Welcome
Bioinformatics is a rapidly advancing interdisciplinary field that combines principles from biology, computer science, and mathematics to analyze and interpret complex biological data. The emergence of high-throughput sequencing technologies and advanced data collection methods has granted researchers access to vast amounts of biological data, including genomic sequences, protein structures, and metabolic pathways. However, extracting meaningful insights from this data poses significant challenges due to its complexity and the intricate patterns that often remain hidden within.
Pattern mining (PM) and machine learning (ML) have emerged as powerful methodologies that enable bioinformatics researchers to uncover hidden relationships, predict biological outcomes, and make informed, data-driven decisions. PM techniques, such as frequent itemset mining (FIM) and clustering, facilitate the identification of recurrent patterns and associations in biological datasets, leading to new discoveries in areas such as disease diagnosis, drug discovery, and personalized medicine. Concurrently, ML provides robust frameworks for extracting valuable information, modeling complex biological phenomena, and enhancing predictive accuracy.
The objective of the PM4B 2025 workshop is to establish a collaborative platform for researchers and practitioners to share theoretical advancements and practical applications of PM and ML in bioinformatics. The primary goal is to identify and explore new research directions that leverage biological data through PM and ML, as well as their integration, to ultimately generate a profound impact on society. Additionally, the workshop will provide a networking opportunity to foster collaborations among researchers, industry professionals, and students interested in bioinformatics. The workshop will contribute to the PAKDD conference by attracting researchers interested in bioinformatics-related topics of data science and ML.
Scope
Topics of interest for the PM4B 2025 workshop include, but are not limited to following:
- Pattern Mining-based Approaches
- Discovering sequential patterns in biological sequences (e.g., DNA, RNA, protein sequences).
- PM for gene expression analysis.
- PM for the identification and characterization of modified nucleotides in RNA sequences.
- PM to identify relationships between genetic markers and diseases.
- Pattern recognition in genomic sequences for mutation detection.
- PM to uncover relationships between nucleotide metabolism and disease states.
- PM techniques in high-throughput sequencing data (e.g., RNA-Seq, ChIP-Seq).
- Causal discovery and graph mining-based approaches for biological data
- Discovering regulatory patterns in gene networks and pathways.
- Impact of PM on data privacy and security in biological research.
- PM for associating nucleotide variations with phenotypic traits.
- Machine learning-based Approaches
- Supervised learning for predicting disease outcomes based on genomic data.
- Unsupervised learning for clustering biological samples and genes.
- Deep learning in image analysis for bioimaging and histopathology.
- ML to predict the 3D structures of nucleic acids.
- ML methods for analyzing large-scale proteomics data.
- Explainable ML techniques for biological data analysis.
- Identification of DNA-protein binding sites
- Predictive modeling for patient stratification and treatment response.
- Integrated Approaches
- Hybrid approaches combining PM with ML for enhanced predictive modeling.
- Analysis of biological networks using PM and ML techniques.
- PM and ML-based decision support systems.
- ML for integrating multi-omics data to understand complex biological systems.
- Biological Data Management and Processing:
- Data quality issues and preprocessing in bioinformatics.
- Privacy-preserving PM and ML for bioinformatics
- Biological data storage, processing, compression, and querying
- Applications and case studies
- Case studies showcasing the effectiveness of integrated methodologies in bioinformatics.
- Real-world applications of PM and ML in clinical settings.
- Success stories in disease diagnosis and personalized medicine.
- Emerging trends in PM and ML in bioinformatics.
- Integration of multi-omics data for comprehensive biological insights.
- Advanced visualization techniques foddr complex biological data.
- Scalability and performance optimization in PM and ML algorith
Publication
Authors of accepted papers will be invited to extend their paper for a special issue in:
lEEE Journal of Biomedical and Health Informatics (SCI Q1, Impact factor: 6.7)
A "best paper award" will be awarded for the best paper of the PM4B 2025 workshop.
Contact
For any questions, please contact the organizing committee.
