NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data.

MOTIVATION: Structural variants (SVs) play a causal role in numerous diseases but can be difficult to detect and accurately genotype (determine zygosity) with short-read genome sequencing data (SRS). Improving SV genotyping accuracy in SRS data, particularly for the many SVs first detected with long-read sequencing, will improve our understanding of genetic variation. RESULTS: NPSV-deep is a deep learning-based approach for genotyping previously reported insertion and deletion SVs that recasts this task as an image similarity problem. NPSV-deep predicts the SV genotype based on the similarity between pileup images generated from the actual SRS data and matching SRS simulations. We show that NPSV-deep consistently matches or improves upon the state-of-the-art for SV genotyping accuracy across different SV call sets, samples and variant types, including a 25% reduction in genotyping errors for the Genome-in-a-Bottle (GIAB) high-confidence SVs. NPSV-deep is not limited to the SVs as described; it improves deletion genotyping concordance a further 1.5 percentage points for GIAB SVs (92%) by automatically correcting imprecise/incorrectly described SVs. AVAILABILITY AND IMPLEMENTATION: Python/C++ source code and pre-trained models freely available at https://github.com/mlinderm/npsv2.

Universality of the Sodium Ion Binding Mechanism in Class†A G-Protein-Coupled Receptors.

The allosteric modulation of G-protein-coupled receptors (GPCRs) by sodium ions has received significant attention as crystal structures of several receptors show Na+ ions bound to the inactive conformations at the conserved Asp2.50 . To date, structures from 24 families of GPCRs have been determined, though mechanistic insights into Na+ binding to the allosteric site are limited. We performed hundreds-of-microsecond long simulations of 18 GPCRs and elucidated their Na+ binding mechanism. In class A GPCRs, the Na+ ion binds to the conserved residue 2.50 whereas in class B receptors, it binds at 3.43b, 6.53b, and 7.49b. Using Markov state models, we obtained the free energy profiles and kinetics of Na+ binding to the allosteric site, which reveal a conserved mechanism of Na+ binding for GPCRs and show the residues that act as major barriers for ion diffusion. Furthermore, we also show that the Na+ ion can bind to GPCRs from the intracellular side when the allosteric site is inaccessible from the extracellular side.

TLmutation: Predicting the Effects of Mutations Using Transfer Learning.

A reccurring challenge in bioinformatics is predicting the phenotypic consequence of amino acid variation in proteins. With the recent advancements in sequencing techniques, sufficient genomic data has become available to train models that predict the evolutionary statistical energies, but there is still inadequate experimental data to directly predict functional effects. One approach to overcome this data scarcity is to apply transfer learning and train more models with available data sets. In this study, we propose a set of transfer learning algorithms we call TLmutation, which implements a supervised transfer learning algorithm that transfers knowledge from survival data of a protein to a particular function of that protein. This is followed by an unsupervised transfer learning algorithm that extends the knowledge to a homologous protein. We explore the application of our algorithms in three cases. First, we test the supervised transfer on 17 previously published deep mutagenesis data sets to complete and refine missing data points. We further investigate these data sets to identify which mutations build better predictors of variant functions. In the second case, we apply the algorithm to predict higher-order mutations solely from single point mutagenesis data. Finally, we perform the unsupervised transfer learning algorithm to predict mutational effects of homologous proteins from experimental data sets. These algorithms are generalized to transfer knowledge between Markov random field models. We show the benefit of our transfer learning algorithms to utilize informative deep mutational data and provide new insights into protein variant functions. As these algorithms are generalized to transfer knowledge between Markov random field models, we expect these algorithms to be applicable to other disciplines.

A simple magnetic solid-phase extraction method based on magnetite/graphene oxide nanocomposite for pre-concentration and determination of melamine by high-performance liquid chromatography.

In this study, a clean and simple magnetic solid-phase extraction (MSPE) procedure using magnetite/graphene oxide nanocomposite as an adsorbent was developed for melamine separation and preconcentration from water and dairy products. After synthesis and characterization of the adsorbent, adsorption isotherms and kinetic studies of the adsorption were carried out. The analyte quantification was performed by reversed phase high-performance liquid chromatography after elution of the preconcentrated analytes from the adsorbent surface. Several factors affecting the extraction/preconcentration procedure such as pH, adsorbent amount, extraction time, sample volume, type, and volume of eluent were investigated. The optimizing of some important parameters was assessed by employing a response surface method. The constructed calibration curve in the optimized conditions is linear in the working range of 0.10-100 µg L-1 with a correlation coefficient of 0.9999. The detection limit, limit of quantification, and enrichment factor are 0.03 µg L-1, 0.10 µg L-1, and 500, respectively. The melamine relative recoveries from different real samples are between 97.20 and 103.10% with relative standard deviations of 1.07-4.98%.

Preconcentration of morphine and codeine using a magnetite/reduced graphene oxide/silver nano-composite and their determination by high-performance liquid chromatography.

A novel magnetic solid-phase extraction technique based on a ternary nano-composite, magnetite/reduced graphene oxide/silver, as a nano-sorbent was developed for simultaneous extraction/preconcentration and measurement of morphine and codeine in biological samples by high-performance liquid chromatography. The magnetic ternary nano-composite was synthesized and its functional groups, morphological structure, and magnetic properties were characterized by field emission scanning electron microscopy, vibrating sample magnetometer, powder X-ray diffraction, energy dispersive X-ray spectroscopy and Fourier transform infrared spectroscopy. The optimizing of the significant variables affecting the extraction process was evaluated by a response surface methodology. In the optimized conditions, the constructed calibration curves for morphine and codeine are linear in the range of 0.01-10 µg L-1 with correlation coefficients of 0.9983 and 0.9976, respectively. The detection limit and enrichment factor for morphine and codeine are 1.8 ng L-1, 1000 and 2.1 ng L-1, 1000, respectively. The presented technique was employed for the monitoring of morphine and codeine in numerous blood and urine samples with relative recoveries between 97.0 and 102.5%, and relative standard deviations of 1.02-5.10% for the spiked samples.

Reinforcement Learning Based Adaptive Sampling: REAPing Rewards by Exploring Protein Conformational Landscapes.

One of the key limitations of Molecular Dynamics (MD) simulations is the computational intractability of sampling protein conformational landscapes associated with either large system size or long time scales. To overcome this bottleneck, we present the REinforcement learning based Adaptive samPling (REAP) algorithm that aims to efficiently sample conformational space by learning the relative importance of each order parameter as it samples the landscape. To achieve this, the algorithm uses concepts from the field of reinforcement learning, a subset of machine learning, which rewards sampling along important degrees of freedom and disregards others that do not facilitate exploration or exploitation. We demonstrate the effectiveness of REAP by comparing the sampling to long continuous MD simulations and least-counts adaptive sampling on two model landscapes (L-shaped and circular) and realistic systems such as alanine dipeptide and Src kinase. In all four systems, the REAP algorithm consistently demonstrates its ability to explore conformational space faster than the other two methods when comparing the expected values of the landscape discovered for a given amount of time. The key advantage of REAP is on-the-fly estimation of the importance of collective variables, which makes it particularly useful for systems with limited structural information.

Enhanced unbiased sampling of protein dynamics using evolutionary coupling information.

One of the major challenges in atomistic simulations of proteins is efficient sampling of pathways associated with rare conformational transitions. Recent developments in statistical methods for computation of direct evolutionary couplings between amino acids within and across polypeptide chains have allowed for inference of native residue contacts, informing accurate prediction of protein folds and multimeric structures. In this study, we assess the use of distances between evolutionarily coupled residues as natural choices for reaction coordinates which can be incorporated into Markov state model-based adaptive sampling schemes and potentially used to predict not only functional conformations but also pathways of conformational change, protein folding, and protein-protein association. We demonstrate the utility of evolutionary couplings in sampling and predicting activation pathways of the ß 2-adrenergic receptor (ß 2-AR), folding of the FiP35 WW domain, and dimerization of the E. coli molybdopterin synthase subunits. We find that the time required for ß 2-AR activation and folding of the WW domain are greatly diminished using evolutionary couplings-guided adaptive sampling. Additionally, we were able to identify putative molybdopterin synthase association pathways and near-crystal structure complexes from protein-protein association simulations.

Publisher Correction: Enhanced unbiased sampling of protein dynamics using evolutionary coupling information.

A correction to this article has been published and is linked from the HTML version of this paper. The error has been fixed in the paper.

Application of Hidden Markov Models in Biomolecular Simulations.

Hidden Markov models (HMMs) provide a framework to analyze large trajectories of biomolecular simulation datasets. HMMs decompose the conformational space of a biological molecule into finite number of states that interconvert among each other with certain rates. HMMs simplify long timescale trajectories for human comprehension, and allow comparison of simulations with experimental data. In this chapter, we provide an overview of building HMMs for analyzing bimolecular simulation datasets. We demonstrate the procedure for building a Hidden Markov model for Met-enkephalin peptide simulation dataset and compare the timescales of the process.