Modeling the interface region of a protein complex paves the way for understanding its dynamics and functionalities. Existing works model the interface region of a complex by using different approaches, such as, the residue composition at the interface region, the geometry of the interface residues, or the structural alignment of interface regions. These approaches are useful for ranking a set of docked conformation or for building scoring function for protein-protein docking, but they do not provide a generic and scalable technique for the extraction of interface patterns leading to functional motif discovery. In this work, we model the interface region of a protein complex by graphs and extract interface patterns of the given complex in the form of frequent subgraphs. To achieve this, we develop a scalable algorithm for frequent subgraph mining. We show that a systematic review of the mined subgraphs provides an effective method for the discovery of functional motifs that exist along the interface region of a given protein complex. In our experiments, we use three PDB protein structure datasets. The first two datasets are composed of PDB structures from different conformations of two dimeric protein complexes: HIV-1 protease (329 structures), and triosephosphate isomerase (TIM) (86 structures). The third dataset is a collection of different enzyme structures protein structures from the six top-level enzyme classes, namely: Oxydoreductase, Transferase, Hydrolase, Lyase, Isomerase, and Ligase. We show that for the first two datasets, our method captures the locking mechanism at the dimeric interface by taking into account the spatial positioning of the interfacial residues through graphs. Indeed, our frequent subgraph mining based approach discovers the patterns representing the dimerization lock which is formed at the base of the structure in 323 of the 329 HIV-1 protease structures. Similarly, for 86 TIM structures, our approach discovers the dimerization lock formation in 50 structures. For the enzyme structures, we show that we are able to capture the functional motifs (active sites) that are specific to each of the six top-level classes of enzymes through frequent subgraphs.

Android systems are widely used in mobile & wireless distributed systems. In the near future, Android is believed to dominate the mobile distributed environment. However, with the popularity of Android-based smartphones/tablets comes the rampancy of Android-based malware. In this paper, we propose a novel topological signature of Android apps based on the function call graphs (FCGs) extracted from their Android App PacKages (APKs). Specifically, by leveraging recent advances on graphlet mining, the proposed method fully captures the invocator-invocatee relationship at local neighborhoods in an FCG without exponentially inflating the state space. Using real benign app and malware samples, we demonstrate that our method, App topologiCal signature through graphleT Sampling (ACTS), can detect malware and identify malware families robustly and efficiently. More importantly, we demonstrate that, without augmenting the FCG with any semantic features such as bytecode-based vertex typing, local topological information captured by ACTS alone can achieve a high malware detection accuracy. Since ACTS only uses structural features, which are orthogonal to semantic features, it is expected that combining them would give a greater improvement in malware detection accuracy than combining non-orthogonal semantic features.

Vector representation of sentences is important for many text processing tasks that involve classifying, clustering, or ranking sentences. For solving these tasks, bag-of-word based representation has been used for a long time. In recent years, distributed representation of sentences learned by neural models from unlabeled data has been shown to outperform traditional bag-of-words representations. However, most existing methods belonging to the neural models consider only the content of a sentence, and disregard its relations with other sentences in the context. In this paper, we first characterize two types of contexts depending on their scope and utility. We then propose two approaches to incorporate contextual information into content-based models. We evaluate our sentence representation models in a setup, where context is available to infer sentence vectors. Experimental results demonstrate that our proposed models outshine existing models on three fundamental tasks, such as, classifying, clustering, and ranking sentences.

In recent years, technology-assisted review (TAR) has become an increasingly important component of the document review process in litigation discovery. This is fueled largely by dramatic growth in data volumes that may be associated with many matters and investigations. Potential review populations frequently exceed several hundred thousands documents, and document counts in the millions are not uncommon. Budgetary and/or time constraints often make a once traditional linear review of these populations impractical, if not impossible — which made "predictive coding" the most discussed TAR approach in recent years. A key challenge in any predictive coding approach is striking the appropriate balance in training the system. The goal is to minimize the time that Subject Matter Experts spend in training the system, while making sure that they perform enough training to achieve acceptable classification performance over the entire review population. Recent research demonstrates that Support Vector Machines (SVM) perform very well in finding a compact, yet effective, training dataset in an iterative fashion using batch-mode active learning. However, this research is limited. Additionally, these efforts have not led to a principled approach for determining the stabilization of the active learning process. In this paper, we propose and compare several batch-mode active learning methods which are integrated within SVM learning algorithm. We also propose methods for determining the stabilization of the active learning method. Experimental results on a set of large-scale, real-life legal document collections validate the superiority of our method over the existing methods for this task.

The entity disambiguation task partitions the records belonging to multiple persons with the objective that each decomposed partition is composed of records of a unique person. Existing solutions to this task use either biographical attributes, or auxiliary features that are collected from external sources, such as Wikipedia. However, for many scenarios, such auxiliary features are not available, or they are costly to obtain. Besides, the attempt of collecting biographical or external data sustains the risk of privacy violation. In this work, we propose a method for solving entity disambiguation task from link information obtained from a collaboration network. Our method is non-intrusive of privacy as it uses only the time-stamped graph topology of an anonymized network. Experimental results on two real-life academic collaboration networks show that the proposed method has satisfactory performance.

Mining labeled subgraph is a popular research task in data mining because of its potential application in many different scientific domains. All the existing methods for this task explicitly or implicitly solve the subgraph isomorphism task which is computationally expensive, so they suffer from the lack of scalability problem when the graphs in the input database are large. In this work, we propose FS3, which is a sampling based method. It mines a small collection of subgraphs that are most frequent in the probabilistic sense. FS3performs a Markov Chain Monte Carlo (MCMC) sampling over the space of a fixed-size subgraphs such that the potentially frequent subgraphs are sampled more often. Besides, FS3is equipped with an innovative queue manager. It stores the sampled subgraph in a finite queue over the course of mining in such a manner that the top-k positions in the queue contain the most frequent subgraphs. Our experiments on database of large graphs show that FS3is efficient, and it obtains subgraphs that are the most frequent amongst the subgraphs of a given size.

DNA fragment assembly problem is one of the crucial challenges faced by computational biologists where, given a set of DNA fragments, we have to construct a complete DNA sequence from them. As it is an NP-hard problem, accurate DNA sequence is hard to find. Moreover, due to experimental limitations, the fragments considered for assembly are exposed to additional errors while reading the fragments. In such scenarios, meta-heuristic based algorithms can come in handy. We analyze the performance of two swarm intelligence based algorithms namely Artificial Bee Colony (ABC) algorithm and Queen Bee Evolution Based on Genetic Algorithm (QEGA) to solve the fragment assembly problem and report quite promising results. Our main focus is to design meta-heuristic based techniques to efficiently handle DNA fragment assembly problem for noisy and noiseless data.