ABSTRACT
Motivation: Automated selection of signals in protein NMR spectra, known as peak picking, has been studied for over 20 years, nevertheless existing peak picking methods are still largely deficient. Accurate and precise automated peak picking would accelerate the structure calculation, and analysis of dynamics and interactions of macromolecules. Recent advancement in handling big data, together with an outburst of machine learning techniques, offer an opportunity to tackle the peak picking problem substantially faster than manual picking and on par with human accuracy. In particular, deep learning has proven to systematically achieve human-level performance in various recognition tasks, and thus emerges as an ideal tool to address automated identification of NMR signals. Results: We have applied a convolutional neural network for visual analysis of multidimensional NMR spectra. A comprehensive test on 31 manually annotated spectra has demonstrated top-tier average precision (AP) of 0.9596, 0.9058 and 0.8271 for backbone, side-chain and NOESY spectra, respectively. Furthermore, a combination of extracted peak lists with automated assignment routine, FLYA, outperformed other methods, including the manual one, and led to correct resonance assignment at the levels of 90.40%, 89.90% and 90.20% for three benchmark proteins. Availability and implementation: The proposed model is a part of a Dumpling software (platform for protein NMR data analysis), and is available at https://dumpling.bio/. Supplementary information: Supplementary data are available at Bioinformatics online.
Subject(s)
Deep Learning , Nuclear Magnetic Resonance, Biomolecular/methods , Proteins/chemistry , Software , Macromolecular Substances/chemistryABSTRACT
Analysis of structure, function and interactions of proteins by NMR spectroscopy usually requires the assignment of resonances to the corresponding nuclei in protein. This task, although automated by methods such as FLYA or PINE, is still frequently performed manually. To facilitate the manual sequence-specific chemical shift assignment of complex proteins, we propose a method based on Dirichlet process mixture model (DPMM) that performs automated matching of groups of signals observed in NMR spectra to corresponding nuclei in protein sequence. The model has been extensively tested on 80 proteins retrieved from the BMRB database and has shown superior performance to the reference method.
Subject(s)
Models, Theoretical , Nuclear Magnetic Resonance, Biomolecular/methods , Proteins/chemistry , Amino Acid Sequence , Databases, ProteinABSTRACT
MOTIVATION: A detailed analysis of multidimensional NMR spectra of macromolecules requires the identification of individual resonances (peaks). This task can be tedious and time-consuming and often requires support by experienced users. Automated peak picking algorithms were introduced more than 25 years ago, but there are still major deficiencies/flaws that often prevent complete and error free peak picking of biological macromolecule spectra. The major challenges of automated peak picking algorithms is both the distinction of artifacts from real peaks particularly from those with irregular shapes and also picking peaks in spectral regions with overlapping resonances which are very hard to resolve by existing computer algorithms. In both of these cases a visual inspection approach could be more effective than a 'blind' algorithm. RESULTS: We present a novel approach using computer vision (CV) methodology which could be better adapted to the problem of peak recognition. After suitable 'training' we successfully applied the CV algorithm to spectra of medium-sized soluble proteins up to molecular weights of 26 kDa and to a 130 kDa complex of a tetrameric membrane protein in detergent micelles. Our CV approach outperforms commonly used programs. With suitable training datasets the application of the presented method can be extended to automated peak picking in multidimensional spectra of nucleic acids or carbohydrates and adapted to solid-state NMR spectra. AVAILABILITY AND IMPLEMENTATION: CV-Peak Picker is available upon request from the authors. CONTACT: gsw@mol.biol.ethz.ch; michal.walczak@mol.biol.ethz.ch; adam.gonczarek@pwr.edu.pl SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Subject(s)
Algorithms , Image Processing, Computer-Assisted/methods , Nuclear Magnetic Resonance, Biomolecular/methods , Pattern Recognition, Visual , Proteins/chemistry , HumansABSTRACT
A simplified analytical model of the effect of high pressure on the critical temperature and other thermodynamic properties of superconducting systems is developed using the general conformal transformation method and group-theoretical arguments. Relationships between the characteristic ratios [Formula: see text] and [Formula: see text] and the stability of the superconducting state is discussed. Including a single two-parameter fluctuation in the density of states, placed away from the Fermi level, stable solutions determined by [Formula: see text] are found. It is shown that the critical temperature Tc(p), as a function of high external pressure, can be predicted from experimental data, based on the values of the two characteristic ratios, the critical temperature, and a pressure coefficient measured at zero pressure. The model can be applied to s-wave low-temperature and high-temperature superconductors, as well as to some novel superconducting systems of the new generation. The problem of emergence of superconductivity under high pressure is explained as well. The discussion is illustrated by using experimental data for superconducting elements available in the literature. A criterion for compatibility of experimental data is formulated, allowing one to identify incompatible measurement data for superconducting systems for which the maximum or the minimum critical temperature is achieved under high pressure.
ABSTRACT
Within the general conformal transformation method a simplified analytical model is proposed to study the effect of external hydrostatic pressure on low- and high-temperature superconducting systems. A single fluctuation in the density of states, placed away from the Fermi level, as well as external pressure are included in the model to derive equations for the superconducting gap, free energy difference, and specific heat difference. The zero- and sub-critical temperature limits are discussed by the method of successive approximations. The critical temperature is found as a function of high external pressure. It is shown that there are four universal types of the response of the system, in terms of dependence of the critical temperature on increasing external pressure. Some effects, which should be possible to be observed experimentally in s-wave superconductors, the cuprates (i.e. high-Tc superconductors) and other superconducting materials of the new generation such as two-gap superconductors, are revealed and discussed. An equation for the ratio [Formula: see text] ≡ 2Δ(0)/Tc, as a function of the introduced parameters, is derived and solved numerically. Analysis of other thermodynamic quantities and the characteristic ratio [Formula: see text] ≡ ΔC(Tc)/CN(Tc) is performed numerically, and mutual relations between the discussed quantities are investigated. The simple analytical model presented in the paper may turn out to be helpful in searching for novel superconducting components with higher critical temperatures induced by pressure effects.
ABSTRACT
We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each molecule separately. These fingerprints are further non-linearly transformed, their inner product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E, MUV and PDBBind databases.