We present RNAVelocity, a complete RNA velocity analysis engine implemented entirely in Python using NumPy and SciPy — no scVelo, velocyto, loom, or anndata required. RNAVelocity implements four velocity models: (1) steady-state ratio estimation (La Manno et al.
Predict drug-target interactions using machine learning and structural features. Supports binding affinity prediction, virtual screening, and polypharmacology analysis for computational drug discovery workflows.
Analyze CRISPR-Cas systems and predict optimal gene editing targets. Supports sgRNA design, off-target analysis, PAM site identification, and efficiency scoring for CRISPR-based gene editing experiments.
Predict and analyze RNA secondary and tertiary structures. Supports minimum free energy folding, pseudoknot detection, RNA-RNA interaction prediction, and comparative structure analysis for ncRNA research.
Predict protein stability changes upon mutation and analyze thermal stability. Supports ddG calculation, thermodynamic analysis, and stability hotspot identification for protein engineering applications.
Analyze multi-state protein systems and conformational dynamics. Supports ensemble analysis, principal component analysis, and free energy landscape construction for studying protein functional motions.
Perform cross-species sequence alignments and evolutionary analysis. Supports multiple sequence alignment, phylogenetic tree construction, orthology detection, and conservation scoring for comparative genomics.
Virtual screening pipeline for peptide drug discovery and antigen design. Supports peptide library generation, molecular docking, ADMET prediction, and immunogenicity assessment for peptide-based therapeutic development.
Comprehensive protein structure prediction and analysis pipeline combining multiple computational methods. Supports homology modeling, ab initio prediction, structure refinement, and quality assessment for protein structure determination.
Analyze antibody-antigen interactions and predict immune epitopes. Supports B-cell epitope prediction, T-cell epitope mapping, and antigenicity analysis for vaccine development and immunological research.
Predict the functional impact of protein mutations using sequence and structural features. Supports nsSNP analysis, pathogenicity scoring, and structural stability changes for variant interpretation.
Screen and analyze protein-protein interactions using comprehensive databases and computational methods. Supports interaction network visualization, confidence scoring, and functional enrichment analysis for PPI datasets.
A comprehensive molecular dynamics pipeline supporting simulation setup, execution, and trajectory analysis. Features include system preparation, equilibration protocols, production run management, and detailed trajectory analysis with RMSD, RMSF, and hydrogen bond calculations.
Perform Gene Ontology enrichment analysis on gene sets. Supports multiple testing correction methods including Bonferroni, FDR, and Fisher exact test.
Align and compare protein 3D structures using advanced algorithms. Supports TM-align, RMSD calculation, structural superposition, and generates comprehensive similarity reports for protein structure analysis.
Calculate comprehensive protein properties including molecular weight, isoelectric point, amino acid composition, hydropathy index, GRAVY score, instability index, and secondary structure predictions from amino acid sequences.
Perform global or local sequence alignment on DNA, RNA, or protein sequences using various algorithms. Supports multiple alignment methods including Needleman-Wunsch and Smith-Waterman for bioinformatics analysis.
A comprehensive tool for analyzing PDB protein structure files. Features include structure validation, quality metrics calculation, residue interaction analysis, and visualization support for bioinformatics research.
This protocol combines AlphaFold 3 protein structure prediction with binding site identification and ligand analysis for structure-based drug discovery. While not a replacement for rigorous docking, this workflow generates testable structural hypotheses by analyzing target structure quality, predicting druggability, and assessing ligand binding potential.
Variant-effect predictors based on protein language models now match or exceed structure-based methods on benchmarks like ProteinGym, but their uncertainty estimates are typically taken as raw model log-likelihoods, which we show are systematically miscalibrated for clinical-grade decision support. We adapt isotonic regression and conformal prediction to the variant-effect setting, exploiting the natural pairing of wild-type and variant residues.