A. K. M. Azad

A. K. M. Azad
Swinburne University of Technology Syndey

Doctor of Philosophy

About

89
Publications
9,360
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
243
Citations
Introduction
My current research interest includes computational systems biology, integrated approaches in systems biology, machine learning, deep learning, data modelling, Bayesian network, Artificial intelligence, and natural language generation.
Additional affiliations
November 2020 - April 2021
University of Technology Sydney
Position
  • Research Associate
November 2019 - November 2020
Kolling Institute of Medical Research
Position
  • Bioinformatician
September 2019 - present
Swinburne University of Technology Sydney
Position
  • Lecturer
Education
June 2013 - June 2017
Monash University (Australia)
Field of study
  • Artificial Intelligence, Bio-statistics, Computational Biology
February 2010 - February 2012
March 2003 - October 2008
University of Dhaka
Field of study
  • Computer Science and Engineering

Publications

Publications (89)
Article
Infection triggers a dynamic cascade of reciprocal events between host and pathogen wherein the host activates complex mechanisms to recognise and kill pathogens while the pathogen often adjusts its virulence and fitness to avoid eradication by the host. The interaction between the pathogen and the host results in large-scale changes in gene expres...
Article
Full-text available
One of the common types of cancer for women is ovarian cancer. Still, at present, there are no drug therapies that can properly cure this deadly disease. However, early-stage detection could boost the life expectancy of the patients. The main aim of this work is to apply machine learning models along with statistical methods to the clinical data ob...
Article
Full-text available
Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes a...
Article
Full-text available
We consider non-Newtonian boundary-layer fluid flow, governed by a power-law Ostwald-de Waele rheology. Boundary-layer flows of non-Newtonian fluids have far-reaching applications, and are very frequently encountered in physical, as well as, engineering and industrial processes. A similarity transformation results in a BVP consisting of an ODE and...
Article
The brain tumor is one of the deadliest cancerous diseases and its severity has turned it to the leading cause of cancer related mortality. The treatment procedure of the brain tumor depends on the type, location and size of the tumor. Relying solely on human inspection for precise categorization can lead to inevitably dangerous situation. This man...
Preprint
Full-text available
Infection triggers a dynamic cascade of reciprocal events between host and pathogen wherein the host activates complex mechanisms to recognise and kill pathogens while the pathogen adjusts its virulence and fitness to avoid eradication by the host. The interaction between the pathogen and the host results in large-scale changes in gene expression i...
Article
Full-text available
Systemic Sclerosis (SSc) is an autoimmune disease associated with changes in the skin's structure in which the immune system attacks the body. A recent meta-analysis has reported a high incidence of cancer prognosis including lung cancer (LC), leukemia (LK), and lymphoma (LP) in patients with SSc as comorbidity but its underlying mechanistic detail...
Article
Full-text available
Inherently ultrasound images are susceptible to noise which leads to several image quality issues. Hence, rating of an image’s quality is crucial since diagnosing diseases requires accurate and high-quality ultrasound images. This research presents an intelligent architecture to rate the quality of ultrasound images. The formulated image quality re...
Article
Full-text available
A substantial amount of data about the COVID-19 pandemic is generated every day. Yet, data streaming, while considerably visualized, is not accompanied with modelling techniques to provide real-time insights. This study introduces a unified platform, COVIDSpread, which integrates visualization capabilities with advanced statistical methods for pred...
Article
Lung cancer, also known as pulmonary cancer, is one of the deadliest cancers, but yet curable if detected at the early stage. At present, the ambiguous features of the lung cancer nodule make the computer-aided automatic diagnosis a challenging task. To alleviate this, we present LungNet, a novel hybrid deep-convolutional neural network-based model...
Article
The coronavirus disease 2019 (COVID-19) is caused by the infection of highly contagious severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as the novel coronavirus. In most countries, the containment of this virus spread is not controlled, which is driving the pandemic towards a more difficult phase. In this study, we investig...
Article
Full-text available
Providing appropriate care for people suffering from COVID-19, the disease caused by the pandemic SARS-CoV-2 virus, is a significant global challenge. Many individuals who become infected may have pre-existing conditions that may interact with COVID-19 to increase symptom severity and mortality risk. COVID-19 patient comorbidities are likely to be...
Preprint
Full-text available
An effective monotherapy to target the complex and multifactorial pathology of SARS-CoV-2 infection poses a challenge to drug repositioning, which can be improved by combination therapy. We developed an online network pharmacology-based drug repositioning platform, COVID-CDR (http://vafaeelab.com/COVID19repositioning.html), that enables a visual an...
Preprint
An effective monotherapy to target the complex and multifactorial pathology of SARS-CoV-2 infection poses a challenge to drug repositioning, which can be improved by combination therapy. We developed an online network pharmacology-based drug repositioning platform, COVID-CDR (http://vafaeelab.com/COVID19repositioning.html), that enables a visual an...
Article
Full-text available
An effective monotherapy to target the complex and multifactorial pathology of SARS-CoV-2 infection poses a challenge to drug repositioning, which can be improved by combination therapy. We developed an online network pharmacology-based drug repositioning platform, COVID-CDR (http://vafaeelab.com/COVID19repositioning.html), that enables a visual an...
Article
Full-text available
Attention is the mental awareness of human on a particular object or a piece of information. The level of attention indicates how intense the focus is on an object or an instance. In this study, several types of human attention level have been observed. After introducing image segmentation and detection technique for facial features, eyeball moveme...
Article
Full-text available
Recently, electroencephalogram-based emotion recognition has become crucial in enabling the Human-Computer Interaction (HCI) system to become more intelligent. Due to the outstanding applications of emotion recognition, e.g., person-based decision making, mind-machine interfacing, cognitive interaction, affect detection, feeling detection, etc., em...
Article
Full-text available
In many complex, real‐world situations, problem solving and decision making require effective reasoning about causation and uncertainty. However, human reasoning in these cases is prone to confusion and error. Bayesian networks (BNs) are an artificial intelligence technology that models uncertain situations, supporting better probabilistic and caus...
Article
Full-text available
Autism spectrum disorder (ASD) is a complex neuro-developmental disorder that affects social skills, language, speech and communication. Early detection of ASD individuals, especially children, could help to devise and strategize right therapeutic plan at right time. Human faces encode important markers that can be used to identify ASD by analyzing...
Article
Full-text available
Coronavirus Disease 2019 (COVID-19), although most commonly demonstrates respiratory symptoms, but there is a growing set of evidence reporting its correlation with the digestive tract and faeces. Interestingly, recent studies have shown the association of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection with gastrointestinal...
Preprint
Full-text available
Good vaccine safety and reliability are essential to prevent infectious disease spread. A small but significant number of apparent adverse reactions to the new COVID-19 vaccines have been reported. Here, we aim to identify possible common causes for such adverse reactions with a view to enabling strategies that reduce patient risk by using patient...
Article
Full-text available
Background: An accurate prediction of COVID-19 patient disease severity would greatly improve care delivery and resource allocation, and thereby reduce mortality risks, especially in less developed countries. There are many patient-related factors, such as pre-existing comorbidities that affect disease severity that could be used to aid prediction...
Article
Full-text available
Objective: Chronic kidney disease (CKD) is a major public health concern worldwide. High costs of late-stage diagnosis and insufficient testing facilities can contribute to high morbidity and mortality rates in CKD patients, particularly in less developed countries. Thus, early diagnosis aided by vital parameter analytics using affordable computer...
Article
Full-text available
Signalling transduction pathways (STPs) are commonly hijacked by many cancers for their growth and malignancy, but demystifying their underlying mechanisms is difficult. Here, we developed methodologies with a fully Bayesian approach in discovering novel driver bio-markers in aberrant STPs given high-throughput gene expression (GE) data. This proje...
Preprint
Full-text available
Genes/Proteins do not work alone within our body, rather as a group they perform certain activities indicated as pathways. Signalling transduction pathways (STPs) are some of the important pathways that transmit biological signals from protein-to-protein controlling several cellular activities. However, many diseases such as cancer target some of t...
Preprint
p>Repurposing of the existing medications has become the mainstream focus of anti-COVID-19 drug discovery as it offers rapid and cost-effective solutions for therapeutic development. However, there is still a great deal to enhance efficacy of repurposing therapeutic options through combination therapy, in which promising drugs with varying mechanis...
Preprint
Full-text available
BACKGROUND Accurate prediction of the disease severity of patients with COVID-19 would greatly improve care delivery and resource allocation and thereby reduce mortality risks, especially in less developed countries. Many patient-related factors, such as pre-existing comorbidities, affect disease severity and can be used to aid this prediction. OB...
Preprint
Full-text available
Introduction: For COVID-19 patients accurate prediction of disease severity and mortality risk would greatly improve care delivery and resource allocation. There are many patient-related factors, such as pre-existing comorbidities that affect disease severity. Since rapid automated profiling of peripheral blood samples is widely available, we inves...
Article
Full-text available
Drug similarity studies are driven by the hypothesis that similar drugs should display similar therapeutic actions and thus can potentially treat a similar constellation of diseases. Drug-drug similarity has been derived by variety of direct and indirect sources of evidence and frequently shown high predictive power in discovering validated reposit...
Preprint
p> Drug similarity studies are driven by the hypothesis that similar drugs should display similar therapeutic actions and thus can potentially treat a similar constellation of diseases. Drug-drug similarity has been derived by variety of direct and indirect sources of evidence and frequently shown high predictive power in discovering validated repo...
Preprint
Full-text available
Substantial amount of data about the COVID-19 pandemic is generated every day. Yet, data streaming, while considerably visualized, is not accompanied with advanced modelling techniques to provide real-time insights. This study introduces a unified platform which integrates visualization capabilities with advanced statistical methods for predicting...
Preprint
Full-text available
In many complex, real-world situations, problem solving and decision making require effective reasoning about causation and uncertainty. However, human reasoning in these cases is prone to confusion and error. Bayesian networks (BNs) are an artificial intelligence technology that models uncertain situations, supporting probabilistic and causal reas...
Preprint
Full-text available
The plethora of single-cell multi-omics data is getting treatment with deep learning, a revolutionary method in artificial intelligence, which has been increasingly expanding its reign over the bioscience frontiers.
Preprint
Full-text available
Cell-cell communication via pathway cross-talks within a single species have been studied in silico recently to decipher various disease phenotype. However, computational prediction of pathway cross-talks among multiple species in a data-driven manner is yet to be explored. In this article, I present XTalkiiS (Cross-talks between inter-/intra speci...
Preprint
Full-text available
Pathway analysis is a very important aspect in computational systems biology as it serves as a crucial component in many computational pipelines. KEGG is one of the prominent databases that host pathway information associated with various organisms. In any pathway analysis pipelines, it is also important to collect and organize the pathway constitu...
Preprint
Full-text available
Motivation Bayesian networks (BNs) are widely used to model biological networks from experimental data. Many software packages exist to infer BN structures, but the chance of getting trapped in local optima is a common challenge. Some recently developed Markov Chain Monte Carlo (MCMC) samplers called the Neighborhood sampler (NS) and Hit-and-Run (H...
Chapter
Full-text available
Data-driven models of signalling networks are becoming increasingly important in systems biology in order to reflect the dynamic patterns of signalling activities in a context-specific manner. State-of-the-art approaches for categorising and detecting signalling cross-talks may not be suitable for such models since they rely on static topologies of...
Chapter
Full-text available
The availability of multiple heterogeneous high-throughput datasets provides an enabling resource for cancer systems biology. Types of data include: Gene expression (GE), copy number aberration (CNA), miRNA expression, methylation, and protein–protein Interactions (PPI). One important problem that can potentially be solved using such data is to det...
Thesis
Full-text available
Acquired resistance (AR) to cancer therapies reduces drug efficacy, and signalling cross-talks play a significant role as an underlying mechanism. In this thesis, I combined a computational and a fully Bayesian statistical approach to model and identify aberrant signalling cross-talks, and characterise their roles in AR in two breast cancer cell-li...
Article
Full-text available
Small molecule inhibitors, such as lapatinib, are effective against breast cancer in clinical trials, but tumor cells ultimately acquire resistance to the drug. Maintaining sensitization to drug action is essential for durable growth inhibition. Recently, adaptive reprogramming of signaling circuitry has been identified as a major cause of acquired...
Data
Supplementary Table 7. CGC genes in all the Type-I, Type-II and Type-III V-structures in SKBR3 and BT474 cell-lines. (XLSX)
Data
Supplementary Table 1. List of identified putative aberrant gene-pairs (for both SKBR3 and BT474) cell-lines in acquired resistance. (XLSX)
Data
Supplementary Table 2. Full results of pathway enrichment tests of identified aberrant gene-pairs in acquired resistance from KEGG, Reactome, and WikiPathway databases for both SKBR3 and BT474 cell-lines. (XLSX)
Data
Supplementary Table 3. Comparing our current model with the previous model by observing the percentages of non-direct (indirect and PPI pair) enriched links (aberrant pairs as known signaling links) in the aberrant signaling pathways from KEGG, Reactome, and WikiPathway databases that were detected by our current but not the previous model, for bot...
Data
Supplementary Table 4. Comparing our current model with the previous model by observing the percentages of non-direct (indirect and PPI pair) enriched links (aberrant pairs as known signaling links) in the aberrant signaling pathways from KEGG, Reactome, and WikiPathway databases that were detected by both of our current and previous models, and we...
Data
Supplementary Table 5. Summary of Type-I, Type-II and Type-III enrichment of V-structures in KEGG, Reactome, and WikiPathway databases in SKBR3 cell-line. (XLSX)
Data
Supplementary Text 1. Supplementary Methods. (PDF)
Data
Supplementary Table 6. Summary of Type-I, Type-II and Type-III enrichment of V-structures in KEGG, Reactome, and WikiPathway databases in BT474 cell-line. (XLSX)
Article
Many applications in graph analysis require a space of graphs or networks to be sampled uniformly at random. For example, one may need to efficiently draw a small representative sample of graphs from a particular large target space. We assume that a uniform distribution has been defined, where N is a set of nodes, E is a set of edges, (N, E) is a g...
Conference Paper
Full-text available
Getting stuck in local maxima is a problem that arises while learning Bayesian networks (BNs) structures. In this paper, we studied a recently proposed Markov chain Monte Carlo (MCMC) sampler, called the Neighbourhood sampler (NS), and examined how efficiently it can sample BNs when local maxima are present. We assume that a posterior distribution...
Conference Paper
Full-text available
We propose a Markov Chain Monte Carlo (MCMC) sampler as a new approach to sample graph spaces from a discrete distribution f(N, E|D) that is defined on a finite graph space X , where D represents data-points observed at discrete times, N is a set of vertices representing variables, and E is a set of directed edges describing the causal relationship...
Article
Full-text available
Background Initial success of inhibitors targeting oncogenes is often followed by tumor relapse due to acquired resistance. In addition to mutations in targeted oncogenes, signaling cross-talks among pathways play a vital role in such drug inefficacy. These include activation of compensatory pathways and altered activities of key effectors in other...
Poster
Full-text available
Cancer initiation and malignance involve a series of events ranging from tumorigenesis to metastasis often caused by perturbations in some crucial signal transduction pathways. Recently, drugs (inhibitors) targeting the critical components of these signaling pathways have been used in clinical trials. However, success of these inhibitors is limited...
Article
Full-text available
Recently, computational approaches integrating copy number aberrations (CNAs) and gene expression (GE) have been extensively studied to identify cancer-related genes and pathways. In this work, we integrate these two data sets with protein-protein interaction (PPI) information to find cancer-related functional modules. To integrate CNA and GE data,...
Data
Distribution of pairwise voting values among genes. (A) is for the GBM data set and (B) for OVC data set. X-axis and y-axis show the vote-values and their corresponding frequencies among all gene pairs. (EPS)
Data
Module overlaps in terms of common genes. In (A) and (C), the ratios of the number of common (overlapping) genes among the number of genes in the module are shown in x-axis, for GBM and OVC data sets, respectively. Frequencies of modules with the corresponding overlapping ratio in x-axis is shown in y-axis. In (B) and (D), the average ratios of ove...
Data
Distributions of topological and data-driven properties in merging pre-modules. (A) and (C) are distributions of topological property values of all pairs of pre-modules, and (B) and (D) are distributions of data-driven property values of all pairs of pre-modules, for GBM and OVC, respectively. (EPS)
Data
Topological and data-driven properties used in the vote calculation. (A) and (B) show the distributions of topological property values of gene-pairs included in pre-modules, for GBM and OVC, respectively. (C) and (D) show the distributions of data-driven property values of gene-pairs included in pre-modules, for GBM and OVC, respectively. In the in...
Data
Distributions of all enumerated pairwise direct relationships among the genes in . (A) is for GBM data set and (B) is for OVC data set. X-axis indicates the absolute Pearson correlation coefficient (PCC) for GE-GE, CNA-GE and CNA-CNA relationships. For each distributions, y-axis indicates the proportion of gene-pairs among the total number of pair-...
Data
Statistical validation of the identified modules and selection of . (A) and (C) show comparison between merging values between the observed case and 100 random cases, for GBM and OVC data sets, respectively. (B) and (D) show -values for merging values at each merging step, for GBM and OVC data sets, respectively. (EPS)
Data
Representation of fractions of gene pairs having direct relationships in modules. The x-axis shows the module ID and the y-axis shows the fractions of gene pairs having each type of direct relationships out of all possible gene pairs for 22 GBM modules (A) and 23 OVC modules (B). For a particular module, there are three vertical bars; a blue vertic...
Data
Comparison between hierarchical clustering and the VToD algorithm. (A) Box charts of CGC and GBM driver gene set enrichments for both the hierarchical clustering and the VToD algorithm. (B) Percentages of modules in the hierarchical clustering and the VToD algorithm that contain different combinations of all three types of direct relationships. (EP...
Data
Topological and data-driven property values while merging pre-modules. (A) and (B) show contributions of both properties to calculate merging-values while merging pre-modules for GBM and OVC data sets, respectively. Topological properties are colored in black and data-driven properties are in blue. (EPS)
Data
CNA genes and locations. (XLSX)
Data
List of identified modules for OVC. (XLSX)
Data
Enrichment test results of GO biological processes for GBM modules (VToD algorithm). (XLSX)
Data
List of identified modules for GBM. (XLSX)
Data
Enrichment test results of KEGG pathways for GBM modules (VToD algorithm). (XLSX)
Data
Enrichment test results of GO biological processes for OVC modules (VToD algorithm). (XLSX)
Data
Comparison of distinct enriched pathways between other methods and VToD for GBM data set. (XLSX)
Data
Summary of enrichment test results for OVC modules (VToD algorithm). (XLSX)