数据与 AI技能

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Read, inspect, download, and write protein structure files with Biopython Bio.PDB. Check chains, residues, atoms, and experimental metadata, convert between PDB and mmCIF formats, or save selected parts of a structure.

中文简介正在准备中。当前显示英语简介。

• Inspect protein structure files and experimental metadata
• Download multiple structures from RCSB PDB
• Convert between PDB and mmCIF

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

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

Measure distances, angles, and contacts in protein structures using Bio.PDB. Compare structures through superposition and RMSD, a measure of positional differences, and calculate solvent accessible surface area to examine exposed and buried residues.

中文简介正在准备中。当前显示英语简介。

• Measuring atomic distances and backbone or sidechain angles
• Superimposing protein structures and comparing RMSD
• Finding nearby atoms and residue contacts

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.

中文简介正在准备中。当前显示英语简介。

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

Compare protein abundance between experimental groups using statistical tests in R or Python. Adjust for testing many proteins, filter results by significance and change size, and visualize candidate proteins in a volcano plot.

中文简介正在准备中。当前显示英语简介。

• Compare protein abundance between treatment and control groups
• Extract candidates using adjusted p-values and change thresholds
• Analyze protein data containing missing values

Analyze gene lists with clusterProfiler to find KEGG pathways and modules represented more often than expected. Prepare gene identifiers, set measured genes as the comparison background, compare groups, and export results or display genes on pathway diagrams.

中文简介正在准备中。当前显示英语简介。

• Finding pathways enriched in a gene list
• Using measured genes as the analysis background
• Comparing pathways between increased and decreased expression

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

• 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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Read, write, and convert molecular files with RDKit and Open Babel. Prepare compound libraries for analysis by checking structures and standardizing chemical representations, including charges, salts, and alternative forms of the same molecule.

中文简介正在准备中。当前显示英语简介。

• Load a compound library into Python
• Convert molecular files between formats
• Standardize molecular structures before analysis

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.

中文简介正在准备中。当前显示英语简介。

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

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.

中文简介正在准备中。当前显示英语简介。

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

Identify translated regions in Ribo-seq data, which records ribosome activity along RNA. Use RiboCode to detect known and novel open reading frames, then quantify their translation and compare counts across experimental conditions.

中文简介正在准备中。当前显示英语简介。

• Find translated regions beyond annotated coding sequences
• Identify upstream open reading frames
• Quantify translation for each open reading frame

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.

中文简介正在准备中。当前显示英语简介。

• 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

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.

中文简介正在准备中。当前显示英语简介。

• 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

Infer protein candidates from identified peptides and group proteins that share the same evidence. Address ambiguity from peptides found in multiple proteins, then filter protein groups using false discovery rates, which estimate the proportion of incorrect identifications.

中文简介正在准备中。当前显示英语简介。

• Resolving protein candidates from shared peptides
• Grouping proteins with identical peptide evidence
• Selecting a small protein set that explains observed peptides

Check proteomics data before further analysis by summarizing detected proteins, missing values, measurement distributions, and agreement between replicates. Generate quality plots and summary metrics, and investigate whether processing batches explain differences between samples.

中文简介正在准备中。当前显示英语简介。

• Review sample quality before downstream proteomics analysis
• Inspect missing values by sample and protein
• Compare replicate correlations and measurement variability

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.

中文简介正在准备中。当前显示英语简介。

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