Malay Bhattacharyya

MicroRNA signatures highlight new breast cancer subtypes

MicroRNAs (miRNAs) are a kind of short non-coding RNAs, of about 22 nucleotides in length, which modulate and sometimes degrade the target mRNAs thereby regulating a number of cellular functions. Recent research in this area establishes the involvement of miRNAs in various disease progressions, including certain types of cancer development. Further, genome-wide expression profiling of miRNAs has been proven to be useful for differentiating various cancer types. In this paper, we have used miRNA expression profiles over a large set of breast cancer tumor samples for identifying subtypes of breast cancers. The experimental results demonstrate that miRNAs carry a unique signature that distinguishes cancer subtypes and reveal new cancer subtypes. Additional survival analyses based on clinical data also strengthen this claim.

MicroRNA Transcription Start Site Prediction with Multi-objective Feature Selection

MicroRNAs (miRNAs) are non-coding, short (21-23nt) regulators of protein-coding genes that are generally transcribed first into primary miRNA (pri-miR), followed by the generation of precursor miRNA (pre-miR). This finally leads to the production of the mature miRNA. A large amount of information is available on the pre- and mature miRNAs. However, very little is known about the pri-miRs, due to a lack of knowledge about their transcription start sites (TSSs). Based on the genomic loci, miRNAs can be categorized into two types x97intragenic (intra-miR) and intergenic (inter-miR). While it is already an established fact that intra-miRs are commonly transcribed in conjunction with their host genes, the transcription machinery of inter-miRs is poorly understood. Although it is assumed that miRNA promoters are similar in structure to gene promoters, since both are transcribed by RNA polymerase II (Pol II), computational validations exhibit poor performance of gene promoter prediction methods on miRNAs. In this paper, we concentrate on the problem of TSS prediction for miRNAs. The present study begins with the identification of positive and negative promoter samples from recently published data stemming from RNA-sequencing studies. From these samples of experimentally validated miRNA TSSs, a number of standard sequence features are extracted. Furthermore, to account for potential footprints related to promoter regulation by CpG dinucleotide targeted DNA methylation, a number of novel features are defined. We develop a support vector machine (SVM) with RBF kernel for the prediction of miRNA TSSs trained on human miRNA promoters. A novel feature reduction technique based on archived multi-objective simulated annealing (AMOSA) identifies the final set of features. The resulting model trained on miRNA promoters shows improved performance over the one trained on protein-coding gene promoters in terms of classification accuracy, sensitivity and specificity. Results are also reported for a completely independent biologically validated test set. In a part of the investigation, the proposed approach is used to predict protein-coding gene TSSs. It shows a significantly improved performance when compared to previously published gene TSS prediction methods.

Judgment analysis of crowdsourced opinions using biclustering

The problem of deriving final judgment from crowdsourced opinions is addressed with an unsupervised approach.Biclustering is shown to be useful for identifying the annotators crucial for a judgment.We establish that a suitable fraction of the entire dataset is sufficient for appropriate judgment analysis.As the proposed method does not work over the entire data, it becomes useful for big data analysis. Annotation by the crowd workers serving online is gaining focus in recent years in diverse fields due to its distributed power of problem solving. Distributing the labeling task among a large set of workers (may be experts or non-experts) and obtaining the final consensus is a popular way of performing large-scale annotation in a limited time. Collection of multiple annotations can be effective for annotation of large-scale datasets for applications like natural language processing, image processing, etc. However, as the crowd workers are not necessarily experts, their opinions might not be accurate enough. This causes problem in deriving the final aggregated judgment. Again, majority voting (MV) is not suitable for such problems because the number of annotators is limited and they have multiple options to choose. This might cause too much conflicts among the opinions provided. Additionally, there might exist annotators who randomly try to annotate (provide spam opinions for) too many questions to maximize their payment. This can incorporate noise while deriving the final judgment. In this paper, we address the problem of crowd judgment analysis in an unsupervised way and a biclustering-based approach is proposed to obtain the judgments appropriately. The effectiveness of this approach is demonstrated on four publicly available small-scale Amazon Mechanical Turk datasets, along with a large-scale CrowdFlower dataset. We also compare the algorithm with MV and some other existing algorithms. In most of the cases the proposed approach is competitively better than others. But most importantly, it does not use the entire dataset for deriving the judgment.

Mining the Largest Quasi-clique in Human Protein Interactome

A clique is a complete subgraph of a graph. Often, a clique is interpreted as a dense module of vertices within a graph. However, in many real-world situations, the classical problem of finding a clique is required to be relaxed. This motivates the problem of finding quasicliques that are almost complete subgraphs of a graph. In sparse and very large scale-free networks, the problem of finding the largest quasi-clique becomes hard to manage with the existing approaches. Here, we propose a heuristic algorithm in this paper for locating the largest quasi-clique from the human protein-protein interaction networks. The results show promise in computational biology research by the exploration of significant protein modules.

A biclustering approach for crowd judgment analysis

Collection of multiple annotations from the crowd workers is useful for diverse applications. In this paper, the problem of obtaining the final judgment from such crowd-based annotations has been addressed in an unsupervised way using a biclustering-based approach. Results on multiple datasets show that the proposed approach is competitively better than others, without even using the entire dataset.

Disease dietomics

How computational biology might help in discovering the missing links between diet and disease.

Finding quasi core with simulated stacked neural networks

Studying networks is promising for diverse applications. We are often interested in exploring significant substructures in different types of real-life networks. Finding cliques, which denote a complete subgraph of a graph, is one such important problem in network analysis. Interestingly, many real-life networks often contain a significant number of almost (quasi) complete subgraphs, which are not entirely complete due to the presence of noise. Considering these networks as weighted adds further challenges to the problem. Finding quasi-complete subgraphs in weighted graphs has never been formally addressed. In this paper, we propose a stacked neural network model for finding out the largest quasi-complete module (core) in weighted graphs. We show the effectiveness of the proposed approach on DIMACS graphs. We also highlight its utility in analyzing scientific collaboration networks, social networks and biological networks.

Integration of Co-expression Networks for Gene Clustering

Simultaneous overexpression or underexpression of multiplegenes, used in various forms as probes in the highthroughput microarray experiments, facilitates the identification of their underlying functional proximity. This kind of functional associativity (or conversely the separability) between the genes can be represented roficiently using coexpression networks. The extensive repository of diversified microarray data encounters a recent problem of multiexperimental data integration for the aforesaid purpose. This paper highlights a novel integration method of gene coexpression networks, based on the search for their consensus network, derived from diverse microarray experimental data for the purpose of clustering. The proposed methodology avoids the bias arising from missing value estimation. The method has been applied on microarray datasets arising from different category of experiments to integrate them. The consensus network, thus produced, reflects robustness based on biological validation.

Network based mechanisms for competitive crowdsourcing

The working principle of crowd in a crowdsourcing platform is either competitive or collaborative. Occasionally, the tasks submitted to crowdsourcing environments are decomposable. They are challenging to solve because decomposition and composition of tasks and proper selection of workers are difficult. We show that by appropriate inclusion of collaboration in a competitive crowdsourcing environment, we can handle decomposable-type tasks given with posted-price in a better way. We initially attempt to manage 2-decomposable tasks with appropriate mechanism design. Extending it further to n-decomposable tasks, we propose a network based mechanism to choose the best mixture of sub-tasks in a competitive environment for selecting the winners. We are currently interested in developing mechanisms to remove the participation bias from such environments.

A Probabilistic Approach to Group Decision Making

Large-scale judgment analysis from multiple opinions is a challenging job in terms of time and cost involved. Over the last few years, with the popularity of crowd-powered models, the process of decision making is efficiently getting done by using the knowledge of crowd. In management science, a closely related class of problems, popularly known as group decision making, is often addressed. Unfortunately, majority of the algorithms developed for this purpose work for binary or multiple opinions without taking care of the semantic meaning of the options. Moreover, group decision considers a feedback set comprising range of continuous values unlike the judgment analysis problem. In this paper, we address this problem, hereafter termed as multi-opinion group decision making, with a probabilistic approach taking into account the annotator accuracy, annotator bias and question difficulty. The effectiveness of the approach is demonstrated by applying this on a benchmark group decision making dataset.