The cloud and other new computational methods to improve molecular modelling

Comprehensive Survey of Consensus Docking for High-Throughput Virtual Screening

The rapid advances of 3D techniques for the structural determination of proteins and the development of numerous computational methods and strategies have led to identifying highly active compounds in computer drug design. Molecular docking is a method widely used in high-throughput virtual screening campaigns to filter potential ligands targeted to proteins. A great variety of docking programs are currently available, which differ in the algorithms and approaches used to predict the binding mode and the affinity of the ligand. All programs heavily rely on scoring functions to accurately predict ligand binding affinity, and despite differences in performance, none of these docking programs is preferable to the others. To overcome this problem, consensus scoring methods improve the outcome of virtual screening by averaging the rank or score of individual molecules obtained from different docking programs. The successful application of consensus docking in high-throughput virtual screening highlights the need to optimize the predictive power of molecular docking methods.

Assessment of a Machine Learning Model Applied to Harmonized Electronic Health Record Data for the Prediction of Incident Atrial Fibrillation

IMPORTANCE

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, and its early detection could lead to significant improvements in outcomes through the appropriate prescription of anticoagulation medication. Although a variety of methods exist for screening for AF, a targeted approach, which requires an efficient method for identifying patients at risk, would be preferred.

OBJECTIVE

To examine machine learning approaches applied to electronic health record data that have been harmonized to the Observational Medical Outcomes Partnership Common Data Model for identifying risk of AF.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study used data from 2 252 219 individuals cared for in the UCHealth hospital system, which comprises 3 large hospitals in Colorado, from January 1, 2011, to October 1, 2018. Initial analysis was performed in December 2018; follow-up analysis was performed in July 2019.

EXPOSURES

All Observational Medical Outcomes Partnership Common Data Model-harmonized electronic health record features, including diagnoses, procedures, medications, age, and sex.

MAIN OUTCOMES AND MEASURES

Classification of incident AF in designated 6-month intervals, adjudicated retrospectively, based on area under the receiver operating characteristic curve and F1 statistic.

RESULTS

Of 2 252 219 individuals (1 225 533 [54.4%] women; mean [SD] age, 42.9 [22.3] years), 28 036 (1.2%) developed incident AF during a designated 6-month interval. The machine learning model that used the 200 most common electronic health record features, including age and sex, and random oversampling with a single-layer, fully connected neural network provided the optimal prediction of 6-month incident AF, with an area under the receiver operating characteristic curve of 0.800 and an F1 score of 0.110. This model performed only slightly better than a more basic logistic regression model composed of known clinical risk factors for AF, which had an area under the receiver operating characteristic curve of 0.794 and an F1 score of 0.079.

CONCLUSIONS AND RELEVANCE

Machine learning approaches to electronic health record data offer a promising method for improving risk prediction for incident AF, but more work is needed to show improvement beyond standard risk factors.

Structural biology meets data science: does anything change?

Data science has emerged from the proliferation of digital data, coupled with advances in algorithms, software and hardware (e.g., GPU computing). Innovations in structural biology have been driven by similar factors, spurring us to ask: can these two fields impact one another in deep and hitherto unforeseen ways? We posit that the answer is yes. New biological knowledge lies in the relationships between sequence, structure, function and disease, all of which play out on the stage of evolution, and data science enables us to elucidate these relationships at scale. Here, we consider the above question from the five key pillars of data science: acquisition, engineering, analytics, visualization and policy, with an emphasis on machine learning as the premier analytics approach.

Protein structure and computational drug discovery

The first protein structures revealed a complex web of weak interactions stabilising the three-dimensional shape of the molecule. Small molecule ligands were then found to exploit these same weak binding events to modulate protein function or act as substrates in enzymatic reactions. As the understanding of ligand–protein binding grew, it became possible to firstly predict how and where a particular small molecule might interact with a protein, and then to identify putative ligands for a specific protein site. Computer-aided drug discovery, based on the structure of target proteins, is now a well-established technique that has produced several marketed drugs. We present here an overview of the various methodologies being used for structure-based computer-aided drug discovery and comment on possible future developments in the field.

Computational design and experimental characterization of a novel β-common receptor inhibitory peptide

In short-term animal models of ischemia, erythropoietin (EPO) signaling through the heterodimeric EPO receptor (EPOR)/β-common receptor (βCR) is believed to elicit tissue protective effects. However, large, randomized, controlled trials demonstrate that targeting a higher hemoglobin level by administering higher doses of EPO, which are more likely to activate the heterodimeric EPOR/βCR, is associated with an increase in adverse cardiovascular events. Thus, inhibition of long-term activation of the βCR may have therapeutic implications. This study aimed to design and evaluate the efficacy of novel computationally designed βCR inhibitory peptides (βIP). These novel βIPs were designed based on a truncated portion of Helix-A from EPO, specifically residues 11-26 (VLERYLLEAKEAEKIT). Seven novel peptides (P1 to P7) were designed. Peptide 7 (P7), VLERYLHEAKHAEKIT, demonstrated the most robust inhibitory activity. We also report here the ability of P7 to inhibit βCR-induced nitric oxide (NO) production and angiogenesis in human umbilical vein endothelial cells (HUVECs). Specifically, we found that P7 βIP completely abolished EPO-induced NO production. The inhibitory effect could be overcome with super physiological doses of EPO, suggesting a competitive inhibition. βCR-induced angiogenesis in HUVEC's was also abolished with treatment of P7 βIP, but P7 βIP did not inhibit vascular endothelial growth factor (VEGF)-induced angiogenesis. In addition, we demonstrate that the novel P7 βIP does not inhibit EPO-induced erythropoiesis with use of peripheral blood mononuclear cells (PBMCs). These results, for the first time, describe a novel, potent βCR peptide inhibitor that inhibit the actions of the βCR without affecting erythropoiesis.

Computational functional group mapping for drug discovery

Computational functional group mapping (cFGM) is emerging as a high-impact complement to existing widely used experimental and computational structure-based drug discovery methods. cFGM provides comprehensive atomic-resolution 3D maps of the affinity of functional groups that can constitute drug-like molecules for a given target, typically a protein. These 3D maps can be intuitively and interactively visualized by medicinal chemists to rapidly design synthetically accessible ligands. Given that the maps can inform selection of functional groups for affinity, specificity, and pharmacokinetic properties, they are of utility for both the optimization of existing drug candidates and creating novel ones. Here, I review recent advances in cFGM with emphasis on the unique information content in the approach that offers the potential of broadly facilitating structure-based ligand design.

De Novo Design at the Edge of Chaos

Computational medicinal chemistry offers viable strategies for finding, characterizing, and optimizing innovative pharmacologically active compounds. Technological advances in both computer hardware and software as well as biological chemistry have enabled a renaissance of computer-assisted "de novo" design of molecules with desired pharmacological properties. Here, we present our current perspective on the concept of automated molecule generation by highlighting chemocentric methods that may capture druglike chemical space, consider ligand promiscuity for hit and lead finding, and provide fresh ideas for the rational design of customized screening of compound libraries.

Applying high-performance computing in drug discovery and molecular simulation

In recent decades, high-performance computing (HPC) technologies and supercomputers in China have significantly advanced, resulting in remarkable achievements. Computational drug discovery and design, which is based on HPC and combines pharmaceutical chemistry and computational biology, has become a critical approach in drug research and development and is financially supported by the Chinese government. This approach has yielded a series of new algorithms in drug design, as well as new software and databases. This review mainly focuses on the application of HPC to the fields of drug discovery and molecular simulation at the Chinese Academy of Sciences, including virtual drug screening, molecular dynamics simulation, and protein folding. In addition, the potential future application of HPC in precision medicine is briefly discussed.