Modified linear regression predicts drug-target interactions accurately.
Ontology highlight
ABSTRACT:
SUBMITTER: Buza K
PROVIDER: S-EPMC7135267 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Modified linear regression predicts drug-target interactions accurately.
Buza Krisztian K Peška Ladislav L Koller Júlia J
PloS one 20200406 4
State-of-the-art approaches for the prediction of drug-target interactions (DTI) are based on various techniques, such as matrix factorisation, restricted Boltzmann machines, network-based inference and bipartite local models (BLM). In this paper, we propose the framework of Asymmetric Loss Models (ALM) which is more consistent with the underlying chemical reality compared with conventional regression techniques. Furthermore, we propose to use an asymmetric loss model with BLM to predict drug-ta ...[more]
Similar Datasets
Project description:Several machine learning approaches have been proposed for predicting new benefits of the existing drugs. Although these methods have introduced new usage(s) of some medications, efficient methods can lead to more accurate predictions. To this end, we proposed a novel machine learning method which is based on a new optimization algorithm, named Trader. To show the capabilities of the proposed algorithm which can be applied to the different scope of science, it was compared with ten other state-of-the-art optimization algorithms based on the standard and advanced benchmark functions. Next, a multi-layer artificial neural network was designed and trained by Trader to predict drug-target interactions (DTIs). Finally, the functionality of the proposed method was investigated on some DTIs datasets and compared with other methods. The data obtained by Trader showed that it eliminates the disadvantages of different optimization algorithms, resulting in a better outcome. Further, the proposed machine learning method was found to achieve a significant level of performance compared to the other popular and efficient approaches in predicting unknown DTIs. All the implemented source codes are freely available at https://github.com/LBBSoft/Trader .
| S-EPMC6597553 | biostudies-literature
Project description:Death investigations often include an effort to establish the postmortem interval (PMI) in cases in which the time of death is uncertain. The postmortem interval can lead to the identification of the deceased and the validation of witness statements and suspect alibis. Recent research has demonstrated that microbes provide an accurate clock that starts at death and relies on ecological change in the microbial communities that normally inhabit a body and its surrounding environment. Here, we explore how to build the most robust Random Forest regression models for prediction of PMI by testing models built on different sample types (gravesoil, skin of the torso, skin of the head), gene markers (16S ribosomal RNA (rRNA), 18S rRNA, internal transcribed spacer regions (ITS)), and taxonomic levels (sequence variants, species, genus, etc.). We also tested whether particular suites of indicator microbes were informative across different datasets. Generally, results indicate that the most accurate models for predicting PMI were built using gravesoil and skin data using the 16S rRNA genetic marker at the taxonomic level of phyla. Additionally, several phyla consistently contributed highly to model accuracy and may be candidate indicators of PMI.
| S-EPMC5852600 | biostudies-literature
Project description:Computational methods for predicting drug-target interactions have become important in drug research because they can help to reduce the time, cost, and failure rates for developing new drugs. Recently, with the accumulation of drug-related data sets related to drug side effects and pharmacological data, it has became possible to predict potential drug-target interactions. In this study, we focus on drug-drug interactions (DDI), their adverse effects ([Formula: see text]) and pharmacological information ([Formula: see text]), and investigate the relationship among chemical structures, side effects, and DDIs from several data sources. In this study, [Formula: see text] data from the STITCH database, [Formula: see text] from drugs.com, and drug-target pairs from ChEMBL and SIDER were first collected. Then, by applying two machine learning approaches, a support vector machine (SVM) and a kernel-based L1-norm regularized logistic regression (KL1LR), we showed that DDI is a promising feature in predicting drug-target interactions. Next, the accuracies of predicting drug-target interactions using DDI were compared to those obtained using the chemical structure and side effects based on the SVM and KL1LR approaches, showing that DDI was the data source contributing the most for predicting drug-target interactions.
| S-EPMC3836969 | biostudies-literature
Project description:The general linear regression model has been one of the most frequently used models over the years, with the ordinary least squares estimator (OLS) used to estimate its parameter. The problems of the OLS estimator for linear regression analysis include that of multicollinearity and outliers, which lead to unfavourable results. This study proposed a two-parameter ridge-type modified M-estimator (RTMME) based on the M-estimator to deal with the combined problem resulting from multicollinearity and outliers. Through theoretical proofs, Monte Carlo simulation, and a numerical example, the proposed estimator outperforms the modified ridge-type estimator and some other considered existing estimators.
| S-EPMC7245687 | biostudies-literature
Project description:Mining of metabolite-protein interaction networks facilitates the identification of design principles underlying the regulation of different cellular processes. However, identification and characterization of the regulatory role that metabolites play in interactions with proteins on a genome-scale level remains a pressing task. Based on availability of high-quality metabolite-protein interaction networks and genome-scale metabolic networks, here we propose a supervised machine learning approach, called CIRI that determines whether or not a metabolite is involved in a competitive inhibitory regulatory interaction with an enzyme. First, we show that CIRI outperforms the naive approach based on a structural similarity threshold for a putative competitive inhibitor and the substrates of a metabolic reaction. We also validate the performance of CIRI on several unseen data sets and databases of metabolite-protein interactions not used in the training, and demonstrate that the classifier can be effectively used to predict competitive inhibitory interactions. Finally, we show that CIRI can be employed to refine predictions about metabolite-protein interactions from a recently proposed PROMIS approach that employs metabolomics and proteomics profiles from size exclusion chromatography in E. coli to predict metabolite-protein interactions. Altogether, CIRI fills a gap in cataloguing metabolite-protein interactions and can be used in directing future machine learning efforts to categorize the regulatory type of these interactions.
| S-EPMC8172118 | biostudies-literature
Project description:The advance in targeted therapy has greatly increased the effectiveness of clinical cancer therapy and reduced the cytotoxicity of treatments to normal cells. However, patients still suffer from cancer relapse due to the occurrence of drug resistance. It is of great need to explore potential combinatorial drug therapy since individual drug alone may not be sufficient to inhibit continuous activation of cancer-addicted genes or pathways. The DREAM challenge has confirmed the potentiality of computational methods for predicting synergistic drug combinations, while the prediction accuracy can be further improved.Based on previous reports, we hypothesized the similarity in biological functions or genes perturbed by two drugs can determine their synergistic effects. To test the feasibility of the hypothesis, we proposed three scoring systems: co-gene score, co-GS score, and co-gene/GS score, measuring the similarities in genes with significant expressional changes, enriched gene sets, and significantly changed genes within an enriched gene sets between a pair of drugs, respectively. Performances of these scoring systems were evaluated by the probabilistic c-index (PC-index) devised by the DREAM consortium. We also applied the proposed method to the Connectivity Map dataset to explore more potential synergistic drug combinations.Using a gold standard derived by the DREAM consortium, we confirmed the prediction power of the three scoring systems (all P-values < 0.05). The co-gene/GS score achieved the best prediction of drug synergy (PC-index = 0.663, P-value < 0.0001), outperforming all methods proposed during DREAM challenge. Furthermore, a binary classification test showed that co-gene/GS scoring was highly accurate and specific. Since our method is constructed on a gene set-based analysis, in addition to synergy prediction, it provides insights into the functional relevance of drug combinations and the underlying mechanisms by which drugs achieve synergy.Here we proposed a novel and simple method to predict and investigate drug synergy, and validated its efficacy to accurately predict synergistic drug combinations and to comprehensively explore their underlying mechanisms. The method is widely applicable to expression profiles of other drug treatments and is expected to accelerate the realization of precision cancer treatment.
| S-EPMC5009556 | biostudies-other
Project description:BackgroundThe problem of multicollinearity in multiple linear regression models arises when the predictor variables are correlated among each other. The variance of the ordinary least squared estimator become unstable in such situation. In order to mitigate the problem of multicollinearity, Liu regression is widely used as a biased method of estimation with shrinkage parameter 'd'. The optimal value of shrinkage parameter plays a vital role in bias-variance trade-off.LimitationSeveral estimators are available in literature for the estimation of shrinkage parameter. But the existing estimators do not perform well in terms of smaller mean squared error when the problem of multicollinearity is high or severe.MethodologyIn this paper, some new estimators for the shrinkage parameter are proposed. The proposed estimators are the class of estimators that are based on quantile of the regression coefficients. The performance of the new estimators is compared with the existing estimators through Monte Carlo simulation. Mean squared error and mean absolute error is considered as evaluation criteria of the estimators. Tobacco dataset is used as an application to illustrate the benefits of the new estimators and support the simulation results.FindingsThe new estimators outperform the existing estimators in most of the considered scenarios including high and severe cases of multicollinearity. 95% mean prediction interval of all the estimators is also computed for the Tobacco data. The new estimators give the best mean prediction interval among all other estimators.The implications of the findingsWe recommend the use of new estimators to practitioners when the problem of high to severe multicollinearity exists among the predictor variables.
| S-EPMC8608338 | biostudies-literature
Project description:BackgroundRisk factor-based equations are used to predict risk of kidney disease progression in patients with type 2 diabetes order to guide treatment decisions. It is, however, unknown whether these models can also be used to predict the effects of drugs on clinical outcomes.MethodsThe previously developed Parameter Response Efficacy (PRE) score, which integrates multiple short-term drug effects, was first compared with the existing risk scores, Kidney Failure Risk Equation (KFRE) and The Action in Diabetes and Vascular Disease: Preterax and Diamicron Modified Release Controlled Evaluation (ADVANCE) renal risk score, in its performance to predict end-stage renal disease (ESRD; KFRE) and doubling of serum creatinine or ESRD (ADVANCE). Second, changes in the risk scores were compared after 6 months' treatment to predict the long-term effects of losartan on these renal outcomes in patients with type 2 diabetes and chronic kidney disease.ResultsThe KFRE, ADVANCE and PRE scores showed similarly good performance in predicting renal risk. However, for prediction of the effect of losartan, the KFRE risk score predicted a relative risk change in the occurrence of ESRD of 3.1% [95% confidence interval (CI) -5 to 12], whereas the observed risk change was -28.8% (95% CI -42.0 to -11.5). For the composite endpoint of doubling of serum creatinine or ESRD, the ADVANCE score predicted a risk change of -12.4% (95% CI -17 to -7), which underestimated the observed risk change -21.8% (95% CI -34 to -6). The PRE score predicted renal risk changes that were close to the observed risk changes with losartan treatment [-24.0% (95% CI -30 to -17) and -22.6% (95% CI -23 to -16) for ESRD and the composite renal outcome, respectively].ConclusionA drug response score such as the PRE score may assist in improving clinical decision making and implement precision medicine strategies.
| S-EPMC7876574 | biostudies-literature
Project description:Multivariate regression is increasingly used to study the relation between fMRI spatial activation patterns and experimental stimuli or behavioral ratings. With linear models, informative brain locations are identified by mapping the model coefficients. This is a central aspect in neuroimaging, as it provides the sought-after link between the activity of neuronal populations and subject's perception, cognition or behavior. Here, we show that mapping of informative brain locations using multivariate linear regression (MLR) may lead to incorrect conclusions and interpretations. MLR algorithms for high dimensional data are designed to deal with targets (stimuli or behavioral ratings, in fMRI) separately, and the predictive map of a model integrates information deriving from both neural activity patterns and experimental design. Not accounting explicitly for the presence of other targets whose associated activity spatially overlaps with the one of interest may lead to predictive maps of troublesome interpretation. We propose a new model that can correctly identify the spatial patterns associated with a target while achieving good generalization. For each target, the training is based on an augmented dataset, which includes all remaining targets. The estimation on such datasets produces both maps and interaction coefficients, which are then used to generalize. The proposed formulation is independent of the regression algorithm employed. We validate this model on simulated fMRI data and on a publicly available dataset. Results indicate that our method achieves high spatial sensitivity and good generalization and that it helps disentangle specific neural effects from interaction with predictive maps associated with other targets.
| S-EPMC6869070 | biostudies-literature
Project description:Background: Tuberculosis disease, caused by Mycobacterium tuberculosis, is a major public health problem. The emergence of M. tuberculosis strains resistant to existing treatments threatens to derail control efforts. Resistance is mainly conferred by mutations in genes coding for drug targets or converting enzymes, but our knowledge of these mutations is incomplete. Whole genome sequencing (WGS) is an increasingly common approach to rapidly characterize isolates and identify mutations predicting antimicrobial resistance and thereby providing a diagnostic tool to assist clinical decision making. Methods: We applied machine learning approaches to 16,688 M. tuberculosis isolates that have undergone WGS and laboratory drug-susceptibility testing (DST) across 14 antituberculosis drugs, with 22.5% of samples being multidrug resistant and 2.1% being extensively drug resistant. We used non-parametric classification-tree and gradient-boosted-tree models to predict drug resistance and uncover any associated novel putative mutations. We fitted separate models for each drug, with and without "co-occurrent resistance" markers known to be causing resistance to drugs other than the one of interest. Predictive performance was measured using sensitivity, specificity, and the area under the receiver operating characteristic curve, assuming DST results as the gold standard. Results: The predictive performance was highest for resistance to first-line drugs, amikacin, kanamycin, ciprofloxacin, moxifloxacin, and multidrug-resistant tuberculosis (area under the receiver operating characteristic curve above 96%), and lowest for third-line drugs such as D-cycloserine and Para-aminosalisylic acid (area under the curve below 85%). The inclusion of co-occurrent resistance markers led to improved performance for some drugs and superior results when compared to similar models in other large-scale studies, which had smaller sample sizes. Overall, the gradient-boosted-tree models performed better than the classification-tree models. The mutation-rank analysis detected no new single nucleotide polymorphisms linked to drug resistance. Discordance between DST and genotypically inferred resistance may be explained by DST errors, novel rare mutations, hetero-resistance, and nongenomic drivers such as efflux-pump upregulation. Conclusion: Our work demonstrates the utility of machine learning as a flexible approach to drug resistance prediction that is able to accommodate a much larger number of predictors and to summarize their predictive ability, thus assisting clinical decision making and single nucleotide polymorphism detection in an era of increasing WGS data generation.
| S-EPMC6775242 | biostudies-literature