binding pocket, we classified amino acids into "pocketphilic" and "pocketphobic" residues, which should be helpful for pocket prediction and drug design. CONCLUSION: D3PM is a comprehensive database about protein motions ranging from residue to domain, which should be useful for exploring diverse protein motions and for understanding protein function and drug design. The D3PM is available on www.d3pharma.com/D3PM/index.php .

D3DistalMutation: a Database to Explore the Effect of Distal Mutations on Enzyme Activity.

Enzyme activity is affected by amino acid mutations, particularly mutations near the active site. Increasing evidence has shown that distal mutations more than 10 Å away from the active site may significantly affect enzyme activity. However, it is difficult to study the enzyme regulation mechanism of distal mutations due to the lack of a systematic collection of three-dimensional (3D) structures, highlighting distal mutation site and the corresponding enzyme activity change. Therefore, we constructed a distal mutation database, namely, D3DistalMutation, which relates the distal mutation to enzyme activity. As a result, we observed that approximately 80% of distal mutations could affect enzyme activity and 72.7% of distal mutations would decrease or abolish enzyme activity in D3DistalMutation. Only 6.6% of distal mutations in D3DistalMutation could increase enzyme activity, which have great potential to the industrial field. Among these mutations, the Y to F, S to D, and T to D mutations are most likely to increase enzyme activity, which sheds some light on industrial catalysis. Distal mutations decreasing enzyme activity in the allosteric pocket play an indispensable role in allosteric drug design. In addition, the pockets in the enzyme structures are provided to explore the enzyme regulation mechanism of distal mutations. D3DistalMutation is accessible free of charge at https://www.d3pharma.com/D3DistalMutation/index.php.

D3Pockets: A Method and Web Server for Systematic Analysis of Protein Pocket Dynamics.

The intrinsic dynamic properties of the ligand-binding pockets of proteins are important for the protein function mechanism and thus are useful to drug discovery and development. Few methods are available to study the dynamic properties, such as pocket stability, continuity, and correlation. In this work, we develop a method and web server, namely, D3Pockets, for exploring the dynamic properties of the protein pocket based on either molecular dynamics (MD) simulation trajectories or conformational ensembles. Application of D3Pockets on five target proteins as examples, namely, HIV-1 protease, BACE1, L-ABP, GPX4, and GR, uncovers more information on the dynamic properties of the ligand-binding pockets, which should be helpful to understanding protein function mechanism and drug design. The D3Pockets web server is available at http://www.d3pharma.com/D3Pocket/index.php .

D3CARP: a comprehensive platform with multiple-conformation based docking, ligand similarity search and deep learning approaches for target prediction and virtual screening.

Resource- and time-consuming biological experiments are unavoidable in traditional drug discovery, which have directly driven the evolution of various computational algorithms and tools for drug-target interaction (DTI) prediction. For improving the prediction reliability, a comprehensive platform is highly expected as some previously reported webservers are small in scale, single-method, or even out of service. In this study, we integrated the multiple-conformation based docking, 2D/3D ligand similarity search and deep learning approaches to construct a comprehensive webserver, namely D3CARP, for target prediction and virtual screening. Specifically, 9352 conformations with positive control of 1970 targets were used for molecular docking, and approximately 2 million target-ligand pairs were used for 2D/3D ligand similarity search and deep learning. Besides, the positive compounds were added as references, and related diseases of therapeutic targets were annotated for further disease-based DTI study. The accuracies of the molecular docking and deep learning approaches were 0.44 and 0.89, respectively. And the average accuracy of five ligand similarity searches was 0.94. The strengths of D3CARP encompass the support for multiple computational methods, ensemble docking, utilization of positive controls as references, cross-validation of predicted outcomes, diverse disease types, and broad applicability in drug discovery. The D3CARP is freely accessible at https://www.d3pharma.com/D3CARP/index.php.

A hollow beam supercontinuum generation by the supermode superposition in a GeO2 doped triangular-core photonic crystal fiber.

A GeO2 doped triangular-core photonic-crystal fiber (PCF) is designed and fabricated to allow the generation of a hollow beam through a nonlinear-optical transformation by femtosecond pulses at 1040 nm from a high power Yb-doped PCF laser oscillator. The hollow beam supercontinuum is obtained at far field by adjusting incident light polarization to excite the high order supermode, behaving as a mode convertor. The supercontinuum ranging from 540 to 1540 nm is achieved with an average power of 1.04 W.

D3AI-Spike: A deep learning platform for predicting binding affinity between SARS-CoV-2 spike receptor binding domain with multiple amino acid mutations and human angiotensin-converting enzyme 2.

The number of SARS-CoV-2 spike Receptor Binding Domain (RBD) with multiple amino acid mutations is huge due to random mutations and combinatorial explosions, making it almost impossible to experimentally determine their binding affinities to human angiotensin-converting enzyme 2 (hACE2). Although computational prediction is an alternative way, there is still no online platform to predict the mutation effect of RBD on the hACE2 binding affinity until now. In this study, we developed a free online platform based on deep learning models, namely D3AI-Spike, for quickly predicting binding affinity between spike RBD mutants and hACE2. The models based on CNN and CNN-RNN methods have the concordance index of around 0.8. Overall, the test results of the models are in agreement with the experimental data. To further evaluate the prediction power of D3AI-Spike, we predicted and experimentally determined the binding affinity of a VUM (variants under monitoring) variant IHU (B.1.640.2), which has fourteen amino acid substitutions, including N501Y and E484K, and 9 deletions located in the spike protein. The predicted average affinity score for wild-type RBD and IHU to hACE2 are 0.483 and 0.438, while the determined Kaff values are 5.39 ± 0.38 × 107 L/mol and 1.02 ± 0.47 × 107 L/mol, respectively, demonstrating the strong predictive power of D3AI-Spike. We think D3AI-Spike will be helpful to the viral transmission prediction for the new emerging SARS-CoV-2 variants. D3AI-Spike is now available free of charge at https://www.d3pharma.com/D3Targets-2019-nCoV/D3AI-Spike/index.php.

Computational Insights into the Conformational Accessibility and Binding Strength of SARS-CoV-2 Spike Protein to Human Angiotensin-Converting Enzyme 2.

The spike protein of SARS-CoV-2 (CoV-2-S) mediates the virus entry into human cells. Experimental studies have shown the stronger binding affinity of the RBD (receptor binding domain) of CoV-2-S to angiotensin-converting enzyme 2 (ACE2) as compared to that of SARS-CoV spike (CoV-S). However, a similar or weaker binding affinity of CoV-2-S compared to that of CoV-S is observed if entire spikes are used in the bioassay. To explore the underlying mechanism, we calculated the binding affinities of the RBDs to ACE2 and simulated the transitions between ACE2-inaccessible and -accessible conformations. We found that the ACE2-accessible angle of CoV-2-S is 52.2° and that the ACE2 binding strength of CoV-2-S RBD is much stronger than that of CoV-S RBD. However, CoV-2-S has much less of an ACE2-accessible conformation and is much more difficult to shift from ACE2-inaccessible to -accessible than CoV-S, making the binding affinity of the entire protein decrease. Further analysis revealed key interactional residues for strong binding and five potential ligand-binding pockets for drug research.

D3Targets-2019-nCoV: a webserver for predicting drug targets and for multi-target and multi-site based virtual screening against COVID-19.

A highly effective medicine is urgently required to cure coronavirus disease 2019 (COVID-19). For the purpose, we developed a molecular docking based webserver, namely D3Targets-2019-nCoV, with two functions, one is for predicting drug targets for drugs or active compounds observed from clinic or in vitro/in vivo studies, the other is for identifying lead compounds against potential drug targets via docking. This server has its unique features, (1) the potential target proteins and their different conformations involving in the whole process from virus infection to replication and release were included as many as possible; (2) all the potential ligand-binding sites with volume larger than 200 Å3 on a protein structure were identified for docking; (3) correlation information among some conformations or binding sites was annotated; (4) it is easy to be updated, and is accessible freely to public (https://www.d3pharma.com/D3Targets-2019-nCoV/index.php). Currently, the webserver contains 42 proteins [20 severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2) encoded proteins and 22 human proteins involved in virus infection, replication and release] with 69 different conformations/structures and 557 potential ligand-binding pockets in total. With 6 examples, we demonstrated that the webserver should be useful to medicinal chemists, pharmacologists and clinicians for efficiently discovering or developing effective drugs against the SARS-CoV-2 to cure COVID-19.

Repositioning organohalogen drugs: a case study for identification of potent B-Raf V600E inhibitors via docking and bioassay.

Drug repositioning has been attracting increasingly attention for its advantages of reducing costs and risks. Statistics showed that around one quarter of the marketed drugs are organohalogens. However, no study has been reported, to the best of our knowledge, to aim at efficiently repositioning organohalogen drugs, which may be attributed to the lack of accurate halogen bonding scoring function. Here, we present a study to show that two organohalogen drugs were successfully repositioned as potent B-Raf V600E inhibitors via molecular docking with halogen bonding scoring function, namely D(3)DOCKxb developed in our lab, and bioassay. After virtual screening by D(3)DOCKxb against the database CMC (Comprehensive Medicinal Chemistry), 3 organohalogen drugs that were predicted to form strong halogen bonding with B-Raf V600E were purchased and tested with ELISA-based assay. In the end, 2 of them, rafoxanide and closantel, were identified as potent inhibitors with IC50 values of 0.07 µM and 1.90 µM, respectively, which are comparable to that of vemurafenib (IC50: 0.17 µM), a marketed drug targeting B-Raf V600E. Single point mutagenesis experiments confirmed the conformations predicted by D(3)DOCKxb. And comparison experiment revealed that halogen bonding scoring function is essential for repositioning those drugs with heavy halogen atoms in their molecular structures.