Pavel-Kravchenko

scRNA-seq dimensionality reduction and clustering using PCA, k-NN graph, UMAP, and Leiden. Includes a guide for parameter selection, implementation patterns, and common pitfalls.

In silico restriction digestion, compatible end detection, primer design (Tm models), and gel simulation.

Genome-Wide Association Studies (GWAS) using NumPy.

Isoform analysis with long reads, featuring Minimap2 for splice alignment, bambu for isoform discovery, and DRIMSeq for differential isoform usage.

scRNA-seq trajectory analysis: pseudotime (DPT), PAGA graph abstraction, and RNA velocity (scVelo). Decision guide, key parameters, and pitfalls.

Viral genome assembly, intra-host variant calling, phylodynamics, and real-time surveillance.

Vision-language model inference patterns for scientific documents.

RNA-seq differential expression analysis and normalization workflows.

Pattern matching algorithms: naive, KMP (failure function), Rabin-Karp (rolling hash), and DFA-based matching for sequence search.

Genomic Foundation Models: Nucleotide Transformers, HyenaDNA, and Evo with NumPy.

A self-balancing BST (Adelson-Velsky & Landis, 1962) guaranteeing O(log n) operations via rotation-based rebalancing.

Dijkstra's Algorithm: Shortest Paths in Weighted Graphs

Suffix trees are compressed tries of all suffixes, enabling O(m) pattern search and O(n) construction via Ukkonen's algorithm.

V(D)J Recombination and Adaptive Immune Receptors

Differential binding analysis for ChIP-seq, covering DiffBind workflow, consensus peaks, normalization, and MA/volcano plots. Useful for comparing ChIP-seq signals across different conditions.

ESM2 Embeddings and ESMFold with NumPy

Module T5-01B: LLM Training Systems (Tracking, Epochs, and Ablations) with Pandas

Zero-Shot Mutation Effect Prediction with NumPy

A singly linked list with a full implementation, featuring head/tail pointers, operations for insert, delete, search, and reverse, along with a complexity table.

Red-black tree: a self-balancing BST with O(log n) operations, maintaining 5 invariants, and fixing insertions with rotations and recoloring.

Metagenomic assembly with MEGAHIT, contig binning with MetaBAT2, and MAG quality assessment with CheckM. Includes binning signals, multi-sample strategy, and MIMAG quality tiers.

Bottom-up Dynamic Programming with tabulation, covering edit distance, LCS, and space optimization using rolling arrays.

Virtual screening for drug discovery: pharmacophore modeling, docking score filtering, and ADMET prediction. Use when computationally screening compound libraries.

Score matching, noise schedules, DDIM sampling, and DDRM inverse problems for diffusion generative models.

Splicing Models: SpliceAI and AlphaGenome with NumPy

Knapsack DP variants, including 0/1, unbounded, and subset sum, with traceback and space optimization.

AlphaFold/ESMFold structure prediction and confidence interpretation.

DNA copy number analysis — read depth normalization, CBS segmentation, CN state calling, and genome-wide visualization.

Flux balance analysis and metabolic modeling with COBRApy. Use when predicting metabolic fluxes, simulating gene knockouts, or analyzing stoichiometric models.

Geneformer and scGPT for Single-Cell Modeling.

Multi-pattern string matching in O(n + m + z) via a trie augmented with KMP-style failure links.

Hash tables (chaining vs open addressing) and Bloom filters: complexity, trade-offs, and implementation patterns.

ChIP-seq pipeline covering quality control, alignment, deduplication, peak calling using MACS2, and signal normalization with deepTools.

Functional Annotation of Metagenomes with NumPy

Enformer architecture for regulatory prediction from DNA, in-silico mutagenesis (ISM), and variant prioritization.

BST operations and complexity, with a clean implementation using parent pointers to support all standard operations.

ATAC-seq quality control and accessibility analysis.

Cancer transcriptomics for melanoma subtype classification (Tirosh/Harbst), employing a preprocessing pipeline, PCA/t-SNE, hierarchical clustering, random forest, and Kaplan-Meier survival analysis.

Multi-omics data harmonization, encompassing normalization strategies, missing data imputation, batch correction, and integration approaches such as MOFA2 and DIABLO.

Epigenetic Clocks and Aging Analysis with Matplotlib

Rabin-Karp hash-based string matching uses a rolling hash for O(n+m) average time complexity and excels at multi-pattern search.

Quick reference for bioinformatics file formats — FASTA, FASTQ, SAM/BAM/CRAM, VCF, BED, GFF/GTF, BigWig, PDB, Newick — specs, coordinate systems, and parsing patterns.

Clinical genomics, covering ACMG/AMP variant classification, ClinVar queries, and clinical reporting workflows.

Differentially Methylated Regions (DMRs)

Metabolite identification from MS/MS spectra: spectral matching, molecular formula prediction, and database searching (HMDB, KEGG). Use when annotating unknown metabolites.

MOFA2 is an unsupervised multi-omics factor analysis for variance decomposition, factor interpretation, and shared/view-specific signal separation. Use it when integrating multiple omics layers.

Molecular Modeling with NumPy

ONT Data Processing with NumPy