Pavel-Kravchenko/Bioinformatics

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run GWAS: SNP QC (MAF/HWE), PCA ancestry covariates, per-SNP logistic/linear regression, Manhattan/QQ plots, genomic inflation, LD clumping. Use when doing GWAS, SNP-array association, or stratification correction.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Type HLA-A/B/C/DRB1 with OptiType/arcasHLA and predict peptide-MHC binding (NetMHCpan %RankEL/IC50) to rank neoantigens. Use for HLA typing, MHC binding, pVACseq, HLA LOH, or HLA-B57:01 screening.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Analyze TCR/BCR repertoires with scirpy: import MiXCR/10x/AIRR clonotypes, define clonotypes, compute clonal expansion/diversity/VDJ usage. Use when analyzing scTCR-seq/scBCR-seq, clonotype tables, or CDR3 spectratypes.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Align ONT/PacBio long reads with Minimap2 splice, call isoforms with bambu (NDR), test differential isoform usage with DRIMSeq. Use for long-read transcriptomics, novel isoform calling, or DTU/isoform-switch analysis.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Preprocess raw LC-MS mzML with XCMS centWave peak picking, obiwarp RT alignment, gap filling, PQN/QC normalization, adduct grouping. Use when building an XCMS pipeline or preprocessing untargeted metabolomics runs.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Classify StringTie/gffcompare transcripts into lncRNA subtypes by class code/length/TPM, score coding potential with CPC2/CPAT, detect circRNAs via CIRI2 BSJ reads. Use for lncRNA annotation or circRNA calls.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Engineer k-mer/GC/CpG DNA features, train scikit-learn classifiers (LogisticRegression, RandomForest, SVC), evaluate with CV/ROC-AUC. Use for promoter/variant classifiers or model comparison on omics features.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run MAGeCK count/test on pooled CRISPR sgRNA screens, scoring gene essentiality via RRA, FDR, and log2 fold-change. Use when analyzing CRISPR screen FASTQ/count data, calling essential or drug-resistance genes, or benchmarking vs DepMap.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run flux balance analysis (FBA/FVA) on genome-scale metabolic models (E. coli core, Recon3D, AGORA2) with COBRApy; simulate single/double gene knockouts and integrate RNA-seq expression via GIMME/iMAT. Use when predicting metabolic fluxes, finding essential genes or drug targets, doing synthetic lethality screens, or…

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Assign molecular formulas from accurate mass/adducts and match MS/MS spectra by cosine similarity to GNPS/MassBank/HMDB. Use for LC-MS peak annotation, MSI confidence scoring, or KEGG metabolite enrichment (MSEA).

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Compute alpha/beta diversity (Shannon, Simpson, Bray-Curtis, UniFrac) from a 16S/ASV feature table with scikit-bio; PCoA ordination, PERMANOVA/ANOSIM. Use for microbiome diversity or community composition questions.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Trim adapters (cutadapt), align to miRBase with Bowtie, quantify with featureCounts, run DESeq2/CPM DE testing and seed-match target prediction. Use for miRNA-seq/small RNA FASTQ processing or miRNA target prediction.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run mixOmics PLS-DA/sPLS-DA/DIABLO to classify samples and pick stable biomarkers from paired RNA-seq/proteomics/methylation blocks. Use for supervised multi-omics classification or DIABLO biomarker discovery.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Run MOFA2 (mofapy2/muon) to fuse RNA-seq, proteomics, methylation into latent factors; decompose per-view R2, interpret weights. Use for multi-omics integration, MOFA/MOFA2 analysis, or latent factor discovery.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Test Hardy-Weinberg equilibrium, simulate Wright-Fisher drift/selection, and compute dN/dS, Tajima's D, and Fst with NumPy/SciPy. Use for neutral theory, molecular clock divergence time, selection scans, or effective population size (Ne) questions.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Train PyTorch Geometric GCN/MPNN on SMILES-derived molecular graphs to predict properties (BBBP, solubility, toxicity); compare vs Morgan-fingerprint RF. Use for GNN property prediction or SMILES-to-graph pipelines.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Compute force-field energy terms (bond/LJ/Coulomb), run energy minimization, and QC MD/homology models (RMSD, RMSF, Ramachandran) in NumPy. Use for force-field, minimization, or homology/docking validation.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Detect PPI/co-expression modules with NetworkX/python-louvain/leidenalg (Louvain, Leiden, modularity Q) and WGCNA eigengenes. Use when clustering a gene network, computing WGCNA modules, or testing DEG/pathway enrichment on network communities.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Decode Phred+33 FASTQ quality scores, compute FastQC-style per-position QC stats, and sliding-window trim reads in Python. Use when parsing FASTQ, decoding quality ASCII, or choosing Illumina/PacBio/Nanopore.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Interpolate missing time points (Newton/cubic spline), estimate derivatives, and compute AUC via trapezoidal/Simpson/curvefit in SciPy. Use for missing qPCR points, PK dC/dt, dose-response/ROC AUC, or Michaelis-Menten/Hill fits.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Basecall ONT POD5/FAST5 signal with Dorado (fast/hac/sup, duplex, 5mC/5hmC), QC with NanoStat/NanoPlot, filter with NanoFilt, and align with Minimap2 map-ont. Use for nanopore raw-signal processing, Q-score/length read filtering, N50 computation, or a POD5-to-aligned-BAM pipeline.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Build time-scaled phylogenies with TreeTime/Augur, validate clock via root-to-tip regression, interpret BEAST2 skyline plots and phylogeography. Use when dating an outbreak, estimating TMRCA, R0, or Ne(t).

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Test Hardy-Weinberg equilibrium, simulate Wright-Fisher drift/selection, and compute dN/dS, Tajima's D, Fst, LD with NumPy/SciPy. Use for allele-frequency, selection, or population-structure questions.

Pavel-Kravchenko/Bioinformatics

Skill Claude CodeCodex

Build and analyze protein-protein interaction (PPI) networks from STRING DB with NetworkX: compute degree/betweenness/closeness/eigenvector centrality, classify hub and bottleneck genes, test scale-free topology, and detect network communities/modules (Louvain, greedy modularity). Use when asked to find hub genes…