Representation Learning for Genomic Data Analysis
Invited talk on sequence-based deep learning approaches for genomic data, including chaos-game representations, hashing-based embeddings, and protein language models.
Talks
Invited academic talks and selected conference presentations.
Invited talks
MIK: Modified Isolation Kernel for Biological Sequence Visualization, Classification, and Clustering
Representation Learning and Sequence Analysis Using AI
Molecular Sequence Analysis and the Role of AI
Virus2Vec: Viral Sequence Classification Using Machine Learning
Efficient Sequence Embedding for SARS-CoV-2 Variants Classification
Representation Learning for Attributed Graphs
Selected conference presentations
BioSequence2Vec: Efficient Embedding Generation for Biological Sequences
PCD2Vec: A Poisson Correction Distance-Based Approach for Viral Host Classification
Empowering Pandemic Response with Federated Learning for Protein Sequence Data Analysis
Hilbert Curve Based Molecular Sequence Analysis
Spike2Vec: An Efficient and Scalable Embedding Approach for COVID-19 Spike Sequences
Preserving Hidden Hierarchical Structure: Poincaré Distance for Enhanced Genomic Sequence Analysis
A New Direction in Membranolytic Anticancer Peptides Classification: Combining Spaced k-Mers with Chaos Game Representation
Conference travel supported by 21 awards (NSF, ACM, SIAM, IEEE) including SIGIR, FAccT, PerCom, BigData, SDM, SaTML, AACR-KCA, and others. See full CV for complete listings.