RESUMO
Predicting accurate protein-ligand binding affinities is an important task in drug discovery but remains a challenge even with computationally expensive biophysics-based energy scoring methods and state-of-the-art deep learning approaches. Despite the recent advances in the application of deep convolutional and graph neural network-based approaches, it remains unclear what the relative advantages of each approach are and how they compare with physics-based methodologies that have found more mainstream success in virtual screening pipelines. We present fusion models that combine features and inference from complementary representations to improve binding affinity prediction. This, to our knowledge, is the first comprehensive study that uses a common series of evaluations to directly compare the performance of three-dimensional (3D)-convolutional neural networks (3D-CNNs), spatial graph neural networks (SG-CNNs), and their fusion. We use temporal and structure-based splits to assess performance on novel protein targets. To test the practical applicability of our models, we examine their performance in cases that assume that the crystal structure is not available. In these cases, binding free energies are predicted using docking pose coordinates as the inputs to each model. In addition, we compare these deep learning approaches to predictions based on docking scores and molecular mechanic/generalized Born surface area (MM/GBSA) calculations. Our results show that the fusion models make more accurate predictions than their constituent neural network models as well as docking scoring and MM/GBSA rescoring, with the benefit of greater computational efficiency than the MM/GBSA method. Finally, we provide the code to reproduce our results and the parameter files of the trained models used in this work. The software is available as open source at https://github.com/llnl/fast. Model parameter files are available at ftp://gdo-bioinformatics.ucllnl.org/fast/pdbbind2016_model_checkpoints/.
Assuntos
Redes Neurais de Computação , Proteínas , Ligantes , Ligação Proteica , Proteínas/metabolismo , SoftwareRESUMO
The catalytic site identification web server provides the innovative capability to find structural matches to a user-specified catalytic site among all Protein Data Bank proteins rapidly (in less than a minute). The server also can examine a user-specified protein structure or model to identify structural matches to a library of catalytic sites. Finally, the server provides a database of pre-calculated matches between all Protein Data Bank proteins and the library of catalytic sites. The database has been used to derive a set of hypothesized novel enzymatic function annotations. In all cases, matches and putative binding sites (protein structure and surfaces) can be visualized interactively online. The website can be accessed at http://catsid.llnl.gov.
Assuntos
Domínio Catalítico , Software , Bases de Dados de Proteínas , Internet , Modelos MolecularesRESUMO
The blood-brain barrier (BBB) is formed by specialized tight junctions between endothelial cells that line brain capillaries to create a highly selective barrier between the brain and the rest of the body. A major problem to overcome in drug design is the ability of the compound in question to cross the BBB. Neuroactive drugs are required to cross the BBB to function. Conversely, drugs that target other parts of the body ideally should not cross the BBB to avoid possible psychotropic side effects. Thus, the task of predicting the BBB permeability of new compounds is of great importance. Two gold-standard experimental measures of BBB permeability are logBB (the concentration of drug in the brain divided by concentration in the blood) and logPS (permeability surface-area product). Both methods are time-consuming and expensive, and although logPS is considered the more informative measure, it is lower throughput and more resource intensive. With continual increases in computer power and improvements in molecular simulations, in silico methods may provide viable alternatives. Computational predictions of these two parameters for a sample of 12 small molecule compounds were performed. The potential of mean force for each compound through a 1,2-dioleoyl-sn-glycero-3-phosphocholine bilayer is determined by molecular dynamics simulations. This system setup is often used as a simple BBB mimetic. Additionally, one-dimensional position-dependent diffusion coefficients are calculated from the molecular dynamics trajectories. The diffusion coefficient is combined with the free energy landscape to calculate the effective permeability (Peff) for each sample compound. The relative values of these permeabilities are compared to experimentally determined logBB and logPS values. Our computational predictions correlate remarkably well with both logBB (R(2) = 0.94) and logPS (R(2) = 0.90). Thus, we have demonstrated that this approach may have the potential to provide reliable, quantitatively predictive BBB permeability, using a relatively quick, inexpensive method.
Assuntos
Barreira Hematoencefálica/metabolismo , Permeabilidade Capilar , Modelos Biológicos , Simulação de Dinâmica Molecular , Preparações Farmacêuticas/sangueRESUMO
OBJECTIVES: To assess the performance of a test (called BV), integrating the blood levels of three immune proteins into a score, to differentiate bacterial from viral infection among adults with suspected lower respiratory tract infection (LRTI). METHODS: Prospective diagnostic accuracy study, enrolling febrile adults >18 years with LRTI signs or symptoms for less than 7 days presenting to several hospitals' emergency departments in Israel. The main exclusion criterion was immunodeficiency. Reference standard diagnosis (bacterial/viral/indeterminate) was based on three experts independently reviewing comprehensive patient data including follow-up data. BV generated three results: viral infection or other nonbacterial condition (0 ≤ score < 35), equivocal (35 ≤ score ≤ 65) and bacterial infection including co-infection (65 < score ≤ 100). BV performance was assessed against the reference standard with indeterminate reference standard and equivocal BV cases removed. RESULTS: Of 490 enrolled patients, 415 met eligibility criteria (median age 56 years, interquartile range 35). The reference standard classified 104 patients as bacterial, 210 as viral and 101 as indeterminate. BV was equivocal in 9.6% (30/314). Excluding indeterminate reference standard diagnoses and equivocal BV results, BV's sensitivity for bacterial infection was 98.1% (101/103; 95% confidence interval 95.4-100), specificity 88.4% (160/181; 83.7-93.1) and negative predictive value 98.8% (160/162; 97.1-100). DISCUSSION: BV exhibited high diagnostic performance for febrile adults with suspected LRTI among patients with reference standard diagnoses of bacterial or viral LRTI.
Assuntos
Infecções Bacterianas , Infecções Respiratórias , Viroses , Humanos , Adulto , Pessoa de Meia-Idade , Proteína C-Reativa/análise , Interferon gama , Biomarcadores , Estudos Prospectivos , Ligantes , Sensibilidade e Especificidade , Infecções Bacterianas/diagnóstico , Infecções Respiratórias/diagnóstico , Infecções Respiratórias/microbiologia , Viroses/diagnóstico , Bactérias , Febre , Fator de Necrose Tumoral alfaRESUMO
A rapid response is necessary to contain emergent biological outbreaks before they can become pandemics. The novel coronavirus (SARS-CoV-2) that causes COVID-19 was first reported in December of 2019 in Wuhan, China and reached most corners of the globe in less than two months. In just over a year since the initial infections, COVID-19 infected almost 100 million people worldwide. Although similar to SARS-CoV and MERS-CoV, SARS-CoV-2 has resisted treatments that are effective against other coronaviruses. Crystal structures of two SARS-CoV-2 proteins, spike protein and main protease, have been reported and can serve as targets for studies in neutralizing this threat. We have employed molecular docking, molecular dynamics simulations, and machine learning to identify from a library of 26 million molecules possible candidate compounds that may attenuate or neutralize the effects of this virus. The viability of selected candidate compounds against SARS-CoV-2 was determined experimentally by biolayer interferometry and FRET-based activity protein assays along with virus-based assays. In the pseudovirus assay, imatinib and lapatinib had IC50 values below 10 µM, while candesartan cilexetil had an IC50 value of approximately 67 µM against Mpro in a FRET-based activity assay. Comparatively, candesartan cilexetil had the highest selectivity index of all compounds tested as its half-maximal cytotoxicity concentration 50 (CC50) value was the only one greater than the limit of the assay (>100 µM).
RESUMO
We present an enzyme protein function identification algorithm, Catalytic Site Identification (CatSId), based on identification of catalytic residues. The method is optimized for highly accurate template identification across a diverse template library and is also very efficient in regards to time and scalability of comparisons. The algorithm matches three-dimensional residue arrangements in a query protein to a library of manually annotated, catalytic residues--The Catalytic Site Atlas (CSA). Two main processes are involved. The first process is a rapid protein-to-template matching algorithm that scales quadratically with target protein size and linearly with template size. The second process incorporates a number of physical descriptors, including binding site predictions, in a logistic scoring procedure to re-score matches found in Process 1. This approach shows very good performance overall, with a Receiver-Operator-Characteristic Area Under Curve (AUC) of 0.971 for the training set evaluated. The procedure is able to process cofactors, ions, nonstandard residues, and point substitutions for residues and ions in a robust and integrated fashion. Sites with only two critical (catalytic) residues are challenging cases, resulting in AUCs of 0.9411 and 0.5413 for the training and test sets, respectively. The remaining sites show excellent performance with AUCs greater than 0.90 for both the training and test data on templates of size greater than two critical (catalytic) residues. The procedure has considerable promise for larger scale searches.
Assuntos
Algoritmos , Biologia Computacional/métodos , Enzimas/química , Enzimas/metabolismo , Sítios de Ligação , Catálise , Domínio Catalítico , Bases de Dados de Proteínas , Modelos Logísticos , Modelos Moleculares , Conformação Proteica , Curva ROC , Reprodutibilidade dos TestesRESUMO
Computational methods for predicting ligand affinity where no protein structure is known generally take the form of regression analysis based on molecular features that have only a tangential relationship to a protein/ligand binding event. Such methods have limited utility when structural variation moves beyond congeneric series. We present a novel approach based on the multiple-instance learning method of Compass, where a physical model of a binding site is induced from ligands and their corresponding activity data. The model consists of molecular fragments that can account for multiple positions of literal protein residues. We demonstrate the method on 5HT1a ligands by training on a series with limited scaffold variation and testing on numerous ligands with variant scaffolds. Predictive error was between 0.5 and 1.0 log units (0.7-1.4 kcal/mol), with statistically significant rank correlations. Accurate activity predictions of novel ligands were demonstrated using a validation approach where a small number of ligands of limited structural variation known at a fixed time point were used to make predictions on a blind test set of widely varying molecules, some discovered at a much later time point.