数据分析、机器学习、LLM 应用、提示词设计（9081 个）
Create a forest plot for a meta-analysis of continuous outcomes from a CSV of study means, standard deviations, and group sizes. The skill checks the input and produces a PNG chart, a CSV data table, and a summary of pooled effects and heterogeneity.
中文简介正在准备中。当前显示英语简介。
Review FASTQC reports for sequencing data to identify quality problems and explain what the metrics indicate. Get actionable recommendations for RNA-seq, DNA-seq, or ChIP-seq, with batch summaries available when several reports need review.
中文简介正在准备中。当前显示英语简介。
Analyze genomic intervals with fast overlap queries, coverage tracks, reference sequence checks, and fragment workflows. The toolkit also converts genomic regions into discrete tokens for machine learning and provides Python bindings and command-line tools for notebooks, pipelines, and batch jobs.
中文简介正在准备中。当前显示英语简介。
Create review-ready forest plots from meta-analysis or subgroup data in CSV or Excel files. Adjust odds ratio markers, confidence interval lines, colors, labels, and output format, with options to show pooled effects and subgroup results.
中文简介正在准备中。当前显示英语简介。
Analyzes experimental data from CSV files with descriptive statistics, assumption checks, and suitable tests such as t-tests or ANOVA. Produces traceable run outputs with test results, effect sizes, tables, charts, and notes on analysis assumptions.
中文简介正在准备中。当前显示英语简介。
Analyze whole genome sequencing data to identify genomic regions with copy number gains or losses. The workflow supports segmentation, genome-wide visualization, and BED output, with examples for cancer genomics and rare disease analysis.
中文简介正在准备中。当前显示英语简介。
Read FCS 2.0–3.1 flow cytometry files and extract event values, channel definitions, and metadata. Prepare data as NumPy arrays or export it to CSV or a Pandas DataFrame, inspect metadata alone, and write modified FCS files.
中文简介正在准备中。当前显示英语简介。
Create a gene structure diagram from a gene symbol, showing exons and introns. Optionally add protein domain annotations and mutation positions, then produce an SVG, PNG, or PDF and save it to a chosen output path.
中文简介正在准备中。当前显示英语简介。
Guides genomics work on the DNAnexus cloud platform, including building Apps and Applets, managing files and projects, and running or monitoring jobs and workflows. It also covers the dxpy Python SDK and common sequencing formats such as FASTQ, BAM, and VCF.
中文简介正在准备中。当前显示英语简介。
Clean and standardize clinical trial data for CDISC SDTM workflows. Validate domain fields, handle missing values, flag or manage lab outliers, standardize dates, and produce cleaned data with an audit trail for submission preparation and review.
中文简介正在准备中。当前显示英语简介。
Use LaminDB to organize searchable biological datasets, standardize annotations with biological ontologies, validate schemas, and track how analyses produce derived data. It also describes integrations with workflow managers, MLOps platforms, and local or cloud storage.
中文简介正在准备中。当前显示英语简介。
Explore scientific data files across more than 200 formats. The skill identifies file types, summarizes structure and statistics, checks data quality, and recommends visualizations or next analyses in a Markdown report. Specialized libraries may be needed for some formats.
中文简介正在准备中。当前显示英语简介。
Use Python statistical libraries to compare groups, test hypotheses, analyze correlations, and correct for multiple testing. The skill also covers confidence intervals, normality checks, and non-parametric alternatives, with results that can be saved in tables.
中文简介正在准备中。当前显示英语简介。
Prepare research analysis code for publication or collaboration by documenting its functions, replacing hardcoded settings with parameters, adding error handling, and specifying dependencies. The workflow also checks whether refactoring preserves behavior and supports repeatable results.
中文简介正在准备中。当前显示英语简介。
Analyze and present phylogenetic or hierarchical trees: read and convert common tree formats, reroot or prune branches, identify gene duplication and speciation events, add NCBI taxonomy, compare topologies, and render figures as PDF, SVG, or PNG.
中文简介正在准备中。当前显示英语简介。
Create clearer gene expression heatmaps from CSV matrices by adding hierarchical clustering trees and color-coded annotations for genes or samples. Adjust labels and export the figure in formats such as PDF, PNG, or SVG for analysis and presentation.
中文简介正在准备中。当前显示英语简介。
Use deepTools to validate sequencing files, convert BAM alignments into coverage tracks, assess sample quality and similarity, and visualize signals around genomic features. It supports common ChIP-seq, RNA-seq, and ATAC-seq workflows with reusable command templates and guidance.
中文简介正在准备中。当前显示英语简介。
Analyze genomic interval data stored in BED files by creating shared peak sets, turning regions or cells into numeric embeddings, and supporting similarity search and downstream machine learning on chromatin accessibility data.
中文简介正在准备中。当前显示英语简介。
Creates publication-styled flow cytometry gating plots from an FCS file. Choose contour, density, or dot visualization to present gated data clearly, with the workflow keeping inputs and assumptions explicit.
中文简介正在准备中。当前显示英语简介。
Analyze metabolic network models with constraint-based methods to simulate growth or product formation, estimate feasible reaction flux ranges, and study gene or reaction knockouts and media changes. The workflow works with models provided in SBML, JSON, or YAML formats.
中文简介正在准备中。当前显示英语简介。
Uses Biopython to align DNA, RNA, or protein sequences globally or locally, process multiple sequence alignment files, and calculate statistics such as identity, coverage, and column conservation. It also supports format conversion and threshold-based filtering.
中文简介正在准备中。当前显示英语简介。
Use Python to parse and convert sequence and structure files, process DNA, RNA, or protein data in batches, query NCBI records, run BLAST searches, and build phylogenetic trees. The skill guides workflows with Biopython modules and their practical constraints.
中文简介正在准备中。当前显示英语简介。
Compare AI-generated clinical notes with expert reference notes using BERTScore and COMET, neural metrics that assess meaning beyond exact word matches. Review individual or batch scores and structured results to identify semantic gaps and overall consistency.
中文简介正在准备中。当前显示英语简介。
Predicts absorption, distribution, metabolism, and excretion properties for small molecules from their structures. Use the results to compare compounds, screen libraries, and review drug-likeness scores in structured outputs. Predictions support prioritization and need experimental validation.
中文简介正在准备中。当前显示英语简介。