Implementation and empirical evaluation of a quantum machine learning pipeline for local classification.

In the current era, quantum resources are extremely limited, and this makes difficult the usage of quantum machine learning (QML) models. Concerning the supervised tasks, a viable approach is the introduction of a quantum locality technique, which allows the models to focus only on the neighborhood of the considered element. A well-known locality technique is the k-nearest neighbors (k-NN) algorithm, of which several quantum variants have been proposed; nevertheless, they have not been employed yet as a preliminary step of other QML models. Instead, for the classical counterpart, a performance enhancement with respect to the base models has already been proven. In this paper, we propose and evaluate the idea of exploiting a quantum locality technique to reduce the size and improve the performance of QML models. In detail, we provide (i) an implementation in Python of a QML pipeline for local classification and (ii) its extensive empirical evaluation. Regarding the quantum pipeline, it has been developed using Qiskit, and it consists of a quantum k-NN and a quantum binary classifier, both already available in the literature. The results have shown the quantum pipeline's equivalence (in terms of accuracy) to its classical counterpart in the ideal case, the validity of locality's application to the QML realm, but also the strong sensitivity of the chosen quantum k-NN to probability fluctuations and the better performance of classical baseline methods like the random forest.

How does decision-making change during challenging times?

Prospect Theory, proposed and developed by Kahneman and Tversky, demonstrated that people do not make rational decisions based on expected utility, but are instead biased by specific cognitive tendencies leading to neglect, under- or over- consider information, depending on the context of presentation. In this vein, the present paper focuses on whether and how individual decision-making attitudes are prone to change in the presence of globally challenging events. We ran three partial replications of the Kahneman and Tversky (1979) paper, focusing on a set of eight prospects, after a terror attack (Paris, November 2015, 134 subjects) and during the Covid-19 pandemic, both during the first lockdown in Italy (Spring 2020, 176 subjects) and after the first reopening (140 subjects). The results confirm patterns of choice characterizing uncertain times, as shown by previous literature. In particular, we note significant increase of risk aversion, both in the gain and in the loss domains, that consistently emerged in the three replications. Given the nature of our sample, and the heterogeneity between the three periods investigated, we suggest that the phenomenon we present can be explained stress-related effects on decision making rather than by other economic effects, such as the income effect.

Vitis OneGenE: A Causality-Based Approach to Generate Gene Networks in Vitis vinifera Sheds Light on the Laccase and Dirigent Gene Families.

The abundance of transcriptomic data and the development of causal inference methods have paved the way for gene network analyses in grapevine. Vitis OneGenE is a transcriptomic data mining tool that finds direct correlations between genes, thus producing association networks. As a proof of concept, the stilbene synthase gene regulatory network obtained with OneGenE has been compared with published co-expression analysis and experimental data, including cistrome data for MYB stilbenoid regulators. As a case study, the two secondary metabolism pathways of stilbenoids and lignin synthesis were explored. Several isoforms of laccase, peroxidase, and dirigent protein genes, putatively involved in the final oxidative oligomerization steps, were identified as specifically belonging to either one of these pathways. Manual curation of the predicted sequences exploiting the last available genome assembly, and the integration of phylogenetic and OneGenE analyses, identified a group of laccases exclusively present in grapevine and related to stilbenoids. Here we show how network analysis by OneGenE can accelerate knowledge discovery by suggesting new candidates for functional characterization and application in breeding programs.

Discovering Causal Relationships in Grapevine Expression Data to Expand Gene Networks. A Case Study: Four Networks Related to Climate Change.

In recent years the scientific community has been heavily engaged in studying the grapevine response to climate change. Final goal is the identification of key genetic traits to be used in grapevine breeding and the setting of agronomic practices to improve climatic resilience. The increasing availability of transcriptomic studies, describing gene expression in many tissues and developmental, or treatment conditions, have allowed the implementation of gene expression compendia, which enclose a huge amount of information. The mining of transcriptomic data represents an effective approach to expand a known local gene network (LGN) by finding new related genes. We recently published a pipeline based on the iterative application of the PC-algorithm, named NES2RA, to expand gene networks in Escherichia coli and Arabidopsis thaliana. Here, we propose the application of this method to the grapevine transcriptomic compendium Vespucci, in order to expand four LGNs related to the grapevine response to climate change. Two networks are related to the secondary metabolic pathways for anthocyanin and stilbenoid synthesis, involved in the response to solar radiation, whereas the other two are signaling networks, related to the hormones abscisic acid and ethylene, possibly involved in the regulation of cell water balance and cuticle transpiration. The expansion networks produced by NES2RA algorithm have been evaluated by comparison with experimental data and biological knowledge on the identified genes showing fairly good consistency of the results. In addition, the algorithm was effective in retaining only the most significant interactions among the genes providing a useful framework for experimental validation. The application of the NES2RA to Vitis vinifera expression data by means of the BOINC-based implementation is available upon request (valter.cavecchia@cnr.it).

Essential protein identification based on essential protein-protein interaction prediction by Integrated Edge Weights.

Essential proteins play a crucial role in cellular survival and development process. Experimentally, essential proteins are identified by gene knockouts or RNA interference, which are expensive and often fatal to the target organisms. Regarding this, an alternative yet important approach to essential protein identification is through computational prediction. Existing computational methods predict essential proteins based on their relative densities in a protein-protein interaction (PPI) network. Degree, betweenness, and other appropriate criteria are often used to measure the relative density. However, no matter what criterion is used, a protein is actually ordered by the attributes of this protein per se. In this research, we presented a novel computational method, Integrated Edge Weights (IEW), to first rank protein-protein interactions by integrating their edge weights, and then identified sub PPI networks consisting of those highly-ranked edges, and finally regarded the nodes in these sub networks as essential proteins. We evaluated IEW on three model organisms: Saccharomyces cerevisiae (S. cerevisiae), Escherichia coli (E. coli), and Caenorhabditis elegans (C. elegans). The experimental results showed that IEW achieved better performance than the state-of-the-art methods in terms of precision-recall and Jackknife measures. We had also demonstrated that IEW is a robust and effective method, which can retrieve biologically significant modules by its highly-ranked protein-protein interactions for S. cerevisiae, E. coli, and C. elegans. We believe that, with sufficient data provided, IEW can be used to any other organisms' essential protein identification. A website about IEW can be accessed from http://digbio.missouri.edu/IEW/index.html.

Identification of essential proteins based on ranking edge-weights in protein-protein interaction networks.

Essential proteins are those that are indispensable to cellular survival and development. Existing methods for essential protein identification generally rely on knock-out experiments and/or the relative density of their interactions (edges) with other proteins in a Protein-Protein Interaction (PPI) network. Here, we present a computational method, called EW, to first rank protein-protein interactions in terms of their Edge Weights, and then identify sub-PPI-networks consisting of only the highly-ranked edges and predict their proteins as essential proteins. We have applied this method to publicly-available PPI data on Saccharomyces cerevisiae (Yeast) and Escherichia coli (E. coli) for essential protein identification, and demonstrated that EW achieves better performance than the state-of-the-art methods in terms of the precision-recall and Jackknife measures. The highly-ranked protein-protein interactions by our prediction tend to be biologically significant in both the Yeast and E. coli PPI networks. Further analyses on systematically perturbed Yeast and E. coli PPI networks through randomly deleting edges demonstrate that the proposed method is robust and the top-ranked edges tend to be more associated with known essential proteins than the lowly-ranked edges.

Protein-specific prediction of mRNA binding using RNA sequences, binding motifs and predicted secondary structures.

BACKGROUND: RNA-binding proteins interact with specific RNA molecules to regulate important cellular processes. It is therefore necessary to identify the RNA interaction partners in order to understand the precise functions of such proteins. Protein-RNA interactions are typically characterized using in vivo and in vitro experiments but these may not detect all binding partners. Therefore, computational methods that capture the protein-dependent nature of such binding interactions could help to predict potential binding partners in silico. RESULTS: We have developed three methods to predict whether an RNA can interact with a particular RNA-binding protein using support vector machines and different features based on the sequence (the Oli method), the motif score (the OliMo method) and the secondary structure (the OliMoSS method). We applied these approaches to different experimentally-derived datasets and compared the predictions with RNAcontext and RPISeq. Oli outperformed OliMoSS and RPISeq, confirming our protein-specific predictions and suggesting that tetranucleotide frequencies are appropriate discriminative features. Oli and RNAcontext were the most competitive methods in terms of the area under curve. A precision-recall curve analysis achieved higher precision values for Oli. On a second experimental dataset including real negative binding information, Oli outperformed RNAcontext with a precision of 0.73 vs. 0.59. CONCLUSIONS: Our experiments showed that features based on primary sequence information are sufficiently discriminating to predict specific RNA-protein interactions. Sequence motifs and secondary structure information were not necessary to improve these predictions. Finally we confirmed that protein-specific experimental data concerning RNA-protein interactions are valuable sources of information that can be used for the efficient training of models for in silico predictions. The scripts are available upon request to the corresponding author.

Operon prediction by Markov clustering.

The prediction of operons is a critical step for the reconstruction of biochemical and regulatory networks at the whole genome level. In this paper, a novel operon prediction model is proposed based on Markov Clustering (MCL). The model employs a graph-clustering method by MCL for prediction and does not need a classifier. In the cross-species validation, the accuracies of E. coli K12, Bacillus subtilis and P. furiosus are 92.1, 86.9 and 87.3%, respectively. Experimental results show that the proposed method has a powerful capability of operon prediction. The compiled program and test data sets are publicly available at http://ccst.jlu.edu.cn/JCSB/OPMC/.

Prokaryotic phylogenies inferred from whole-genome sequence and annotation data.

Phylogenetic trees are used to represent the evolutionary relationship among various groups of species. In this paper, a novel method for inferring prokaryotic phylogenies using multiple genomic information is proposed. The method is called CGCPhy and based on the distance matrix of orthologous gene clusters between whole-genome pairs. CGCPhy comprises four main steps. First, orthologous genes are determined by sequence similarity, genomic function, and genomic structure information. Second, genes involving potential HGT events are eliminated, since such genes are considered to be the highly conserved genes across different species and the genes located on fragments with abnormal genome barcode. Third, we calculate the distance of the orthologous gene clusters between each genome pair in terms of the number of orthologous genes in conserved clusters. Finally, the neighbor-joining method is employed to construct phylogenetic trees across different species. CGCPhy has been examined on different datasets from 617 complete single-chromosome prokaryotic genomes and achieved applicative accuracies on different species sets in agreement with Bergey's taxonomy in quartet topologies. Simulation results show that CGCPhy achieves high average accuracy and has a low standard deviation on different datasets, so it has an applicative potential for phylogenetic analysis.

Link Clustering with Extended Link Similarity and EQ Evaluation Division.

Link Clustering (LC) is a relatively new method for detecting overlapping communities in networks. The basic principle of LC is to derive a transform matrix whose elements are composed of the link similarity of neighbor links based on the Jaccard distance calculation; then it applies hierarchical clustering to the transform matrix and uses a measure of partition density on the resulting dendrogram to determine the cut level for best community detection. However, the original link clustering method does not consider the link similarity of non-neighbor links, and the partition density tends to divide the communities into many small communities. In this paper, an Extended Link Clustering method (ELC) for overlapping community detection is proposed. The improved method employs a new link similarity, Extended Link Similarity (ELS), to produce a denser transform matrix, and uses the maximum value of EQ (an extended measure of quality of modularity) as a means to optimally cut the dendrogram for better partitioning of the original network space. Since ELS uses more link information, the resulting transform matrix provides a superior basis for clustering and analysis. Further, using the EQ value to find the best level for the hierarchical clustering dendrogram division, we obtain communities that are more sensible and reasonable than the ones obtained by the partition density evaluation. Experimentation on five real-world networks and artificially-generated networks shows that the ELC method achieves higher EQ and In-group Proportion (IGP) values. Additionally, communities are more realistic than those generated by either of the original LC method or the classical CPM method.

Widespread uncoupling between transcriptome and translatome variations after a stimulus in mammalian cells.

BACKGROUND: The classical view on eukaryotic gene expression proposes the scheme of a forward flow for which fluctuations in mRNA levels upon a stimulus contribute to determine variations in mRNA availability for translation. Here we address this issue by simultaneously profiling with microarrays the total mRNAs (the transcriptome) and the polysome-associated mRNAs (the translatome) after EGF treatment of human cells, and extending the analysis to other 19 different transcriptome/translatome comparisons in mammalian cells following different stimuli or undergoing cell programs. RESULTS: Triggering of the EGF pathway results in an early induction of transcriptome and translatome changes, but 90% of the significant variation is limited to the translatome and the degree of concordant changes is less than 5%. The survey of other 19 different transcriptome/translatome comparisons shows that extensive uncoupling is a general rule, in terms of both RNA movements and inferred cell activities, with a strong tendency of translation-related genes to be controlled purely at the translational level. By different statistical approaches, we finally provide evidence of the lack of dependence between changes at the transcriptome and translatome levels. CONCLUSIONS: We propose a model of diffused independency between variation in transcript abundances and variation in their engagement on polysomes, which implies the existence of specific mechanisms to couple these two ways of regulating gene expression.

About neighborhood counting measure metric and minimum risk metric.

In a 2006 TPAMI paper, Wang proposed the Neighborhood Counting Measure, a similarity measure for the k-NN algorithm. In his paper, Wang mentioned the Minimum Risk Metric (MRM), an early distance measure based on the minimization of the risk of misclassification. Wang did not compare NCM to MRM because of its allegedly excessive computational load. In this comment paper, we complete the comparison that was missing in Wang's paper and, from our empirical evaluation, we show that MRM outperforms NCM and that its running time is not prohibitive as Wang suggested.

Methods for labeling error detection in microarrays based on the effect of data perturbation on the regression model.

MOTIVATION: Mislabeled samples often appear in gene expression profile because of the similarity of different sub-type of disease and the subjective misdiagnosis. The mislabeled samples deteriorate supervised learning procedures. The LOOE-sensitivity algorithm is an approach for mislabeled sample detection for microarray based on data perturbation. However, the failure of measuring the perturbing effect makes the LOOE-sensitivity algorithm a poor performance. The purpose of this article is to design a novel detection method for mislabeled samples of microarray, which could take advantage of the measuring effect of data perturbations. RESULTS: To measure the effect of data perturbation, we define an index named perturbing influence value (PIV), based on the support vector machine (SVM) regression model. The Column Algorithm (CAPIV), Row Algorithm (RAPIV) and progressive Row Algorithm (PRAPIV) based on the PIV value are proposed to detect the mislabeled samples. Experimental results obtained by using six artificial datasets and five microarray datasets demonstrate that all proposed methods in this article are superior to LOOE-sensitivity. Moreover, compared with the simple SVM and CL-stability, the PRAPIV algorithm shows an increase in precision and high recall. AVAILABILITY: The program and source code (in JAVA) are publicly available at http://ccst.jlu.edu.cn/CSBG/PIVS/index.htm

Towards the integration of computational systems biology and high-throughput data: supporting differential analysis of microarray gene expression data.

The paradigmatic shift occurred in biology that led first to high-throughput experimental techniques and later to computational systems biology must be applied also to the analysis paradigm of the relation between local models and data to obtain an effective prediction tool. In this work we introduce a unifying notational framework for systems biology models and high-throughput data in order to allow new integrations on the systemic scale like the use of in silico predictions to support the mining of gene expression datasets. Using the framework, we propose two applications concerning the use of system level models to support the differential analysis of microarray expression data. We tested the potentialities of the approach with a specific microarray experiment on the phosphate system in Saccharomyces cerevisiae and a computational model of the PHO pathway that supports the systems biology concepts.

Detecting potential labeling errors in microarrays by data perturbation.

MOTIVATION: Classification is widely used in medical applications. However, the quality of the classifier depends critically on the accurate labeling of the training data. But for many medical applications, labeling a sample or grading a biopsy can be subjective. Existing studies confirm this phenomenon and show that even a very small number of mislabeled samples could deeply degrade the performance of the obtained classifier, particularly when the sample size is small. The problem we address in this paper is to develop a method for automatically detecting samples that are possibly mislabeled. RESULTS: We propose two algorithms, a classification-stability algorithm and a leave-one-out-error-sensitivity algorithm for detecting possibly mislabeled samples. For both algorithms, the key structure is the computation of the leave-one-out perturbation matrix. The classification-stability algorithm is based on measuring the stability of the label of a sample with respect to label changes of other samples and the version of this algorithm based on the support vector machine appears to be quite accurate for three real datasets. The suspect list produced by the version is of high quality. Furthermore, when human intervention is not available, the correction heuristic appears to be beneficial.

Clinical validation of an automated system for supporting the early diagnosis of melanoma.

BACKGROUND: Early diagnosis and surgical excision is the most effective treatment of melanoma. Well-trained dermatologists reach a high level of diagnostic accuracy with good sensitivity and specificity. Their performances increase using some technical aids as digital epiluminescence microscopy. Several studies describe the development of computerized systems whose aim is supporting dermatologists in the early diagnosis of melanoma. In many cases, the performances of those systems were comparable to those of dermatologists. However, this cannot tell us whether a system is able to support dermatologists. Actually, the computerized system might correctly recognize the same lesions that the dermatologist does, without providing them any useful advice and therefore being useless in recognizing early malignant lesions. PURPOSE: We present a novel approach to enhance dermatologists' performances in the diagnosis of early melanoma. We provide results of our evaluation of a computerized system combined with dermatologists. METHODS: A Multiple-Classifier system was developed on a set of 152 cases and combined to a group of eight dermatologists to support them by improving their sensitivity. RESULTS: The eight dermatologists have average sensitivity and specificity values of 0.83 and 0.66, respectively. The Multiple-Classifier system performs as well as the eight dermatologists (sensitivity range: 0.75-0.86; specificity range: 0.64-0.89). The combination with the dermatologists shows an average improvement of 11% (P=0.022) of dermatologists' sensitivity. CONCLUSION: Our results suggest that an automated system can be effective in supporting dermatologists because it recognizes different malignant melanomas with respect to the dermatologists.

A multiple classifier system for early melanoma diagnosis.

Melanoma is the most dangerous skin cancer and early diagnosis is the key factor in its successful treatment. Well-trained dermatologists reach a diagnosis via visual inspection, and reach sensitivity and specificity levels of about 80%. Several computerised diagnostic systems were reported in the literature using different classification algorithms. In this paper, we will illustrate a novel approach by which a suitable combination of different classifiers is used in order to improve the diagnostic performances of single classifiers. We used three different kinds of classifiers, namely linear discriminant analysis (LDA), k-nearest neighbour (k-NN) and a decision tree, the inputs of which are 38 geometric and colorimetric features automatically extracted from digital images of skin lesions. Multiple classifiers were generated by combining the diagnostic outputs of single classifiers with appropriate voting schemata. This approach was evaluated on a set of 152 digital skin images. We compared the performances of multiple classifiers (2- and 3-classifier groups) between them and with respect to single ones (1-classifier group). We further compared the classifiers' performances with those of eight dermatologists. Classifiers' performances were measured in terms of distance from the ideal classifier. Compared with 1- and 2-classifier groups, performances of 3-classifier systems were significantly higher (P<0.0005 and P<0.001, respectively). No statistically significant differences were found between the 1- and 2-classifier groups (P=0.352). While the dermatologists group showed a level of performances significantly higher than the 1-classifier systems (P<0.020), no differences were found between the multiple classifier groups and the dermatologists groups, indicating comparable performances. This work suggests that a suitable combination of different kinds of classifiers can improve the performances of an automatic diagnostic system.