数据与 AI技能

Use Evo 2 to score DNA sequences, turn genomic regions into numerical representations for classification, and generate sequences from a supplied prefix. Compare reference and variant sequences or assess coding and regulatory regions across species.

中文简介正在准备中。当前显示英语简介。

• Comparing scores before and after a DNA variant
• Preparing numerical features for genomic region classification
• Generating DNA from a supplied prefix

Predict three-dimensional structures of complexes containing proteins, RNA, DNA, and small molecules with Chai-1. Compare candidate structures using confidence scores and clash indicators, or run repeated predictions from Python to evaluate designed binders.

中文简介正在准备中。当前显示英语简介。

• Predicting antibody–antigen complex structures
• Evaluating protein–ligand binding structures
• Reassessing designed binders

Predict how a small molecule may sit within a protein using structural inputs. Generate ranked 3D poses without defining a search region, then use those poses as starting points for further evaluation.

中文简介正在准备中。当前显示英语简介。

• Predicting ligand poses from a protein structure and SMILES
• Generating ranked poses for a small fragment library
• Preparing starting poses for downstream rescoring

Predict patterns of gene expression and other genomic measurements from DNA sequences with Borzoi. Compare reference and altered sequences to estimate regulatory effects, generate predicted coverage tracks, and prioritize variants in regions that do not encode proteins.

中文简介正在准备中。当前显示英语简介。

• Comparing predicted effects before and after a DNA variant
• Generating predicted coverage tracks for a genomic region
• Prioritizing variants in non-coding regions

Analyze single-cell RNA sequencing data with scVI and scANVI. Combine experimental batches while correcting technical differences, produce compact cell features for clustering, assign cell types using reference labels, and assess differences in gene expression between groups.

中文简介正在准备中。当前显示英语简介。

• Integrating single-cell RNA sequencing batches
• Preparing cell features for clustering
• Assigning cell types from reference annotations

Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.

中文简介正在准备中。当前显示英语简介。

• Predicting complex structures from single sequences
• Assessing designed binders with ESMFold2-Fast
• Predicting structures using aligned related sequences

Predict structures for single proteins or protein complexes with AlphaFold2 through ColabFold. Use confidence scores and comparisons with a designed structure to assess whether a designed sequence folds as intended.

中文简介正在准备中。当前显示英语简介。

• Predicting a single protein's structure from its sequence
• Predicting structures of protein complexes
• Checking designed sequences against a target structure

Use scGPT to convert single-cell gene expression data into numerical representations of cells and genes. These representations support clustering, data integration, cell-type annotation, and analyses of gene perturbations or regulatory relationships.

中文简介正在准备中。当前显示英语简介。

• Creating cell representations from AnnData
• Preparing single-cell data for clustering and integration
• Annotating cell types with or without fine-tuning

Design protein sequences while accounting for bound small molecules, nucleic acids, or metals. Use LigandMPNN to redesign binding pockets or metal-coordinating sites, and export sequence files alongside PDB structures with the designed sequences applied.

中文简介正在准备中。当前显示英语简介。

• Redesign a binding pocket around a small molecule or cofactor
• Design residues around a metal-coordinating site
• Export designed sequences as FASTA and PDB files

Convert protein sequences into numerical features with Meta AI's ESM-2 for machine learning. Extract features for individual amino acids or whole sequences, score mutations, and predict which positions in a protein may contact each other.

中文简介正在准备中。当前显示英语简介。

• Extracting protein features for machine learning
• Scoring the effects of amino acid mutations
• Predicting contacts from protein sequences

Use Boltz-2 to predict structures of complexes containing proteins, DNA, RNA, and small molecules. Obtain structure files and confidence scores to assess designed binders, with optional predictions of binding strength between a protein and a small molecule.

中文简介正在准备中。当前显示英语简介。

• Assessing a designed binder against its target
• Predicting a protein and small-molecule complex
• Predicting complexes containing DNA or RNA

Predict structures of complexes containing proteins, DNA, RNA, and ligands with OpenFold3, an AlphaFold3 reproduction with publicly available model weights. Prepare JSON inputs, generate candidate structures, and inspect confidence scores and molecular clashes.

中文简介正在准备中。当前显示英语简介。

• Predicting structures of protein–ligand complexes
• Predicting complexes containing DNA or RNA
• Comparing confidence scores across candidate structures

Find and run over 2,000 AI models and API tools through one MCP connection, a shared interface for agents. Inspect inputs and pricing before generating media, searching the web, or retrieving structured and social data.

中文简介正在准备中。当前显示英语简介。

• Finding and running image or video generation models
• Retrieving social media posts
• Searching the web and extracting page content

Write MATLAB or GNU Octave scripts for matrix calculations, data analysis, signal processing, and scientific plots. The skill also helps explain syntax and functions, convert code between MATLAB and Python, and run scripts when an interpreter is installed.

中文简介正在准备中。当前显示英语简介。

• Analyzing experimental CSV data and saving plots
• Solving matrix equations and differential equations
• Analyzing signal frequencies and applying filters

Choose statistical tests for research data, check their assumptions, and interpret effect sizes, which describe the magnitude of differences or relationships. This skill also supports sample size planning and produces results in APA reporting style, with figures and tables.

中文简介正在准备中。当前显示英语简介。

• Choosing a test for group comparisons or relationships
• Checking normality, variance, and outliers before analysis
• Estimating the sample size needed for a study

Create charts in Python with detailed control over colors, axes, labels, legends, and layouts. Use it to build scientific figures, arrange multiple plots, and export results as PNG, PDF, or SVG files for papers and presentations.

中文简介正在准备中。当前显示英语简介。

• Creating figures for papers and presentations
• Arranging multiple charts in one figure
• Adjusting colors, axes, labels, and legends

Process astronomical data in Python with Astropy. This skill covers celestial coordinate, unit, and time conversions; reading and editing FITS astronomy files; matching object catalogs; and calculating cosmic distances using cosmological models.

中文简介正在准备中。当前显示英语简介。

• Converting celestial coordinates for an observing time and location
• Reading FITS images and inspecting their headers
• Matching objects across astronomical catalogs

Inspect scientific data files to understand their format, structure, and quality. Covering over 200 formats, this skill produces Markdown reports with statistical summaries, potential issues, and recommendations for preprocessing, visualization, and further analysis.

中文简介正在准备中。当前显示英语简介。

• Inspecting an unfamiliar scientific data file
• Checking missing values and duplicates in experimental tables
• Reviewing sequence lengths and quality scores in FASTQ files

Build Python machine learning workflows for classification, numerical prediction, and grouping similar records. Use scikit-learn guidance and examples to prepare data, compare algorithms, tune model settings, and evaluate results with repeatable processing steps.

中文简介正在准备中。当前显示英语简介。

• Building classification and numerical prediction models
• Grouping customers by similar characteristics
• Preparing data with missing values and categorical fields

Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.

中文简介正在准备中。当前显示英语简介。

• Interpret regression coefficients and confidence intervals
• Model binary outcomes or event counts
• Forecast time series with uncertainty intervals

Create statistical charts from tabular data to explore distributions, relationships, and group differences. This skill guides plot selection, multi-panel layouts, and styling, including box plots, heatmaps, and charts with estimates and uncertainty bands.

中文简介正在准备中。当前显示英语简介。

• Exploring data distributions and unusual values
• Comparing measurements across groups
• Visualizing correlations between variables

Explore design options in Python when goals such as cost and performance compete. This skill guides optimization, constraint handling, and visualization of trade-offs, then helps compare candidate solutions using stated preferences.

中文简介正在准备中。当前显示英语简介。

• Comparing designs with competing cost and performance goals
• Finding solutions that meet design constraints
• Comparing optimization algorithms on benchmark problems

Model queues, production lines, logistics, and other systems that share limited resources in Python. Use discrete-event simulation, which advances through individual events, to measure waiting times, resource use, and throughput when comparing staffing or equipment levels.

中文简介正在准备中。当前显示英语简介。

• Comparing queue times for different staffing levels
• Examining production line bottlenecks
• Testing inventory and logistics flows

Forecast sales, sensor readings, or other time series without training a custom model. Using Google's TimesFM, this skill produces forecasts and uncertainty ranges from CSV files or arrays, supports batch processing, and checks local computing resources before use.

中文简介正在准备中。当前显示英语简介。

• Forecasting monthly sales from a CSV file
• Forecasting demand across multiple stores
• Plotting sensor forecasts with uncertainty ranges