Prediction of Optimal Conditions of Hydrogenation Reaction Using the Likelihood Ranking Approach.
Ontology highlight
ABSTRACT:
SUBMITTER: Afonina VA
PROVIDER: S-EPMC8745269 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Retrosynthesis is an important task in organic chemistry. Recently, numerous data-driven approaches have achieved promising results in this task. However, in practice, these data-driven methods might lead to sub-optimal outcomes by making predictions based on the training data distribution, a phenomenon we refer as frequency bias. For example, in template-based approaches, low-ranked predictions are typically generated by less common templates with low confidence scores which might be too low to be comparable, and it is observed that recorded reactants can be among these low-ranked predictions. In this work, we introduce RetroRanker, a ranking model built upon graph neural networks, designed to mitigate the frequency bias in predictions of existing retrosynthesis models through re-ranking. RetroRanker incorporates potential reaction changes of each set of predicted reactants in obtaining the given product to lower the rank of chemically unreasonable predictions. The predicted re-ranked results on publicly available retrosynthesis benchmarks demonstrate that we can achieve improvement on most state-of-the-art models with RetroRanker. Our preliminary studies also indicate that RetroRanker can enhance the performance of multi-step retrosynthesis.
| S-EPMC10249296 | biostudies-literature
Project description:A computationally efficient approach for ranking mutant enzymes according to the catalytic reaction rates is presented. This procedure requires the generation and equilibration of the mutant structures, followed by the calculation of partial free energy curves using an empirical valence bond potential in conjunction with biased molecular dynamics simulations and umbrella integration. The individual steps are automated and optimized for computational efficiency. This approach is used to rank a series of 15 dihydrofolate reductase mutants according to the hydride transfer reaction rate. The agreement between the calculated and experimental changes in the free energy barrier upon mutation is encouraging. The computational approach predicts the correct direction of the change in free energy barrier for all mutants, and the correlation coefficient between the calculated and experimental data is 0.82. This general approach for ranking protein designs has implications for protein engineering and drug design.
| S-EPMC2664535 | biostudies-literature
Project description:The optimization of organic reaction conditions to obtain the target product in high yield is crucial to avoid expensive and time-consuming chemical experiments. Advancements in artificial intelligence have enabled various data-driven approaches to predict suitable chemical reaction conditions. However, for many novel syntheses, the process to determine good reaction conditions is inevitable. Bayesian optimization (BO), an iterative optimization algorithm, demonstrates exceptional performance to identify reagents compared to synthesis experts. However, BO requires several initial randomly selected experimental results (yields) to train a surrogate model (approximately 10 experimental trials). Parts of this process, such as the cold-start problem in recommender systems, are inefficient. Here, we present an efficient optimization algorithm to determine suitable conditions based on BO that is guided by a graph neural network (GNN) trained on a million organic synthesis experiment data. The proposed method determined 8.0 and 8.7% faster high-yield reaction conditions than state-of-the-art algorithms and 50 human experts, respectively. In 22 additional optimization tests, the proposed method needed 4.7 trials on average to find conditions higher than the yield of the conditions recommended by five synthesis experts. The proposed method is considered in a situation of having a reaction dataset for training GNN.
| S-EPMC9753507 | biostudies-literature
Project description:OBJECTIVE:As one of the most popular designs used in genetic research, family-based design has been well recognized for its advantages, such as robustness against population stratification and admixture. With vast amounts of genetic data collected from family-based studies, there is a great interest in studying the role of genetic markers from the aspect of risk prediction. This study aims to develop a new statistical approach for family-based risk prediction analysis with an improved prediction accuracy compared with existing methods based on family history. METHODS:In this study, we propose an ensemble-based likelihood ratio (ELR) approach, Fam-ELR, for family-based genomic risk prediction. Fam-ELR incorporates a clustered receiver operating characteristic (ROC) curve method to consider correlations among family samples, and uses a computationally efficient tree-assembling procedure for variable selection and model building. RESULTS:Through simulations, Fam-ELR shows its robustness in various underlying disease models and pedigree structures, and attains better performance than two existing family-based risk prediction methods. In a real-data application to a family-based genome-wide dataset of conduct disorder, Fam-ELR demonstrates its ability to integrate potential risk predictors and interactions into the model for improved accuracy, especially on a genome-wide level. CONCLUSIONS:By comparing existing approaches, such as genetic risk-score approach, Fam-ELR has the capacity of incorporating genetic variants with small or moderate marginal effects and their interactions into an improved risk prediction model. Therefore, it is a robust and useful approach for high-dimensional family-based risk prediction, especially on complex disease with unknown or less known disease etiology.
| S-EPMC6305257 | biostudies-literature
Project description:We develop a Regression-based Ranking by Pairwise Cluster Comparisons (RRPCC) method to rank clusters of similar protein complex conformations generated by an underlying docking program. The method leverages robust regression to predict the relative quality difference between any pair or clusters and combines these pairwise assessments to form a ranked list of clusters, from higher to lower quality. We apply RRPCC to clusters produced by the automated docking server ClusPro and, depending on the training/validation strategy, we show improvement by 24-100% in ranking acceptable or better quality clusters first, and by 15-100% in ranking medium or better quality clusters first. We compare the RRPCC-ClusPro combination to a number of alternatives, and show that very different machine learning approaches to scoring docked structures yield similar success rates. Finally, we discuss the current limitations on sampling and scoring, looking ahead to further improvements. Interestingly, some features important for improved scoring are internal energy terms that occur only due to the local energy minimization applied in the refinement stage following rigid body docking.
| S-EPMC8102165 | biostudies-literature
Project description:The translation of human genome discoveries into health practice is one of the major challenges in the coming decades. The use of emerging genetic knowledge for early disease prediction, prevention, and pharmacogenetics will advance genome medicine and lead to more effective prevention/treatment strategies. For this reason, studies to assess the combined role of genetic and environmental discoveries in early disease prediction represent high priority research projects, as manifested in the multiple risk prediction studies now underway. However, the risk prediction models formed to date lack sufficient accuracy for clinical use. Converging evidence suggests that diseases with the same or similar clinical manifestations could have different pathophysiological and etiological processes. When heterogeneous subphenotypes are treated as a single entity, the effect size of predictors can be reduced substantially, leading to a low-accuracy risk prediction model. The use of more refined subphenotypes facilitates the identification of new predictors and leads to improved risk prediction models. To account for the phenotypic heterogeneity, we have developed a multiclass likelihood-ratio approach, which simultaneously determines the optimum number of subphenotype groups and builds a risk prediction model for each group. Simulation results demonstrated that the new approach had more accurate and robust performance than existing approaches under various underlying disease models. The empirical study of type II diabetes (T2D) by using data from the Genes and Environment Initiatives suggested heterogeneous etiology underlying obese and nonobese T2D patients. Considering phenotypic heterogeneity in the analysis leads to improved risk prediction models for both obese and nonobese T2D subjects.
| S-EPMC3917316 | biostudies-literature
Project description:Computational identification of blood-secretory proteins, especially proteins with differentially expressed genes in diseased tissues, can provide highly useful information in linking transcriptomic data to proteomic studies for targeted disease biomarker discovery in serum.A new algorithm for prediction of blood-secretory proteins is presented using an information-retrieval technique, called manifold ranking. On a dataset containing 305 known blood-secretory human proteins and a large number of other proteins that are either not blood-secretory or unknown, the new method performs better than the previous published method, measured in terms of the area under the recall-precision curve (AUC). A key advantage of the presented method is that it does not explicitly require a negative training set, which could often be noisy or difficult to derive for most biological problems, hence making our method more applicable than classification-based data mining methods in general biological studies.We believe that our program will prove to be very useful to biomedical researchers who are interested in finding serum markers, especially when they have candidate proteins derived through transcriptomic or proteomic analyses of diseased tissues. A computer program is developed for prediction of blood-secretory proteins based on manifold ranking, which is accessible at our website http://csbl.bmb.uga.edu/publications/materials/qiliu/blood_secretory_protein.html.
| S-EPMC2877692 | biostudies-literature
Project description:An epistatic genetic architecture can have a significant impact on prediction accuracies of genomic prediction (GP) methods. Machine learning methods predict traits comprised of epistatic genetic architectures more accurately than statistical methods based on additive mixed linear models. The differences between these types of GP methods suggest a diagnostic for revealing genetic architectures underlying traits of interest. In addition to genetic architecture, the performance of GP methods may be influenced by the sample size of the training population, the number of QTL, and the proportion of phenotypic variability due to genotypic variability (heritability). Possible values for these factors and the number of combinations of the factor levels that influence the performance of GP methods can be large. Thus, efficient methods for identifying combinations of factor levels that produce most accurate GPs is needed. Herein, we employ response surface methods (RSMs) to find the experimental conditions that produce the most accurate GPs. We illustrate RSM with an example of simulated doubled haploid populations and identify the combination of factors that maximize the difference between prediction accuracies of best linear unbiased prediction (BLUP) and support vector machine (SVM) GP methods. The greatest impact on the response is due to the genetic architecture of the population, heritability of the trait, and the sample size. When epistasis is responsible for all of the genotypic variance and heritability is equal to one and the sample size of the training population is large, the advantage of using the SVM method vs. the BLUP method is greatest. However, except for values close to the maximum, most of the response surface shows little difference between the methods. We also determined that the conditions resulting in the greatest prediction accuracy for BLUP occurred when genetic architecture consists solely of additive effects, and heritability is equal to one.
| S-EPMC5592935 | biostudies-literature
Project description:A common practice in predictive medicine is to use current study data to construct a stratification procedure, which groups subjects according to baseline information and forms stratum-specific prevention or intervention strategies. A desirable stratification scheme would not only have small intra-stratum variation but also have a clinically meaningful discriminatory capability. We show how to obtain optimal stratification rules with such desirable properties from fitting a set of regression models relating the outcome to baseline covariates and creating scoring systems for predicting potential outcomes. We propose that all available optimal stratifications be evaluated with an independent dataset to select a final stratification. Lastly, we obtain inferential results for this selected stratification scheme with a holdout dataset. When only one study of moderate size is available, we combine the first two steps via crossvalidation. Extensive simulation studies are used to compare the proposed stratification strategy with alternatives. We illustrate the new proposal using an AIDS clinical trial for binary outcomes and a cardiovascular clinical study for censored event time outcomes.
| S-EPMC5793688 | biostudies-literature
Project description:Identifying optimal dosing of antibiotics has proven challenging-some antibiotics are most effective when they are administered periodically at high doses, while others work best when minimizing concentration fluctuations. Mechanistic explanations for why antibiotics differ in their optimal dosing are lacking, limiting our ability to predict optimal therapy and leading to long and costly experiments. We use mathematical models that describe both bacterial growth and intracellular antibiotic-target binding to investigate the effects of fluctuating antibiotic concentrations on individual bacterial cells and bacterial populations. We show that physicochemical parameters, e.g. the rate of drug transmembrane diffusion and the antibiotic-target complex half-life are sufficient to explain which treatment strategy is most effective. If the drug-target complex dissociates rapidly, the antibiotic must be kept constantly at a concentration that prevents bacterial replication. If antibiotics cross bacterial cell envelopes slowly to reach their target, there is a delay in the onset of action that may be reduced by increasing initial antibiotic concentration. Finally, slow drug-target dissociation and slow diffusion out of cells act to prolong antibiotic effects, thereby allowing for less frequent dosing. Our model can be used as a tool in the rational design of treatment for bacterial infections. It is easily adaptable to other biological systems, e.g. HIV, malaria and cancer, where the effects of physiological fluctuations of drug concentration are also poorly understood.
| S-EPMC5257006 | biostudies-literature