데이터·AI 스킬

Find mainland Chinese A-share, Hong Kong, and US stocks by company name or ticker. Retrieve historical prices and trading volume for a chosen period, plus company information such as sector, market capitalization, and price-to-earnings ratio.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find a stock ticker from a company name
• Retrieve historical stock prices and trading volume
• Check a company's sector, market capitalization, and valuation

Generate financial market forecasts with Kronos using time-series data, meaning observations recorded over time. An agent then adjusts the numerical forecast using recent news sentiment and reasoning, combining a quantitative baseline with a subjective assessment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Forecasting financial market trends from time-series data
• Adjusting a baseline forecast using recent news
• Combining quantitative forecasts with news sentiment

Analyze financial text with local FinBERT or an LLM to identify positive, negative, or neutral sentiment. Return a numeric score and short reason, with support for batch processing unanalyzed news using FinBERT.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Classifying sentiment in financial news
• Batch processing unanalyzed news with FinBERT
• Using an LLM when sentiment analysis needs reasoning

Read conversion steps, retention curves, and recorded user actions to investigate why people leave a product. Check tracking issues first, then produce ranked design hypotheses with clear evidence that would support or rule out each explanation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating where users abandon a signup flow
• Interpreting changes in user retention
• Checking tracking issues before changing a design

Generate FASTQ sequencing quality reports with FastQC and combine them with MultiQC. Inspect quality at each base position, adapter contamination, GC composition bias, and duplicate reads, then compare samples or check results before and after trimming.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check raw sequencing data quality
• Compare quality across multiple samples
• Validate quality before and after trimming

Preprocess Illumina sequencing reads with fastp by removing adapter sequences, filtering by quality and length, and optionally removing duplicates. Produce cleaned FASTQ files alongside HTML reports for review and JSON statistics for further processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Remove adapters and low-quality sections from FASTQ reads
• Preprocess paired-end RNA-seq reads
• Remove poly-G sequences from NovaSeq or NextSeq reads

Process paired FASTQ files containing reads from both ends of DNA fragments with Biopython. Keep R1/R2 records together while filtering by quality or length, check pair IDs and counts, and combine or split alternating records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking R1/R2 record IDs and counts
• Filtering read pairs by quality or length
• Combining paired reads into alternating records

Explore protein structure files with Biopython Bio.PDB. Access individual chains, residues, and atoms, extract amino acid sequences and atomic coordinates, filter structural components, and count them across models, including structures with multiple conformations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrieving atomic coordinates from a specified chain or residue
• Extracting amino acid sequences from PDB files
• Listing water molecules and ligands separately

Identify peptide sequences and proteins from tandem mass spectra. The skill covers protein database searches, comparisons with reference spectra, and false discovery rate estimation to assess how many accepted matches may be incorrect.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Identifying peptide sequences from MS/MS spectra
• Inspecting peptide matches in idXML search results
• Filtering search results by false discovery rate

Combine gene expression, methylation, and other molecular measurements into one patient similarity network using SNFtool in R. Discover patient groups, visualize their relationships, and compare the resulting clusters with known subtypes, individual datasets, or survival outcomes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Discover patient subtypes from multiple molecular datasets
• Visualize an integrated patient similarity network
• Compare integrated clusters with known subtypes

Process sequencing reads tagged with unique molecular identifiers, short sequences that label original molecules. Extract these tags, remove PCR duplicates using tags and alignment positions, and produce deduplicated files or molecule counts by gene and cell.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract UMI tags from raw sequencing reads
• Remove PCR duplicates from UMI-tagged RNA-seq data
• Count molecules by gene and cell in single-cell data

Remove sequencing adapter sequences from FASTQ files with Cutadapt or Trimmomatic. Handle single-end and paired-end reads, select standard or custom adapters, filter trimmed reads, and check the resulting files with FastQC before alignment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing adapter contamination detected by FastQC
• Trimming paired-end reads before alignment
• Removing custom adapter sequences

Build and manage spectral libraries, reference collections for identifying peptides in proteomics data. Use measured or predicted spectra, convert library formats, check quality, and merge libraries for DIA, a mass spectrometry acquisition method.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a spectral library from experimental search results
• Prepare libraries using predicted spectra and retention times
• Convert libraries into formats used by DIA analysis tools

Read biological sequence files with Biopython Bio.SeqIO and extract sequence IDs, quality scores, and annotations. Process records individually, retrieve sequences by ID from large files, or use lightweight parsers for faster reading.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Listing sequence IDs and lengths from FASTA files
• Reading quality scores from FASTQ or ABI files
• Extracting annotated coding sequences from GenBank files

Analyze DIA proteomics data, a mass spectrometry approach that fragments precursors across acquisition windows. Use DIA-NN with or without a spectral library to identify and quantify proteins, prepare analysis matrices, and assess identification counts and missing values.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyzing DIA data without a pre-built spectral library
• Quantifying proteins using an existing spectral library
• Checking identification counts and missing values per run

Analyze chemical modifications added to proteins after production, including phosphorylation, acetylation, and ubiquitination. Filter modification sites by confidence, examine surrounding sequence patterns, and compare site quantities while accounting for changes in overall protein abundance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Filtering confident phosphorylation sites from MaxQuant output
• Examining sequence patterns around modification sites
• Comparing modification levels between experimental groups

Screen sequencing reads against multiple reference genomes with FastQ Screen to investigate contamination from other species, bacteria, viruses, or adapters. Generate visual reports, combine sample results with MultiQC, and select reads based on their reference matches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unexpected species in sequencing data
• Checking samples for bacterial or viral contamination
• Comparing contamination reports across samples

Extract protein abundance estimates from mass spectrometry data for comparisons between samples. Covers label-free measurements, TMT/iTRAQ chemical tags, and SILAC metabolic labels, with normalization, protein-level summaries, and heavy-to-light ratio calculations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Normalize label-free protein measurements
• Summarize TMT/iTRAQ signals by protein
• Calculate SILAC heavy-to-light ratios

Edit protein structure files with Biopython Bio.PDB. Covers moving and rotating coordinates, adding or removing atoms and residues, extracting or copying chains, updating atom properties, and constructing or merging structures through Python code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing water molecules or hydrogen atoms from structures
• Extracting chains or selected residue ranges
• Moving and rotating structure coordinates

Analyze gene lists against WikiPathways to find biological pathways with more matching genes than expected. Test ranked expression changes, compare gene groups, and create plots or CSV tables using R tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding pathways enriched in differentially expressed genes
• Analyzing ranked expression changes with GSEA
• Comparing pathways across upregulated and downregulated genes

Import mass spectrometry files and protein quantification results into Python or R for analysis. Access spectra, organize protein measurements by sample, remove flagged contaminants and reverse hits, and assess missing values across proteins and samples.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Load mzML or mzXML files for spectrum analysis
• Filter and extract measurements from MaxQuant results
• Reshape DIA-NN reports into protein-by-sample tables

Integrate RNA, protein, and other molecular measurements with mixOmics to find related features and distinguish sample groups. Covers feature selection, visualizations, classification performance checks, and export of selected features for further analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding related features across RNA and protein measurements
• Selecting features that distinguish experimental groups
• Comparing sample separation and feature networks in plots

Turn clusterProfiler enrichment results, which identify overrepresented biological functions or pathways, into figures with enrichplot in R. Create summary charts, gene relationship networks, and gene set enrichment plots, customize their appearance, and export PDF or PNG files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Summarizing GO or KEGG enrichment results
• Visualizing links between genes and biological terms
• Plotting GSEA scores and gene set distributions

Assign taxonomic names to ASVs, distinct DNA sequences obtained from amplicon processing. Use reference databases such as SILVA, GTDB, or UNITE with DADA2, QIIME2, or IDTAXA, set confidence thresholds, and organize results in phyloseq.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assigning taxonomy to ASVs after DADA2 processing
• Classifying fungal ITS sequences with UNITE
• Setting confidence thresholds for taxonomy assignments