Bioinformatics and Multi-Omics: NGS, Transcriptomics, Single-Cell and Spatial Biology, Digital Pathology, and Machine Learning (Bioluminescence: From Sequences to Systems)

From "what is a FASTQ file" to models you can defend.

A self-contained course that takes you from the first line of shell to building and honestly evaluating deep-learning and generative models on genomic, single-cell, spatial, and histopathology data — and applying them to disease biology and drug discovery. Every concept is explained from first principles, with runnable code, comparison tables, and worked exercises. Nothing here says "see the literature" in place of an explanation.

Written for three readers at once

• Wet-lab biologists and clinicians who know the biology and the data, and need the command line, the statistics, and the modelling.
• CS and ML people who know models and evaluation, and need molecular biology, assay artefacts, and the reasons biological data breaks i.i.d. assumptions.
• Bioinformaticians levelling up from pipelines and standard analyses into modern single-cell and spatial methods, deep learning, foundation models, and drug discovery.

There is no prerequisite beyond high-school biology and a willingness to type commands into a terminal.

In this volume

• Module 1 — The Working Environment and Toolkit. Shell, conda environments, Python and pandas, R and Bioconductor, Jupyter, git, SLURM, and where public data lives.
• Module 2 — Molecular Biology as a Data Model. The central dogma in coordinates, 0- vs 1-based indexing, assemblies and liftover, identifiers, variation, ontologies.
• Module 3 — Sequences, Alignment, and the Databases. FASTQ/SAM/BAM/VCF/BED/GFF anatomy, Needleman–Wunsch and Smith–Waterman worked by hand, BLAST statistics, the BWT and FM-index, profile HMMs, phylogenetics, and the NCBI/Ensembl/UniProt APIs.
• Module 4 — Next-Generation Sequencing, End to End. Platform chemistries and error profiles, depth mathematics, QC, alignment, germline and somatic calling, SV and CNV, ChIP/ATAC/Hi-C/methylation, long reads, Snakemake and Nextflow.
• Module 5 — Bulk Transcriptomics. Library prep consequences, salmon vs STAR, normalisation, the negative binomial, DESeq2/edgeR/limma end to end, GSEA done properly, WGCNA, deconvolution.
• Module 6 — Single-Cell Transcriptomics and Multi-Omics. Chemistries, ambient RNA and doublets, the normalisation debate, clustering and annotation, integration and benchmarking, pseudobulk DE, trajectories, CITE-seq and multiome.
• Module 7 — Spatial Transcriptomics and Spatial Biology. Visium and Stereo-seq against MERFISH, Xenium and CosMx; deconvolution vs segmentation; Moran's I; spatial domains; ligand–receptor inference.
• Module 8 — Histology, Digital Pathology, and Tissue Imaging. What pathologists score, whole-slide image formats, tiling and stain normalisation, attention-MIL implemented from scratch, pathology foundation models, site confounding.
• Module 9 — Machine Learning for Biological Data. Bias–variance derived, p ≫ n, nested and grouped cross-validation, calibration, the full leakage taxonomy, a leakage-free worked pipeline.
• Module 10 — Deep Learning for Biology. Backprop by hand, PyTorch, CNNs and transformers and GNNs derived, the genomics model zoo, protein models and AlphaFold confidence, a complete trained example with chromosome-held-out splits.

The companion volume, Artificial Intelligence and Large Language Models for Biology, covers language models of biology, generative design, drug discovery, precision medicine, reproducible practice, and ten graded capstone projects, and carries the full glossary and cheatsheets.

Dr. Ashok Kumar Dwivedi