Pairwise Feature Research Articles

Modeling context appearance changes for person re-identification via IPES-GCN

Most of the previous person re-identification works focus on learning discriminative features for individuals, and retrieve a query person only based on pair-wise individual feature similarities, ignoring context relationships among gallery images. Consequently, it is hard to re-identify a query person when large appearance changes occur. To address this problem, we propose the IPES-GCN model to exploit context relationships across gallery images. In the IPES-GCN, we first construct an Individual Pivot Expansion Subgraph (IPES) to enrich the context representation of each individual. By taking high-order nearest neighbors of each individual into account, we can model more positive appearance changes into the representation. Then GCN is employed to explicitly model various appearance changes contained in the IPES into a graph embedding for each enriched individual. Finally, the graph embeddings are utilized to re-rank the gallery images. Experiments on the Market1501, DukeMTMC and MSMT17 datasets show that the proposed method has strong generalization and can yield favorable results to the state-of-the-art methods.

A novel constrained non-negative matrix factorization method based on users and items pairwise relationship for recommender systems

Non-negative matrix factorization (NMF) is a famous method to learn parts-based representations of non-negative data. It has been used successfully in various applications such as information retrieval and recommender systems. Most of the current NMF methods only focus on how each decomposed matrices vector should be modeled and disregard the relation among pairwise feature vectors of users and items. In recommender systems, the relationship between users’ factors or items’ features provides better factorization. This paper proposes a constrained non-negative matrix factorization for recommender systems (CNMF-RS), which puts constraints on pairwise vectors of users and items by applying penalties using similarity. Two cost functions are proposed to generate the corresponding updating rules for finding unknown ratings. The computational complexity analysis confirmed that CNMF-RS does not raise time complexity using constraints compared with the basic NMF. Experiments on benchmark datasets indicate that the suggested update rules converge quickly and obtain outstanding results compared to other methods.

Learning multi-scale heterogenous network topologies and various pairwise attributes for drug-disease association prediction.

Identifying new therapeutic effects for the approved drugs is beneficial for effectively reducing the drug development cost and time. Most of the recent computational methods concentrate on exploiting multiple kinds of information about drugs and disease to predict the candidate associations between drugs and diseases. However, the drug and disease nodes have neighboring topologies with multiple scales, and the previous methods did not fully exploit and deeply integrate these topologies. We present a prediction method, multi-scale topology learning for drug-disease (MTRD), to integrate and learn multi-scale neighboring topologies and the attributes of a pair of drug and disease nodes. First, for multiple kinds of drug similarities, multiple drug-disease heterogenous networks are constructed respectively to integrate the similarities and associations related to drugs and diseases. Moreover, each heterogenous network has its specific topology structure, which is helpful for learning the corresponding specific topology representation. We formulate the topology embeddings for each drug node and disease node by random walking on each heterogeneous network, and the embeddings cover the neighboring topologies with different scopes. Because the multi-scale topology embeddings have context relationships, we construct Bi-directional long short-term memory-based module to encode these embeddings and their relationships and learn the neighboring topology representation. We also design the attention mechanisms at feature level and at scale level to obtain the more informative pairwise features and topology embeddings. A module based on multi-layer convolutional networks is constructed to learn the representative attributes of the drug-disease node pair according to their related similarity and association information. Comprehensive experimental results indicate that MTRD achieves the superior performance than several state-of-the-art methods for predicting drug-disease associations. MTRD also retrieves more actual drug-disease associations in the top-ranked candidates of the prediction result. Case studies on five drugs further demonstrate MTRD's ability in discovering the potential candidate diseases for the interested drugs.

Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures

Electrocardiogram (ECG) serves as the gold standard for noninvasive diagnosis of several types of heart disorders. In this study, a novel hybrid approach of deep neural network combined with linear and nonlinear features extracted from ECG and heart rate variability (HRV) is proposed for ECG multi-class classification. The proposed system enhances the ECG diagnosis performance by combining optimized deep learning features with an effective aggregation of ECG features and HRV measures using chaos theory and fragmentation analysis. The constant-Q non-stationary Gabor transform technique is employed to convert the 1-D ECG signal into 2-D image which is sent to a pre-trained convolutional neural network structure, called AlexNet. The pair-wise feature proximity algorithm is employed to select the optimal features from the AlexNet output feature vector to be concatenated with the ECG and HRV measures. The concatenated features are sent to different types of classifiers to distinguish three distinct subjects, namely congestive heart failure, arrhythmia, and normal sinus rhythm (NSR). The results reveal that the linear discriminant analysis classifier has the highest accuracy compared to the other classifiers. The proposed system is investigated with real ECG data taken from well-known databases, and the experimental results show that the proposed diagnosis system outperforms other recent state-of-the-art systems in terms of accuracy 98.75%, specificity 99.00%, sensitivity of 98.18%, and computational time 0.15 s. This demonstrates that the proposed system can be used to assist cardiologists in enhancing the accuracy of ECG diagnosis in real-time clinical setting.

Learning to Adapt to Label-Scarce Image Domain via Angular Distance-Based Feature Alignment

Most recent domain adaptation (DA) methods deal with unsupervised setup, which requires numerous target images for training. However, constructing a large-scale image set of the target domain is occasionally much harder than preparing a smaller number of image and label pairs. To cope with the problem, a great attention is recently paid to supervised domain adaptation (SDA), which takes an extremely small amount of labeled target images for training (e.g., at most three examples per category). In the SDA setup, adapting deep networks towards target domain is very challenging due to the lack of target data, and we tackle this problem as follows. Given labeled images from source and target domains, we first extract deep features and project them to hyper-spherical space via l2-normalization. Afterwards, an additive angular margin loss is embedded so that deep features of both domains are compactly grouped on the basis of shared class prototypes. To further relieve domain discrepancy, a pairwise spherical feature alignment loss is incorporated. All of our loss functions are defined in the hyper-spherical space, and the advantage of each ingredient is analyzed in the literature. Comparative evaluation results demonstrate that the proposed approach is superior to existing SDA methods, achieving 60.7% (1-shot) and 64.4% (3-shot) average accuracies for the DomainNet benchmark dataset using the ResNet-34 backbone. In addition, by applying a semi-supervised learning scheme to a network initialized by our SDA method, we achieve the state-of-the-art performance on semi-supervised domain adaptation (SSDA) as well.

Hierarchical Pseudo Labeling Based Embranchment Learning for One-Shot Person Re-Identification

In this paper, one-shot person re-identification (person re-ID) task is brought into focus, where there is only one labeled sample of each pedestrian. Existing one-shot person re-ID researches usually utilize data insufficiently or treat both labeled and pseudo-labeled data in the same way. To solve these problems, we propose a Hierarchical Pseudo Labeling strategy based on Density and Distance and an Embranchment Learning framework. The pseudo labeling strategy can fully exploit the unlabeled data information and generate accurate pseudo labels by multiple clustering based on pairwise feature distances and distribution densities hierarchically. Our Embranchment Learning framework learns data in an individualized way by feeding data with labels from different sources into distinct network branches paired with personalized loss functions. Besides, Batch Distance Loss and Global Center Loss are designed to target the characteristics of distinct input data. They are capable of distinguishing diverse categories and reducing the intra-class distance respectively. Our method outperforms the existing state-of-the-art algorithm by 36.1, 28.7 of mAP and shortens the training time 6 and 10 epochs on Market-1501 and DukeMTMC-reID respectively.

A Financial Ratio Analysis on BIST Information and Technology Index (XUTEK) Using AHP-weighted Grey Relational Analysis

The financial ratio analysis is an important issue for the stock exchange markets which have many sub-sectoral indexes. During Industry 4.0 revolution and transition, the sector of information and technology is shown as one of the sectors that have great strategic importance in the global change and development process. So, the performance of the information and technology sector provides a significant added value to the economies. In this study, multi-criteria decision-making (MCDM) approaches will be used to determine the weights of the criteria with considering the experts’ opinions used in the evaluation of the financial performance of the companies operating in the field of Information and Technology Sector of BIST Stock Index (XUTEK). In order to measure the financial performance of companies with MCDM methods, the ratios of the liquidity, operational/activity, financial structure, and profitability are obtained from the financial statements are frequently applied in the scientific literature. In the study, criteria weights were determined by using the pairwise comparison feature of the analytical hierarchy process method and expert opinions. Then, the smallest and largest values of the financial ratio values in quarterly periods in 2020 and the uncertainty formed were evaluated with the gray relational analysis method. After all; XUTEK stocks to be included in the priority investment portfolio in terms of financial performance have been determined.

A Scheme of Pairwise Feature Combinations to Improve Sentiment Classification Using Book Review Dataset

Sentiment Analysis is a Natural Language Processing (NLP) domain related to the identification or extraction of user sentiments or opinions from written language. Although the approaches to achieve the goals may vary, Machine Learning (ML) methods are gradually becoming the preferred method because of their ability to automatically draw useful insight from data regardless of their complexity. However, an important prerequisite for most ML algorithms to learn from text data is to encode them into numerical vectors. Popular approaches to this include word level representation methods TF-IDF, distributed word representations (word2vec) and distributed document representations (doc2vec). Each of these methods has demonstrated remarkable success in representing the encoded text, however we found that no method has been set to be excellence in all tasks. Motivated by this challenge, an improved scheme of pairwise fusion are proposed for sentiment classification of book reviews. In the experimental findings, Artificial Neural Networks (ANN) and Logistic Regression (LR) classifiers showed that the proposed scheme improved the performance compared to the single method vectorization method. We see that TF-IDF-word2vec performed best among other methods with a mean accuracy of 91.0% (ANN) and 92.5% (LR); showed an improvement of 0.7% and 0.2% respectively over TF-IDF which is the best single vector method. Thus, the proposed method can used as a compact alternative to the popular bag-of-n-gram models as it captures contextual information of encoded document with a less sparse data.

Deciphering Feature Effects on Decision-Making in Ordinal Regression Problems: An Explainable Ordinal Factorization Model

Ordinal regression predicts the objects’ labels that exhibit a natural ordering, which is vital to decision-making problems such as credit scoring and clinical diagnosis. In these problems, the ability to explain how the individual features and their interactions affect the decisions is as critical as model performance. Unfortunately, the existing ordinal regression models in the machine learning community aim at improving prediction accuracy rather than explore explainability. To achieve high accuracy while explaining the relationships between the features and the predictions, we propose a new method for ordinal regression problems, namely the Explainable Ordinal Factorization Model (XOFM). XOFM uses piecewise linear functions to approximate the shape functions of individual features, and renders the pairwise features interaction effects as heat-maps. The proposed XOFM captures the nonlinearity in the main effects and ensures the interaction effects’ same flexibility. Therefore, the underlying model yields comparable performance while remaining explainable by explicitly describing the main and interaction effects. To address the potential sparsity problem caused by discretizing the whole feature scale into several sub-intervals, XOFM integrates the Factorization Machines (FMs) to factorize the model parameters. Comprehensive experiments with benchmark real-world and synthetic datasets demonstrate that the proposed XOFM leads to state-of-the-art prediction performance while preserving an easy-to-understand explainability.

Bayesian feature interaction selection for factorization machines

Factorization machines are a generic supervised method for a wide range of tasks in the field of artificial intelligence, such as prediction, inference, etc., which can effectively model feature interactions. However, handling combinations of features is expensive due to the exponential growth of feature interactions with the order. In nature, not all feature interactions are equally useful for prediction. Recently, a large number of methods that perform feature interaction selection have attracted great attention because of their effectiveness at filtering out useless feature interactions. Current feature interaction selection methods suffered from the following limitations: (1) they assume that all users share the same feature interactions; and (2) they select pairwise feature interactions only. In this paper, we propose novel Bayesian variable selection methods, targeting feature interaction selection for factorization machines, which effectively reduce the number of interactions. We study personalized feature interaction selection to account for individual preferences, and further extend the model to investigate higher-order feature interaction selection on higher-order factorization machines. We provide empirical evidence for the advantages of the proposed Bayesian feature interaction selection methods using different prediction tasks.

Ultra-short echo-time magnetic resonance imaging lung segmentation with under-Annotations and domain shift.

Ultra-short echo-time (UTE) magnetic resonance imaging (MRI) provides enhanced visualization of pulmonary structural and functional abnormalities and has shown promise in phenotyping lung disease. Here, we describe the development and evaluation of a lung segmentation approach to facilitate UTE MRI methods for patient-based imaging. The proposed approach employs a k-means algorithm in kernel space for pair-wise feature clustering and imposes image domain continuous regularization, coined as continuous kernel k-means (CKKM). The high-order CKKM algorithm was simplified through upper bound relaxation and solved within an iterative continuous max-flow framework. We combined the CKKM with U-net and atlas-based approaches and comprehensively evaluated the performance on 100 images from 25 patients with asthma and bronchial pulmonary dysplasia enrolled at Robarts Research Institute (Western University, London, Canada) and Centre Hospitalier Universitaire (Sainte-Justine, Montreal, Canada). For U-net, we trained the network five times on a mixture of five different images with under-annotations and applied the model to 64 images from the two centres. We also trained a U-net on five images with full and brush annotations from one centre, and tested the model on 32 images from the other centre. For an atlas-based approach, we employed three atlas images to segment 64 target images from the two centres through straightforward atlas registration and label fusion. We applied the CKKM algorithm to the baseline U-net and atlas outputs and refined the initial segmentation through multi-volume image fusion. The integration of CKKM substantially improved baseline results and yielded, with minimal computational cost, segmentation accuracy, and precision that were greater than some state-of-the-art deep learning models and similar to experienced observer manual segmentation. This suggests that deep learning and atlas-based approaches may be utilized to segment UTE MRI datasets using relatively small training datasets with under-annotations.

A novel regularized asymmetric non-negative matrix factorization for text clustering

Non-negative matrix factorization (NMF) is a dimension reduction method that extracts semantic features from high-dimensional data. Most of the developed optimization methods for NMF only pay attention to how each feature vector of factorized matrices should be modeled, and ignore the relationships among feature vectors. Such a relationship among documents’ feature vectors provides better factorization for text clustering. This paper proposes a novel regularized asymmetric non-negative matrix factorization (RANMF) for text clustering. The proposed method puts regularized constraints on pairwise feature vectors by applying penalties using distance-based measures. We design a new cost function based on the Kullback–Leibler divergence and develop an optimization scheme to solve the cost function by suggesting novel multiplicative updating rules. The proposed method considers the documents from the same cluster closely together in the new representation space. Hence, the acquired parts-based representation has consistent cluster labeling with the original space and has a more discriminating ability. The complexity analysis showed that RANMF does not increase time cost by applying regularizers when comparing with the original NMF. Regarding experiments, the proposed RANMF converges very fast because it terminates in less than ten iterations. The complete proof of convergence and experimental results on the benchmark data sets demonstrate that the proposed multiplicative updating rules converge fast and achieve superior results compared to other algorithms.

Learning Attention-Aware Interactive Features for Fine-Grained Vegetable and Fruit Classification

Vegetable and fruit recognition can be considered as a fine-grained visual categorization (FGVC) task, which is challenging due to the large intraclass variances and small interclass variances. A mainstream direction to address the challenge is to exploit fine-grained local/global features to enhance the feature extraction and representation in the learning pipeline. However, unlike the human visual system, most of the existing FGVC methods only extract features from individual images during training. In contrast, human beings can learn discriminative features by comparing two different images. Inspired by this intuition, a recent FGVC method, named Attentive Pairwise Interaction Network (API-Net), takes as input an image pair for pairwise feature interaction and demonstrates superior performance in several open FGVC data sets. However, the accuracy of API-Net on VegFru, a domain-specific FGVC data set, is lower than expected, potentially due to the lack of spatialwise attention. Following this direction, we propose an FGVC framework named Attention-aware Interactive Features Network (AIF-Net) that refines the API-Net by integrating an attentive feature extractor into the backbone network. Specifically, we employ a region proposal network (RPN) to generate a collection of informative regions and apply a biattention module to learn global and local attentive feature maps, which are fused and fed into an interactive feature learning subnetwork. The novel neural structure is verified through extensive experiments and shows consistent performance improvement in comparison with the SOTA on the VegFru data set, demonstrating its superiority in fine-grained vegetable and fruit recognition. We also discover that a concatenation fusion operation applied in the feature extractor, along with three top-scoring regions suggested by an RPN, can effectively boost the performance.

Machine learning elastic constants of multi-component alloys

The present manuscript explores application of machine learning methods for determining elastic constants and other derived mechanical properties of multi-component alloys. A number of machine learning models, including linear regression, neural network and random forest based models, are trained and tested on a dataset of binary alloys generated using density functional theory (DFT) calculations and spanning over a large number of elemental species in the periodic table. Starting with a wide range of simple and easily accessible compositionally-averaged elemental features, a correlation-based feature selection strategy was used to systematically down-select a set of most relevant features towards the prediction of the elasticity tensor components. The true predictive performance and the associated uncertainties of the models were established by testing on unseen data and bootstrapping, respectively. A single and pair-wise feature partial dependence analysis was performed to visualize the average property trends in the multi-dimensional feature space in order to further understand the achieved predictive performance. The utility of the trained model is further demonstrated by obtaining sufficiently accurate yet highly efficient approximations for bulk modulus, Young’s modulus, shear modulus and Poisson’s ratio for alloys beyond the binary space (i.e., two-component alloys) on which the model was originally trained. More importantly, we test and validate the predictive performance of the developed model directly against the experimentally measured elastic constants of technologically relevant multi-component alloys (such as, Ni- and Ti-based alloys). Finally, utility of such a data-enabled route is demonstrated by predicting the possible range of various elastic properties for vast composition space available within the five component Ni-Cr-Fe-Mo-W alloy system in a high-throughput manner.

Fast and Robust Certifiable Estimation of the Relative Pose Between Two Calibrated Cameras

This work contributes an efficient algorithm to compute the Relative Pose problem (RPp) between calibrated cameras and certify the optimality of the solution, given a set of pair-wise feature correspondences affected by noise and probably corrupted by wrong matches. We propose a family of certifiers that is shown to increase the ratio of detected optimal solutions. This set of certifiers is incorporated into a fast essential matrix estimation pipeline that, given any initial guess for the RPp, refines it iteratively on the product space of 3D rotations and 2-sphere. In addition, this fast certifiable pipeline is integrated into a robust framework that combines Graduated Non-convexity and the Black-Rangarajan duality between robust functions and line processes. We proved through extensive experiments on synthetic and real data that the proposed framework provides a fast and robust relative pose estimation. We make the code publicly available \url{https://github.com/mergarsal/FastCertRelPose.git}.

Fused lasso for feature selection using structural information

Most state-of-the-art feature selection methods tend to overlook the structural relationship between a pair of samples associated with each feature dimension, which may encapsulate useful information for refining the performance of feature selection. Moreover, they usually consider candidate feature relevancy equivalent to selected feature relevancy, and therefore, some less relevant features may be misinterpreted as salient features. To overcome these issues, we propose a new feature selection method based on graph-based feature representations and the Fused Lasso framework in this paper. Unlike state-of-the-art feature selection approaches, our method has two main advantages. First, it can accommodate structural relationship between a pair of samples through a graph-based feature representation. Second, our method can enhance the trade-off between the relevancy of each individual feature on the one hand and its redundancy between pairwise features on the other. This is achieved through the use of a Fused Lasso framework applied to features reordered on the basis of their relevance with respect to the target feature. To effectively solve the optimization problem, an iterative algorithm is developed to identify the most discriminative features. Experiments demonstrate that our proposed approach can outperform its competitors on benchmark datasets.

Practical Demonstration of a Hybrid Model for Optimising the Reliability, Risk, and Maintenance of Rolling Stock Subsystem

Railway transport system (RTS) failures exert enormous strain on end-users and operators owing to in-service reliability failure. Despite the extensive research on improving the reliability of RTS, such as signalling, tracks, and infrastructure, few attempts have been made to develop an effective optimisation model for improving the reliability, and maintenance of rolling stock subsystems. In this paper, a new hybrid model that integrates reliability, risk, and maintenance techniques is proposed to facilitate engineering failure and asset management decision analysis. The upstream segment of the model consists of risk and reliability techniques for bottom-up and top-down failure analysis using failure mode effects and criticality analysis and fault tree analysis, respectively. The downstream segment consists of a (1) decision-making grid (DMG) for the appropriate allocation of maintenance strategies using a decision map and (2) group decision-making analysis for selecting appropriate improvement options for subsystems allocated to the worst region of the DMG map using the multi-criteria pairwise comparison features of the analytical hierarchy process. The hybrid model was illustrated through a case study for replacing an unreliable pneumatic brake unit (PBU) using operational data from a UK-based train operator where the frequency of failures and delay minutes exceeded the operator’s original target by 300% and 900%, respectively. The results indicate that the novel hybrid model can effectively analyse and identify a new PBU subsystem that meets the operator’s reliability, risk, and maintenance requirements.

Self-calibration dense bundle adjustment of multi-view Worldview-3 basic images

Very high-resolution satellite images (VHRSIs) with improved spatial resolution provide unprecedented opportunities to explore the geometric and semantic information of the world. Accordingly, to compensate for the bias of exterior orientation parameters, bundle adjustment of VHRSIs is required. Owing to the sparse points, the bundle adjustment of a few VHRSIs omits high-frequency errors and attitude jitters; therefore, the rational function model (RFM) can achieve an accuracy comparable to that of a rigorous sensor model (RSM), despite the significant difference between the RSM and RFM. In this study, we provide insight into the role of RSM in modeling attitude jitters for the Worldview-3 basic imagery product. Penalized splines were proposed to model the attitude jitters. After correcting the photogrammetric refraction using Saastamoinen’s model and light aberration, the RSM was built for agile satellites. The difference between RSM and RFM is consistent with attitude jitters, which is calculated using the penalized splines model and third-degree polyniomials. To fully explore the attitude jitters, a dense bundle adjustment was proposed to process 47 scenes of the Worldview-3 basic product imagery, which was provided by Johns Hopkins University Applied Physics Laboratory for the “Multi-View Stereo 3D Challenge.” Pairwise feature matching and feature tracking were adopted to generate over 16 000 tie-points (TPs), which were detected in an average of 9.38 images. The bundle adjustment residuals with RFM exhibited distortions similar to those of the attitude jitter. The experiments verified that the bundle adjustment with RFM introduced significant errors triggered by attitude jitters, with a maximum of over 5.0 pixels. The bundle adjustment with RSM could eliminate significant errors caused by attitude jitters and reduce the root mean square errors (RMSEs) from 1.12 pixels to 0.61 pixels. However, the basic product imagery of Worldview-3 exhibited errors in the interior orientation parameters. After analyzing the physical meanings of bias compensation, a self-calibration model was proposed. After comparing the shift compensation, affine compensation, self-calibration, temporal self-calibration, second-degree self-calibration, and second-degree polynomial models, the dense bundle adjustment with self-calibration was suggested because it could compensate for errors in the interior orientation parameters (IOPs) and obtain an accuracy similar to that of high-degree models. Thus, a self-calibration dense bundle adjustment with RSM compensates for the attitude jitters and errors in the IOPs, and achieves a remarkable accuracy of 0.49 pixels in the image coordinates.

Intelligent fault diagnosis method for common rail injectors based on hierarchical weighted permutation entropy and pair-wise feature proximity feature selection

It is of great significance for intelligent manufacturing to study diagnosis methods to realize the diagnosis of mechanical equipment faults. Multiscale weighted permutation entropy is an effective method recently proposed to measure the complexity and dynamic changes of dynamic systems. To solve the shortcoming of multiscale weighted permutation entropy that does not consider high-frequency components, this article proposes hierarchical weighted permutation entropy, which can comprehensively and accurately reflect the low-frequency and high-frequency information of the time series. The simulation signal verifies the effectiveness and superiority of hierarchical weighted permutation entropy. Then, a novel intelligent fault diagnosis method for common rail injectors based on hierarchical weighted permutation entropy and pair-wise feature proximity is proposed. Finally, the proposed method is applied to the common rail injector fault data, and the results verify the effectiveness of the proposed method. Compared with other methods, this method has a higher fault recognition rate and stronger robustness.

Malignant Pleural Mesothelioma Interactome with 364 Novel Protein-Protein Interactions.

Simple SummaryInternal organs like the heart and lungs, and body cavities like the thoracic and abdominal cavities, are covered by a thin, slippery layer called the mesothelium. Malignant pleural mesothelioma (MPM) is an aggressive cancer of the lining of the lung, where genetics and asbestos exposure play a role. It is not diagnosable until it becomes invasive, offering only a short survival time to the patient. To help understand the role of the genes that relate to this disease most of which are poorly understood, we constructed the ‘MPM interactome’, including in it the protein-protein interactions that we predicted computationally and those that are previously known in the literature. Five novel protein-protein interactions (PPIs) were tested and validated experimentally. 85.65% of the interactome is supported by genetic variant, transcriptomic, and proteomic evidence. Comparative transcriptome analysis revealed 5 repurposable drugs targeting the interactome proteins. We make the interactome available on a freely accessible web application, Wiki-MPM.Malignant pleural mesothelioma (MPM) is an aggressive cancer affecting the outer lining of the lung, with a median survival of less than one year. We constructed an ‘MPM interactome’ with over 300 computationally predicted protein-protein interactions (PPIs) and over 2400 known PPIs of 62 literature-curated genes whose activity affects MPM. Known PPIs of the 62 MPM associated genes were derived from Biological General Repository for Interaction Datasets (BioGRID) and Human Protein Reference Database (HPRD). Novel PPIs were predicted by applying the HiPPIP algorithm, which computes features of protein pairs such as cellular localization, molecular function, biological process membership, genomic location of the gene, and gene expression in microarray experiments, and classifies the pairwise features as interacting or non-interacting based on a random forest model. We validated five novel predicted PPIs experimentally. The interactome is significantly enriched with genes differentially ex-pressed in MPM tumors compared with normal pleura and with other thoracic tumors, genes whose high expression has been correlated with unfavorable prognosis in lung cancer, genes differentially expressed on crocidolite exposure, and exosome-derived proteins identified from malignant mesothelioma cell lines. 28 of the interactors of MPM proteins are targets of 147 U.S. Food and Drug Administration (FDA)-approved drugs. By comparing disease-associated versus drug-induced differential expression profiles, we identified five potentially repurposable drugs, namely cabazitaxel, primaquine, pyrimethamine, trimethoprim and gliclazide. Preclinical studies may be con-ducted in vitro to validate these computational results. Interactome analysis of disease-associated genes is a powerful approach with high translational impact. It shows how MPM-associated genes identified by various high throughput studies are functionally linked, leading to clinically translatable results such as repurposed drugs. The PPIs are made available on a webserver with interactive user interface, visualization and advanced search capabilities.