Search

Abstract Background the problem in early diagnosis of sporadic cancer is understanding the individual’s risk to develop disease. In response to this need, global scientific research is focusing on developing predictive models based on non-invasive screening tests. A tentative solution to the problem may be a cancer screening blood-based test able to discover those cell requirements triggering subclinical and clinical onset latency, at the stage when the cell disorder, i.e. atypical epithelial hyperplasia, is still in a subclinical stage of proliferative dysregulation. Methods a well-established procedure to identify proliferating circulating tumor cells was deployed to measure the cell proliferation of circulating non-haematological cells which may suggest tumor pathology. Moreover, the data collected were processed by a supervised machine learning model to make the prediction. Results the developed test combining circulating non-haematological cell proliferation data and artificial intelligence shows 98.8% of accuracy, 100% sensitivity, and 95% specificity. Conclusion this proof of concept study demonstrates that integration of innovative non invasive methods and predictive-models can be decisive in assessing the health status of an individual, and achieve cutting-edge results in cancer prevention and management.

Edible flowers, with their increasing demand in the market, face a challenge in labor-intensive hand-picking practices, hindering their attractiveness for growers. This study explores the application of artificial intelligence vision for robotic harvesting, focusing on the fundamental elements: detection, pose estimation, and plucking point estimation. The objective was to assess the adaptability of this technology across various species and varieties of edible flowers. The developed computer vision framework utilizes YOLOv5 for 2D flower detection and leverages the zero-shot capabilities of the Segmentation Anything Model for extracting points of interest from a 3D point cloud, facilitating 3D space flower localization. Additionally, we provide a pose estimation method, a key factor in plucking point identification. The plucking point is determined through a linear regression correlating flower diameter with the height of the plucking point. The results showed effective 2D detection. Further, the zero-shot and standard machine learning techniques employed achieved promising 3D localization, pose estimation, and plucking point estimation.

Functional near-infrared spectroscopy (fNIRS) is beneficial for studying brain activity in naturalistic settings due to its tolerance for movement. However, residual motion artifacts still compromise fNIRS data quality and might lead to spurious results. Although some motion artifact correction algorithms have been proposed in the literature, their development and accurate evaluation have been challenged by the lack of ground truth information. This is because ground truth information is time- and labor-intensive to manually annotate. This work investigates the feasibility and reliability of a deep learning computer vision (CV) approach for automated detection and annotation of head movements from video recordings. Fifteen participants performed controlled head movements across three main rotational axes (head up/down, head left/right, bend left/right) at two speeds (fast and slow), and in different ways (half, complete, repeated movement). Sessions were video recorded and head movement information was obtained using a CV approach. A 1-dimensional UNet model (1D-UNet) that detects head movements from head orientation signals extracted via a pre-trained model (SynergyNet) was implemented. Movements were manually annotated as a ground truth for model evaluation. The model’s performance was evaluated using the Jaccard index. The model showed comparable performance between the training and test sets (J train = 0.954; J test = 0.865). Moreover, it demonstrated good and consistent performance at annotating movement across movement axes and speeds. However, performance varied by movement type, with the best results being obtained for repeated (J test = 0.941), followed by complete (J test = 0.872), and then half movements (J test = 0.826). This study suggests that the proposed CV approach provides accurate ground truth movement information. Future research can rely on this CV approach to evaluate and improve fNIRS motion artifact correction algorithms.

Abstract Miscarriage is the spontaneous termination of a pregnancy before 24 weeks of gestation. We studied the genome of euploid miscarried embryos from mothers in the range of healthy adult individuals to understand genetic susceptibility to miscarriage not caused by chromosomal aneuploidies. We developed gp , a pipeline that we used to prioritize 439 unique variants in 399 genes, including genes known to be associated with miscarriages. Among the prioritized genes we found STAG2 coding for the cohesin complex subunit, for which inactivation in mouse is lethal, and TLE4 a target of Notch and Wnt, physically interacting with a region on chromosome 9 associated to miscarriages.

Deep Learning (DL) is rapidly permeating the field of Digital Pathology with algorithms successfully applied to ease daily clinical practice and to discover novel associations. However, most DL workflows for Digital Pathology include custom code for data preprocessing, usually tailored to data and tasks of interest, resulting in software that is error-prone and hard to understand, peer-review, and test. In this work, we introduce histolab, a Python package designed to standardize the preprocessing of Whole Slide Images in a reproducible environment, supported by automated testing. In addition, the package provides functions for building datasets of WSI tiles, including augmentation and morphological operators, a tile scoring framework, and stain normalization methods. histolab is modular, extensible, and easily integrable into DL pipelines, with support of the OpenSlide and large_image backends. To guarantee robustness, histolab embraces software engineering best practices such as multiplatform automated testing and Continuous Integration.

Food samples are routinely screened for food-contaminating beetles (i.e., pantry beetles) due to their adverse impact on the economy, environment, public health and safety. If found, their remains are subsequently analyzed to identify the species responsible for the contamination; each species poses different levels of risk, requiring different regulatory and management steps. At present, this identification is done through manual microscopic examination since each species of beetle has a unique pattern on its elytra (hardened forewing). Our study sought to automate the pattern recognition process through machine learning. Such automation will enable more efficient identification of pantry beetle species and could potentially be scaled up and implemented across various analysis centers in a consistent manner. In our earlier studies, we demonstrated that automated species identification of pantry beetles is feasible through elytral pattern recognition. Due to poor image quality, however, we failed to achieve prediction accuracies of more than 80%. Subsequently, we modified the traditional imaging technique, allowing us to acquire high-quality elytral images. In this study, we explored whether high-quality elytral images can truly achieve near-perfect prediction accuracies for 27 different species of pantry beetles. To test this hypothesis, we developed a convolutional neural network (CNN) model and compared performance between two different image sets for various pantry beetles. Our study indicates improved image quality indeed leads to better prediction accuracy; however, it was not the only requirement for achieving good accuracy. Also required are many high-quality images, especially for species with a high number of variations in their elytral patterns. The current study provided a direction toward achieving our ultimate goal of automated species identification through elytral pattern recognition.

Abstract Background Oncopanel genomic testing, which identifies important somatic variants, is increasingly common in medical practice and especially in clinical trials. Currently, there is a paucity of reliable genomic reference samples having a suitably large number of pre-identified variants for properly assessing oncopanel assay analytical quality and performance. The FDA-led Sequencing and Quality Control Phase 2 (SEQC2) consortium analyze ten diverse cancer cell lines individually and their pool, termed Sample A, to develop a reference sample with suitably large numbers of coding positions with known (variant) positives and negatives for properly evaluating oncopanel analytical performance. Results In reference Sample A, we identify more than 40,000 variants down to 1% allele frequency with more than 25,000 variants having less than 20% allele frequency with 1653 variants in COSMIC-related genes. This is 5–100× more than existing commercially available samples. We also identify an unprecedented number of negative positions in coding regions, allowing statistical rigor in assessing limit-of-detection, sensitivity, and precision. Over 300 loci are randomly selected and independently verified via droplet digital PCR with 100% concordance. Agilent normal reference Sample B can be admixed with Sample A to create new samples with a similar number of known variants at much lower allele frequency than what exists in Sample A natively, including known variants having allele frequency of 0.02%, a range suitable for assessing liquid biopsy panels. Conclusion These new reference samples and their admixtures provide superior capability for performing oncopanel quality control, analytical accuracy, and validation for small to large oncopanels and liquid biopsy assays.

Abstract Background Targeted sequencing using oncopanels requires comprehensive assessments of accuracy and detection sensitivity to ensure analytical validity. By employing reference materials characterized by the U.S. Food and Drug Administration-led SEquence Quality Control project phase2 (SEQC2) effort, we perform a cross-platform multi-lab evaluation of eight Pan-Cancer panels to assess best practices for oncopanel sequencing. Results All panels demonstrate high sensitivity across targeted high-confidence coding regions and variant types for the variants previously verified to have variant allele frequency (VAF) in the 5–20% range. Sensitivity is reduced by utilizing VAF thresholds due to inherent variability in VAF measurements. Enforcing a VAF threshold for reporting has a positive impact on reducing false positive calls. Importantly, the false positive rate is found to be significantly higher outside the high-confidence coding regions, resulting in lower reproducibility. Thus, region restriction and VAF thresholds lead to low relative technical variability in estimating promising biomarkers and tumor mutational burden. Conclusion This comprehensive study provides actionable guidelines for oncopanel sequencing and clear evidence that supports a simplified approach to assess the analytical performance of oncopanels. It will facilitate the rapid implementation, validation, and quality control of oncopanels in clinical use.

Tumour-infiltrating lymphocytes play a crucial role in neuroblastoma, but their relationship to other immune cells is poorly understood. Here the authors identify the cellular and gene signatures of intratumoural dendritic cells and natural killer cells that predict the clinical outcome of neuroblastoma.

Abstract Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising a total of 57,464 clinical concepts. We introduce a representation learning model based on word embeddings, convolutional neural networks, and autoencoders (i.e., ConvAE) to transform patient trajectories into low-dimensional latent vectors. We evaluated these representations as broadly enabling patient stratification by applying hierarchical clustering to different multi-disease and disease-specific patient cohorts. ConvAE significantly outperformed several baselines in a clustering task to identify patients with different complex conditions, with 2.61 entropy and 0.31 purity average scores. When applied to stratify patients within a certain condition, ConvAE led to various clinically relevant subtypes for different disorders, including type 2 diabetes, Parkinson’s disease, and Alzheimer’s disease, largely related to comorbidities, disease progression, and symptom severity. With these results, we demonstrate that ConvAE can generate patient representations that lead to clinically meaningful insights. This scalable framework can help better understand varying etiologies in heterogeneous sub-populations and unlock patterns for EHR-based research in the realm of personalized medicine.

Abstract Background Drug-induced liver injury (DILI) is a major concern in drug development, as hepatotoxicity may not be apparent at early stages but can lead to life threatening consequences. The ability to predict DILI from in vitro data would be a crucial advantage. In 2018, the Critical Assessment Massive Data Analysis group proposed the CMap Drug Safety challenge focusing on DILI prediction. Methods and results The challenge data included Affymetrix GeneChip expression profiles for the two cancer cell lines MCF7 and PC3 treated with 276 drug compounds and empty vehicles. Binary DILI labeling and a recommended train/test split for the development of predictive classification approaches were also provided. We devised three deep learning architectures for DILI prediction on the challenge data and compared them to random forest and multi-layer perceptron classifiers. On a subset of the data and for some of the models we additionally tested several strategies for balancing the two DILI classes and to identify alternative informative train/test splits. All the models were trained with the MAQC data analysis protocol (DAP), i.e., 10x5 cross-validation over the training set. In all the experiments, the classification performance in both cross-validation and external validation gave Matthews correlation coefficient (MCC) values below 0.2. We observed minimal differences between the two cell lines. Notably, deep learning approaches did not give an advantage on the classification performance. Discussion We extensively tested multiple machine learning approaches for the DILI classification task obtaining poor to mediocre performance. The results suggest that the CMap expression data on the two cell lines MCF7 and PC3 are not sufficient for accurate DILI label prediction. Reviewers This article was reviewed by Maciej Kandula and Paweł P. Labaj.

Recent technological advances and international efforts, such as The Cancer Genome Atlas (TCGA), have made available several pan-cancer datasets encompassing multiple omics layers with detailed clinical information in large collection of samples. The need has thus arisen for the development of computational methods aimed at improving cancer subtyping and biomarker identification from multi-modal data. Here we apply the Integrative Network Fusion (INF) pipeline, which combines multiple omics layers exploiting Similarity Network Fusion (SNF) within a machine learning predictive framework. INF includes a feature ranking scheme (rSNF) on SNF-integrated features, used by a classifier over juxtaposed multi-omics features (juXT). In particular, we show instances of INF implementing Random Forest (RF) and linear Support Vector Machine (LSVM) as the classifier, and two baseline RF and LSVM models are also trained on juXT. A compact RF model, called rSNFi, trained on the intersection of top-ranked biomarkers from the two approaches juXT and rSNF is finally derived. All the classifiers are run in a 10x5-fold cross-validation schema to warrant reproducibility, following the guidelines for an unbiased Data Analysis Plan by the US FDA-led initiatives MAQC/SEQC. INF is demonstrated on four classification tasks on three multi-modal TCGA oncogenomics datasets. Gene expression, protein expression and copy number variants are used to predict estrogen receptor status (BRCA-ER, N = 381) and breast invasive carcinoma subtypes (BRCA-subtypes, N = 305), while gene expression, miRNA expression and methylation data is used as predictor layers for acute myeloid leukemia and renal clear cell carcinoma survival (AML-OS, N = 157; KIRC-OS, N = 181). In test, INF achieved similar Matthews Correlation Coefficient (MCC) values and 97% to 83% smaller feature sizes (FS), compared with juXT for BRCA-ER (MCC: 0.83 vs. 0.80; FS: 56 vs. 1801) and BRCA-subtypes (0.84 vs. 0.80; 302 vs. 1801), improving KIRC-OS performance (0.38 vs. 0.31; 111 vs. 2319). INF predictions are generally more accurate in test than one-dimensional omics models, with smaller signatures too, where transcriptomics consistently play the leading role. Overall, the INF framework effectively integrates multiple data levels in oncogenomics classification tasks, improving over the performance of single layers alone and naive juxtaposition, and provides compact signature sizes1.

Abstract Background High-throughput methodologies such as microarrays and next-generation sequencing are routinely used in cancer research, generating complex data at different omics layers. The effective integration of omics data could provide a broader insight into the mechanisms of cancer biology, helping researchers and clinicians to develop personalized therapies. Results In the context of CAMDA 2017 Neuroblastoma Data Integration challenge, we explore the use of Integrative Network Fusion (INF), a bioinformatics framework combining a similarity network fusion with machine learning for the integration of multiple omics data. We apply the INF framework for the prediction of neuroblastoma patient outcome, integrating RNA-Seq, microarray and array comparative genomic hybridization data. We additionally explore the use of autoencoders as a method to integrate microarray expression and copy number data. Conclusions The INF method is effective for the integration of multiple data sources providing compact feature signatures for patient classification with performances comparable to other methods. Latent space representation of the integrated data provided by the autoencoder approach gives promising results, both by improving classification on survival endpoints and by providing means to discover two groups of patients characterized by distinct overall survival (OS) curves. Reviewers This article was reviewed by Djork-Arné Clevert and Tieliu Shi.

Abstract Background Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Results Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Conclusion Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

The high level of heterogeneity in Autism Spectrum Disorder (ASD) and the lack of systematic measurements complicate predicting outcomes of early intervention and the identification of better-tailored treatment programs. Computational phenotyping may assist therapists in monitoring child behavior through quantitative measures and personalizing the intervention based on individual characteristics; still, real-world behavioral analysis is an ongoing challenge. For this purpose, we designed EYE-C, a system based on OpenPose and Gaze360 for fine-grained analysis of eye-contact episodes in unconstrained therapist-child interactions via a single video camera. The model was validated on video data varying in resolution and setting, achieving promising performance. We further tested EYE-C on a clinical sample of 62 preschoolers with ASD for spectrum stratification based on eye-contact features and age. By unsupervised clustering, three distinct sub-groups were identified, differentiated by eye-contact dynamics and a specific clinical phenotype. Overall, this study highlights the potential of Artificial Intelligence in categorizing atypical behavior and providing translational solutions that might assist clinical practice.

The lack of open-source tools for physiological signal processing hinders the development of standardized pipelines in physiology. Researchers usually must rely on commercial software that, by implementing black-box algorithms, undermines the control on the analysis and prevents the comparison of the results, ultimately affecting the scientific reproducibility. We introduce pyphysio as a step towards a data science approach oriented to compute physiological indicators, in particular of the Autonomic Nervous System activity. pyphysio serves as a basis for machine learning modules and it implements a suite of combinable algorithms for processing of signals from either by wearable or medical-grade quality devices. Keywords: Physiological signal processing, Psychophysiology, Autonomic indicators, Data science, Python

Artificial Intelligence is exponentially increasing its impact on healthcare. As deep learning is mastering computer vision tasks, its application to digital pathology is natural, with the promise of aiding in routine reporting and standardizing results across trials. Deep learning features inferred from digital pathology scans can improve validity and robustness of current clinico-pathological features, up to identifying novel histological patterns, e.g., from tumor infiltrating lymphocytes. In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. We introduce the DAPPER framework for validation based on a rigorous Data Analysis Plan derived from the FDA's MAQC project, designed to analyze causes of variability in predictive biomarkers. We apply the framework on models that identify tissue of origin on 787 Whole Slide Images from the Genotype-Tissue Expression (GTEx) project. We test three different deep learning architectures (VGG, ResNet, Inception) as feature extractors and three classifiers (a fully connected multilayer, Support Vector Machine and Random Forests) and work with four datasets (5, 10, 20 or 30 classes), for a total of 53, 000 tiles at 512 × 512 resolution. We analyze accuracy and feature stability of the machine learning classifiers, also demonstrating the need for diagnostic tests (e.g., random labels) to identify selection bias and risks for reproducibility. Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1, 060 annotated tiles and validated on 265 unseen ones. The DAPPER software, including its deep learning pipeline and the Histological Imaging-Newsy Tiles (HINT) benchmark dataset derived from GTEx, is released as a basis for standardization and validation initiatives in AI for digital pathology.

Although pediatric malignant extracranial germ-cell tumors (meGCTs) are among the most chemosensitive solid tumors, a group of patients relapse and die of disease. To identify new markers predicting clinical outcome, we examined the prognostic relevance of tumor-infiltrating T lymphocytes (TILs) and the expression of PD-1 and PD-L1 in a cohort of pediatric meGCTs by in situ immunohistochemistry. MeGCTs were variously infiltrated by T cell-subtypes according to the tumor subtype, tumor location and age at diagnosis. We distinguished three different phenotypes: i) tumors not infiltrated by T cells (immature teratomas and half of the yolk sac tumors), ii) tumors highly infiltrated by CD8+ T cells expressing PD-1, which identifies activated tumor-reactive T cells (seminomas and dysgerminomas), iii) tumors highly infiltrated by CD8+ T cells within an immunosuppressive tumor microenvironment characterized by CD4+FOXP3+ Treg cells and PD-L1-expressing tumor cells (embryonal carcinomas, choriocarcinomas and the remaining yolk sac tumors). Tumor subtypes belonging mixed meGCTs were variously infiltrated, suggesting the coexistence of multiple immune microenvironments either facilitating or precluding the entry of T cells. These findings support the hypothesis that TILs influence the development of meGCTs and might be of clinical relevance to improve risk stratification and the treatment of pediatric patients.

Background: Observational research plays an important part in developmental research due to its noninvasiveness. However, it has been hardly applied to investigate efficacy of the child–therapist interaction in the context of naturalistic developmental behavioral interventions (NDBI). In particular, the characteristics of child–therapist interplay are thought to have a significant impact in NDBIs in children with autism spectrum disorder (ASD). Quantitative approaches may help to identify the key features of interaction during therapy and could be translated as instruments to monitor early interventions. Methods: n = 24 children with autism spectrum disorder (ASD) were monitored from the time of the diagnosis (T0) and after about one year of early intervention (T1). A novel observational coding system was applied to video recorded sessions of intervention to extract quantitative behavioral descriptors. We explored the coding scheme reliability together with its convergent and predictive validity. Further, we applied computational techniques to investigate changes and associations between interaction profiles and developmental outcomes. Results: Significant changes in interaction variables emerged with time, suggesting that a favorable outcome is associated with interactions characterized by increased synchrony, better therapist’s strategies to successfully engage the child and scaffold longer, more complex and engaging interchanges. Interestingly, data models linked interaction profiles, outcome measures and response trajectories. Conclusion: Current research stresses the need for process measures to understand the hows and the whys of ASD early intervention. Combining observational techniques with computational approaches may help in explaining interindividual variability. Further, it could disclose successful features of interaction associated with better response trajectories or to different ASD behavioral phenotypes that could require specific dyadic modalities.

A key access point to the functioning of the autonomic nervous system is the investigation of peripheral signals. Wearable devices (WDs) enable the acquisition and quantification of peripheral signals in a wide range of contexts, from personal uses to scientific research. WDs have lower costs and higher portability than medical-grade devices. However, the achievable data quality can be lower, and data are subject to artifacts due to body movements and data losses. It is therefore crucial to evaluate the reliability and validity of WDs before their use in research. In this study, we introduce a data analysis procedure for the assessment of WDs for multivariate physiological signals. The quality of cardiac and electrodermal activity signals is validated with a standard set of signal quality indicators. The pipeline is available as a collection of open source Python scripts based on the pyphysio package. We apply the indicators for the analysis of signal quality on data simultaneously recorded from a clinical-grade device and two WDs. The dataset provides signals of six different physiological measures collected from 18 subjects with WDs. This study indicates the need to validate the use of WDs in experimental settings for research and the importance of both technological and signal processing aspects to obtain reliable signals and reproducible results.

Monitoring healthcare providers’ cognitive workload during surgical procedures can provide insight into the dynamic changes of mental states that may affect patient clinical outcomes. The role of cognitive factors influencing both technical and non-technical skill are increasingly being recognized, especially as the opportunities to unobtrusively collect accurate and sensitive data are improving. Applying sensors to capture these data in a complex real-world setting such as the cardiac surgery operating room, however, is accompanied by myriad social, physical, and procedural constraints. The goal of this study was to investigate the feasibility of overcoming logistical barriers in order to effectively collect multi-modal psychophysiological inputs via heart rate (HR) and near-infrared spectroscopy (NIRS) acquisition in the real-world setting of the operating room. The surgeon was outfitted with HR and NIRS sensors during aortic valve surgery, and validation analysis was performed to detect the influence of intra-operative events on cardiovascular and prefrontal cortex changes. Signals collected were significantly correlated and noted intra-operative events and subjective self-reports coincided with observable correlations among cardiovascular and cerebral activity across surgical phases. The primary novelty and contribution of this work is in demonstrating the feasibility of collecting continuous sensor data from a surgical team member in a real-world setting.

We introduce here the Grape Berries Counting Net (GBCNet), a tool for accurate fruit yield estimation from smartphone cameras, by adapting Deep Learning algorithms originally developed for crowd counting. We test GBCNet using cross-validation procedure on two original datasets CR1 and CR2 of grape pictures taken in-field before veraison. A total of 35,668 berries have been manually annotated for the task. GBCNet achieves good performances on both the seven grape varieties dataset CR1, although with a different accuracy level depending on the variety, and on the single variety dataset CR2: in particular Mean Average Error (MAE) ranges from 0.85% for Pinot Gris to 11.73% for Marzemino on CR1 and reaches 7.24% on the Teroldego CR2 dataset.

One of the most crucial applications of radar-based precipitation nowcasting systems is the short-term forecast of extreme rainfall events such as flash floods and severe thunderstorms. While deep learning nowcasting models have recently shown to provide better overall skill than traditional echo extrapolation models, they suffer from conditional bias, sometimes reporting lower skill on extreme rain rates compared to Lagrangian persistence, due to excessive prediction smoothing. This work presents a novel method to improve deep learning prediction skills in particular for extreme rainfall regimes. The solution is based on model stacking, where a convolutional neural network is trained to combine an ensemble of deep learning models with orographic features, doubling the prediction skills with respect to the ensemble members and their average on extreme rain rates, and outperforming them on all rain regimes. The proposed architecture was applied on the recently released TAASRAD19 radar dataset: the initial ensemble was built by training four models with the same TrajGRU architecture over different rainfall thresholds on the first six years of the dataset, while the following three years of data were used for the stacked model. The stacked model can reach the same skill of Lagrangian persistence on extreme rain rates while retaining superior performance on lower rain regimes.

We introduce the CDRP (Concatenated Diagnostic-Relapse Prognostic) architecture for multi-task deep learning that incorporates a clinical algorithm, e.g., a risk stratification schema to improve prognostic profiling. We present the first application to survival prediction in High-Risk (HR) Neuroblastoma from transcriptomics data, a task that studies from the MAQC consortium have shown to remain the hardest among multiple diagnostic and prognostic endpoints predictable from the same dataset. To obtain a more accurate risk stratification needed for appropriate treatment strategies, CDRP combines a first component (CDRP-A) synthesizing a diagnostic task and a second component (CDRP-N) dedicated to one or more prognostic tasks. The approach leverages the advent of semi-supervised deep learning structures that can flexibly integrate multimodal data or internally create multiple processing paths. CDRP-A is an autoencoder trained on gene expression on the HR/non-HR risk stratification by the Children's Oncology Group, obtaining a 64-node representation in the bottleneck layer. CDRP-N is a multi-task classifier for two prognostic endpoints, i.e., Event-Free Survival (EFS) and Overall Survival (OS). CDRP-A provides the HR embedding input to the CDRP-N shared layer, from which two branches depart to model EFS and OS, respectively. To control for selection bias, CDRP is trained and evaluated using a Data Analysis Protocol (DAP) developed within the MAQC initiative. CDRP was applied on Illumina RNA-Seq of 498 Neuroblastoma patients (HR: 176) from the SEQC study (12,464 Entrez genes) and on Affymetrix Human Exon Array expression profiles (17,450 genes) of 247 primary diagnostic Neuroblastoma of the TARGET NBL cohort. On the SEQC HR patients, CDRP achieves Matthews Correlation Coefficient (MCC) 0.38 for EFS and MCC = 0.19 for OS in external validation, improving over published SEQC models. We show that a CDRP-N embedding is indeed parametrically associated to increasing severity and the embedding can be used to better stratify patients' survival.

When modeling coexpression networks from high-throughput time course data, Pearson Correlation Coefficient (PCC) is one of the most effective and popular similarity functions. However, its reliability is limited since it cannot capture non-linear interactions and time shifts. Here we propose to overcome these two issues by employing a novel similarity function, Dynamic Time Warping Maximal Information Coefficient (DTW-MIC), combining a measure taking care of functional interactions of signals (MIC) and a measure identifying time lag (DTW). By using the Hamming-Ipsen-Mikhailov (HIM) metric to quantify network differences, the effectiveness of the DTW-MIC approach is demonstrated on a set of four synthetic and one transcriptomic datasets, also in comparison to TimeDelay ARACNE and Transfer Entropy.

Detecting and monitoring of abnormal movement behaviors in patients with Parkinson’s Disease (PD) and individuals with Autism Spectrum Disorders (ASD) are beneficial for adjusting care and medical treatment in order to improve the patient’s quality of life. Supervised methods commonly used in the literature need annotation of data, which is a time-consuming and costly process. In this paper, we propose deep normative modeling as a probabilistic novelty detection method, in which we model the distribution of normal human movements recorded by wearable sensors and try to detect abnormal movements in patients with PD and ASD in a novelty detection framework. In the proposed deep normative model, a movement disorder behavior is treated as an extreme of the normal range or, equivalently, as a deviation from the normal movements. Our experiments on three benchmark datasets indicate the effectiveness of the proposed method, which outperforms one-class SVM and the reconstruction-based novelty detection approaches. Our contribution opens the door toward modeling normal human movements during daily activities using wearable sensors and eventually real-time abnormal movement detection in neuro-developmental and neuro-degenerative disorders.

The number of available algorithms to infer a biological network from a dataset of high-throughput measurements is overwhelming and keeps growing. However, evaluating their performance is unfeasible unless a 'gold standard' is available to measure how close the reconstructed network is to the ground truth. One measure of this is the stability of these predictions to data resampling approaches. We introduce NetSI, a family of Network Stability Indicators, to assess quantitatively the stability of a reconstructed network in terms of inference variability due to data subsampling. In order to evaluate network stability, the main NetSI methods use a global/local network metric in combination with a resampling (bootstrap or cross-validation) procedure. In addition, we provide two normalized variability scores over data resampling to measure edge weight stability and node degree stability, and then introduce a stability ranking for edges and nodes. A complete implementation of the NetSI indicators, including the Hamming-Ipsen-Mikhailov (HIM) network distance adopted in this paper is available with the R package nettools. We demonstrate the use of the NetSI family by measuring network stability on four datasets against alternative network reconstruction methods. First, the effect of sample size on stability of inferred networks is studied in a gold standard framework on yeast-like data from the Gene Net Weaver simulator. We also consider the impact of varying modularity on a set of structurally different networks (50 nodes, from 2 to 10 modules), and then of complex feature covariance structure, showing the different behaviours of standard reconstruction methods based on Pearson correlation, Maximum Information Coefficient (MIC) and False Discovery Rate (FDR) strategy. Finally, we demonstrate a strong combined effect of different reconstruction methods and phenotype subgroups on a hepatocellular carcinoma miRNA microarray dataset (240 subjects), and we validate the analysis on a second dataset (166 subjects) with good reproducibility.

WebValley è un'iniziativa di avvicinamento dei giovani alla ricerca scientifica interdisciplinare. Ha come azione principale l’organizzazione di una scuola estiva che permette a studenti delle superiori, di 18 anni, di lavorare in team con ricercatori ed esperti internazionali a un progetto di ricerca per tre settimane, in un'atmosfera vivace e interattiva, caratterizzata dal lavoro in gruppo e dall’uso di tecnologie web per risolvere un problema scientifico a forte connotazione etica, proposto da un esperto esterno. Vengono inizialmente fornite competenze tecniche, con forte attenzione all’open source per il calcolo scientifico e per trattare dati complessi. Si definisce da queste basi un progetto in cui sono gli stessi studenti a organizzarsi in gruppi, selezionare le tecnologie e sviluppare nuove soluzioni. Al termine essi restituiscono al committente e a specialisti del settore i loro risultati in una presentazione pubblica, negli ultimi anni, in lingua inglese e in teleconferenza. WebValley si caratterizza anche per il luogo in cui si svolge: a rotazione, in piccoli paesi di montagna del Trentino, per mostrare come sia possibile sviluppare innovazione in località periferiche disponendo di strumenti tecnici, connessione e conoscenze. Dal 2001, hanno frequentato la scuola circa 220 studenti, molti dei quali si sono poi indirizzati verso una carriera in materie scientifiche e tecnologiche, hanno tenuto i contatti tra loro, collaborando con i ricercatori anche nell’organizzazione della

MotivationThe identification of robust lists of molecular biomarkers related to a disease is a fundamental step for early diagnosis and treatment. However, methodologies for the discovery of biomarkers using microarray data often provide results with limited overlap. These differences are imputable to 1) dataset size (few subjects with respect to the number of features); 2) heterogeneity of the disease; 3) heterogeneity of experimental protocols and computational pipelines employed in the analysis. In this paper, we focus on the first two issues and assess, both on simulated (through an in silico regulation network model) and real clinical datasets, the consistency of candidate biomarkers provided by a number of different methods.MethodsWe extensively simulated the effect of heterogeneity characteristic of complex diseases on different sets of microarray data. Heterogeneity was reproduced by simulating both intrinsic variability of the population and the alteration of regulatory mechanisms. Population variability was simulated by modeling evolution of a pool of subjects; then, a subset of them underwent alterations in regulatory mechanisms so as to mimic the disease state.ResultsThe simulated data allowed us to outline advantages and drawbacks of different methods across multiple studies and varying number of samples and to evaluate precision of feature selection on a benchmark with known biomarkers. Although comparable classification accuracy was reached by different methods, the use of external cross-validation loops is helpful in finding features with a higher degree of precision and stability. Application to real data confirmed these results.

IntroductionThe traditional staging system is inadequate to identify those patients with stage II colorectal cancer (CRC) at high risk of recurrence or with stage III CRC at low risk. A number of gene expression signatures to predict CRC prognosis have been proposed, but none is routinely used in the clinic. The aim of this work was to assess the prediction ability and potential clinical usefulness of these signatures in a series of independent datasets.MethodsA literature review identified 31 gene expression signatures that used gene expression data to predict prognosis in CRC tissue. The search was based on the PubMed database and was restricted to papers published from January 2004 to December 2011. Eleven CRC gene expression datasets with outcome information were identified and downloaded from public repositories. Random Forest classifier was used to build predictors from the gene lists. Matthews correlation coefficient was chosen as a measure of classification accuracy and its associated p-value was used to assess association with prognosis. For clinical usefulness evaluation, positive and negative post-tests probabilities were computed in stage II and III samples.ResultsFive gene signatures showed significant association with prognosis and provided reasonable prediction accuracy in their own training datasets. Nevertheless, all signatures showed low reproducibility in independent data. Stratified analyses by stage or microsatellite instability status showed significant association but limited discrimination ability, especially in stage II tumors. From a clinical perspective, the most predictive signatures showed a minor but significant improvement over the classical staging system.ConclusionsThe published signatures show low prediction accuracy but moderate clinical usefulness. Although gene expression data may inform prognosis, better strategies for signature validation are needed to encourage their widespread use in the clinic.

The outcome of a functional genomics pipeline is usually a partial list of genomic features, ranked by their relevance in modelling biological phenotype in terms of a classification or regression model. Due to resampling protocols or to a meta-analysis comparison, it is often the case that sets of alternative feature lists (possibly of different lengths) are obtained, instead of just one list. Here we introduce a method, based on permutations, for studying the variability between lists ("list stability") in the case of lists of unequal length. We provide algorithms evaluating stability for lists embedded in the full feature set or just limited to the features occurring in the partial lists. The method is demonstrated by finding and comparing gene profiles on a large prostate cancer dataset, consisting of two cohorts of patients from different countries, for a total of 455 samples.

We show that the Confusion Entropy, a measure of performance in multiclass problems has a strong (monotone) relation with the multiclass generalization of a classical metric, the Matthews Correlation Coefficient. Analytical results are provided for the limit cases of general no-information (n-face dice rolling) of the binary classification. Computational evidence supports the claim in the general case.

BACKGROUND: Individual-based models can provide the most reliable estimates of the spread of infectious diseases. In the present study, we evaluated the diffusion of pandemic influenza in Italy and the impact of various control measures, coupling a global SEIR model for importation of cases with an individual based model (IBM) describing the Italian epidemic. METHODOLOGY/PRINCIPAL FINDINGS: We co-located the Italian population (57 million inhabitants) to households, schools and workplaces and we assigned travel destinations to match the 2001 census data. We considered different R(0 )values (1.4; 1.7; 2), evaluating the impact of control measures (vaccination, antiviral prophylaxis -AVP-, international air travel restrictions and increased social distancing). The administration of two vaccine doses was considered, assuming that first dose would be administered 1-6 months after the first world case, and different values for vaccine effectiveness (VE). With no interventions, importation would occur 37-77 days after the first world case. Air travel restrictions would delay the importation of the pandemic by 7-37 days. With an R(0 )of 1.4 or 1.7, the use of combined measures would reduce clinical attack rates (AR) from 21-31% to 0.3-4%. Assuming an R(0) of 2, the AR would decrease from 38% to 8%, yet only if vaccination were started within 2 months of the first world case, in combination with a 90% reduction in international air traffic, closure of schools/workplaces for 4 weeks and AVP of household and school/work close contacts of clinical cases. Varying VE would not substantially affect the results. CONCLUSIONS: This IBM, which is based on country-specific demographic data, could be suitable for the real-time evaluation of measures to be undertaken in the event of the emergence of a new pandemic influenza virus. All preventive measures considered should be implemented to mitigate the pandemic.