Learning ON Large Datasets Using Bit-String Trees

TL;DR

This paper introduces novel computational methods including ComBI for fast approximate nearest-neighbor search, GRAF for ensemble classification, and CRCS for interpreting genetic mutations, enabling scalable and interpretable analysis of large biomedical datasets.

Contribution

It presents new algorithms—ComBI, GRAF, and CRCS—that improve efficiency, accuracy, and interpretability in large-scale data analysis and biomedical research.

Findings

ComBI achieves 0.90 precision with up to 296X speed-up on billion-sample datasets.

GRAF outperforms traditional classifiers across 115 datasets in accuracy.

CRCS effectively identifies driver mutations and predicts cancer survival.

Abstract

This thesis develops computational methods in similarity-preserving hashing, classification, and cancer genomics. Standard space partitioning-based hashing relies on Binary Search Trees (BSTs), but their exponential growth and sparsity hinder efficiency. To overcome this, we introduce Compressed BST of Inverted hash tables (ComBI), which enables fast approximate nearest-neighbor search with reduced memory. On datasets of up to one billion samples, ComBI achieves 0.90 precision with 4X-296X speed-ups over Multi-Index Hashing, and also outperforms Cellfishing.jl on single-cell RNA-seq searches with 2X-13X gains. Building on hashing structures, we propose Guided Random Forest (GRAF), a tree-based ensemble classifier that integrates global and local partitioning, bridging decision trees and boosting while reducing generalization error. Across 115 datasets, GRAF delivers competitive or superior accuracy, and its unsupervised variant (uGRAF) supports guided hashing and importance sampling. We show that GRAF and ComBI can be used to estimate per-sample classifiability, which enables scalable prediction of cancer patient survival. To address challenges in interpreting mutations, we introduce Continuous Representation of Codon Switches (CRCS), a deep learning framework that embeds genetic changes into numerical vectors. CRCS allows identification of somatic mutations without matched normals, discovery of driver genes, and scoring of tumor mutations, with survival prediction validated in bladder, liver, and brain cancers. Together, these methods provide efficient, scalable, and interpretable tools for large-scale data analysis and biomedical applications.