Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

Detection of Optimal Models in Parameter Space with Support Vector Machines

The paper proposes an approach aimed at detecting optimal model parameter combinations to achieve the most representative description of uncertainty in the model performance. A classification problem is posed to find the regions of good fitting models according to the values of a cost function. Support Vector Machine (SVM) classification in the parameter space is applied to decide if a forward model simulation is to be computed for a particular generated model. SVM is particularly designed to tackle classification problems in high-dimensional space in a non-parametric and non-linear way. SVM decision boundaries determine the regions that are subject to the largest uncertainty in the cost function classification, and, therefore, provide guidelines for further iterative exploration of the model space. The proposed approach is illustrated by a synthetic example of fluid flow through porous media, which features highly variable response due to the parameter values' combination.

Predicted effects of small decreases in energy expenditure on weight gain in adult women.

Small daily positive energy imbalances of 200 to 800 kJ (about 50 to 200 kcal) due to reduced resting energy expenditure (REE), reduced diet-induced thermogenesis, or physical inactivity are believed to predispose to obesity. However, estimates of the magnitude of the weight gain often fail to account for concurrent changes in body composition and increases in maintenance energy requirements as weight increases and energy equilibrium is re-established. Using previously reported data on body composition and REE in women and the energy cost of tissue deposition, we used mathematical models to predict the theoretical effect of a persistent reduction in energy expenditure on long-term weight gain, assuming no adaptation in energy intake. The analyses indicate the following effects of a reduced level of energy expenditure in lean and obese women: (i) REE rises more slowly with increasing degrees of obesity due to a declining proportion of the more metabolically active fat-free mass; so, for the same positive energy balance, a significantly greater weight gain is expected for obese than for lean women before energy equilibrium is re-established; (ii) due to the greater energy density of adipose tissue, the time course of weight gain to achieve energy balance is longer for obese subjects: in general, this is approximately five years for lean and ten years for obese women; (iii) the magnitude of weight gain of lean women in response to a reduced energy expenditure of 200 to 800 kJ/day is only about 3 to 15 kg, amounts insufficient to explain severe obesity.

Individual Classification of Mild Cognitive Impairment Subtypes by Support Vector Machine Analysis of White Matter DTI.

BACKGROUND AND PURPOSE: MCI was recently subdivided into sd-aMCI, sd-fMCI, and md-aMCI. The current investigation aimed to discriminate between MCI subtypes by using DTI. MATERIALS AND METHODS: Sixty-six prospective participants were included: 18 with sd-aMCI, 13 with sd-fMCI, and 35 with md-aMCI. Statistics included group comparisons using TBSS and individual classification using SVMs. RESULTS: The group-level analysis revealed a decrease in FA in md-aMCI versus sd-aMCI in an extensive bilateral, right-dominant network, and a more pronounced reduction of FA in md-aMCI compared with sd-fMCI in right inferior fronto-occipital fasciculus and inferior longitudinal fasciculus. The comparison between sd-fMCI and sd-aMCI, as well as the analysis of the other diffusion parameters, yielded no significant group differences. The individual-level SVM analysis provided discrimination between the MCI subtypes with accuracies around 97%. The major limitation is the relatively small number of cases of MCI. CONCLUSIONS: Our data show that, at the group level, the md-aMCI subgroup has the most pronounced damage in white matter integrity. Individually, SVM analysis of white matter FA provided highly accurate classification of MCI subtypes.

Retinal degeneration progression changes lentiviral vector cell targeting in the retina.

In normal mice, the lentiviral vector (LV) is very efficient to target the RPE cells, but transduces retinal neurons well only during development. In the present study, the tropism of LV has been investigated in the degenerating retina of mice, knowing that the retina structure changes during degeneration. We postulated that the viral transduction would be increased by the alteration of the outer limiting membrane (OLM). Two different LV pseudotypes were tested using the VSVG and the Mokola envelopes, as well as two animal models of retinal degeneration: light-damaged Balb-C and Rhodopsin knockout (Rho-/-) mice. After light damage, the OLM is altered and no significant increase of the number of transduced photoreceptors can be obtained with a LV-VSVG-Rhop-GFP vector. In the Rho-/- mice, an alteration of the OLM was also observed, but the possibility of transducing photoreceptors was decreased, probably by ongoing gliosis. The use of a ubiquitous promoter allows better photoreceptor transduction, suggesting that photoreceptor-specific promoter activity changes during late stages of photoreceptor degeneration. However, the number of targeted photoreceptors remains low. In contrast, LV pseudotyped with the Mokola envelope allows a wide dispersion of the vector into the retina (corresponding to the injection bleb) with preferential targeting of Müller cells, a situation which does not occur in the wild-type retina. Mokola-pseudotyped lentiviral vectors may serve to engineer these glial cells to deliver secreted therapeutic factors to a diseased area of the retina.

Morphometric shape analysis using learning vector quantization neural networks - an example distinguishing two microtine vole species

Closely related species may be very difficult to distinguish morphologically, yet sometimes morphology is the only reasonable possibility for taxonomic classification. Here we present learning-vector-quantization artificial neural networks as a powerful tool to classify specimens on the basis of geometric morphometric shape measurements. As an example, we trained a neural network to distinguish between field and root voles from Procrustes transformed landmark coordinates on the dorsal side of the skull, which is so similar in these two species that the human eye cannot make this distinction. Properly trained neural networks misclassified only 3% of specimens. Therefore, we conclude that the capacity of learning vector quantization neural networks to analyse spatial coordinates is a powerful tool among the range of pattern recognition procedures that is available to employ the information content of geometric morphometrics.

Retinal degeneration progression changes lentiviral vector cell targeting in the retina

Ce travail de thèse a été réalisé au sein de l'Unité de Thérapie Génique et Biologie des Cellules Souches de l'Hôpital Jules- Gonin dans le Service d'Ophtalmologie de l'Université de Lausanne. Ce laboratoire recherche des solutions thérapeutiques pour des maladies dégénératives et incurables de la rétine comme les rétinites pigmentaires (RP). Ayant déjà montré certains résultats dans le domaine, la thérapie génique a été notre outil pour ce travail. Cette méthode se base sur le principe de remplacer un gène déficient par sa copie normale, en transportant celle-ci au coeur même du noyau par un vecteur. Il existe à l'heure actuelle différents vecteurs. Un des plus efficaces est un vecteur viral non-réplicatif : le lentivirus, dérivé de HIV-1. Celui-ci a la capacité d'intégrer le génome de la cellule cible, lui conférant ainsi un nouveau matériel génétique. Notre but a été d'établir le tropisme du lentivirus dans une rétine en dégénérescence. Ce lentivirus est connu pour transduire efficacement les cellules de l'épithélium pigmentaire rétinien dans l'oeil adulte sain, ainsi que celles de la neurorétine, mais ce, uniquement durant le développement. On sait aussi que le vecteur lentiviral présente un tropisme différent selon les enveloppes dont il est muni ; par exemple, le lentivirus avec une enveloppe Mokola est connu pour transduire les cellules gliales du système nerveux central. La rétine qui dégénère montre quant à elle des changements de sa structure qui pourraient influencer la diffusion du vecteur et/ou son tropisme. Le postulat de base a été le suivant : chez l'adulte, la transduction des neurones de la rétine via le lentivirus pourrait être facilitée par l'altération de la membrane limitante externe induite par la dégénérescence (meilleure pénétrance du virus). D'un point de vue technique, nous avons utilisé deux types distincts de modèles murins de dégénérescence rétinienne : des souris Balb/C soumises à une dose toxique de lumière et les souris Rhodopsin knockout, animaux génétiquement modifiés. Comme vecteur viral, nous avons employé deux différents pseudotypes de lentivirus (caractérisés par les enveloppes virales) avec différents promoteurs (séquence d'ADN qui initie la transduction et confère la spécificité d'expression d'un gène). En changeant l'enveloppe et le promoteur, nous avons essayé de trouver la meilleure combinaison pour augmenter l'affinité du vecteur vis-à-vis des photorécepteurs d'abord, puis vis-à-vis d'autres cellules de la rétine. Nos résultats ont montré que la membrane limitante externe est effectivement altérée chez les deux modèles de dégénérescence, mais que cette modification ne favorise pas la transduction des photorécepteurs lorsqu'on utilise un vecteur lentiviral contenant une enveloppe VSVG et un promoteur photorécepteur-spécifique ou ubiquitaire. En effet, une forte réaction gliale a été observée. Par contre, en utilisant le lentivirus avec une enveloppe Mokola et un promoteur ubiquitaire, nous avons constaté une très bonne transduction au niveau des cellules de Millier dans la rétine en dégénérescence, phénomène non observé chez les souris sauvages. Ce travail a donc permis de trouver un vecteur viral efficace pour atteindre et transduire les cellules de Miiller, ceci seulement pendant la dégénérescence de la rétine. Ces cellules, une fois transduites, pourraient être utilisées pour sécréter dans la rétine des agents thérapeutiques tels que des facteurs neurotrophiques pour soutenir la survie des photorécepteurs ou des facteurs anti-angiogéniques pour prévenir la néo-vascularisation lors de diabète ou de dégénérescence maculaire liée à l'âge. - In normal mice, the lentiviral vector (LV) is very efficient to target the RPE cells, but transduces retinal neurons well only during development. In the present study, the tropism of LV has been investigated in the degenerating retina of mice, knowing that the retina structure changes during degeneration. We postulated that the viral transduction would be increased by the alteration of the iuter limiting membrane (OLM). Two different LV pseudotypes were tested using the VSVG arid the Mokola envelopes, as well as two animal models of retinal degeneration: light-damaged Balb-C and Rhodopsin knockout (Rho-/-) mice. After light damage, the OLM is altered and no significant increase of the number of transduced photoreceptors can be obtained with a LV-VSVG-Rhop-GFP vector. In the Rho-/- mice, an altération of the OLM was also observed, but the possibility of transducing photoreceptors was decreased, probably by ongoing gliosis. The use of a ubiquitous promoter allows better photoreceptor transduction, suggesting that photoreceptór-specific promoter activity change during late stages of photoreceptor degeneration. However, the number of targeted photoreceptors remains low. In contrast, LV pseudotyped with the tfokola envelope allows a wide dispersion of the ctor into the retina (corresponding to the injection bleb) with preferential targeting of Muller cells, a situation Mc\ does ot occur in the wild- type retina. Mokola-pseudotyped lentiviral vectors may serve to engineer these glial cells to deliver secreted therapeutic factors to a diseased area of the retina.

Meal-induced thermogenesis and obesity: is a fat meal a risk factor for fat gain in children?

Diet composition, in particular fat intake, has been suggested to be a risk factor for obesity in humans. Several mechanisms may contribute to explain the impact of fat intake on fat gain. One factor may be the low thermogenesis induced by a mixed meal rich in fat. In a group of 11 girls (10.1 +/- 0.3 yr), 6 obese (body mass index, 25.6 +/- 0.6 kg/m(2)), and 5 nonobese (body mass index, 19 +/- 1.6 kg/m(2)), we tested the hypothesis that a mixed meal rich in fat can elicit energy saving compared with an isocaloric and isoproteic meal rich in carbohydrate. The postabsorptive resting energy expenditure and the thermic effect of a meal (TEM) after a low fat (LF; 20% fat, 68% carbohydrate, and 12% protein) or an isocaloric (2500 kJ or 600 Cal) and isoproteic high fat (HF; 48% fat, 40% carbohydrate, and 12% protein) meal were measured by indirect calorimetry. Each girl repeated the test with a different, randomly assigned menu (HF or LF) 1 week after the first test. TEM, expressed as a percentage of energy intake was significantly higher after a LF meal than after a HF meal (6.5 +/- 0.7% vs. 4.3 +/- 0.4%; P < 0.01). The postprandial respiratory quotient (RQ) was significantly higher after a LF meal than after a HF meal (0.86 +/- 0.013 vs. 0.83 +/- 0.014; P < 0.001). The HF low carbohydrate meal induced a significantly lower increase in carbohydrate oxidation than the LF meal (20.3 +/- 6.2 vs. 61.3 +/- 7.8 mg/min; P < 0.001). On the contrary, fat oxidation was significantly higher after a HF meal than after a LF meal (-1.3 +/- 2.4 vs. -15.1 +/- 3.6 mg/min; P < 0.01). However, the postprandial fat storage was 8-fold higher after a HF meal than after a LF meal (17.2 +/- 1.7 vs. 1.9 +/- 1.8 g; P < 0.001). These results suggest that a high fat meal is able to induce lower thermogenesis and a higher positive fat balance than an isocaloric and isoproteic low fat meal. Therefore, diet composition per se must be taken into account among the various risk factors that induce obesity in children.

Uncertainty Quantification with Support Vector Regression Prediction Models

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. The paper considers a data driven approach in modelling uncertainty in spatial predictions. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic features and describe stochastic variability and non-uniqueness of spatial properties. It is able to capture and preserve key spatial dependencies such as connectivity, which is often difficult to achieve with two-point geostatistical models. Semi-supervised SVR is designed to integrate various kinds of conditioning data and learn dependences from them. A stochastic semi-supervised SVR model is integrated into a Bayesian framework to quantify uncertainty with multiple models fitted to dynamic observations. The developed approach is illustrated with a reservoir case study. The resulting probabilistic production forecasts are described by uncertainty envelopes.

Gain of function mutations in CgPDR1 of Candida glabrata not only mediate antifungal resistance but also enhance virulence.

CgPdr1p is a Candida glabrata Zn(2)-Cys(6) transcription factor involved in the regulation of the ABC-transporter genes CgCDR1, CgCDR2, and CgSNQ2, which are mediators of azole resistance. Single-point mutations in CgPDR1 are known to increase the expression of at least CgCDR1 and CgCDR2 and thus to contribute to azole resistance of clinical isolates. In this study, we investigated the incidence of CgPDR1 mutations in a large collection of clinical isolates and tested their relevance, not only to azole resistance in vitro and in vivo, but also to virulence. The comparison of CgPDR1 alleles from azole-susceptible and azole-resistant matched isolates enabled the identification of 57 amino acid substitutions, each positioned in distinct CgPDR1 alleles. These substitutions, which could be grouped into three different "hot spots," were gain of function (GOF) mutations since they conferred hyperactivity to CgPdr1p revealed by constitutive high expression of ABC-transporter genes. Interestingly, the major transporters involved in azole resistance (CgCDR1, CgCDR2, and CgSNQ2) were not always coordinately expressed in presence of specific CgPDR1 GOF mutations, thus suggesting that these are rather trans-acting elements (GOF in CgPDR1) than cis-acting elements (promoters) that lead to azole resistance by upregulating specific combinations of ABC-transporter genes. Moreover, C. glabrata isolates complemented with CgPDR1 hyperactive alleles were not only more virulent in mice than those with wild type alleles, but they also gained fitness in the same animal model. The presence of CgPDR1 hyperactive alleles also contributed to fluconazole treatment failure in the mouse model. In conclusion, this study shows for the first time that CgPDR1 mutations are not only responsible for in vitro/in vivo azole resistance but that they can also confer a selective advantage under host conditions.

Composition of weight gain during the neonatal period and longitudinal growth follow-up in premature babies.

Changes in the rate of growth and adiposity index (Quetelet index), calculated as weight/(length)2, kg/m2, were monitored from birth to 3 years in 19 premature babies (post-conceptional age 31.2 +/- 2 weeks) who were subjected during rapid growth (16 +/- 4 g/kg.day) to initial metabolic balance studies in the first weeks of life. These studies showed that the rate of fat accretion in these infants (3.3 +/- 0.9 g/kg.day) was substantially greater than that observed in fetuses of the same gestational age (2 g/kg.day) but the adiposity index was lower (9.6 +/- 1 kg/m2) than intrauterine values (11 kg/m2). Since at 6 months of age (corrected for gestational age at birth) the adiposity index was close to normality (103% of standard), the greater rate of fat accretion in early life contributed to progressively restore total body fat in premature babies. It is concluded that despite substantial fat deposition during the first weeks of life, the future evolution of these premature babies is favourable as judged from the normalization of adiposity index within the first 2 years of life.