A5100705489- Sentiment Analysis and Opinion Mining
- Mental Health via Writing
- Complex Network Analysis Techniques
- Computational Drug Discovery Methods
- Bioinformatics and Genomic Networks
- Bayesian Modeling and Causal Inference
- Gene expression and cancer classification
- Topic Modeling
- Data-Driven Disease Surveillance
- Machine Learning in Materials Science
- Recommender Systems and Techniques
- Domain Adaptation and Few-Shot Learning
- Machine Learning and Data Classification
- Machine Learning and Algorithms
- Mental Health Research Topics
- Protein Structure and Dynamics
- Text and Document Classification Technologies
- Human Mobility and Location-Based Analysis
- Statistical Methods and Inference
- Advanced Graph Neural Networks
- Autism Spectrum Disorder Research
- Explainable Artificial Intelligence (XAI)
- Digital Mental Health Interventions
- Emotion and Mood Recognition
- Single-cell and spatial transcriptomics
Deakin University
2015-2024
Eastern International University
2024
Los Alamos National Laboratory
2023
Thai Nguyen University
2023
Thang Long University
2023
Thai Nguyen University Of Education
2023
Da Nang University of Technology
2022
University of Da Nang
2022
Curtin University
2010-2021
Allen Institute for Artificial Intelligence
2019-2020
Abstract Summary The development of new drugs is costly, time consuming and often accompanied with safety issues. Drug repurposing can avoid the expensive lengthy process drug by finding uses for already approved drugs. In order to repurpose effectively, it useful know which proteins are targeted Computational models that estimate interaction strength drug–target pairs have potential expedite repurposing. Several been proposed this task. However, these represent as strings, not a natural way...
A large number of people use online communities to discuss mental health issues, thus offering opportunities for new understanding these communities. This paper aims study the characteristics depression (CLINICAL) in comparison with those joining other (CONTROL). We machine learning and statistical methods discriminate messages between control using mood, psycholinguistic processes content topics extracted from posts generated by members All aspects including written writing style are found...
Efficient and reliable monitoring of wild animals in their natural habitats is essential to inform conservation management decisions. Automatic covert cameras or "camera traps" are being an increasingly popular tool for wildlife due effectiveness reliability collecting data unobtrusively, continuously large volume. However, processing such a volume images videos captured from camera traps manually extremely expensive, time-consuming also monotonous. This presents major obstacle scientists...
Drug response prediction is an important problem in computational personalized medicine. Many machine-learning-based methods, especially deep learning-based ones, have been proposed for this task. However, these methods often represent the drugs as strings, which are not a natural way to depict molecules. Also, interpretation (e.g., what mutation or copy number aberration contributing drug response) has considered thoroughly.In study, we propose novel method, GraphDRP, based on graph...
Abstract Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly pathogenic virus that has caused the global COVID-19 pandemic. Tracing evolution and transmission of crucial to respond control pandemic through appropriate intervention strategies. This paper reports analyses genomic mutations in coding regions SARS-CoV-2 their probable protein secondary structure solvent accessibility changes, which are predicted using deep learning models. Prediction results suggest mutation...
Abstract Despite decades of intensive search for compounds that modulate the activity particular protein targets, a large proportion human kinome remains as yet undrugged. Effective approaches are therefore required to map massive space unexplored compound–kinase interactions novel and potent activities. Here, we carry out crowdsourced benchmarking predictive algorithms kinase inhibitor potencies across multiple families tested on unpublished bioactivity data. We find top-performing...
Predicting the interaction between a compound and target is crucial for rapid drug repurposing. Deep learning has been successfully applied in drug-target affinity (DTA)problem. However, previous deep learning-based methods ignore modeling direct interactions protein residues. This would lead to inaccurate of representation which may change due binding effects. In addition, DTA learn solely based on small number sequences datasets while neglecting use proteins outside datasets. We propose...
Mental illness has a deep impact on individuals, families, and by extension, society as whole. Social networks allow individuals with mental disorders to communicate others sufferers via online communities, providing an invaluable resource for studies textual signs of psychological health problems. often occur in combinations, e.g., patient anxiety disorder may also develop depression. This co-occurring condition provides the focus our work classifying communities interest For this, we have...
Multimodal dimensional emotion recognition has drawn a great attention from the affective computing community and numerous schemes have been extensively investigated, making significant progress in this area. However, several questions still remain unanswered for most of existing approaches including: (i) how to simultaneously learn compact yet representative features multimodal data, (ii) effectively capture complementary streams, (iii) perform all tasks an end-to-end manner. To address...
Abstract The development of new drugs is costly, time consuming, and often accompanied with safety issues. Drug repurposing can avoid the expensive lengthy process drug by finding uses for already approved drugs. In order to repurpose effectively, it useful know which proteins are targeted Computational models that estimate interaction strength drug--target pairs have potential expedite repurposing. Several been proposed this task. However, these represent as strings, not a natural way...
Existing score-based methods for directed acyclic graph (DAG) learning from observational data struggle to recover the causal accurately and sample-efficiently. To overcome this, in this study, we propose DrBO (DAG recovery via Bayesian Optimization)-a novel DAG framework leveraging optimization (BO) find high-scoring DAGs. We show that, by sophisticatedly choosing promising DAGs explore, can higher-scoring ones much more efficiently. address scalability issues of conventional BO learning,...
Background: Long COVID, or Post–Acute Sequelae of COVID–19 (PASC), involves persistent, multisystemic symptoms in about 10–20% COVID-19 patients. Although age, sex, ethnicity, and comorbidities are recognized as risk factors, identifying genetic contributors is essential for developing targeted therapies. Methods: We developed a multi–omics framework using Transcriptome-Wide Mendelian Randomization (TWMR) Control Theory (CT). This approach integrates Expression Quantitative Trait Loci...
Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate models for forward and reverse translations. This not only doubles the computational cost but also restricts practicality. In this work, we introduce Bidirectional Bridge Model (BDBM), a scalable approach that facilitates bidirectional between two coupled distributions using single network. BDBM leverages...
Estimation of a person's influence and personality traits from social media data has many applications. We use linkage criteria, such as number followers friends, proxies to form corpora, popular blogging site Livejournal, for examining two two-class classification problems: influential vs. non-influential, extraversion introversion. Classification is performed using automatically-derived psycholinguistic mood-based features user's textual messages. experiment with three sub-corpora 10000...
Data generated within social media platforms may present a new way to identify individuals who are experiencing mental illness. This study aimed investigate the associations between linguistic features in individuals’ blog data and their symptoms of depression, generalised anxiety, suicidal ideation. Individuals blogged were invited participate longitudinal which they completed fortnightly symptom scales for depression anxiety (PHQ-9, GAD-7) period 36 weeks. Blog published same was also...
For years, we have relied on population surveys to keep track of regional public health statistics, including the prevalence non-communicable diseases. Because cost and limitations such surveys, often do not up-to-date data outcomes a region. In this paper, examined feasibility inferring from socio-demographic that are widely available timely updated through national censuses community surveys. Using for 50 American states (excluding Washington DC) 2007 2012, constructed machine-learning...
The Internet has provided an ever increasingly popular platform for individuals to voice their thoughts, and like-minded people share stories. This unintentionally leaves characteristics of communities, which are often difficult be collected in traditional studies. Individuals with autism such a case, the could facilitate even more communication given its social-spatial distance being characteristic preference autism. Previous studies examined traces left posts online communities (Autism)...
ABSTRACT Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly pathogenic virus that has caused the global COVID-19 pandemic. Tracing evolution and transmission of crucial to respond control pandemic through appropriate intervention strategies. This paper reports analyses genomic mutations in coding regions SARS-CoV-2 their probable protein secondary structure solvent accessibility changes, which are predicted using deep learning models. Prediction results suggest mutation...
Predicting the drug-target interaction is crucial for drug discovery as well repurposing. Machine learning commonly used in affinity (DTA) problem. However, machine model faces cold-start problem where performance drops when predicting of a novel or target. Previous works try to solve cold start by target representation using unsupervised learning. While can be learned an manner, it still lacks information, which critical interaction. To incorporate information into and protein interaction,...
Single-cell RNA-sequencing (scRNAseq) technologies are rapidly evolving. Although very informative, in standard scRNAseq experiments, the spatial organization of cells tissue origin is lost. Conversely, RNA-seq designed to maintain cell localization have limited throughput and gene coverage. Mapping genes with information increases coverage while providing location. However, methods perform such mapping not yet been benchmarked. To fill this gap, we organized DREAM Single-Cell...