Search

This paper investigates statistical reproducibility of the [Formula: see text]-test. We formulate reproducibility as a predictive inference problem and apply the nonparametric predictive inference method. Within our research framework, statistical reproducibility provides inference on the probability that the same test outcome would be reached, if the test were repeated under identical conditions. We present an nonparametric predictive inference algorithm to calculate the reproducibility of the [Formula: see text]-test and then use simulations to explore the reproducibility both under the null and alternative hypotheses. We then apply nonparametric predictive inference reproducibility to a real-life scenario of a preclinical experiment, which involves multiple pairwise comparisons of test groups, where different groups are given a different concentration of a drug. The aim of the experiment is to decide the concentration of the drug which is most effective. In both simulations and the application scenario, we study the relationship between reproducibility and two test statistics, the Cohen’s [Formula: see text] and the [Formula: see text]-value. We also compare the reproducibility of the [Formula: see text]-test with the reproducibility of the Wilcoxon Mann–Whitney test. Finally, we examine reproducibility for the final decision of choosing a particular dose in the multiple pairwise comparisons scenario. This paper presents advances on the topic of test reproducibility with relevance for tests used in pharmaceutical research.

In an age where the volume of data regarding biological systems exceeds our ability to analyse it, many researchers are looking towards systems biology and computational modelling to help unravel the complexities of gene and protein regulatory networks. In particular, the use of discrete modelling allows generation of signalling networks in the absence of full quantitative descriptions of systems, which are necessary for ordinary differential equation (ODE) models. In order to make such techniques more accessible to mainstream researchers, tools such as the BioModelAnalyzer (BMA) have been developed to provide a user-friendly graphical interface for discrete modelling of biological systems. Here we use the BMA to build a library of discrete target functions of known canonical molecular interactions, translated from ordinary differential equations (ODEs). We then show that these BMA target functions can be used to reconstruct complex networks, which can correctly predict many known genetic perturbations. This new library supports the accessibility ethos behind the creation of BMA, providing a toolbox for the construction of complex cell signalling models without the need for extensive experience in computer programming or mathematical modelling, and allows for construction and simulation of complex biological systems with only small amounts of quantitative data.

We present two applications of conformal prediction relevant to drug discovery. The first application is around interpretation of predictions and the second one around the selection of compounds to progress in a drug discovery project setting.

The high cost for new medicines is hindering their development and machine learning is therefore being used to avoid carrying out physical experiments. Here, we present a comparison between three different machine learning approaches in a classification setting where learning and prediction follow a teaching schedule to mimic the drug discovery process. The approaches are standard SVM classification, SVM based multi-kernel classification and SVM classification based on learning using privileged information. Our two main conclusions are derived using experimental in-vitro data and compound structure descriptors. The in-vitro data is assumed to i) be completely absent in the standard SVM setting, ii) be available at all times when applying multi-kernel learning, or iii) be available as privileged information during training only. The structure descriptors are always available. One conclusion is that multi-kernel learning has higher odds than standard SVM in producing higher accuracy. The second is that learning using privileged information does not have higher odds than the standard SVM, although it may improve accuracy when the training sets are small.

While deep learning has seen many recent applications to drug discovery, most have focused on predicting activity or toxicity directly from chemical structure. Phenotypic changes exhibited in cellular images are also indications of the mechanism of action (MoA) of chemical compounds. In this paper, we show how pre-trained convolutional image features can be used to assist scientists in discovering interesting chemical clusters for further investigation. Our method reduces the dimensionality of raw fluorescent stained images from a high throughput imaging (HTI) screen, producing an embedding space that groups together images with similar cellular phenotypes. Running standard unsupervised clustering on this embedding space yields a set of distinct phenotypic clusters. This allows scientists to further select and focus on interesting clusters for downstream analyses. We validate the consistency of our embedding space qualitatively with t-sne visualizations, and quantitatively by measuring embedding variance among images that are known to be similar. Results suggested the usefulness of our proposed workflow using deep learning and clustering and it can lead to robust HTI screening and compound triage.

A single click ensemble segmentation (SCES) approach based on an existing "Click & Grow" algorithm is presented. The SCES approach requires only one operator selected seed point as compared with multiple operator inputs, which are typically needed. This facilitates processing large numbers of cases. Evaluation on a set of 129 CT lung tumor images using a similarity index (SI) was done. The average SI is above 93% using 20 different start seeds, showing stability. The average SI for 2 different readers was 79.53%. We then compared the SCES algorithm with the two readers, the level set algorithm and the skeleton graph cut algorithm obtaining an average SI of 78.29%, 77.72%, 63.77% and 63.76%, respectively. We can conclude that the newly developed automatic lung lesion segmentation algorithm is stable, accurate and automated.

Age-related sarcopenia results in frailty and decreased mobility, which are associated with increased falls and long-term disability in the elderly. Given the global increase in lifespan, sarcopenia is a growing, unmet medical need. This report aims to systematically characterize muscle aging in preclinical models, which may facilitate the development of sarcopenia therapies. Naïve rats and mice were subjected to noninvasive micro X-ray computed tomography (micro-CT) imaging, terminal in situ muscle function characterizations, and ATPase-based myofiber analysis. We developed a Definiens (Parsippany, NJ)-based algorithm to automate micro-CT image analysis, which facilitates longitudinal in vivo muscle mass analysis. We report development and characterization of translational in situ skeletal muscle performance assay systems in rat and mouse. The systems incorporate a custom-designed animal assay stage, resulting in enhanced force measurement precision, and LabVIEW (National Instruments, Austin, TX)-based algorithms to support automated data acquisition and data analysis. We used ATPase-staining techniques for myofibers to characterize fiber subtypes and distribution. Major parameters contributing to muscle performance were identified using data mining and integration, enabled by Labmatrix (BioFortis, Columbia, MD). These technologies enabled the systemic and accurate monitoring of muscle aging from a large number of animals. The data indicated that longitudinal muscle cross-sectional area measurement effectively monitors change of muscle mass and function during aging. Furthermore, the data showed that muscle performance during aging is also modulated by myofiber remodeling factors, such as changes in myofiber distribution patterns and changes in fiber shape, which affect myofiber interaction. This in vivo muscle assay platform has been applied to support identification and validation of novel targets for the treatment of sarcopenia.

OBJECTIVE: This study was designed to characterize the reproducibility of measurement for tumor volumes and their longest tumor diameters (LDs) and estimate the potential impact of using changes in tumor volumes instead of LDs as the basis for response assessments. METHODS: We studied patients with advanced lung cancer who have been observed longitudinally with x-ray computed tomography in a multinational trial. A total of 71 time points from 10 patients with 13 morphologically complex target lesions were analyzed. A total of 6461 volume measurements and their corresponding LDs were made by seven independent teams using their own work flows and image analysis tools. Interteam agreement and overall interrater concurrence were characterized. RESULTS: Interteam agreement between volume measurements was better than between LD measurements (i = 0.945 vs 0.734, P = .005). The variability in determining the nadir was lower for volumes than for LDs ( P = .005). Use of standard thresholds for the RECIST-based method and use of experimentally determined cutoffs for categorizing responses showed that volume measurements had a significantly greater sensitivity for detecting partial responses and disease progression. Earlier detection of progression would have led to earlier changes in patient management in most cases. CONCLUSIONS: Our findings indicate that measurement of changes in tumor volumes is adequately reproducible. Using tumor volumes as the basis for response assessments could have a positive impact on both patient management and clinical trials. More authoritative work to qualify or discard changes in volume as the basis for response assessments should proceed.

The aim of this study was to evaluate the efficacy of genetic vaccination with rat ErbB2 antigen in a therapeutic setting for the BALB-neuT mouse model of mammary carcinoma and to establish immunological correlates with vaccine efficacy. To define an early therapeutic setting we performed imaging studies of mouse mammary glands with a high-frequency ultrasound system that allowed the diagnosis of tumor lesions before they become palpable, starting from week 13 after mouse births. An intensive immunization protocol of vaccination was implemented at this stage, consisting of four weekly DNA injections with electroporation followed by two injections of adenovirus carrying the codon usage-optimized cDNA encoding the extracellular-transmembrane domain of rat ErbB2. Immunological parameters were monitored in each individual mouse by analyzing peripheral blood leukocytes. The appearance of the first palpable tumor in vaccinated mice was delayed and there was a statistically significant time gap before additional masses developed, indicating disease stabilization. As a result of the immunization, antibodies and CD8(+) T cells to rat ErbB2 were detected and the amplitude of elicited responses correlated with the efficacy of vaccination. Moreover, the vaccination regimen specifically halted the rise in circulating myeloid suppressor cells (MSCs). All three parameters, that is, CD8(+) T cells, antibodies to rat ErbB2, and circulating MSCs, measured at the end of vaccination could be used as predictive biomarkers for future tumor development. This study emphasizes the potential of genetic vaccines for the therapeutic treatment of malignancies and suggests possible predictive biomarkers to be further validated in the clinic for the follow-up of vaccinated cancer patients.

Specific Aim To review the evidence indicating that volumetric image analysis of computed tomography scans meets specifications for qualification as a biomarker in clinical trials or the management of individual patients with lung cancer. Methods Claims of value were broken down into questions about technical feasibility, accuracy, the precision of measurement, sensitivity, the correlations with health outcomes, and the risks of producing misleading information. For each claim, the pertinent literature was reviewed. Results Technical feasibility has now been shown, but only in limited contexts. Accuracy has been demonstrated, but only for tumors with favorable anatomical features. Measurement error still makes the assessment of change in small nodules precarious in diagnostic settings unless rigorous image acquisition and analysis procedures are followed. Precision is sufficient in some larger masses to make volumetrics a sensitive biomarker. In a few trials, correlations with clinical outcomes have been higher for volumetric-based measures than for unidimensional or bidimensional diameters. Value in clinical practice settings and clinical trials has been suggested, but not proven. Conclusion The weight of the evidence indicates there are circumstances in which volumetric image analysis adds value to clinical trial science and the practice of medicine.