Validate docking, pose-prediction, rescoring, and virtual-screening workflows with leakage-aware controls and prespecified metrics. Use before interpreting AutoDock Vina, GNINA, DiffDock, or related docking outputs.
原文の言語: 英語
メニュー
このリポジトリの skills
SkillsMP は eightmm/codex-science から 420 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
eightmm/codex-science収集済み skill 420 件中 40 件を表示しています。
Validate docking, pose-prediction, rescoring, and virtual-screening workflows with leakage-aware controls and prespecified metrics. Use before interpreting AutoDock Vina, GNINA, DiffDock, or related docking outputs.
原文の言語: 英語
Formulate, solve, simulate, and verify electrostatics, magnetostatics, circuits, induction, electromagnetic waves, and boundary-value problems using Maxwell's equations, potentials, constitutive relations, and conservation laws.
原文の言語: 英語
Extract reproducible ESM-2 protein embeddings, residue representations, likelihoods, or zero-shot mutation scores. Use when a frozen protein language model is needed as a feature extractor or baseline.
原文の言語: 英語
Run released Biohub ESMC protein language models for representations, masked likelihoods, sequence scoring, mutation analysis, or sparse-autoencoder features. Use as the current ESMC alternative to ESM-2 when model scale, revision, and inference boundaries…
原文の言語: 英語
Run the legacy public ESMFold v1 single-sequence structure model reproducibly for proteins or simple multimers. Use for the 2022 ESM-2-based model; use the separate ESMFold2 skill for Biohub's 2026 diffusion/all-atom model.
原文の言語: 英語
Run Biohub ESMFold2 locally from the released Hugging Face weights or through the approved Biohub Platform. Use for all-atom prediction of proteins, complexes, DNA, modifications, and ligands with optional MSA input and diffusion sampling; distinct from the…
原文の言語: 英語
Run pinned Evo 2 DNA sequence scoring, embeddings, variant scoring, or controlled generation. Use for long-context genomic foundation-model analyses when compatible local GPU hardware and explicit genome/strand provenance are available.
原文の言語: 英語
Formulate and verify geometry and topology arguments. Use for metric and topological spaces, continuity, compactness, connectedness, manifolds, curves and surfaces, homotopy, covering spaces, Euler characteristic, and geometric invariants.
原文の言語: 英語
Run reproducible local GNINA docking or CNN rescoring on protein-ligand systems. Use when GPU-assisted pose generation, refinement, or CNN reranking is wanted; keep CNN pose score, predicted affinity, and experimental affinity as distinct quantities.
原文の言語: 英語
Prepare and run staged, checkpointed molecular dynamics with a pinned GROMACS build. Use when GROMACS workflows, HPC execution, established .mdp protocols, or interoperability with GROMACS topology/trajectory formats is required.
原文の言語: 英語
Build an evidence-traceable indication dossier for a disease, target, mechanism, drug, biomarker, or therapeutic hypothesis. Use for landscape assessment, target-indication rationale, clinical pipeline review, translational gaps, and evidence-backed go/no-go…
原文の言語: 英語
Formulate and solve inverse problems with stable regularization and calibrated uncertainty. Use for parameter or field recovery, deconvolution, tomography, system identification, data assimilation, Bayesian inversion, and learned inverse models.
原文の言語: 英語
Solve exact and numerical linear algebra problems with explicit field, dimensions, bases, rank structure, conditioning, and residual checks. Use for linear systems, vector spaces, linear maps, eigenproblems, least squares, SVD, quadratic forms, and matrix…
原文の言語: 英語
Identify and quantify support for analytes from mass spectrometry with explicit acquisition context, calibration, false-discovery control, and isomer-aware evidence. Use for GC-MS, LC-MS, MS/MS, accurate mass, isotope patterns, adducts, fragments, library…
原文の言語: 英語
Analyze OpenMM, GROMACS, and other molecular dynamics trajectories with MDAnalysis using topology-aware selections, periodic-boundary handling, prespecified observables, convergence checks, and uncertainty estimates.
原文の言語: 英語
Drive a concrete scientific modeling problem from supplied inputs through model selection, falsifiable plan, one-time approval, environment setup, smoke test, full execution, downstream analysis, provenance, and review. Use when the user provides sequences,…
原文の言語: 英語
Prepare receptors and small molecules for docking or simulation with explicit stereochemistry, protonation, tautomer, charge, conformer, cofactor, water, and pocket provenance. Use before AutoDock Vina, GNINA, DiffDock, OpenMM, GROMACS, or any protein-ligand…
原文の言語: 英語
Process, assign, and verify molecular NMR evidence. Use for 1D or 2D solution NMR, FID processing, chemical shifts, multiplicities, couplings, integrations, COSY, HSQC, HMBC, NOE or ROE evidence, mixture assessment, and molecular structure or stereochemical…
原文の言語: 英語
Formulate and verify nuclear and particle physics calculations. Use for reactions, decays, relativistic kinematics, conservation laws, cross sections, lifetimes, quantum numbers, detector yields, backgrounds, and statistical significance.
原文の言語: 英語
Classify, solve, approximate, and verify ordinary and partial differential equations with explicit domains, initial or boundary data, well-posedness, residuals, and convergence checks. Use for IVPs, BVPs, dynamical systems, eigenvalue problems, Fourier…
原文の言語: 英語
Parameterize drug-like small molecules for molecular simulation with pinned OpenFF Toolkit/force fields and explicit charge, stereochemistry, and coverage checks. Use before OpenMM or GROMACS when ligands or nonstandard organic molecules need parameters.
原文の言語: 英語
Run pinned OpenFold3 preview inference for proteins, nucleic acids, noncanonical residues, and small-molecule complexes. Use when an open AlphaFold3-style workflow is wanted and preview-status limitations are acceptable.
原文の言語: 英語
Build, equilibrate, run, checkpoint, and analyze reproducible molecular dynamics with OpenMM. Use for proteins, nucleic acids, solvated complexes, or parameterized protein-ligand systems when local CPU/GPU simulation is requested.
原文の言語: 英語
Model and verify optical and wave phenomena. Use for ray optics, wave propagation, polarization, interference, diffraction, coherence, resonators, dispersion, scattering, imaging, and electromagnetic boundary problems.
原文の言語: 英語
Formulate, solve, and verify finite-dimensional optimization and calculus-of-variations problems. Use for convex programs, constrained extrema, KKT systems, duality, optimal control, Euler-Lagrange equations, and numerical optimization.
原文の言語: 英語
Profile noncovalent protein-ligand interactions with a pinned PLIP release and compare interaction fingerprints across experimental structures, docking poses, or trajectory representatives. Use after structure preparation or pose generation.
原文の言語: 英語
Formulate, solve, simulate, and verify probability and stochastic-process problems. Use for conditional probability, random variables, limit theorems, Markov chains, Poisson processes, martingales, stochastic simulation, and uncertainty in random systems.
原文の言語: 英語
Design or score protein sequences for fixed backbones with ProteinMPNN, LigandMPNN, or SolubleMPNN. Use for backbone-conditioned design, ligand-context design, soluble-protein design, residue constraints, or side-chain packing.
原文の言語: 英語
Run pinned Protenix structure prediction for protein, nucleic-acid, ligand, antibody-antigen, template, MSA, or constrained complexes. Use Protenix-v2 or another explicitly selected released model with a recorded training-data cutoff and inference budget.
原文の言語: 英語
Formulate, solve, simulate, and verify nonrelativistic quantum mechanics problems using states, operators, boundary conditions, symmetries, stationary and time-dependent evolution, approximation methods, measurement, and open-system dynamics.
原文の言語: 英語
Formulate and verify special- and general-relativity problems. Use for Lorentz transformations, four-vectors, relativistic kinematics, metrics, geodesics, curvature, gravitational fields, horizons, and stress-energy dynamics.
原文の言語: 英語
Run pinned RFdiffusion for unconditional generation, motif scaffolding, binder backbones, symmetric assemblies, partial diffusion, or macrocyclic peptide design. Use when structural conditioning and a downstream sequence/refolding validation funnel are…
原文の言語: 英語
Run RoseTTAFold All-Atom for proteins, nucleic acids, small molecules, metals, covalent modifications, and higher-order assemblies. Use when its Hydra input model and confidence metrics fit the problem and licensed dependencies are available.
原文の言語: 英語
Run pinned scGPT checkpoints for single-cell embeddings, cell-type annotation, reference mapping, perturbation modeling, or fine-tuning. Use when a pretrained single-cell transformer is requested and donor/batch/feature provenance can be preserved.
原文の言語: 英語
Build and evaluate reproducible scvi-tools workflows for single-cell RNA, protein, chromatin, spatial, or multimodal data using scVI, scANVI, totalVI, MultiVI, PeakVI, DestVI, or related models.
原文の言語: 英語
Run Apple's released SimpleFold flow-matching protein structure models with PyTorch or MLX. Use for single-protein folding, conformer ensembles, or Apple-silicon inference when model-size and model-license constraints are acceptable.
原文の言語: 英語
Analyze experimental spectra with traceable preprocessing, calibration, peak or band inference, uncertainty, and alternative-model checks. Use for UV-Vis, fluorescence, IR, Raman, absorbance, emission, reflectance, and related one-dimensional spectral…
原文の言語: 英語
Compute and verify tensor-calculus and differential-geometry results. Use for coordinate transformations, metrics, differential forms, covariant derivatives, connections, geodesics, curvature, Lie derivatives, and coordinate-independent geometric identities.
原文の言語: 英語
Solve and verify equilibrium thermodynamics and statistical mechanics problems using explicit systems, sign conventions, equations of state, thermodynamic potentials, ensembles, partition functions, fluctuations, and phase-equilibrium conditions.
原文の言語: 英語
Analyze and verify X-ray diffraction and scattering data. Use for powder XRD, phase identification, indexing, lattice parameters, Rietveld refinement, crystallite size or strain, texture, amorphous content, SAXS, WAXS, pair distributions, and comparison with…
原文の言語: 英語