M. Shahriar Hossain

Connecting the Dots between PubMed Abstracts

Background There are now a multitude of articles published in a diversity of journals providing information about genes, proteins, pathways, and diseases. Each article investigates subsets of a biological process, but to gain insight into the functioning of a system as a whole, we must integrate information from multiple publications. Particularly, unraveling relationships between extra-cellular inputs and downstream molecular response mechanisms requires integrating conclusions from diverse publications. Methodology We present an automated approach to biological knowledge discovery from PubMed abstracts, suitable for “connecting the dots” across the literature. We describe a storytelling algorithm that, given a start and end publication, typically with little or no overlap in content, identifies a chain of intermediate publications from one to the other, such that neighboring publications have significant content similarity. The quality of discovered stories is measured using local criteria such as the size of supporting neighborhoods for each link and the strength of individual links connecting publications, as well as global metrics of dispersion. To ensure that the story stays coherent as it meanders from one publication to another, we demonstrate the design of novel coherence and overlap filters for use as post-processing steps. Conclusions We demonstrate the application of our storytelling algorithm to three case studies: i) a many-one study exploring relationships between multiple cellular inputs and a molecule responsible for cell-fate decisions, ii) a many-many study exploring the relationships between multiple cytokines and multiple downstream transcription factors, and iii) a one-to-one study to showcase the ability to recover a cancer related association, viz. the Warburg effect, from past literature. The storytelling pipeline helps narrow down a scientists focus from several hundreds of thousands of relevant documents to only around a hundred stories. We argue that our approach can serve as a valuable discovery aid for hypothesis generation and connection exploration in large unstructured biological knowledge bases.

Unifying dependent clustering and disparate clustering for non-homogeneous data

Modern data mining settings involve a combination of attribute-valued descriptors over entities as well as specified relationships between these entities. We present an approach to cluster such non-homogeneous datasets by using the relationships to impose either dependent clustering or disparate clustering constraints. Unlike prior work that views constraints as boolean criteria, we present a formulation that allows constraints to be satisfied or violated in a smooth manner. This enables us to achieve dependent clustering and disparate clustering using the same optimization framework by merely maximizing versus minimizing the objective function. We present results on both synthetic data as well as several real-world datasets.

Coordinated clustering algorithms to support charging infrastructure design for electric vehicles

The confluence of several developments has created an opportune moment for energy system modernization. In the past decade, smart grids have attracted many research activities in different domains. To realize the next generation of smart grids, we must have a comprehensive understanding of interdependent networks and processes. Next-generation energy systems networks cannot be effectively designed, analyzed, and controlled in isolation from the social, economic, sensing, and control contexts in which they operate. In this paper, we develop coordinated clustering techniques to work with network models of urban environments to aid in placement of charging stations for an electrical vehicle deployment scenario. We demonstrate the multiple factors that can be simultaneously leveraged in our framework in order to achieve practical urban deployment. Our ultimate goal is to help realize sustainable energy system management in urban electrical infrastructure by modeling and analyzing networks of interactions between electric systems and urban populations.

Narratives in the network: interactive methods for mining cell signaling networks.

In this article, we describe our work on graph mining as applied to the cellular signaling pathways in the Signal Transduction Knowledge Environment (STKE). We present new algorithms and a graphical tool that can help biologists discover relationships between pathways by looking at structural overlaps within the database. We address the problem of determining pathway relationships by using two data mining approaches: clustering and storytelling. In the first approach, our tool brings similar pathways to the same cluster, and in the second, our tool determines intermediate overlapping pathways that can lead biologists to new hypotheses and experiments regarding relationships between the pathways. We formulate the problem of discovering pathway relationships as a subgraph discovery problem and propose a new technique called Subgraph-Extension Generation (SEG), which outperforms the traditional Frequent Subgraph Discovery (FSG) approach by magnitudes. Our tool provides an interface to compare these two approaches with a variety of similarity measures and clustering techniques as well as in terms of computational performance measures such as runtime and memory consumption.

AutoLCA: A Framework for Sustainable Redesign and Assessment of Products

With increasing public consciousness regarding sustainability, companies are ever more eager to introduce eco-friendly products and services. Assessing environmental footprints and designing sustainable products are challenging tasks since they require analysis of each component of a product through their life cycle. To achieve sustainable design of products, companies need to evaluate the environmental impact of their system, identify the major contributors to the footprint, and select the design alternative with the lowest environmental footprint. In this article, we formulate sustainable design as a series of clustering and classification problems, and propose a framework called AutoLCA that simplifies the effort of estimating the environmental footprint of a product bill of materials by more than an order of magnitude over current methods, which are mostly labor intensive. We apply AutoLCA to real data from a large computer manufacturer. We conduct a case study on bill of materials of four different products, perform a “hotspot” assessment analysis to identify major contributors to carbon footprint, and determine design alternatives that can reduce the carbon footprint from 1% to 36%.

Charging and Storage Infrastructure Design for Electric Vehicles

Ushered by recent developments in various areas of science and technology, modern energy systems are going to be an inevitable part of our societies. Smart grids are one of these modern systems that have attracted many research activities in recent years. Before utilizing the next generation of smart grids, we should have a comprehensive understanding of the interdependent energy networks and processes. Next-generation energy systems networks cannot be effectively designed, analyzed, and controlled in isolation from the social, economic, sensing, and control contexts in which they operate. In this article, we present a novel framework to support charging and storage infrastructure design for electric vehicles. We develop coordinated clustering techniques to work with network models of urban environments to aid in placement of charging stations for an electrical vehicle deployment scenario. Furthermore, we evaluate the network before and after the deployment of charging stations, to recommend the installation of appropriate storage units to overcome the extra load imposed on the network by the charging stations. We demonstrate the multiple factors that can be simultaneously leveraged in our framework to achieve practical urban deployment. Our ultimate goal is to help realize sustainable energy system management in urban electrical infrastructure by modeling and analyzing networks of interactions between electric systems and urban populations.

Reconstructing and evolving software architectures using a coordinated clustering framework

During a long maintenance period, software projects experience architectural erosion and drift, making maintenance tasks more challenging to perform for software engineers unfamiliar with the code base. This paper presents a framework that assists software engineers in recovering a software project’s architecture from its source code. The architectural recovery process is an iterative one that combines clustering based on contextual and structural information in the code base with incremental developer feedback. This process converges when the developer is satisfied with the proposed decomposition of the software, and, as an additional benefit, the framework becomes tuned to aid future evolution of the project. The paper provides both analytic and empirical evaluations of the obtained results; experimental results show a reasonably superior performance of our framework over alternative conventional methods. The proposed framework utilizes a novel compartmentalization technique Coordinated Clustering of Heterogeneous Datasets (CCHD) that relies on contextual and structural information in the code base, but, unlike most previous approaches, does not require specific weights for each information type, which allows it to adapt to different project types and domains.

Analyst's workspace: Protecting vastopolis

Analysts Workspace is a sensemaking environment designed specifically for use of large, high-resolution displays. It employs a spatial workspace to integrate foraging and synthesis activities into a unified process. In this paper we describe how Analysts Workspace solved the VAST 2011 mini-challenge #3 and discuss some of the unique features of the environment.

Analyzing evolving stories in news articles

There is an overwhelming number of news articles published every day around the globe. Following the evolution of a news story is a difficult task given that there is no such mechanism available to track back in time to discover and study the hidden relationships between relevant events in digital news feeds. The techniques developed so far to extract meaningful information from a massive corpus rely on similarity search, which results in a myopic loopback to the same topic without providing the needed insights to hypothesize the origin of a story that may be completely different than the news today. In this paper, we present an algorithm that mines historical news data to detect the origin of an event, segments the timeline into disjoint groups of coherent news articles, and outlines the most important documents in a timeline with a soft probability to provide a better understanding of the evolution of a story. Qualitative and quantitative evaluations of our framework demonstrate that our algorithm discovers statistically significant and meaningful stories in reasonable time. Additionally, a relevant case study on a set of news articles demonstrates that the generated output of the algorithm holds the promise to aid prediction of future entities (e.g., actors) in a story.

Concurrent Inference of Topic Models and Distributed Vector Representations

Topic modeling techniques have been widely used to uncover dominant themes hidden inside an unstructured document collection. Though these techniques first originated in the probabilistic analysis of word distributions, many deep learning approaches have been adopted recently. In this paper, we propose a novel neural network based architecture that produces distributed representation of topics to capture topical themes in a dataset. Unlike many state-of-the-art techniques for generating distributed representation of words and documents that directly use neighboring words for training, we leverage the outcome of a sophisticated deep neural network to estimate the topic labels of each document. The networks, for topic modeling and generation of distributed representations, are trained concurrently in a cascaded style with better runtime without sacrificing the quality of the topics. Empirical studies reported in the paper show that the distributed representations of topics represent intuitive themes using smaller dimensions than conventional topic modeling approaches.