Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction.

Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, natural language processing based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

Multicenter observational study evaluating the impact of platelet transport bags on product wastage.

BACKGROUND: Platelets are the most commonly discarded blood product in Canada, with the most common cause of in-date product loss being improper storage. Transport containers to maintain temperature and extend acceptable return time may represent a method to reduce wastage. The objective of this study was to evaluate the impact of a validated Platelet Transport Bag (PTB) on platelet wastage. STUDY DESIGN AND METHODS: Thirty-six hospitals with the highest platelet discards were invited to participate in a before-after observational study. Hospitals were instructed to utilize a validated 4-h PTB for clinical situations where immediate transfusion was not planned. Five hospitals audited in-date platelet discards from July 2018 to November 2019 to characterize wastage causes. In-date platelet discard data 12 months before and after the start date for each site were analyzed to determine changes in wastage. RESULTS: Of 36 hospital sites, 16 agreed to participate. Pre- and postdiscards were 277 and 301, respectively, for all sites combined. There were no significant before-after change in wastage rate (+0.05%, p = .51). Fifty discards were included in the detailed audit; the most common reasons were return to the blood bank after more than 60 min outside a PTB (n = 17, 34%) and return in a red cell cooler (n = 10, 20%). CONCLUSION: Implementation of PTB did not improve wastage. Common causes of in-date discards were return after 1 h outside of a PTB and placement in a red cell cooler in error. Further research is required to investigate potential strategies to mitigate in-date platelet wastage.

Utilizing longitudinal microbiome taxonomic profiles to predict food allergy via Long Short-Term Memory networks.

Food allergy is usually difficult to diagnose in early life, and the inability to diagnose patients with atopic diseases at an early age may lead to severe complications. Numerous studies have suggested an association between the infant gut microbiome and development of allergy. In this work, we investigated the capacity of Long Short-Term Memory (LSTM) networks to predict food allergies in early life (0-3 years) from subjects' longitudinal gut microbiome profiles. Using the DIABIMMUNE dataset, we show an increase in predictive power using our model compared to Hidden Markov Model, Multi-Layer Perceptron Neural Network, Support Vector Machine, Random Forest, and LASSO regression. We further evaluated whether the training of LSTM networks benefits from reduced representations of microbial features. We considered sparse autoencoder for extraction of potential latent representations in addition to standard feature selection procedures based on Minimum Redundancy Maximum Relevance (mRMR) and variance prior to the training of LSTM networks. The comprehensive evaluation reveals that LSTM networks with the mRMR selected features achieve significantly better performance compared to the other tested machine learning models.

Electronic patient identification for sample labeling reduces wrong blood in tube errors.

BACKGROUND: Wrong blood in tube (WBIT) errors are a preventable cause of ABO-mismatched RBC transfusions. Electronic patient identification systems (e.g., scanning a patient's wristband barcode before pretransfusion sample collection) are thought to reduce WBIT errors, but the effectiveness of these systems is unclear. STUDY DESIGN AND METHODS: Part 1: Using retrospective data, we compared pretransfusion sample WBIT rates at hospitals using manual patient identification (n = 16 sites; >1.6 million samples) with WBIT rates at hospitals using electronic patient identification for some or all sample collections (n = 4 sites; >0.5 million samples). Also, we compared WBIT rates after implementation of electronic patient identification with preimplementation WBIT rates. Causes and frequencies of WBIT errors were evaluated at each site. Part 2: Transfusion service laboratories (n = 18) prospectively typed mislabeled (rejected) samples (n = 2844) to determine WBIT rates among samples with minor labeling errors. RESULTS: Part 1: The overall unadjusted WBIT rate at sites using manual patient identification was 1:10,110 versus 1:35,806 for sites using electronic identification (p < 0.0001). Correcting for repeat samples and silent WBIT errors yielded overall adjusted WBIT rates of 1:3046 for sites using manual identification and 1:14,606 for sites using electronic identification (p < 0.0001), with wide variation among individual sites. Part 2: The unadjusted WBIT rate among mislabeled (rejected) samples was 1:71 (adjusted WBIT rate, 1:28). CONCLUSION: In this study, using electronic patient identification at the time of pretransfusion sample collection was associated with approximately fivefold fewer WBIT errors compared with using manual patient identification. WBIT rates were high among mislabeled (rejected) samples, confirming that rejecting samples with even minor labeling errors helps mitigate the risk of ABO-incompatible transfusions.

Constrained Active Learning for Anchor Link Prediction Across Multiple Heterogeneous Social Networks.

Nowadays, people are usually involved in multiple heterogeneous social networks simultaneously. Discovering the anchor links between the accounts owned by the same users across different social networks is crucial for many important inter-network applications, e.g., cross-network link transfer and cross-network recommendation. Many different supervised models have been proposed to predict anchor links so far, but they are effective only when the labeled anchor links are abundant. However, in real scenarios, such a requirement can hardly be met and most anchor links are unlabeled, since manually labeling the inter-network anchor links is quite costly and tedious. To overcome such a problem and utilize the numerous unlabeled anchor links in model building, in this paper, we introduce the active learning based anchor link prediction problem. Different from the traditional active learning problems, due to the one-to-one constraint on anchor links, if an unlabeled anchor link a = ( u , v ) is identified as positive (i.e., existing), all the other unlabeled anchor links incident to account u or account v will be negative (i.e., non-existing) automatically. Viewed in such a perspective, asking for the labels of potential positive anchor links in the unlabeled set will be rewarding in the active anchor link prediction problem. Various novel anchor link information gain measures are defined in this paper, based on which several constraint active anchor link prediction methods are introduced. Extensive experiments have been done on real-world social network datasets to compare the performance of these methods with state-of-art anchor link prediction methods. The experimental results show that the proposed Mean-entropy-based Constrained Active Learning (MC) method can outperform other methods with significant advantages.

Aggregator: a machine learning approach to identifying MEDLINE articles that derive from the same underlying clinical trial.

OBJECTIVE: It is important to identify separate publications that report outcomes from the same underlying clinical trial, in order to avoid over-counting these as independent pieces of evidence. METHODS: We created positive and negative training sets (comprised of pairs of articles reporting on the same condition and intervention) that were, or were not, linked to the same clinicaltrials.gov trial registry number. Features were extracted from MEDLINE and PubMed metadata; pairwise similarity scores were modeled using logistic regression. RESULTS: Article pairs from the same trial were identified with high accuracy (F1 score=0.843). We also created a clustering tool, Aggregator, that takes as input a PubMed user query for RCTs on a given topic, and returns article clusters predicted to arise from the same clinical trial. DISCUSSION: Although painstaking examination of full-text may be needed to be conclusive, metadata are surprisingly accurate in predicting when two articles derive from the same underlying clinical trial.

Nuggets: findings shared in multiple clinical case reports.

OBJECTIVE: The researchers assessed prevalence in the clinical case report literature of multiple reports independently reporting the same (or nearly the same) main finding. METHODS: Results from forty-five PubMed queries were examined for incidence and features of main findings ("nuggets") shared in at least four case reports. RESULTS: The authors found that nuggets are surprisingly prevalent and large in the case report literature, the largest found so far was reported in seventeen articles. In most cases, the main findings of case reports were evident from examining titles alone. CONCLUSIONS: Our curated examples should serve as gold standards for developing specific automated methods for finding nuggets. Nuggets potentially enable finding-based (instead of topic-based) information retrieval.

G-Bean: an ontology-graph based web tool for biomedical literature retrieval.

BACKGROUND: Currently, most people use NCBI's PubMed to search the MEDLINE database, an important bibliographical information source for life science and biomedical information. However, PubMed has some drawbacks that make it difficult to find relevant publications pertaining to users' individual intentions, especially for non-expert users. To ameliorate the disadvantages of PubMed, we developed G-Bean, a graph based biomedical search engine, to search biomedical articles in MEDLINE database more efficiently. METHODS: G-Bean addresses PubMed's limitations with three innovations: (1) Parallel document index creation: a multithreaded index creation strategy is employed to generate the document index for G-Bean in parallel; (2) Ontology-graph based query expansion: an ontology graph is constructed by merging four major UMLS (Version 2013AA) vocabularies, MeSH, SNOMEDCT, CSP and AOD, to cover all concepts in National Library of Medicine (NLM) database; a Personalized PageRank algorithm is used to compute concept relevance in this ontology graph and the Term Frequency - Inverse Document Frequency (TF-IDF) weighting scheme is used to re-rank the concepts. The top 500 ranked concepts are selected for expanding the initial query to retrieve more accurate and relevant information; (3) Retrieval and re-ranking of documents based on user's search intention: after the user selects any article from the existing search results, G-Bean analyzes user's selections to determine his/her true search intention and then uses more relevant and more specific terms to retrieve additional related articles. The new articles are presented to the user in the order of their relevance to the already selected articles. RESULTS: Performance evaluation with 106 OHSUMED benchmark queries shows that G-Bean returns more relevant results than PubMed does when using these queries to search the MEDLINE database. PubMed could not even return any search result for some OHSUMED queries because it failed to form the appropriate Boolean query statement automatically from the natural language query strings. G-Bean is available at http://bioinformatics.clemson.edu/G-Bean/index.php. CONCLUSIONS: G-Bean addresses PubMed's limitations with ontology-graph based query expansion, automatic document indexing, and user search intention discovery. It shows significant advantages in finding relevant articles from the MEDLINE database to meet the information need of the user.

Provable Unrestricted Adversarial Training without Compromise with Generalizability.

Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the existing AT methods still suffer from two challenges. First, they are unable to handle unrestricted adversarial examples (UAEs), which are built from scratch, as opposed to restricted adversarial examples (RAEs), which are created by adding perturbations bound by an lp norm to observed examples. Second, the existing AT methods often achieve adversarial robustness at the expense of standard generalizability (i.e., the accuracy on natural examples) because they make a tradeoff between them. To overcome these challenges, we propose a unique viewpoint that understands UAEs as imperceptibly perturbed unobserved examples. Also, we find that the tradeoff results from the separation of the distributions of adversarial examples and natural examples. Based on these ideas, we propose a novel AT approach called Provable Unrestricted Adversarial Training (PUAT), which can provide a target classifier with comprehensive adversarial robustness against both UAE and RAE, and simultaneously improve its standard generalizability. Particularly, PUAT utilizes partially labeled data to achieve effective UAE generation by accurately capturing the natural data distribution through a novel augmented triple-GAN. At the same time, PUAT extends the traditional AT by introducing the supervised loss of the target classifier into the adversarial loss and achieves the alignment between the UAE distribution, the natural data distribution, and the distribution learned by the classifier, with the collaboration of the augmented triple-GAN. Finally, the solid theoretical analysis and extensive experiments conducted on widely-used benchmarks demonstrate the superiority of PUAT.

Towards complex dynamic physics system simulation with graph neural ordinary equations.

The great learning ability of deep learning facilitates us to comprehend the real physical world, making learning to simulate complicated particle systems a promising endeavour both in academia and industry. However, the complex laws of the physical world pose significant challenges to the learning based simulations, such as the varying spatial dependencies between interacting particles and varying temporal dependencies between particle system states in different time stamps, which dominate particles' interacting behavior and the physical systems' evolution patterns. Existing learning based methods fail to fully account for the complexities, making them unable to yield satisfactory simulations. To better comprehend the complex physical laws, we propose a novel model - Graph Networks with Spatial-Temporal neural Ordinary Differential Equations (GNSTODE) - that characterizes the varying spatial and temporal dependencies in particle systems using a united end-to-end framework. Through training with real-world particle-particle interaction observations, GNSTODE can simulate any possible particle systems with high precisions. We empirically evaluate GNSTODE's simulation performance on two real-world particle systems, Gravity and Coulomb, with varying levels of spatial and temporal dependencies. The results show that GNSTODE yields better simulations than state-of-the-art methods, showing that GNSTODE can serve as an effective tool for particle simulation in real-world applications. Our code is made available at https://github.com/Guangsi-Shi/AI-for-physics-GNSTODE.

Automated Quality Evaluation of Large-Scale Benchmark Datasets for Vision-Language Tasks.

Large-scale benchmark datasets are crucial in advancing research within the computer science communities. They enable the development of more sophisticated AI models and serve as "golden" benchmarks for evaluating their performance. Thus, ensuring the quality of these datasets is of utmost importance for academic research and the progress of AI systems. For the emerging vision-language tasks, some datasets have been created and frequently used, such as Flickr30k, COCO, and NoCaps, which typically contain a large number of images paired with their ground-truth textual descriptions. In this paper, an automatic method is proposed to assess the quality of large-scale benchmark datasets designed for vision-language tasks. In particular, a new cross-modal matching model is developed, which is capable of automatically scoring the textual descriptions of visual images. Subsequently, this model is employed to evaluate the quality of vision-language datasets by automatically assigning a score to each 'ground-truth' description for every image picture. With a good agreement between manual and automated scoring results on the datasets, our findings reveal significant disparities in the quality of the ground-truth descriptions included in the benchmark datasets. Even more surprising, it is evident that a small portion of the descriptions are unsuitable for serving as reliable ground-truth references. These discoveries emphasize the need for careful utilization of these publicly accessible benchmark databases.

MultiFair: Model Fairness With Multiple Sensitive Attributes.

While existing fairness interventions show promise in mitigating biased predictions, most studies concentrate on single-attribute protections. Although a few methods consider multiple attributes, they either require additional constraints or prediction heads, incurring high computational overhead or jeopardizing the stability of the training process. More critically, they consider per-attribute protection approaches, raising concerns about fairness gerrymandering where certain attribute combinations remain unfair. This work aims to construct a neutral domain containing fused information across all subgroups and attributes. It delivers fair predictions as the fused input contains neutralized information for all considered attributes. Specifically, we adopt mixup operations to generate samples with fused information. However, our experiments reveal that directly adopting the operations leads to degraded prediction results. The excessive mixup operations result in unrecognizable training data. To this end, we design three distinct mixup schemes that balance information fusion across attributes while retaining distinct visual features critical for training valid models. Extensive experiments with multiple datasets and up to eight sensitive attributes demonstrate that the proposed MultiFair method can deliver fairness protections for multiple attributes while maintaining valid prediction results.

Deep Clustering: A Comprehensive Survey.

Cluster analysis plays an indispensable role in machine learning and data mining. Learning a good data representation is crucial for clustering algorithms. Recently, deep clustering (DC), which can learn clustering-friendly representations using deep neural networks (DNNs), has been broadly applied in a wide range of clustering tasks. Existing surveys for DC mainly focus on the single-view fields and the network architectures, ignoring the complex application scenarios of clustering. To address this issue, in this article, we provide a comprehensive survey for DC in views of data sources. With different data sources, we systematically distinguish the clustering methods in terms of methodology, prior knowledge, and architecture. Concretely, DC methods are introduced according to four categories, i.e., traditional single-view DC, semi-supervised DC, deep multiview clustering (MVC), and deep transfer clustering. Finally, we discuss the open challenges and potential future opportunities in different fields of DC.

Reinforced GNNs for Multiple Instance Learning.

Multiple instance learning (MIL) trains models from bags of instances, where each bag contains multiple instances, and only bag-level labels are available for supervision. The application of graph neural networks (GNNs) in capturing intrabag topology effectively improves MIL. Existing GNNs usually require filtering low-confidence edges among instances and adapting graph neural architectures to new bag structures. However, such asynchronous adjustments to structure and architecture are tedious and ignore their correlations. To tackle these issues, we propose a reinforced GNN framework for MIL (RGMIL), pioneering the exploitation of multiagent deep reinforcement learning (MADRL) in MIL tasks. MADRL enables the flexible definition or extension of factors that influence bag graphs or GNNs and provides synchronous control over them. Moreover, MADRL explores structure-to-architecture correlations while automating adjustments. Experimental results on multiple MIL datasets demonstrate that RGMIL achieves the best performance with excellent explainability. The code and data are available at https://github.com/RingBDStack/RGMIL.

Motif-Based Contrastive Learning for Community Detection.

Community detection has become a prominent task in complex network analysis. However, most of the existing methods for community detection only focus on the lower order structure at the level of individual nodes and edges and ignore the higher order connectivity patterns that characterize the fundamental building blocks within the network. In recent years, researchers have shown interest in motifs and their role in network analysis. However, most of the existing higher order approaches are based on shallow methods, failing to capture the intricate nonlinear relationships between nodes. In order to better fuse higher order and lower order structural information, a novel deep learning framework called motif-based contrastive learning for community detection (MotifCC) is proposed. First, a higher order network is constructed based on motifs. Subnetworks are then obtained by removing isolated nodes, addressing the fragmentation issue in the higher order network. Next, the concept of contrastive learning is applied to effectively fuse various kinds of information from nodes, edges, and higher order and lower order structures. This aims to maximize the similarity of corresponding node information, while distinguishing different nodes and different communities. Finally, based on the community structure of subnetworks, the community labels of all nodes are obtained by using the idea of label propagation. Extensive experiments on real-world datasets validate the effectiveness of MotifCC.

An R package for analyzing and modeling ranking data.

BACKGROUND: In medical informatics, psychology, market research and many other fields, researchers often need to analyze and model ranking data. However, there is no statistical software that provides tools for the comprehensive analysis of ranking data. Here, we present pmr, an R package for analyzing and modeling ranking data with a bundle of tools. The pmr package enables descriptive statistics (mean rank, pairwise frequencies, and marginal matrix), Analytic Hierarchy Process models (with Saaty's and Koczkodaj's inconsistencies), probability models (Luce model, distance-based model, and rank-ordered logit model), and the visualization of ranking data with multidimensional preference analysis. RESULTS: Examples of the use of package pmr are given using a real ranking dataset from medical informatics, in which 566 Hong Kong physicians ranked the top five incentives (1: competitive pressures; 2: increased savings; 3: government regulation; 4: improved efficiency; 5: improved quality care; 6: patient demand; 7: financial incentives) to the computerization of clinical practice. The mean rank showed that item 4 is the most preferred item and item 3 is the least preferred item, and significance difference was found between physicians' preferences with respect to their monthly income. A multidimensional preference analysis identified two dimensions that explain 42% of the total variance. The first can be interpreted as the overall preference of the seven items (labeled as "internal/external"), and the second dimension can be interpreted as their overall variance of (labeled as "push/pull factors"). Various statistical models were fitted, and the best were found to be weighted distance-based models with Spearman's footrule distance. CONCLUSIONS: In this paper, we presented the R package pmr, the first package for analyzing and modeling ranking data. The package provides insight to users through descriptive statistics of ranking data. Users can also visualize ranking data by applying a thought multidimensional preference analysis. Various probability models for ranking data are also included, allowing users to choose that which is most suitable to their specific situations.

Higher Order Connection Enhanced Community Detection in Adversarial Multiview Networks.

Community detection in multiview networks has drawn an increasing amount of attention in recent years. Many approaches have been developed from different perspectives. Despite the success, the problem of community detection in adversarial multiview networks remains largely unsolved. An adversarial multiview network is a multiview network that suffers an adversarial attack on community detection in which the attackers may deliberately remove some critical edges so as to hide the underlying community structure, leading to the performance degeneration of the existing approaches. To address this problem, we propose a novel approach, called higher order connection enhanced multiview modularity (HCEMM). The main idea lies in enhancing the intracommunity connection of each view by means of utilizing the higher order connection structure. The first step is to discover the view-specific higher order Microcommunities (VHM-communities) from the higher order connection structure. Then, for each view of the original multiview network, additional edges are added to make the nodes in each of its VHM-communities fully connected like a clique, by which the intracommunity connection of the multiview network can be enhanced. Therefore, the proposed approach is able to discover the underlying community structure in a multiview network while recovering the missing edges. Extensive experiments conducted on 16 real-world datasets confirm the effectiveness of the proposed approach.

Balancing Learning Model Privacy, Fairness, and Accuracy With Early Stopping Criteria.

As deep learning models mature, one of the most prescient questions we face is: what is the ideal tradeoff between accuracy, fairness, and privacy (AFP)? Unfortunately, both the privacy and the fairness of a model come at the cost of its accuracy. Hence, an efficient and effective means of fine-tuning the balance between this trinity of needs is critical. Motivated by some curious observations in privacy-accuracy tradeoffs with differentially private stochastic gradient descent (DP-SGD), where fair models sometimes result, we conjecture that fairness might be better managed as an indirect byproduct of this process. Hence, we conduct a series of analyses, both theoretical and empirical, on the impacts of implementing DP-SGD in deep neural network models through gradient clipping and noise addition. The results show that, in deep learning, the number of training epochs is central to striking a balance between AFP because DP-SGD makes the training less stable, providing the possibility of model updates at a low discrimination level without much loss in accuracy. Based on this observation, we designed two different early stopping criteria to help analysts choose the optimal epoch at which to stop training a model so as to achieve their ideal tradeoff. Extensive experiments show that our methods can achieve an ideal balance between AFP.

Model-Based Self-Advising for Multi-Agent Learning.

In multiagent learning, one of the main ways to improve learning performance is to ask for advice from another agent. Contemporary advising methods share a common limitation that a teacher agent can only advise a student agent if the teacher has experience with an identical state. However, in highly complex learning scenarios, such as autonomous driving, it is rare for two agents to experience exactly the same state, which makes the advice less of a learning aid and more of a one-time instruction. In these scenarios, with contemporary methods, agents do not really help each other learn, and the main outcome of their back and forth requests for advice is an exorbitant communications' overhead. In human interactions, teachers are often asked for advice on what to do in situations that students are personally unfamiliar with. In these, we generally draw from similar experiences to formulate advice. This inspired us to provide agents with the same ability when asked for advice on an unfamiliar state. Hence, we propose a model-based self-advising method that allows agents to train a model based on states similar to the state in question to inform its response. As a result, the advice given can not only be used to resolve the current dilemma but also many other similar situations that the student may come across in the future via self-advising. Compared with contemporary methods, our method brings a significant improvement in learning performance with much lower communication overheads.

Multiview Clustering via Proximity Learning in Latent Representation Space.

Most existing multiview clustering methods are based on the original feature space. However, the feature redundancy and noise in the original feature space limit their clustering performance. Aiming at addressing this problem, some multiview clustering methods learn the latent data representation linearly, while performance may decline if the relation between the latent data representation and the original data is nonlinear. The other methods which nonlinearly learn the latent data representation usually conduct the latent representation learning and clustering separately, resulting in that the latent data representation might be not well adapted to clustering. Furthermore, none of them model the intercluster relation and intracluster correlation of data points, which limits the quality of the learned latent data representation and therefore influences the clustering performance. To solve these problems, this article proposes a novel multiview clustering method via proximity learning in latent representation space, named multiview latent proximity learning (MLPL). For one thing, MLPL learns the latent data representation in a nonlinear manner which takes the intercluster relation and intracluster correlation into consideration simultaneously. For another, through conducting the latent representation learning and consensus proximity learning simultaneously, MLPL learns a consensus proximity matrix with k connected components to output the clustering result directly. Extensive experiments are conducted on seven real-world datasets to demonstrate the effectiveness and superiority of the MLPL method compared with the state-of-the-art multiview clustering methods.