Pavel-Kravchenko/Bioinformatics

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Fetch sequences from NCBI Entrez/UniProt/PDB/Ensembl REST APIs via BioPython SeqIO; read/write FASTA/GenBank/FASTQ. Use when downloading by accession/gene name, batch-fetching records, or converting sequence file formats.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Parse SMILES/SDF with RDKit, build ChEMBL QSAR models, dock ligands with AutoDock Vina, predict ADMET/Lipinski properties. Use for compound screening, Tanimoto similarity, Rule of Five filtering.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Align/call ChIP-seq peaks with Bowtie2+MACS3, run DiffBind binding and ChIPseeker annotation in R, visualize with deepTools. Use for TF/histone peak calling, narrow vs broad peaks, FRiP/NSC/RSC QC, or peak annotation.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Classify variants via ACMG/AMP + CADD/REVEL/SpliceAI; dock ligands with AutoDock Vina; set up GROMACS MD; run Scanpy scRNA-seq QC/clustering. Use for variant classification, docking, MD setup, or scRNA-seq.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Align WGBS/RRBS bisulfite reads with Bismark; call DMRs/DMPs with methylKit or BSmooth. Use when analyzing bisulfite sequencing, CpG beta values, .cov/cytosinereport files, or DNAm epigenetic age (Horvath/GrimAge).

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Retrieve PDF/image pages with ColPali late-interaction embeddings and answer questions via Qwen2-VL/LLaVA. Use when doing document RAG, PDF QA, or retrieval over scanned papers/reports.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Write robust Bash scripts to batch-process FASTQ/BAM/VCF/FASTA files: variables, set -euo pipefail error handling, loops over sample sheets, functions, traps, and awk/sed text processing. Use when automating a multi-sample pipeline, writing a shell wrapper around samtools/bcftools/fastqc/blast, validating CLI input…

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run t-test/Mann-Whitney/ANOVA/chi-square tests, BH-FDR correction, and power analysis in SciPy, statsmodels, R. Use when comparing groups, interpreting p-values/CIs, correcting many gene-level tests, or sizing an experiment.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Fix UTF-8/Latin-1/CP1251 decode errors, strip BOM, repair mojibake, normalize CRLF endings, remove hidden Unicode in FASTA/GFF text. Use when hitting UnicodeDecodeError or garbled text from Windows/Excel exports.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Version-control bioinformatics scripts with git init/add/commit/branch/merge/stash/tag and .gitignore for FASTQ/BAM/VCF. Use when setting up a repo, undoing a commit, or resolving a merge conflict.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Linux CLI basics: cp/mv/rm, grep/awk/find, pipes, chmod, gzip/tar, wget/scp/rsync, ps/kill. Use when writing a bash pipeline, inspecting FASTA/FASTQ/BAM/BED/VCF on a server, or filtering lines with grep/awk.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Model bioinformatics data with probability distributions (Normal, Binomial, Poisson, Negative Binomial) using scipy.stats — compute PMF/PDF/CDF/SF/PPF, simulate variant allele counts, mutation rates, and RNA-seq overdispersion. Use when doing probability calculations, distribution fitting, p-value derivation from a…

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Read/write R syntax for bioinformatics (vectors, data.frame, matrices, d/p/q/r distributions, DESeq2). Use when porting Python to R, debugging R from a paper/pipeline, or running DESeq2/edgeR/Seurat scripts.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run exact/nonparametric hypothesis tests in R: binom.test, sign test, wilcox.test/wilcox.exact (Wilcoxon signed-rank and Mann-Whitney U), kruskal.test with Dunn post-hoc, Hodges-Lehmann CIs, and binomial power/sample-size functions. Use when a user asks to test proportions, compare paired or independent samples that…

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Fit/diagnose R lm() regression and compute Pearson/Spearman/Kendall correlation with Fisher z CIs. Use for lm() regression, residual diagnostics, correlation CIs, or t.test/shapiro.test checks.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run scipy.stats/statsmodels tests (t-test, Mann-Whitney, ANOVA, chi-square, Fisher's exact, Pearson/Spearman) on expression/count/genotype data. Use when comparing groups, correcting p-values (FDR), or computing power/sample size in Python.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Restore images (denoising, inpainting, super-resolution) via DDRM SVD data-consistency projection with DDIM diffusion sampling in NumPy. Use for cryo-EM/MRI restoration or inverse problems y=Hx with a diffusion prior.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Choose/run DNA foundation models (Nucleotide Transformer, HyenaDNA, Evo, Enformer, Borzoi) via transformers: embed sequences, fine-tune, score variants with Enformer ISM. Use for genomic LLM choice or variant scoring.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Build DNA embeddings via k-mer frequency vectors or genomic LMs (Nucleotide Transformer, DNABERT-2, HyenaDNA). Use when embedding DNA for ML, choosing k-mer/BPE tokenization, or probing embedding quality.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Route coding variants to AlphaFold2/3 or RoseTTAFold and rank by missense/expression/rarity evidence weighted by pLDDT/PAE confidence. Use when triaging variants for structure prediction or picking AlphaFold vs RoseTTAFold.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Implement BFS/DFS, Dijkstra, Kruskal/Prim MST, topological sort, and DP (knapsack, Needleman-Wunsch, Smith-Waterman) in Python. Use for from-scratch alignment, PPI shortest paths, phylogenetic MST, gene-panel knapsack selection.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Analyze scTCR/BCR-seq with scirpy on 10x VDJ contigs, type HLA with OptiType, and score neoantigens with NetMHCpan/pVACseq. Use when doing clonotype/repertoire analysis, HLA typing, or building neoantigen pipelines.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Implement Python linked lists, stacks/queues, BST/AVL/Red-Black trees, hash tables, Bloom filters with Big-O tradeoffs. Use when choosing a data structure, k-mer hash counting, VCF dedup Bloom filters, or interval trees.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Write set -euo pipefail bash pipelines, parse FASTA/FASTQ/VCF/GTF/BED with grep/awk/sed and BAM with samtools, and run git workflows. Use when writing/debugging shell scripts or fixing git/BOM/CRLF issues.