Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance.

Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78-0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64-0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76-0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation. KEY POINTS: •LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density. •Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework. •The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.

An Account of Models of Molecular Circuits for Associative Learning with Reinforcement Effect and Forced Dissociation.

The development of synthetic biology has enabled massive progress in biotechnology and in approaching research questions from a brand-new perspective. In particular, the design and study of gene regulatory networks in vitro, in vivo, and in silico have played an increasingly indispensable role in understanding and controlling biological phenomena. Among them, it is of great interest to understand how associative learning is formed at the molecular circuit level. Mathematical models are increasingly used to predict the behaviours of molecular circuits. Fernando's model, which is one of the first works in this line of research using the Hill equation, attempted to design a synthetic circuit that mimics Hebbian learning in a neural network architecture. In this article, we carry out indepth computational analysis of the model and demonstrate that the reinforcement effect can be achieved by choosing the proper parameter values. We also construct a novel circuit that can demonstrate forced dissociation, which was not observed in Fernando's model. Our work can be readily used as reference for synthetic biologists who consider implementing circuits of this kind in biological systems.

Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients.

BACKGROUND: An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK. METHODS: Three hundred and seventy-nine patients with available measurements of three urine biomarkers, (LYVE1, REG1B and TFF1) using retrospectively collected samples, as well as creatinine and age, were randomly split into training and validation sets, following stratification into cases (PDAC) and controls (healthy patients). Several machine learning algorithms were used, and their performance characteristics were compared. The latter included AUC (area under ROC curve) and sensitivity at clinically relevant specificity. RESULTS: None of the algorithms significantly outperformed all others. A logistic regression model, the easiest to interpret, was incorporated into a PancRISK score and subsequently evaluated on the whole data set. The PancRISK performance could be even further improved when CA19-9, commonly used PDAC biomarker, is added to the model. CONCLUSION: PancRISK score enables easy interpretation of the biomarker panel data and is currently being tested to confirm that it can be used for stratification of patients at risk of developing pancreatic cancer completely non-invasively, using urine samples.

Improved early detection of ovarian cancer using longitudinal multimarker models.

BACKGROUND: Ovarian cancer has a poor survival rate due to late diagnosis and improved methods are needed for its early detection. Our primary objective was to identify and incorporate additional biomarkers into longitudinal models to improve on the performance of CA125 as a first-line screening test for ovarian cancer. METHODS: This case-control study nested within UKCTOCS used 490 serial serum samples from 49 women later diagnosed with ovarian cancer and 31 control women who were cancer-free. Proteomics-based biomarker discovery was carried out using pooled samples and selected candidates, including those from the literature, assayed in all serial samples. Multimarker longitudinal models were derived and tested against CA125 for early detection of ovarian cancer. RESULTS: The best performing models, incorporating CA125, HE4, CHI3L1, PEBP4 and/or AGR2, provided 85.7% sensitivity at 95.4% specificity up to 1 year before diagnosis, significantly improving on CA125 alone. For Type II cases (mostly high-grade serous), models achieved 95.5% sensitivity at 95.4% specificity. Predictive values were elevated earlier than CA125, showing the potential of models to improve lead time. CONCLUSIONS: We have identified candidate biomarkers and tested longitudinal multimarker models that significantly improve on CA125 for early detection of ovarian cancer. These models now warrant independent validation.

Integrated Information in the Spiking-Bursting Stochastic Model.

Integrated information has been recently suggested as a possible measure to identify a necessary condition for a system to display conscious features. Recently, we have shown that astrocytes contribute to the generation of integrated information through the complex behavior of neuron-astrocyte networks. Still, it remained unclear which underlying mechanisms governing the complex behavior of a neuron-astrocyte network are essential to generating positive integrated information. This study presents an analytic consideration of this question based on exact and asymptotic expressions for integrated information in terms of exactly known probability distributions for a reduced mathematical model (discrete-time, discrete-state stochastic model) reflecting the main features of the "spiking-bursting" dynamics of a neuron-astrocyte network. The analysis was performed in terms of the empirical "whole minus sum" version of integrated information in comparison to the "decoder based" version. The "whole minus sum" information may change sign, and an interpretation of this transition in terms of "net synergy" is available in the literature. This motivated our particular interest in the sign of the "whole minus sum" information in our analytical considerations. The behaviors of the "whole minus sum" and "decoder based" information measures are found to bear a lot of similarity-they have mutual asymptotic convergence as time-uncorrelated activity increases, and the sign transition of the "whole minus sum" information is associated with a rapid growth in the "decoder based" information. The study aims at creating a theoretical framework for using the spiking-bursting model as an analytically tractable reference point for applying integrated information concepts to systems exhibiting similar bursting behavior. The model can also be of interest as a new discrete-state test bench for different formulations of integrated information.

Current detection rates and time-to-detection of all identifiable BRCA carriers in the Greater London population.

BACKGROUND: BRCA carrier identification offers opportunities for early diagnoses, targeted treatment and cancer prevention. We evaluate BRCA- carrier detection rates in general and Ashkenazi Jewish (AJ) populations across Greater London and estimate time-to-detection of all identifiable BRCA carriers. METHODS: BRCA carrier data from 1993 to 2014 were obtained from National Health Service genetic laboratories and compared with modelled predictions of BRCA prevalence from published literature and geographical data from UK Office for National Statistics. Proportion of BRCA carriers identified was estimated. Prediction models were developed to fit BRCA detection rate data. BRCA carrier identification rates were evaluated for an 'Angelina Jolie effect'. Maps for four Greater London regions were constructed, and their relative BRCA detection rates were compared. Models developed were used to predict future time-to-identify all detectable BRCA carriers in AJ and general populations. RESULTS: Until 2014, only 2.6% (3072/111 742 estimated) general population and 10.9% (548/4985 estimated) AJ population BRCA carriers have been identified in 16 696 608 (AJ=190 997) Greater London population. 57% general population and 54% AJ mutations were identified through cascade testing. Current detection rates mirror linear fit rather than parabolic model and will not identify all BRCA carriers. Addition of unselected ovarian/triple-negative breast cancer testing would take >250 years to identify all BRCA carriers. Doubling current detection rates can identify all 'detectable' BRCA carriers in the general population by year 2181, while parabolic and triple linear rates can identify 'detectable' BRCA carriers by 2084 and 2093, respectively. The linear fit model can identify 'detectable' AJ carriers by 2044. We did not find an Angelina Jolie effect on BRCA carrier detection rates. There was a significant difference in BRCA detection rates between geographical regions over time (P<0.001). CONCLUSIONS: The majority of BRCA carriers have not been identified, missing key opportunities for prevention/earlier diagnosis. Enhanced and new strategies/approaches are needed.

Integrated Information as a Measure of Cognitive Processes in Coupled Genetic Repressilators.

Intercellular communication and its coordination allow cells to exhibit multistability as a form of adaptation. This conveys information processing from intracellular signaling networks enabling self-organization between other cells, typically involving mechanisms associated with cognitive systems. How information is integrated in a functional manner and its relationship with the different cell fates is still unclear. In parallel, drawn originally from studies on neuroscience, integrated information proposes an approach to quantify the balance between integration and differentiation in the causal dynamics among the elements in any interacting system. In this work, such an approach is considered to study the dynamical complexity in a genetic network of repressilators coupled by quorum sensing. Several attractors under different conditions are identified and related to proposed measures of integrated information to have an insight into the collective interaction and functional differentiation in cells. This research particularly accounts for the open question about the coding and information transmission in genetic systems.

Leptin induces upregulation of sphingosine kinase 1 in oestrogen receptor-negative breast cancer via Src family kinase-mediated, janus kinase 2-independent pathway.

INTRODUCTION: Obesity is a known risk factor for breast cancer. Sphingosine kinase 1 (SK1) is an oncogenic lipid kinase that is overexpressed in breast tumours and linked with poor prognosis, however, its role in obesity-driven breast cancer was never elucidated. METHODS: Human primary and secondary breast cancer tissues were analysed for SK1 and leptin receptor expression using quantitative real-time polymerase chain reaction (qRT-PCR) assay. Leptin-induced signalling was analysed in human oestrogen receptor (ER)-positive and negative breast cancer cells using Western blotting, qRT-PCR and radiolabelling assays. RESULTS: Our findings show for the first time that human primary breast tumours and associated lymph node metastases exhibit a strong correlation between SK1 and leptin receptor expression (Pearson R = 0.78 and R = 0.77, respectively, P <0.001). Both these genes are elevated in metastases of ER-negative patients and show a significant increase in patients with higher body mass index (BMI). Leptin induces SK1 expression and activation in ER-negative breast cancer cell lines MDAMB-231 and BT-549, but not in ER-positive cell lines. Pharmacological inhibition and gene knockdown showed that leptin-induced SK1 activity and expression are mediated by activation of extracellular signal-regulated kinases 1/2 (ERK1/2) and Src family kinase (SFK) pathways, but not by the major pathways downstream of leptin receptor (LEPR) - janus kinase 2 (JAK2) and signal transducer and activator of transcription 3 (STAT3). Src-homology 2 domain-containing phosphatase 2 (SHP2) appeared to be key to SK1 activation, and may function as an adaptor protein between SFKs and LEPR. Importantly, leptin-induced breast cancer cell proliferation was abrogated by SK1-specific small interfering RNA (siRNA). CONCLUSIONS: Overall, our findings demonstrate a novel SFK/ERK1/2-mediated pathway that links leptin signalling and expression of oncogenic enzyme SK1 in breast tumours and suggest the potential significance of this pathway in ER-negative breast cancer.

Cancer-associated autoantibodies to MUC1 and MUC4--a blinded case­control study of colorectal cancer in UK collaborative trial of ovarian cancer screening.

Recent reports suggest that autoantibodies directed to aberrantly glycosylated mucins, in particular MUC1 and MUC4, are found in patients with colorectal cancer. There is, however, limited information on the autoantibody levels before clinical diagnosis, and their utility in cancer screening in the general population. In our study, we have generated O-glycosylated synthetic MUC1 and MUC4 peptides in vitro, to mimic cancer-associated glycoforms, and displayed these on microarrays. The assay's performance was tested through an initial screening of serum samples taken from patients at the time of colorectal cancer diagnosis and healthy controls. Subsequently, the selected biomarkers were evaluated in a blinded nested case­control study using stored serum samples from among the 50,640 women randomized to the multimodal arm of the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS), where women gave annual blood samples for several years. Cases were 97 postmenopausal women who developed colorectal cancer after recruitment and were age-matched to 97 women without any history of cancer. MUC1-STn and MUC1-Core3 IgG autoantibodies identified cases with 8.2 and 13.4% sensitivity, respectively, at 95% specificity. IgA to MUC4 glycoforms were unable to discriminate between cases and controls in the UKCTOCS sera. Additional analysis was undertaken by combining the data of MUC1-STn and MUC1-Core3 with previously generated data on autoantibodies to p53 peptides, which increased the sensitivity to 32.0% at 95% specificity. These findings suggest that a combination of antibody signatures may have a role as part of a biomarker panel for the early detection of colorectal cancer.

The sex hormone system in carriers of BRCA1/2 mutations: a case-control study.

BACKGROUND: Penetrance for breast cancer, ovarian cancer, or both in carriers of BRCA1/BRCA2 mutations is disproportionately high. Sex hormone dysregulation and altered end-organ hormone sensitivity might explain this organ-specific penetrance. We sought to identify differences in hormone regulation between carriers of BRCA1/2 and women who are negative for BRCA1/2 mutations. METHODS: We assessed endometrial thickness for each menstrual cycle day (as an index of hormone regulation) in 393 scans from 228 women in the UK Familial Ovarian Cancer Screening Study (UK FOCSS) known to carry either mutation and 1573 scans from 754 women known to be negative for the mutations. To quantify differences in endometrial thickness we focused on days 10-14 and days 21-26, and calculated the area under the curve. We then compared serum oestradiol and progesterone titres during these days of the menstrual cycle in the same groups. Follicular and luteal oestradiol and progesterone serum titres were grouped into quartiles and odds ratios were calculated with logistic regression. FINDINGS: Follicular phase endometrial thickness of carriers of the mutations adjusted for age and day of the menstrual cycle was higher (odds ratio [OR] 1·11, 95% CI 1·03-1·20; p=0·0063) and luteal phase endometrial thickness lower (0·90, 0·83-0·98; p=0·027) than for women negative for the mutations. Median luteal phase titres of progesterone were 121% higher (p=0·00037) in carriers than in women negative for the mutations, and for oestradiol were 33% higher (p=0·007)-ie, 59% of carriers had concentrations of serum progesterone that would have been in the top quartile of concentrations in the control group (OR 8·0, 95% CI 2·1-52·57; p=0·008). INTERPRETATION: Carriers of BRCA1/BRCA2 mutations are exposed to higher titres of oestradiol and progesterone-known risk-factors for breast cancer. Higher titres of oestradiol in carriers are compatible with this hormone having a role in ovarian carcinogenesis in such women. Our findings could not be explained by differential contraceptive pill use.

Bayesian and deep-learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers.

BACKGROUND: Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best-performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models. METHODS: Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change-point detection and recurrent neural networks. RESULTS: We obtained a significantly higher performance for CA125-HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change-point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125-HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125. CONCLUSIONS: Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer.

Emergent digital bio-computation through spatial diffusion and engineered bacteria.

Biological computing is a promising field with potential applications in biosafety, environmental monitoring, and personalized medicine. Here we present work on the design of bacterial computers using spatial patterning to process information in the form of diffusible morphogen-like signals. We demonstrate, mathematically and experimentally, that single, modular, colonies can perform simple digital logic, and that complex functions can be built by combining multiple colonies, removing the need for further genetic engineering. We extend our experimental system to incorporate sender colonies as morphogen sources, demonstrating how one might integrate different biochemical inputs. Our approach will open up ways to perform biological computation, with applications in bioengineering, biomaterials and biosensing. Ultimately, these computational bacterial communities will help us explore information processing in natural biological systems.

Prediction of spontaneous preterm birth in women with previous full dilatation cesarean delivery.

BACKGROUND: A previous term (≥37 weeks' gestation), full-dilatation cesarean delivery is associated with an increased risk for a subsequent spontaneous preterm birth. The mechanism is unknown. We hypothesized that the cesarean delivery scar characteristics and scar position relative to the internal cervical os may compromise cervical function, thereby leading to shortening of the cervical length and spontaneous preterm birth. OBJECTIVE: This study aimed to determine the relationship of cesarean delivery scar characteristics and position, assessed by transvaginal ultrasound, in pregnant women with previous full-dilatation cesarean delivery with the risk of shortening cervical length and spontaneous preterm birth. STUDY DESIGN: This was a single-center, prospective cohort study of singleton pregnant women (14 to 24 weeks' gestation) with a previous term full-dilatation cesarean delivery who attended a high-risk preterm birth surveillance clinic (2017-2021). Women underwent transvaginal ultrasound assessment of cervical length, cesarean delivery scar distance relative to the internal cervical os, and scar niche parameters using a reproducible transvaginal ultrasound technique. Spontaneous preterm birth prophylactic interventions (vaginal cervical cerclage or vaginal progesterone) were offered for short cervical length (≤25 mm) and to women with a history of spontaneous preterm birth or late miscarriage after full-dilatation cesarean delivery. The primary outcome was spontaneous preterm birth; secondary outcomes included short cervical length and a need for prophylactic interventions. A multivariable logistic regression analysis was used to develop multiparameter models that combined cesarean delivery scar parameters, cervical length, history of full-dilatation cesarean delivery, and maternal characteristics. The predictive performance of models was examined using the area under the receiver operating characteristics curve and the detection rate at various fixed false positive rates. The optimal cutoff for cesarean delivery scar distance to best predict a short cervical length and spontaneous preterm birth was analyzed. RESULTS: Cesarean delivery scars were visualized in 90.5% (220/243) of the included women. The spontaneous preterm birth rate was 4.1% (10/243), and 12.8% (31/243) of women developed a short cervical length. A history- (n=4) or ultrasound-indicated (n=19) cervical cerclage was performed in 23 of 243 (9.5%) women; among those, 2 (8.7%) spontaneously delivered prematurely. A multiparameter model based on absolute scar distance from the internal os best predicted spontaneous preterm birth (area under the receiver operating characteristics curve, 0.73; 95% confidence interval, 0.57-0.89; detection rate of 60% for a fixed 25% false positive rate). Models based on the relative anatomic position of the cesarean delivery scar to the internal os and the cesarean delivery scar position with niche parameters (length, depth, and width) best predicted the development of a short cervical length (area under the receiver operating characteristics curve, 0.79 [95% confidence interval, 0.71-0.87]; and 0.81 [95% confidence interval, 0.73-0.89], respectively; detection rate of 73% at a fixed 25% false positive rate). Spontaneous preterm birth was significantly more likely when the cesarean delivery scar was <5.0 mm above or below the internal os (adjusted odds ratio, 6.87; 95% confidence interval, 1.34-58; P =.035). CONCLUSION: In pregnancies following a full-dilatation cesarean delivery, cesarean delivery scar characteristics and distance from the internal os identified women who were at risk for spontaneous preterm birth and developing short cervical length. Overall, the spontaneous preterm birth rate was low, but it was significantly increased among women with a scar located <5.0 mm above or below the internal cervical os. Shortening of cervical length was strongly associated with a low scar position. Our novel findings indicate that a low cesarean delivery scar can compromise the functional integrity of the internal cervical os, leading to cervical shortening and/or spontaneous preterm birth. Assessment of the cesarean delivery scar characteristics and position seem to have use in preterm birth clinical surveillance among women with a previous, full-dilatation cesarean delivery and could better identify women who would benefit from prophylactic interventions.

Technology of the photobiostimulation of the brain's drainage system during sleep for improvement of learning and memory in male mice.

In this study on healthy male mice using confocal imaging of dye spreading in the brain and its further accumulation in the peripheral lymphatics, we demonstrate stronger effects of photobiomodulation (PBM) on the brain's drainage system in sleeping vs. awake animals. Using the Pavlovian instrumental transfer probe and the 2-objects-location test, we found that the 10-day course of PBM during sleep vs. wakefulness promotes improved learning and spatial memory in mice. For the first time, we present the technology for PBM under electroencephalographic (EEG) control that incorporates modern state of the art facilities of optoelectronics and biopotential detection and that can be built of relatively cheap and commercially available components. These findings open a new niche in the development of smart technologies for phototherapy of brain diseases during sleep.

An efficient reduced-lattice model of IP3R for probing Ca2+ dynamics.

Numerous cellular processes are regulated by Ca2+ signals, and the endoplasmic reticulum (ER) membrane's inositol triphosphate receptor (IP3R) is critical for modulating intracellular Ca2+ dynamics. The IP3Rs are seen to be clustered in a variety of cell types. The combination of IP3Rs clustering and IP3Rs-mediated Ca2+-induced Ca2+ release results in the hierarchical organization of the Ca2+ signals, which challenges the numerical simulation given the multiple spatial and temporal scales that must be covered. The previous methods rather ignore the spatial feature of IP3Rs or fail to coordinate the conflicts between the real biological relevance and the computational cost. In this work, a general and efficient reduced-lattice model is presented for the simulation of IP3Rs-mediated multiscale Ca2+ dynamics. The model highlights biological details that make up the majority of the calcium events, including IP3Rs clustering and calcium domains, and it reduces the complexity by approximating the minor details. The model's extensibility provides fresh insights into the function of IP3Rs in producing global Ca2+ events and supports the research under more physiological circumstances. Our work contributes to a novel toolkit for modeling multiscale Ca2+ dynamics and advances knowledge of Ca2+ signals.

Using a Recurrent Neural Network To Inform the Use of Prostate-specific Antigen (PSA) and PSA Density for Dynamic Monitoring of the Risk of Prostate Cancer Progression on Active Surveillance.

The global uptake of prostate cancer (PCa) active surveillance (AS) is steadily increasing. While prostate-specific antigen density (PSAD) is an important baseline predictor of PCa progression on AS, there is a scarcity of recommendations on its use in follow-up. In particular, the best way of measuring PSAD is unclear. One approach would be to use the baseline gland volume (BGV) as a denominator in all calculations throughout AS (nonadaptive PSAD, PSADNA), while another would be to remeasure gland volume at each new magnetic resonance imaging scan (adaptive PSAD, PSADA). In addition, little is known about the predictive value of serial PSAD in comparison to PSA. We applied a long short-term memory recurrent neural network to an AS cohort of 332 patients and found that serial PSADNA significantly outperformed both PSADA and PSA for follow-up prediction of PCa progression because of its high sensitivity. Importantly, while PSADNA was superior in patients with smaller glands (BGV ≤55 ml), serial PSA was better in men with larger prostates of >55 ml. Patient summary: Repeat measurements of prostate-specific antigen (PSA) and PSA density (PSAD) are the mainstay of active surveillance in prostate cancer. Our study suggests that in patients with a prostate gland of 55 ml or smaller, PSAD measurements are a better predictor of tumour progression, whereas men with a larger gland may benefit more from PSA monitoring.

Situation-Based Neuromorphic Memory in Spiking Neuron-Astrocyte Network.

Mammalian brains operate in very special surroundings: to survive they have to react quickly and effectively to the pool of stimuli patterns previously recognized as danger. Many learning tasks often encountered by living organisms involve a specific set-up centered around a relatively small set of patterns presented in a particular environment. For example, at a party, people recognize friends immediately, without deep analysis, just by seeing a fragment of their clothes. This set-up with reduced "ontology" is referred to as a "situation." Situations are usually local in space and time. In this work, we propose that neuron-astrocyte networks provide a network topology that is effectively adapted to accommodate situation-based memory. In order to illustrate this, we numerically simulate and analyze a well-established model of a neuron-astrocyte network, which is subjected to stimuli conforming to the situation-driven environment. Three pools of stimuli patterns are considered: external patterns, patterns from the situation associative pool regularly presented to the network and learned by the network, and patterns already learned and remembered by astrocytes. Patterns from the external world are added to and removed from the associative pool. Then, we show that astrocytes are structurally necessary for an effective function in such a learning and testing set-up. To demonstrate this we present a novel neuromorphic computational model for short-term memory implemented by a two-net spiking neural-astrocytic network. Our results show that such a system tested on synthesized data with selective astrocyte-induced modulation of neuronal activity provides an enhancement of retrieval quality in comparison to standard spiking neural networks trained via Hebbian plasticity only. We argue that the proposed set-up may offer a new way to analyze, model, and understand neuromorphic artificial intelligence systems.

Integrated Placental Modelling of Histology with Gene Expression to Identify Functional Impact on Fetal Growth.

Fetal growth restriction (FGR) is a leading cause of perinatal morbidity and mortality. Altered placental formation and functional capacity are major contributors to FGR pathogenesis. Relating placental structure to function across the placenta in healthy and FGR pregnancies remains largely unexplored but could improve understanding of placental diseases. We investigated integration of these parameters spatially in the term human placenta using predictive modelling. Systematic sampling was able to overcome heterogeneity in placental morphological and molecular features. Defects in villous development, elevated fibrosis, and reduced expression of growth and functional marker genes (IGF2, VEGA, SLC38A1, and SLC2A3) were seen in age-matched term FGR versus healthy control placentas. Characteristic histopathological changes with specific accompanying molecular signatures could be integrated through computational modelling to predict if the placenta came from a healthy or FGR pregnancy. Our findings yield new insights into the spatial relationship between placental structure and function and the etiology of FGR.

Serum biomarker-based early detection of pancreatic ductal adenocarcinomas with ensemble learning.

BACKGROUND: Earlier detection of pancreatic ductal adenocarcinoma (PDAC) is key to improving patient outcomes, as it is mostly detected at advanced stages which are associated with poor survival. Developing non-invasive blood tests for early detection would be an important breakthrough. METHODS: The primary objective of the work presented here is to use a dataset that is prospectively collected, to quantify a set of cancer-associated proteins and construct multi-marker models with the capacity to predict PDAC years before diagnosis. The data used is part of a nested case-control study within the UK Collaborative Trial of Ovarian Cancer Screening and is comprised of 218 samples, collected from a total of 143 post-menopausal women who were diagnosed with pancreatic cancer within 70 months after sample collection, and 249 matched non-cancer controls. We develop a stacked ensemble modelling technique to achieve robustness in predictions and, therefore, improve performance in newly collected datasets. RESULTS: Here we show that with ensemble learning we can predict PDAC status with an AUC of 0.91 (95% CI 0.75-1.0), sensitivity of 92% (95% CI 0.54-1.0) at 90% specificity, up to 1 year prior to diagnosis, and at an AUC of 0.85 (95% CI 0.74-0.93) up to 2 years prior to diagnosis (sensitivity of 61%, 95% CI 0.17-0.83, at 90% specificity). CONCLUSIONS: The ensemble modelling strategy explored here outperforms considerably biomarker combinations cited in the literature. Further developments in the selection of classifiers balancing performance and heterogeneity should further enhance the predictive capacity of the method.

Pancreatic cancers are most frequently detected at an advanced stage. This limits treatment options and contributes to the dismal survival rates currently recorded. The development of new tests that could improve detection of early-stage disease is fundamental to improve outcomes. Here, we use advanced data analysis techniques to devise an early detection test for pancreatic cancer. We use data on markers in the blood from people enrolled on a screening trial. Our test correctly identifies as positive for pancreatic cancer 91% of the time up to 1 year prior to diagnosis, and 78% of the time up to 2 years prior to diagnosis. These results surpass previously reported tests and should encourage further evaluation of the test in different populations, to see whether it should be adopted in the clinic.