Playing Extensive Games with Learning of Opponent's Cognition.

Decision-making is a basic component of agents' (e.g., intelligent sensors) behaviors, in which one's cognition plays a crucial role in the process and outcome. Extensive games, a class of interactive decision-making scenarios, have been studied in diverse fields. Recently, a model of extensive games was proposed in which agent cognition of the structure of the underlying game and the quality of the game situations are encoded by artificial neural networks. This model refines the classic model of extensive games, and the corresponding equilibrium concept-cognitive perfect equilibrium (CPE)-differs from the classic subgame perfect equilibrium, since CPE takes agent cognition into consideration. However, this model neglects the consideration that game-playing processes are greatly affected by agents' cognition of their opponents. To this end, in this work, we go one step further by proposing a framework in which agents' cognition of their opponents is incorporated. A method is presented for evaluating opponents' cognition about the game being played, and thus, an algorithm designed for playing such games is analyzed. The resulting equilibrium concept is defined as adversarial cognition equilibrium (ACE). By means of a running example, we demonstrate that the ACE is more realistic than the CPE, since it involves learning about opponents' cognition. Further results are presented regarding the computational complexity, soundness, and completeness of the game-solving algorithm and the existence of the equilibrium solution. This model suggests the possibility of enhancing an agent's strategic ability by evaluating opponents' cognition.

Temporal attention networks for biomedical hypothesis generation.

OBJECTIVES: Hypothesis Generation (HG) is a task that aims to uncover hidden associations between disjoint scientific terms, which influences innovations in prevention, treatment, and overall public health. Several recent studies strive to use Recurrent Neural Network (RNN) to learn evolutional embeddings for HG. However, the complex spatiotemporal dependencies of term-pair relations will be difficult to depict due to the inherent recurrent structure. This paper aims to accurately model the temporal evolution of term-pair relations using only attention mechanisms, for capturing crucial information on inferring the future connectivities. METHODS: This paper proposes a Temporal Attention Networks (TAN) to produce powerful spatiotemporal embeddings for Biomedical Hypothesis Generation. Specifically, we formulate HG problem as a future connectivity prediction task in a temporal attributed graph. Our TAN develops a Temporal Spatial Attention Module (TSAM) to establish temporal dependencies of node-pair (term-pair) embeddings between any two time-steps for smoothing spatiotemporal node-pair embeddings. Meanwhile, a Temporal Difference Attention Module (TDAM) is proposed to sharpen temporal differences of spatiotemporal embeddings for highlighting the historical changes of node-pair relations. As such, TAN can adaptively calibrate spatiotemporal embeddings by considering both continuity and difference of node-pair embeddings. RESULTS: Three real-world biomedical term relationship datasets are constructed from PubMed papers. TAN significantly outperforms the best baseline with 12.03%, 4.59 and 2.34% Micro-F1 Score improvement in Immunotherapy, Virology and Neurology, respectively. Extensive experiments demonstrate that TAN can model complex spatiotemporal dependencies of term-pairs for explicitly capturing the temporal evolution of relation, significantly outperforming existing state-of-the-art methods. CONCLUSION: We proposed a novel TAN to learn spatiotemporal embeddings based on pure attention mechanisms for HG. TAN learns the evolution of relationships by modeling both the continuity and difference of temporal term-pair embeddings. The important spatiotemporal dependencies of term-pair relations are extracted based solely on attention mechanism for generating hypotheses.

Learning temporal difference embeddings for biomedical hypothesis generation.

MOTIVATION: Hypothesis generation (HG) refers to the discovery of meaningful implicit connections between disjoint scientific terms, which is of great significance for drug discovery, prediction of drug side effects and precision treatment. More recently, a few initial studies attempt to model the dynamic meaning of the terms or term pairs for HG. However, most existing methods still fail to accurately capture and utilize the dynamic evolution of scientific term relations. RESULTS: This article proposes a novel temporal difference embedding (TDE) learning framework to model the temporal difference information evolution of term-pair relations for predicting future interactions. Specifically, the HG problem is formulated as a future connectivity prediction task on a temporal sequence of a dynamic attributed graph. Our approach models both the local neighbor changes of the term-pairs and the changes of the global graph structure over time, learning local and global TDE of node-pairs, respectively. Future term-pair relations can be inferred in a recurrent network based on the local and global TDE. Experiments on three real-world biomedical term relationship datasets show the effectiveness and superiority of the proposed approach. AVAILABILITY AND IMPLEMENTATION: The data and source codes related to TDE are publicly available at https://github.com/Huiweizhou/TDE. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Improving neural protein-protein interaction extraction with knowledge selection.

Protein-protein interaction (PPI) extraction from published scientific literature provides additional support for precision medicine efforts. Meanwhile, knowledge bases (KBs) contain huge amounts of structured information of protein entities and their relations, which can be encoded in entity and relation embeddings to help PPI extraction. However, the prior knowledge of protein-protein pairs must be selectively used so that it is suitable for different contexts. This paper proposes a Knowledge Selection Model (KSM) to fuse the selected prior knowledge and context information for PPI extraction. Firstly, two Transformers encode the context sequence of a protein pair according to each protein embedding, respectively. Then, the two outputs are fed to a mutual attention to capture the important context features towards the protein pair. Next, the context features are used to distill the relation embedding by a knowledge selector. Finally, the selected relation embedding and the context features are concatenated for PPI extraction. Experiments on the BioCreative VI PPI dataset show that KSM achieves a new state-of-the-art performance (38.08 % F1-score) by adding knowledge selection.

The Robust Classification Model Based on Combinatorial Features.

Analyzing the disease data from the view of combinatorial features may better characterize the disease phenotype. In this study, a novel method is proposed to construct feature combinations and a classification model (CFC-CM) by mining key feature relationships. CFC-CM iteratively tests for differences in the feature relationship between different groups. To do this, it uses a modified $k$k-top-scoring pair (M-$k$k-TSP) algorithm and then selects the most discriminative feature pairs in the current feature set to infer the combinatorial features and build the classification model. Compared with support vector machines, random forests, least absolute shrinkage and selection operator, elastic net, and M-$k$k-TSP, the superior performance of CFC-CM on nine public gene expression datasets validates its potential for more precise identification of complex diseases. Subsequently, CFC-CM was applied to two metabolomics datasets, it obtained accuracy rates of $88.73\pm 2.06\%$88.73±2.06% and $79.11\pm 2.70\%$79.11±2.70% in distinguishing between hepatocellular carcinoma and hepatic cirrhosis groups and between acute kidney injury (AKI) and non-AKI samples, results superior to those of the other five methods. In summary, the better results of CFC-CM show that in contrast to molecules and combinations constituted by just two features, the combinations inferred by appropriate number of features could better identify the complex diseases.

A Computational Method of Defining Potential Biomarkers based on Differential Sub-Networks.

Analyzing omics data from a network-based perspective can facilitate biomarker discovery. To improve disease diagnosis and identify prospective information indicating the onset of complex disease, a computational method for identifying potential biomarkers based on differential sub-networks (PB-DSN) is developed. In PB-DSN, Pearson correlation coefficient (PCC) is used to measure the relationship between feature ratios and to infer potential networks. A differential sub-network is extracted to identify crucial information for discriminating different groups and indicating the emergence of complex diseases. Subsequently, PB-DSN defines potential biomarkers based on the topological analysis of these differential sub-networks. In this study, PB-DSN is applied to handle a static genomics dataset of small, round blue cell tumors and a time-series metabolomics dataset of hepatocellular carcinoma. PB-DSN is compared with support vector machine-recursive feature elimination, multivariate empirical Bayes statistics, analyzing time-series data based on dynamic networks, molecular networks based on PCC, PinnacleZ, graph-based iterative group analysis, KeyPathwayMiner and BioNet. The better performance of PB-DSN not only demonstrates its effectiveness for the identification of discriminative features that facilitate disease classification, but also shows its potential for the identification of warning signals.

Proton magnetic resonance spectroscopy in the evaluation of infiltration zone of cerebral alveolar echinococcosis.

BACKGROUND: Cerebral alveolar echinococcosis (CAE) grows infiltratively like a malignant tumor, causing great harm to the human body. It is possible to display mass lesions of CAE using various imaging systems, but regarding the infiltrating proliferation active regions, it is difficult to evaluate its actual range using conventional magnetic resonance imaging (cMRI). This research focused on proton magnetic resonance spectroscopy ((1)HMRS) techniques to find the mass and infiltration zone of CAE. We explored the marginal zone (MZ) of CAE nearly close to the actual infiltrating scope, to provide reliable images for clinical purposes, to overcome shortcomings of cMRI, to formulate beneficial clinical surgical plans and assess prognosis. METHODS: Between September 2005 and May 2011, 15 patients who were suffering from CAE (36 effective lesions altogether) were examined by (1)HMRS at the first affiliated hospital of Xinjiang Medical University. Multi-voxel (1)HMRS was acquired with a 1.5T MRI scanner. Concentrations and the ratios of the metabolites of CAE were calculated. Furthermore, changes in the concentrations of the metabolites containing N-acetyl-aspartic-acid (NAA), choline (Cho), creatine (Cr), lipids and lactate (Lip + Lac) and the ratios of Cho/Cr, NAA/Cr, (Lip + Lac) /Cr were compared in the substantial region, 0 - 10 mm MZ, and 11 - 20 mm MZ of the infiltration zone, as well as the corresponding contralateral part of the normal brain parenchyma area (control group). RESULTS: In this study, the ratios of Cho/Cr in the substantial region, 0 - 10 mm MZ of infiltration zone and the control group were 1.78 ± 0.70, 1.90 ± 0.54, and 0.78 ± 0.15, respectively; the ratios of NAA/Cr were 1.60 ± 0.20, 1.80 ± 0.42, 2.24 ± 0.86, respectively; the ratios of (Lip + Lac)/Cr were 25.69 ± 13.84, 25.18 ± 16.03, and 0.61 ± 0.15, respectively. From the control group, 11 - 20 mm MZ to 0 - 10 mm MZ and the substantial region of CAE, the concentrations of the metabolites showed that NAA and Cho decreased gradually and markedly. But (Lip + Lac) increased gradually and markedly. The ratios of Cho/Cr and NAA/Cr, (Lip + Lac)/Cr were statistically significant (P < 0.0083) between the substantial region and the control group, as well as between the 0 - 10 mm MZ and the control group. The ratios of Cho/Cr and NAA/Cr, (Lip + Lac)/Cr displayed no statistically significant differences (P > 0.0083) between the substantial region and the 0 - 10 mm MZ. CONCLUSIONS: There was a pathological spectrum surrounding the infiltration zone of CAE. Multi-voxel 1HMRS has great clinical value for discerning the main lesion and the infiltration zone of CAE.