Application of Artificial Intelligence/Machine Vision & Learning for the Development of a Live Single-cell Phenotypic Biomarker Test to Predict Prostate Cancer Tumor Aggressiveness

To assess the usefulness and applications of machine vision (MV) and machine learning (ML) techniques that have been used to develop a single cell-based phenotypic (live and fixed biomarkers) platform that correlates with tumor biological aggressiveness and risk stratification, 100 fresh prostate samples were acquired, and areas of prostate cancer were determined by post-surgery pathology reports logged by an independent pathologist. The prostate samples were dissociated into single-cell suspensions in the presence of an extracellular matrix formulation. These samples were analyzed via live-cell microscopy. Dynamic and fixed phenotypic biomarkers per cell were quantified using objective MV software and ML algorithms. The predictive nature of the ML algorithms was developed in two stages. First, random forest (RF) algorithms were developed using 70% of the samples. The developed algorithms were then tested for their predictive performance using the blinded test dataset that contained 30% of the samples in the second stage. Based on the ROC (receiver operating characteristic) curve analysis, thresholds were set to maximize both sensitivity and specificity. We determined the sensitivity and specificity of the assay by comparing the algorithm-generated predictions with adverse pathologic features in the radical prostatectomy (RP) specimens. Using MV and ML algorithms, the biomarkers predictive of adverse pathology at RP were ranked and a prostate cancer patient risk stratification test was developed that distinguishes patients based on surgical adverse pathology features. The ability to identify and track large numbers of individual cells over the length of the microscopy experimental monitoring cycles, in an automated way, created a large biomarker dataset of primary biomarkers. This biomarker dataset was then interrogated with ML algorithms used to correlate with post-surgical adverse pathology findings. Algorithms were generated that predicted adverse pathology with >0.85 sensitivity and specificity and an AUC (area under the curve) of >0.85. Phenotypic biomarkers provide cellular and molecular details that are informative for predicting post-surgical adverse pathologies when considering tumor biopsy samples. Artificial intelligence ML-based approaches for cancer risk stratification are emerging as important and powerful tools to compliment current measures of risk stratification. These techniques have capabilities to address tumor heterogeneity and the molecular complexity of prostate cancer. Specifically, the phenotypic test is a novel example of leveraging biomarkers and advances in MV and ML for developing a powerful prognostic and risk-stratification tool for prostate cancer patients.     

ALS/FTD‐associated FUS activates GSK‐3β to disrupt the VAPB–PTPIP51 interaction and ER–mitochondria associations

Defective FUS metabolism is strongly associated with amyotrophic lateral sclerosis and frontotemporal dementia (ALS/FTD), but the mechanisms linking FUS to disease are not properly understood. However, many of the functions disrupted in ALS/FTD are regulated by signalling between the endoplasmic reticulum (ER) and mitochondria. This signalling is facilitated by close physical associations between the two organelles that are mediated by binding of the integral ER protein VAPB to the outer mitochondrial membrane protein PTPIP51, which act as molecular scaffolds to tether the two organelles. Here, we show that FUS disrupts the VAPB–PTPIP51 interaction and ER–mitochondria associations. These disruptions are accompanied by perturbation of Ca²⁺ uptake by mitochondria following its release from ER stores, which is a physiological read‐out of ER–mitochondria contacts. We also demonstrate that mitochondrial ATP production is impaired in FUS‐expressing cells; mitochondrial ATP production is linked to Ca²⁺ levels. Finally, we demonstrate that the FUS‐induced reductions to ER–mitochondria associations and are linked to activation of glycogen synthase kinase‐3β (GSK‐3β), a kinase already strongly associated with ALS/FTD.     

Prediction and course of symptoms and lung function around an exacerbation in chronic obstructive pulmonary disease

Background

Frequent exacerbations induce a high burden to Chronic Obstructive Pulmonary Disease (COPD). We investigated the course of exacerbations in the published COSMIC study that investigated the effects of 1-year withdrawal of fluticasone after a 3-month run-in treatment period with salmeterol/fluticasone in patients with COPD.

Methods

In 373 patients, we evaluated diary cards for symptoms, Peak Expiratory Flow (PEF), and salbutamol use and assessed their course during exacerbations.

Results

There were 492 exacerbations in 224 patients. The level of symptoms of cough, sputum, dyspnea and nocturnal awakening steadily increased from 2 weeks prior to exacerbation, with a sharp rise during the last week. Symptoms of cough, sputum, and dyspnea reverted to baseline values at different rates (after 4, 4, and 7 weeks respectively), whereas symptoms of nocturnal awakening were still increased after eight weeks. The course of symptoms was similar around a first and second exacerbation. Increases in symptoms and salbutamol use and decreases in PEF were associated with a higher risk to develop an exacerbation, but with moderate predictive values, the areas under the receiver operating curves ranging from 0.63 to 0.70.

Conclusions

Exacerbations of COPD are associated with increased symptoms that persist for weeks and the course is very similar between a first and second exacerbation. COPD exacerbations are preceded by increased symptoms and salbutamol use and lower PEF, yet predictive values are too low to warrant daily use in clinical practice.     

Acceptor specificity of the human leukocyte alpha3 fucosyltransferase: role of FucT-VII in the generation of selectin ligands

The alpha3 fucosyltransferase, FucT-VII, is one of the key glycosyltransferases involved in the biosynthesis of the sialyl Lewis X (sLex) antigen on human leukocytes. The sialyl Lewis X antigen (NeuAcalpha(2-3)Galbeta(1-4)[Fucalpha(1-3)]GlcNAc-R) is an essential component of the recruitment of leukocytes to sites of inflammation, mediating the primary interaction between circulating leukocytes and activated endothelium. In order to characterize the enzymatic properties of the leukocyte alpha3 fucosyltransferase FucT-VII, the enzyme has been expressed in Trichoplusia ni insect cells. The enzyme is capable of synthesizing both sLexand sialyl-dimeric-Lexstructures in vitro , from 3'-sialyl-lacNAc and VIM-2 structures, respectively, with only low levels of fucose transfer observed to neutral or 3'-sulfated acceptors. Studies using fucosylated NeuAcalpha(2-3)-(Galbeta(1- 4)GlcNAc)3-Me acceptors demonstrate that FucT-VII is able to synthesize both di-fucosylated and tri-fucosylated structures from mono- fucosylated precursors, but preferentially fucosylates the distal GlcNAc within a polylactosamine chain. Furthermore, the rate of fucosylation of the internal GlcNAc residues is reduced once fucose has been added to the distal GlcNAc. These results indicate that FucT-VII is capable of generating complex selectin ligands, in vitro , however the order of fucose addition to the lactosamine chain affects the rate of selectin ligand synthesis.      

Quirks of dye nomenclature. 9. Fluorescein

Adolf Baeyer announced the discovery of fluorescein in 1871 and named it after its most striking property, i.e., fluorescence. I describe here the synthesis of fluorescein. There are seven molecular species in both the solid state or in solution. I also summarize some of the diverse applications of the dye, both medical and nonmedical, which depend mostly on the facile detection of fluorescein at low concentration. Both animal and human toxicity are examined.     

Turmeric: old spice,new spice

The history of chemical investigations into the yellow components of turmeric can be traced from 1815. Although the major yellow component of turmeric, curcumin, often is represented as a 1,3-diketone in the solid state and in nonaqueous solution, it exists in the enol form. The struggle to identify the chemical structure of curcumin continued for nearly a century and was complicated by the difficult purification of curcumin and by the presence of two additional yellow components. Food remains the main use for turmeric (old spice); its use as a dye has diminished since the 19th century, but it may have pharmaceutical uses (new spice).     

SIMPLE: implementation of recommendations from international evidence-based guidelines on caesarean sections in the Netherlands. Protocol for a controlled before and after study

Background

Caesarean section (CS) rates are rising worldwide. In the Netherlands, the most significant rise is observed in healthy women with a singleton in vertex position between 37 and 42 weeks gestation, whereas it is doubtful whether an improved outcome for the mother or her child was obtained. It can be hypothesized that evidence-based guidelines on CS are not implemented sufficiently. Therefore, the present study has the following objectives: to develop quality indicators on the decision to perform a CS based on key recommendations from national and international guidelines; to use the quality indicators in order to gain insight into actual adherence of Dutch gynaecologists to guideline recommendations on the performance of a CS; to explore barriers and facilitators that have a direct effect on guideline application regarding CS; and to develop, execute, and evaluate a strategy in order to reduce the CS incidence for a similar neonatal outcome (based on the information gathered in the second and third objectives).

Methods

An independent expert panel of Dutch gynaecologists and midwives will develop a set of quality indicators on the decision to perform a CS. These indicators will be used to measure current care in 20 hospitals with a population of 1,000 women who delivered by CS, and a random selection of 1,000 women who delivered vaginally in the same period. Furthermore, by interviewing healthcare professionals and patients, the barriers and facilitators that may influence the decision to perform a CS will be measured. Based on the results, a tailor-made implementation strategy will be developed and tested in a controlled before-and-after study in 12 hospitals (six intervention, six control hospitals) with regard to effectiveness, experiences, and costs.

Discussion

This study will offer insight into the current CS care and into the hindering and facilitating factors influencing obstetrical policy on CS. Furthermore, it will allow definition of patient categories or situations in which a tailor-made implementation strategy will most likely be meaningful and cost effective, without negatively affecting the outcome for mother and child.

Trial registration

http://www.clinicaltrials.gov: NCT01261676     

Using ontologies to describe mouse phenotypes

The mouse is an important model of human genetic disease. Describing phenotypes of mutant mice in a standard, structured manner that will facilitate data mining is a major challenge for bioinformatics. Here we describe a novel, compositional approach to this problem which combines core ontologies from a variety of sources. This produces a framework with greater flexibility, power and economy than previous approaches. We discuss some of the issues this approach raises.