50 research outputs found
Is EC class predictable from reaction mechanism?
No full textWe thank the Scottish Universities Life Sciences Alliance (SULSA) and the Scottish Overseas Research Student Awards Scheme of the Scottish Funding Council (SFC) for financial support.Background: We investigate the relationships between the EC (Enzyme Commission) class, the associated chemical reaction, and the reaction mechanism by building predictive models using Support Vector Machine (SVM), Random Forest (RF) and k-Nearest Neighbours (kNN). We consider two ways of encoding the reaction mechanism in descriptors, and also three approaches that encode only the overall chemical reaction. Both cross-validation and also an external test set are used. Results: The three descriptor sets encoding overall chemical transformation perform better than the two descriptions of mechanism. SVM and RF models perform comparably well; kNN is less successful. Oxidoreductases and hydrolases are relatively well predicted by all types of descriptor; isomerases are well predicted by overall reaction descriptors but not by mechanistic ones. Conclusions: Our results suggest that pairs of similar enzyme reactions tend to proceed by different mechanisms. Oxidoreductases, hydrolases, and to some extent isomerases and ligases, have clear chemical signatures, making them easier to predict than transferases and lyases. We find evidence that isomerases as a class are notably mechanistically diverse and that their one shared property, of substrate and product being isomers, can arise in various unrelated ways. The performance of the different machine learning algorithms is in line with many cheminformatics applications, with SVM and RF being roughly equally effective. kNN is less successful, given the role that non-local information plays in successful classification. We note also that, despite a lack of clarity in the literature, EC number prediction is not a single problem; the challenge of predicting protein function from available sequence data is quite different from assigning an EC classification from a cheminformatics representation of a reaction.Peer reviewe
A note on utilising binary features as ligand descriptors
No full textMussa and Mitchell thank the BBSRC for funding this research through grant BB/I00596X/1. Mitchell thanks the Scottish Universities Life Sciences Alliance (SULSA) for financial support.It is common in cheminformatics to represent the properties of a ligand as a string of 1’s and 0’s, with the intention of elucidating, inter alia, the relationship between the chemical structure of a ligand and its bioactivity. In this commentary we note that, where relevant but non-redundant features are binary, they inevitably lead to a classifier capable of capturing only a linear relationship between structural features and activity. If, instead, we were to use relevant but non-redundant real-valued features, the resulting predictive model would be capable of describing a non-linear structure-activity relationship. Hence, we suggest that real-valued features, where available, are to be preferred in this scenario.Peer reviewe
Verifying the fully “Laplacianised” posterior Naïve Bayesian approach and more
No full textMussa and Glen would like to thank Unilever for financial support, whereas Mussa and Mitchell thank the BBSRC for funding this research through grant BB/I00596X/1. Mitchell thanks the Scottish Universities Life Sciences Alliance (SULSA) for financial support.Background In a recent paper, Mussa, Mitchell and Glen (MMG) have mathematically demonstrated that the “Laplacian Corrected Modified Naïve Bayes” (LCMNB) algorithm can be viewed as a variant of the so-called Standard Naïve Bayes (SNB) scheme, whereby the role played by absence of compound features in classifying/assigning the compound to its appropriate class is ignored. MMG have also proffered guidelines regarding the conditions under which this omission may hold. Utilising three data sets, the present paper examines the validity of these guidelines in practice. The paper also extends MMG’s work and introduces a new version of the SNB classifier: “Tapered Naïve Bayes” (TNB). TNB does not discard the role of absence of a feature out of hand, nor does it fully consider its role. Hence, TNB encapsulates both SNB and LCMNB. Results LCMNB, SNB and TNB performed differently on classifying 4,658, 5,031 and 1,149 ligands (all chosen from the ChEMBL Database) distributed over 31 enzymes, 23 membrane receptors, and one ion-channel, four transporters and one transcription factor as their target proteins. When the number of features utilised was equal to or smaller than the “optimal” number of features for a given data set, SNB classifiers systematically gave better classification results than those yielded by LCMNB classifiers. The opposite was true when the number of features employed was markedly larger than the “optimal” number of features for this data set. Nonetheless, these LCMNB performances were worse than the classification performance achieved by SNB when the “optimal” number of features for the data set was utilised. TNB classifiers systematically outperformed both SNB and LCMNB classifiers. Conclusions The classification results obtained in this study concur with the mathematical based guidelines given in MMG’s paper—that is, ignoring the role of absence of a feature out of hand does not necessarily improve classification performance of the SNB approach; if anything, it could make the performance of the SNB method worse. The results obtained also lend support to the rationale, on which the TNB algorithm rests: handled judiciously, taking into account absence of features can enhance (not impair) the discriminatory classification power of the SNB approach.Peer reviewe
Machine learning methods in chemoinformatics
No full textMachine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure-activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers.Peer reviewe
A novel hybrid ultrafast shape descriptor method for use in virtual screening
No full textThe authors thank the EPSRC and Unilever plc for funding.Background We have introduced a new Hybrid descriptor composed of the MACCS key descriptor encoding topological information and Ballester and Richards' Ultrafast Shape Recognition (USR) descriptor. The latter one is calculated from the moments of the distribution of the interatomic distances, and in this work we also included higher moments than in the original implementation. Results The performance of this Hybrid descriptor is assessed using Random Forest and a dataset of 116,476 molecules. Our dataset includes 5,245 molecules in ten classes from the 2005 World Anti-Doping Agency (WADA) dataset and 111,231 molecules from the National Cancer Institute (NCI) database. In a 10-fold Monte Carlo cross-validation this dataset was partitioned into three distinct parts for training, optimisation of an internal threshold that we introduced, and validation of the resulting model. The standard errors obtained were used to assess statistical significance of observed improvements in performance of our new descriptor. Conclusion The Hybrid descriptor was compared to the MACCS key descriptor, USR with the first three (USR), four (UF4) and five (UF5) moments, and a combination of MACCS with USR (three moments). The MACCS key descriptor was not combined with UF5, due to similar performance of UF5 and UF4. Superior performance in terms of all figures of merit was found for the MACCS/UF4 Hybrid descriptor with respect to all other descriptors examined. These figures of merit include recall in the top 1% and top 5% of the ranked validation sets, precision, F-measure, area under the Receiver Operating Characteristic curve and Matthews Correlation Coefficient.Peer reviewe
Erratum - Influence of edge enhancement applied in endoscopic systems on sharpness and noise (Erratum)
No full text[This corrects the article DOI: 10.1117/1.JBO.27.10.106001.].ImPhys/Computational ImagingImPhys/Rieger grou
Quantitative and evolutionary global analysis of enzyme reaction mechanisms
No full textThe most widely used classification system describing enzyme-catalysed reactions
is the Enzyme Commission (EC) number. Understanding enzyme
function is important for both fundamental scientific and pharmaceutical
reasons. The EC classification is essentially unrelated to the reaction mechanism.
In this work we address two important questions related to enzyme
function diversity. First, to investigate the relationship between the reaction
mechanisms as described in the MACiE (Mechanism, Annotation,
and Classification in Enzymes) database and the main top-level class of the
EC classification. Second, how well these enzymes biocatalysis are adapted
in nature.
In this thesis, we have retrieved 335 enzyme reactions from the MACiE
database. We consider two ways of encoding the reaction mechanism in
descriptors, and three approaches that encode only the overall chemical
reaction.
To proceed through my work, we first develop a basic model to cluster
the enzymatic reactions. Global study of enzyme reaction mechanism
may provide important insights for better understanding of the diversity of
chemical reactions of enzymes. Clustering analysis in such research is very
common practice. Clustering algorithms suffer from various issues, such as
requiring determination of the input parameters and stopping criteria, and
very often a need to specify the number of clusters in advance.
Using several well known metrics, we tried to optimize the clustering
outputs for each of the algorithms, with equivocal results that suggested the
existence of between two and over a hundred clusters. This motivated us to
design and implement our algorithm, PFClust (Parameter-Free Clustering),
where no prior information is required to determine the number of cluster. The analysis highlights the structure of the enzyme overall and mechanistic
reaction. This suggests that mechanistic similarity can influence approaches
for function prediction and automatic annotation of newly discovered protein
and gene sequences.
We then develop and evaluate the method for enzyme function prediction
using machine learning methods. Our results suggest that pairs of similar
enzyme reactions tend to proceed by different mechanisms. The machine
learning method needs only chemoinformatics descriptors as an input and
is applicable for regression analysis.
The last phase of this work is to test the evolution of chemical mechanisms
mapped onto ancestral enzymes. This domain occurrence and abundance
in modern proteins has showed that the / architecture is probably
the oldest fold design. These observations have important implications for
the origins of biochemistry and for exploring structure-function relationships.
Over half of the known mechanisms are introduced before architectural
diversification over the evolutionary time. The other halves of the mechanisms
are invented gradually over the evolutionary timeline just after organismal
diversification. Moreover, many common mechanisms includes fundamental
building blocks of enzyme chemistry were found to be associated
with the ancestral fold
Mapping optical path length and image enhancement using quantitative orientation-independent differential interference contrast microscopy
No full textAuthor Posting. © Society of Photo Optical Instrumentation Engineers, 2017. This article is posted here by permission of Society of Photo Optical Instrumentation Engineers for personal use, not for redistribution. The definitive version was published in Journal of Biomedical Optics 22 (2017): 016006, doi:10.1117/1.JBO.22.1.016006.We describe the principles of using orientation-independent differential interference contrast (OI-DIC) microscopy for mapping optical path length (OPL). Computation of the scalar two-dimensional OPL map is based on an experimentally received map of the OPL gradient vector field. Two methods of contrast enhancement for the OPL image, which reveal hardly visible structures and organelles, are presented. The results obtained can be used for reconstruction of a volume image. We have confirmed that a standard research grade light microscope equipped with the OI-DIC and 100×/1.3 NA objective lens, which was not specially selected for minimum wavefront and polarization aberrations, provides OPL noise level of ∼0.5 nm and lateral resolution if ∼300 nm at a wavelength of 546 nm. The new technology is the next step in the development of the DIC microscopy. It can replace standard DIC prisms on existing commercial microscope systems without modification. This will allow biological researchers that already have microscopy setups to expand the performance of their systems.This
publication was made possible by Grant No. R01-GM101701
from the National Institute of General Medical Sciences,
National Institutes of Health
Simultaneous feature selection and parameter optimisation using an artificial ant colony : case study of melting point prediction
No full textWe present a novel feature selection algorithm, Winnowing Artificial Ant Colony (WAAC), that performs simultaneous feature selection and model parameter optimisation for the development of predictive quantitative structure-property relationship (QSPR) models. The WAAC algorithm is an extension of the modified ant colony algorithm of Shen et al. (J Chem Inf Model 2005, 45: 1024-1029). We test the ability of the algorithm to develop a predictive partial least squares model for the Karthikeyan dataset (J Chem Inf Model 2005, 45: 581-590) of melting point values. We also test its ability to perform feature selection on a support vector machine model for the same dataset.\ Starting from an initial set of 203 descriptors, the WAAC algorithm selected a PLS model with 68 descriptors which has an RMSE on an external test set of 46.6 degrees C and R2 of 0.51. The number of components chosen for the model was 49, which was close to optimal for this feature selection. The selected SVM model has 28 descriptors (cost of 5, epsilon of 0.21) and an RMSE of 45.1 degrees C and R2 of 0.54. This model outperforms a kNN model (RMSE of 48.3 degrees C, R2 of 0.47) for the same data and has similar performance to a Random Forest model (RMSE of 44.5 degrees C, R2 of 0.55). However it is much less prone to bias at the extremes of the range of melting points as shown by the slope of the line through the residuals: -0.43 for WAAC/SVM, -0.53 for Random Forest.\ With a careful choice of objective function, the WAAC algorithm can be used to optimise machine learning and regression models that suffer from overfitting. Where model parameters also need to be tuned, as is the case with support vector machine and partial least squares models, it can optimise these simultaneously. The moving probabilities used by the algorithm are easily interpreted in terms of the best and current models of the ants, and the winnowing procedure promotes the removal of irrelevant descriptors
Why do sequence signatures predict enzyme mechanism? Homology versus Chemistry
No full textWe identify, firstly, InterPro sequence signatures representing evolutionary relatedness and, secondly, signatures identifying specific chemical machinery. Thus, we predict the chemical mechanisms of enzyme catalysed reactions from “catalytic” and “non-catalytic” subsets of InterPro signatures. We first scanned our 249 sequences with InterProScan and then used the MACiE database to identify those amino acid residues which are important for catalysis. The sequences were mutated in silico to replace these catalytic residues with glycine, and then again scanned with InterProScan. Those signature matches from the original scan which disappeared on mutation were called “catalytic”. Mechanism was predicted using all signatures, only the 78 “catalytic” signatures, or only the 519 “non-catalytic” signatures. The noncatalytic signatures gave results indistinguishable from those for the whole feature set, with precision of 0.991 and sensitivity of 0.970. The catalytic signatures alone gave less impressive predictivity, with precision and sensitivity of 0.791 and 0.735, respectively. These results show that our successful prediction of enzyme mechanism is mostly by homology rather than by identifying catalytic machinery.Peer reviewe
