scholarly journals Improvement of Epitope Prediction Using Peptide Sequence Descriptors and Machine Learning

2019 ◽  
Vol 20 (18) ◽  
pp. 4362
Author(s):  
Cristian R. Munteanu ◽  
Marcos Gestal ◽  
Yunuen G. Martínez-Acevedo ◽  
Nieves Pedreira ◽  
Alejandro Pazos ◽  
...  
Keyword(s):  
Machine Learning ◽  
Current Model ◽  
External Validation ◽  
Epitope Prediction ◽  
Vaccine Design ◽  
Peptide Sequence ◽  
Operating Characteristics ◽  
Experimental Conditions ◽  
Epitope Sequence

In this work, we improved a previous model used for the prediction of proteomes as new B-cell epitopes in vaccine design. The predicted epitope activity of a queried peptide is based on its sequence, a known reference epitope sequence under specific experimental conditions. The peptide sequences were transformed into molecular descriptors of sequence recurrence networks and were mixed under experimental conditions. The new models were generated using 709,100 instances of pair descriptors for query and reference peptide sequences. Using perturbations of the initial descriptors under sequence or assay conditions, 10 transformed features were used as inputs for seven Machine Learning methods. The best model was obtained with random forest classifiers with an Area Under the Receiver Operating Characteristics (AUROC) of 0.981 ± 0.0005 for the external validation series (five-fold cross-validation). The database included information about 83,683 peptides sequences, 1448 epitope organisms, 323 host organisms, 15 types of in vivo processes, 28 experimental techniques, and 505 adjuvant additives. The current model could improve the in silico predictions of epitopes for vaccine design. The script and results are available as a free repository.

scholarly journals Prediction of Antimalarial Drug-Decorated Nanoparticle Delivery Systems with Random Forest Models

Biology ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 198
Author(s):  
Diana V. Urista ◽  
Diego B. Carrué ◽  
Iago Otero ◽  
Sonia Arrasate ◽  
Viviana F. Quevedo-Tumailli ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Information Fusion ◽  
High Performance ◽  
Antimalarial Activity ◽  
Classification Model ◽  
Operating Characteristics ◽  
Experimental Conditions ◽  
Nanoparticle Delivery ◽  
Random Forest Models

Drug-decorated nanoparticles (DDNPs) have important medical applications. The current work combined Perturbation Theory with Machine Learning and Information Fusion (PTMLIF). Thus, PTMLIF models were proposed to predict the probability of nanoparticle–compound/drug complexes having antimalarial activity (against Plasmodium). The aim is to save experimental resources and time by using a virtual screening for DDNPs. The raw data was obtained by the fusion of experimental data for nanoparticles with compound chemical assays from the ChEMBL database. The inputs for the eight Machine Learning classifiers were transformed features of drugs/compounds and nanoparticles as perturbations of molecular descriptors in specific experimental conditions (experiment-centered features). The resulting dataset contains 107 input features and 249,992 examples. The best classification model was provided by Random Forest, with 27 selected features of drugs/compounds and nanoparticles in all experimental conditions considered. The high performance of the model was demonstrated by the mean Area Under the Receiver Operating Characteristics (AUC) in a test subset with a value of 0.9921 ± 0.000244 (10-fold cross-validation). The results demonstrated the power of information fusion of the experimental-centered features of drugs/compounds and nanoparticles for the prediction of nanoparticle–compound antimalarial activity. The scripts and dataset for this project are available in the open GitHub repository.

scholarly journals Model for Vaccine Design by Prediction of B-Epitopes of IEDB Given Perturbations in Peptide Sequence, In Vivo Process, Experimental Techniques, and Source or Host Organisms

2014 ◽  
Vol 2014 ◽  
pp. 1-15 ◽  
Author(s):  
Humberto González-Díaz ◽  
Lázaro G. Pérez-Montoto ◽  
Florencio M. Ubeira
Keyword(s):  
Boundary Conditions ◽  
Structural Changes ◽  
Biological Process ◽  
Vaccine Design ◽  
General Purpose ◽  
Peptide Sequence ◽  
Experimental Techniques ◽  
Structure Property ◽  
Biomolecular Systems

Perturbation methods add variation terms to a known experimental solution of one problem to approach a solution for a related problem without known exact solution. One problem of this type in immunology is the prediction of the possible action of epitope of one peptide after a perturbation or variation in the structure of a known peptide and/or other boundary conditions (host organism, biological process, and experimental assay). However, to the best of our knowledge, there are no reports of general-purpose perturbation models to solve this problem. In a recent work, we introduced a new quantitative structure-property relationship theory for the study of perturbations in complex biomolecular systems. In this work, we developed the first model able to classify more than 200,000 cases of perturbations with accuracy, sensitivity, and specificity >90% both in training and validation series. The perturbations include structural changes in >50000 peptides determined in experimental assays with boundary conditions involving >500 source organisms, >50 host organisms, >10 biological process, and >30 experimental techniques. The model may be useful for the prediction of new epitopes or the optimization of known peptides towards computational vaccine design.

scholarly journals Human and machine learning of prognostic prediction for prelabor rupture of membranes and the time of delivery: a nationwide development, validation, and deployment using medical history

2021 ◽  
Author(s):  
Herdiantri Sufriyana ◽  
Yu-Wei Wu ◽  
Emily Chia-Yu Su
Keyword(s):  
Machine Learning ◽  
Web Application ◽  
External Validation ◽  
Machine Learning Algorithms ◽  
Operating Characteristics ◽  
Specific Test ◽  
High Resource ◽  
Resource Setting ◽  
Prelabor Rupture Of Membranes ◽  
Prognostic Prediction

Prognostic prediction of prelabor rupture of membrane (PROM) lacks of sample size and external validation. We compared a statistical model, machine learning algorithms, and a deep-insight visible neural network (DI-VNN) for PROM and estimating the time of delivery. We selected visits, including PROM (n=23,791/170,730), retrospectively from a nationwide health insurance dataset. DI-VNN achieved the best prediction (area under receiver operating characteristics curve [AUROC] 0.73, 95% CI 0.72 to 0.75). Meanwhile, random forest using principal components achieved the best estimation with root mean squared errors ± 2.2 and 2.6 weeks respectively for the predicted event and nonevent. DI-VNN outperformed previous models by an external validation set, including one using a biomarker (AUROC 0.641; n=1,177). We deployed our models as a web application requiring diagnosis/procedure codes and dates. In conclusion, our models may be used solely in low-resource settings or as a preliminary model to reduce a specific test requiring high-resource setting.

scholarly journals In Silico Epitope Prediction And VP1 Modelling For Foot-And-Mouth Serotype SAT 2 For Vaccine Design In East Africa

2021 ◽  
Author(s):  
Jean Claude Udahemuka ◽  
Accadius Lunayo ◽  
George Ogello Obiero ◽  
Gabriel Oluga Aboge ◽  
Phiyani Justice Lebea
Keyword(s):  
East Africa ◽  
Epitope Prediction ◽  
Foot And Mouth Disease ◽  
Vaccine Design ◽  
Cell Mediated Immunity ◽  
In Vivo Experiments ◽  
Mouth Disease Virus ◽  
Foot And Mouth

Foot and Mouth Disease Virus has seven distinct, geographically localized, serotypes and a vaccination targeting one serotype does not confer immunity against another serotype. The use of inactivated vaccines is not safe and confers an immunity with a relatively shorter time. Using the VP1 sequences isolated in East Africa, we have predicted epitopes able to induce humoral and cell-mediated immunity in cattle. The Wu-Kabat variability index calculated in this study reflects the variable, including the known GH loop, and conserved regions, with the latter being good candidates for region-tailored vaccine design. Furthermore, we modelled the identified epitopes on a 3D model (PDB ID:5aca) to represent the epitopes structurally. This study can be used for in vitro and in vivo experiments.

scholarly journals Benchmarking Datasets from Malaria Cytotoxic T-cell Epitopes Using Machine Learning Approach

2021 ◽  
Author(s):  
Rama Adiga
Keyword(s):  
Machine Learning ◽  
T Cell ◽  
Cell Epitope ◽  
Epitope Prediction ◽  
Machine Learning Algorithms ◽  
Peptide Sequence ◽  
Cytotoxic T Cell ◽  
Learning Approach ◽  
T Cell Epitopes ◽  
Machine Learning Approach

Background: Epitope prediction remains a major challenge in malaria due to the unique parasite biology, in addition to rapidly evolving parasite sequence variation in Plasmodium species. Although several models for epitope prediction exist, they are not useful in Plasmodium specific epitope development. Hence, it was proposed to use machine learning based methods to develop a peptide sequence based epitope predictor specific for malaria. Methods: Model datasets were developed and performance was tested using various machine learning algorithms. Machine learning classifiers were trained on epitope data using sequence features and comparison of amino acid physicochemical properties was done to yield a valid prediction model. Results: The findings from the analysis reveal that the model developed using selected classifiers after preprocessing by Waikato Environment for Knowledge Analysis (WEKA) performed better than other methods. The datasets for benchmarks of performance are deposited in the repository https://github.com/githubramaadiga/epito-pe_dataset. Conclusion: The study is the first in-silico study on benchmarking Plasmodium cytotoxic T cell epitope datasets using machine learning approach. The peptide based predictors have been used for the first time to classify cytotoxic T cell epitopes in malaria. Algorithms has been evaluated using real datasets from malaria to obtain the model

Superoxide, Xanthine Oxidase and Platelet Reactions: Further Studies on Mechanisms by which Oxidants Influence Platelets

1981 ◽  
Vol 45 (03) ◽  
pp. 290-293 ◽  
Author(s):  
Peter H Levine ◽  
Danielle G Sladdin ◽  
Norman I Krinsky
Keyword(s):  
Superoxide Dismutase ◽  
Cytochrome C ◽  
Xanthine Oxidase ◽  
Direct Effect ◽  
Platelet Function ◽  
Experimental Conditions ◽  
Release Reaction

SummaryIn the course of studying the effects on platelets of the oxidant species superoxide (O- 2), Of was generated by the interaction of xanthine oxidase plus xanthine. Surprisingly, gel-filtered platelets, when exposed to xanthine oxidase in the absence of xanthine substrate, were found to generate superoxide (O- 2), as determined by the reduction of added cytochrome c and by the inhibition of this reduction in the presence of superoxide dismutase.In addition to generating Of, the xanthine oxidase-treated platelets display both aggregation and evidence of the release reaction. This xanthine oxidase induced aggreagtion is not inhibited by the addition of either superoxide dismutase or cytochrome c, suggesting that it is due to either a further metabolite of O- 2, or that O- 2 itself exerts no important direct effect on platelet function under these experimental conditions. The ability of Of to modulate platelet reactions in vivo or in vitro remains in doubt, and xanthine oxidase is an unsuitable source of O- 2 in platelet studies because of its own effects on platelets.

Desmopressin (DDAVP) Enhances Platelet Adhesion to the Extracellular Matrix of Cultured Human Endothelial Cells through Increased Expression of Tissue Factor

1997 ◽  
Vol 77 (05) ◽  
pp. 0975-0980 ◽  
Author(s):  
Angel Gálvez ◽  
Goretti Gómez-Ortiz ◽  
Maribel Díaz-Ricart ◽  
Ginés Escolar ◽  
Rogelio González-Sarmiento ◽  
...  
Keyword(s):  
Extracellular Matrix ◽  
Endothelial Cells ◽  
Tissue Factor ◽  
Platelet Adhesion ◽  
Umbilical Vein ◽  
Procoagulant Activity ◽  
Experimental Conditions ◽  
Chromogenic Assay

SummaryThe effect of desmopressin (DDAVP) on thrombogenicity, expression of tissue factor and procoagulant activity (PCA) of extracellular matrix (ECM) generated by human umbilical vein endothelial cells cultures (HUVEC), was studied under different experimental conditions. HUVEC were incubated with DDAVP (1, 5 and 30 ng/ml) and then detached from their ECM. The reactivity towards platelets of this ECM was tested in a perfusion system. Coverslips covered with DD A VP-treated ECMs were inserted in a parallel-plate chamber and exposed to normal blood anticoagulated with low molecular weight heparin (Fragmin®, 20 U/ml). Perfusions were run for 5 min at a shear rate of 800 s1. Deposition of platelets on ECMs was significantly increased with respect to control ECMs when DDAVP was used at 5 and 30 ng/ml (p <0.05 and p <0.01 respectively). The increase in platelet deposition was prevented by incubation of ECMs with an antibody against human tissue factor prior to perfusion. Immunofluorescence studies positively detected tissue factor antigen on DDAVP derived ECMs. A chromogenic assay performed under standardized conditions revealed a statistically significant increase in the procoagulant activity of the ECMs produced by ECs incubated with 30 ng/ml DDAVP (p <0.01 vs. control samples). Northern blot analysis revealed increased levels of tissue factor mRNA in extracts from ECs exposed to DDAVP. Our data indicate that DDAVP in vitro enhances platelet adhesion to the ECMs through increased expression of tissue factor. A similar increase in the expression of tissue factor might contribute to the in vivo hemostatic effect of DDAVP.

In vivo Production of Soluble Inorganic Pyrophosphatases in Two Strains of Vibrio cholerae

1970 ◽  
Vol 24 (1) ◽  
pp. 38-41
Author(s):  
Taslima Taher Lina ◽  
Mohammad Ilias
Keyword(s):  
Vibrio Cholerae ◽  
Specific Activity ◽  
Experimental Conditions ◽  
Environmental Strain ◽  
Cell Extracts ◽  
Atcc Strain ◽  
The Family ◽  
Effects Of Ph ◽  
Vibrio Cholerae O1

The in vivo production of soluble inorganic pyrophosphatases (PPases) was investigated in two strains, namely, Vibrio cholerae EM 004 (environmental strain) and Vibrio cholerae O1 757 (ATCC strain). V. cholerae is known to contain both family I and family II PPase coding sequences. The production of family I and family II PPases were determined by measuring the enzyme activity in cell extracts. The effects of pH, temperature, salinity of the growth medium on the production of soluble PPases were studied. In case of family I PPase, V. cholerae EM 004 gave the highest specific activity at pH 9.0, with 2% NaCl + 0.011% NaF and at 37°C. The strain V. cholerae O1 757 gave the highest specific activity at pH 9.0, with media containing 0% NaCl and at 37°C. On the other hand, under all the conditions family II PPase did not give any significant specific activity, suggesting that the family II PPase was not produced in vivo in either strains of V. cholerae under different experimental conditions. Keywords: Vibrio cholerae, Pyrophosphatases (PPases), Specific activityDOI: http://dx.doi.org/10.3329/bjm.v24i1.1235 Bangladesh J Microbiol, Volume 24, Number 1, June 2007, pp 38-41

Applicability of Instability Index for In vitro Protein Stability Prediction

2019 ◽  
Vol 26 (5) ◽  
pp. 339-347 ◽  
Author(s):  
Dilani G. Gamage ◽  
Ajith Gunaratne ◽  
Gopal R. Periyannan ◽  
Timothy G. Russell
Keyword(s):  
Protein Stability ◽  
Caulobacter Crescentus ◽  
Effect Of Temperature ◽  
Instability Index ◽  
Dipeptide Composition ◽  
Experimental Conditions ◽  
The Stability ◽  
Vitro Protein

Background: The dipeptide composition-based Instability Index (II) is one of the protein primary structure-dependent methods available for in vivo protein stability predictions. As per this method, proteins with II value below 40 are stable proteins. Intracellular protein stability principles guided the original development of the II method. However, the use of the II method for in vitro protein stability predictions raises questions about the validity of applying the II method under experimental conditions that are different from the in vivo setting. Objective: The aim of this study is to experimentally test the validity of the use of II as an in vitro protein stability predictor. Methods: A representative protein CCM (CCM - Caulobacter crescentus metalloprotein) that rapidly degrades under in vitro conditions was used to probe the dipeptide sequence-dependent degradation properties of CCM by generating CCM mutants to represent stable and unstable II values. A comparative degradation analysis was carried out under in vitro conditions using wildtype CCM, CCM mutants and two other candidate proteins: metallo-β-lactamase L1 and α -S1- casein representing stable, borderline stable/unstable, and unstable proteins as per the II predictions. The effect of temperature and a protein stabilizing agent on CCM degradation was also tested. Results: Data support the dipeptide composition-dependent protein stability/instability in wt-CCM and mutants as predicted by the II method under in vitro conditions. However, the II failed to accurately represent the stability of other tested proteins. Data indicate the influence of protein environmental factors on the autoproteolysis of proteins. Conclusion: Broader application of the II method for the prediction of protein stability under in vitro conditions is questionable as the stability of the protein may be dependent not only on the intrinsic nature of the protein but also on the conditions of the protein milieu.

scholarly journals Non-invasive skin sampling of tryptophan/kynurenine ratio in vitro towards a skin cancer biomarker

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Skaidre Jankovskaja ◽  
Johan Engblom ◽  
Melinda Rezeli ◽  
György Marko-Varga ◽  
Tautgirdas Ruzgas ◽  
...  
Keyword(s):  
Skin Cancer ◽  
Relative Increase ◽  
Cancer Biomarker ◽  
Cancer Diagnostics ◽  
Sampling Time ◽  
Skin Permeability ◽  
Experimental Conditions ◽  
Non Invasive

AbstractThe tryptophan to kynurenine ratio (Trp/Kyn) has been proposed as a cancer biomarker. Non-invasive topical sampling of Trp/Kyn can therefore serve as a promising concept for skin cancer diagnostics. By performing in vitro pig skin permeability studies, we conclude that non-invasive topical sampling of Trp and Kyn is feasible. We explore the influence of different experimental conditions, which are relevant for the clinical in vivo setting, such as pH variations, sampling time, and microbial degradation of Trp and Kyn. The permeabilities of Trp and Kyn are overall similar. However, the permeated Trp/Kyn ratio is generally higher than unity due to endogenous Trp, which should be taken into account to obtain a non-biased Trp/Kyn ratio accurately reflecting systemic concentrations. Additionally, prolonged sampling time is associated with bacterial Trp and Kyn degradation and should be considered in a clinical setting. Finally, the experimental results are supported by the four permeation pathways model, predicting that the hydrophilic Trp and Kyn molecules mainly permeate through lipid defects (i.e., the porous pathway). However, the hydrophobic indole ring of Trp is suggested to result in a small but noticeable relative increase of Trp diffusion via pathways across the SC lipid lamellae, while the shunt pathway is proposed to slightly favor permeation of Kyn relative to Trp.

Sign in / Sign up

Export Citation Format

Share Document