scikit-bio
Overview
scikit-bio is a comprehensive Python library for working with biological data. Apply this skill for bioinformatics analyses spanning sequence manipulation, alignment, phylogenetics, microbial ecology, and multivariate statistics.
When to Use This Skill
This skill should be used when the user:
- Works with biological sequences (DNA, RNA, protein)
- Needs to read/write biological file formats (FASTA, FASTQ, GenBank, Newick, BIOM, etc.)
- Performs sequence alignments or searches for motifs
- Constructs or analyzes phylogenetic trees
- Calculates diversity metrics (alpha/beta diversity, UniFrac distances)
- Performs ordination analysis (PCoA, CCA, RDA)
- Runs statistical tests on biological/ecological data (PERMANOVA, ANOSIM, Mantel)
- Analyzes microbiome or community ecology data
- Works with protein embeddings from language models
- Needs to manipulate biological data tables
Core Capabilities
1. Sequence Manipulation
Work with biological sequences using specialized classes for DNA, RNA, and protein data.
Key operations:
- Read/write sequences from FASTA, FASTQ, GenBank, EMBL formats
- Sequence slicing, concatenation, and searching
- Reverse complement, transcription (DNA→RNA), and translation (RNA→protein)
- Find motifs and patterns using regex
- Calculate distances (Hamming, k-mer based)
- Handle sequence quality scores and metadata
Common patterns:
import skbio
# Read sequences from file
seq = skbio.DNA.read('input.fasta')
# Sequence operations
rc = seq.reverse_complement()
rna = seq.transcribe()
protein = rna.translate()
# Find motifs
motif_positions = seq.find_with_regex('ATG[ACGT]{3}')
# Check for properties
has_degens = seq.has_degenerates()
seq_no_gaps = seq.degap()
Important notes:
- Use
DNA, RNA, Protein classes for grammared sequences with validation
- Use
Sequence class for generic sequences without alphabet restrictions
- Quality scores automatically loaded from FASTQ files into positional metadata
- Metadata types: sequence-level (ID, description), positional (per-base), interval (regions/features)
2. Sequence Alignment
Perform pairwise and multiple sequence alignments using dynamic programming algorithms.
Key capabilities:
- Global alignment (Needleman-Wunsch with semi-global variant)
- Local alignment (Smith-Waterman)
- Configurable scoring schemes (match/mismatch, gap penalties, substitution matrices)
- CIGAR string conversion
- Multiple sequence alignment storage and manipulation with
TabularMSA
Common patterns:
from skbio.alignment import local_pairwise_align_ssw, TabularMSA
# Pairwise alignment
alignment = local_pairwise_align_ssw(seq1, seq2)
# Access aligned sequences
msa = alignment.aligned_sequences
# Read multiple alignment from file
msa = TabularMSA.read('alignment.fasta', constructor=skbio.DNA)
# Calculate consensus
consensus = msa.consensus()
Important notes:
- Use
local_pairwise_align_ssw for local alignments (faster, SSW-based)
- Use
StripedSmithWaterman for protein alignments
- Affine gap penalties recommended for biological sequences
- Can convert between scikit-bio, BioPython, and Biotite alignment formats
3. Phylogenetic Trees
Construct, manipulate, and analyze phylogenetic trees representing evolutionary relationships.
Key capabilities:
- Tree construction from distance matrices (UPGMA, WPGMA, Neighbor Joining, GME, BME)
- Tree manipulation (pruning, rerooting, traversal)
- Distance calculations (patristic, cophenetic, Robinson-Foulds)
- ASCII visualization
- Newick format I/O
Common patterns:
from skbio import TreeNode
from skbio.tree import nj
# Read tree from file
tree = TreeNode.read('tree.nwk')
# Construct tree from distance matrix
tree = nj(distance_matrix)
# Tree operations
subtree = tree.shear(['taxon1', 'taxon2', 'taxon3'])
tips = [node for node in tree.tips()]
lca = tree.lowest_common_ancestor(['taxon1', 'taxon2'])
# Calculate distances
patristic_dist = tree.find('taxon1').distance(tree.find('taxon2'))
cophenetic_matrix = tree.cophenetic_matrix()
# Compare trees
rf_distance = tree.robinson_foulds(other_tree)
Important notes:
- Use
nj() for neighbor joining (classic phylogenetic method)
- Use
upgma() for UPGMA (assumes molecular clock)
- GME and BME are highly scalable for large trees
- Trees can be rooted or unrooted; some metrics require specific rooting
4. Diversity Analysis
Calculate alpha and beta diversity metrics for microbial ecology and community analysis.
Key capabilities:
- Alpha diversity: richness, Shannon entropy, Simpson index, Faith's PD, Pielou's evenness
- Beta diversity: Bray-Curtis, Jaccard, weighted/unweighted UniFrac, Euclidean distances
- Phylogenetic diversity metrics (require tree input)
- Rarefaction and subsampling
- Integration with ordination and statistical tests
Common patterns:
from skbio.diversity import alpha_diversity, beta_diversity
import skbio
# Alpha diversity
alpha = alpha_diversity('shannon', counts_matrix, ids=sample_ids)
faith_pd = alpha_diversity('faith_pd', counts_matrix, ids=sample_ids,
tree=tree, otu_ids=feature_ids)
# Beta diversity
bc_dm = beta_diversity('braycurtis', counts_matrix, ids=sample_ids)
unifrac_dm = beta_diversity('unweighted_unifrac', counts_matrix,
ids=sample_ids, tree=tree, otu_ids=feature_ids)
# Get available metrics
from skbio.diversity import get_alpha_diversity_metrics
print(get_alpha_diversity_metrics())
Important notes:
- Counts must be integers representing abundances, not relative frequencies
- Phylogenetic metrics (Faith's PD, UniFrac) require tree and OTU ID mapping
- Use
partial_beta_diversity() for computing specific sample pairs only
- Alpha diversity returns Series, beta diversity returns DistanceMatrix
5. Ordination Methods
Reduce high-dimensional biological data to visualizable lower-dimensional spaces.
Key capabilities:
- PCoA (Principal Coordinate Analysis) from distance matrices
- CA (Correspondence Analysis) for contingency tables
- CCA (Canonical Correspondence Analysis) with environmental constraints
- RDA (Redundancy Analysis) for linear relationships
- Biplot projection for feature interpretation
Common patterns:
from skbio.stats.ordination import pcoa, cca
# PCoA from distance matrix
pcoa_results = pcoa(distance_matrix)
pc1 = pcoa_results.samples['PC1']
pc2 = pcoa_results.samples['PC2']
# CCA with environmental variables
cca_results = cca(species_matrix, environmental_matrix)
# Save/load ordination results
pcoa_results.write('ordination.txt')
results = skbio.OrdinationResults.read('ordination.txt')
Important notes:
- PCoA works with any distance/dissimilarity matrix
- CCA reveals environmental drivers of community composition
- Ordination results include eigenvalues, proportion explained, and sample/feature coordinates
- Results integrate with plotting libraries (matplotlib, seaborn, plotly)
6. Statistical Testing
Perform hypothesis tests specific to ecological and biological data.
Key capabilities:
- PERMANOVA: test group differences using distance matrices
- ANOSIM: alternative test for group differences
- PERMDISP: test homogeneity of group dispersions
- Mantel test: correlation between distance matrices
- Bioenv: find environmental variables correlated with distances
Common patterns:
from skbio.stats.distance import permanova, anosim, mantel
# Test if groups differ significantly
permanova_results = permanova(distance_matrix, grouping, permutations=999)
print(f"p-value: {permanova_results['p-value']}")
# ANOSIM test
anosim_results = anosim(distance_matrix, grouping, permutations=999)
# Mantel test between two distance matrices
mantel_results = mantel(dm1, dm2, method='pearson', permutations=999)
print(f"Correlation: {mantel_results[0]}, p-value: {mantel_results[1]}")
Important notes:
- Permutation tests provide non-parametric significance testing
- Use 999+ permutations for robust p-values
- PERMANOVA sensitive to dispersion differences; pair with PERMDISP
- Mantel tests assess matrix correlation (e.g., geographic vs genetic distance)
7. File I/O and Format Conversion
Read and write 19+ biological file formats with automatic format detection.
Supported formats:
- Sequences: FASTA, FASTQ, GenBank, EMBL, QSeq
- Alignments: Clustal, PHYLIP, Stockholm
- Trees: Newick
- Tables: BIOM (HDF5 and JSON)
- Distances: delimited square matrices
- Analysis: BLAST+6/7, GFF3, Ordination results
- Metadata: TSV/CSV with validation
Common patterns:
import skbio
# Read with automatic format detection
seq = skbio.DNA.read('file.fasta', format='fasta')
tree = skbio.TreeNode.read('tree.nwk')
# Write to file
seq.write('output.fasta', format='fasta')
# Generator for large files (memory efficient)
for seq in skbio.io.read('large.fasta', format='fasta', constructor=skbio.DNA):
process(seq)
# Convert formats
seqs = list(skbio.io.read('input.fastq', format='fastq', constructor=skbio.DNA))
skbio.io.write(seqs, format='fasta', into='output.fasta')
Important notes:
- Use generators for large files to avoid memory issues
- Format can be auto-detected when
into parameter specified
- Some objects can be written to multiple formats
- Support for stdin/stdout piping with
verify=False
8. Distance Matrices
Create and manipulate distance/dissimilarity matrices with statistical methods.
Key capabilities:
- Store symmetric (DistanceMatrix) or asymmetric (DissimilarityMatrix) data
- ID-based indexing and slicing
- Integration with diversity, ordination, and statistical tests
- Read/write delimited text format
Common patterns:
from skbio import DistanceMatrix
import numpy as np
# Create from array
data = np.array([[0, 1, 2], [1, 0, 3], [2, 3, 0]])
dm = DistanceMatrix(data, ids=['A', 'B', 'C'])
# Access distances
dist_ab = dm['A', 'B']
row_a = dm['A']
# Read from file
dm = DistanceMatrix.read('distances.txt')
# Use in downstream analyses
pcoa_results = pcoa(dm)
permanova_results = permanova(dm, grouping)
Important notes:
- DistanceMatrix enforces symmetry and zero diagonal
- DissimilarityMatrix allows asymmetric values
- IDs enable integration with metadata and biological knowledge
- Compatible with pandas, numpy, and scikit-learn
9. Biological Tables
Work with feature tables (OTU/ASV tables) common in microbiome research.
Key capabilities:
- BIOM format I/O (HDF5 and JSON)
- Integration with pandas, polars, AnnData, numpy
- Data augmentation techniques (phylomix, mixup, compositional methods)
- Sample/feature filtering and normalization
- Metadata integration
Common patterns:
from skbio import Table
# Read BIOM table
table = Table.read('table.biom')
# Access data
sample_ids = table.ids(axis='sample')
feature_ids = table.ids(axis='observation')
counts = table.matrix_data
# Filter
filtered = table.filter(sample_ids_to_keep, axis='sample')
# Convert to/from pandas
df = table.to_dataframe()
table = Table.from_dataframe(df)
Important notes:
- BIOM tables are standard in QIIME 2 workflows
- Rows typically represent samples, columns represent features (OTUs/ASVs)
- Supports sparse and dense representations
- Output format configurable (pandas/polars/numpy)
10. Protein Embeddings
Work with protein language model embeddings for downstream analysis.
Key capabilities:
- Store embeddings from protein language models (ESM, ProtTrans, etc.)
- Convert embeddings to distance matrices
- Generate ordination objects for visualization
- Export to numpy/pandas for ML workflows
Common patterns:
from skbio.embedding import ProteinEmbedding, ProteinVector
# Create embedding from array
embedding = ProteinEmbedding(embedding_array, sequence_ids)
# Convert to distance matrix for analysis
dm = embedding.to_distances(metric='euclidean')
# PCoA visualization of embedding space
pcoa_results = embedding.to_ordination(metric='euclidean', method='pcoa')
# Export for machine learning
array = embedding.to_array()
df = embedding.to_dataframe()
Important notes:
- Embeddings bridge protein language models with traditional bioinformatics
- Compatible with scikit-bio's distance/ordination/statistics ecosystem
- SequenceEmbedding and ProteinEmbedding provide specialized functionality
- Useful for sequence clustering, classification, and visualization
Best Practices
Installation
uv pip install scikit-bio
Performance Considerations
- Use generators for large sequence files to minimize memory usage
- For massive phylogenetic trees, prefer GME or BME over NJ
- Beta diversity calculations can be parallelized with
partial_beta_diversity()
- BIOM format (HDF5) more efficient than JSON for large tables
Integration with Ecosystem
- Sequences interoperate with Biopython via standard formats
- Tables integrate with pandas, polars, and AnnData
- Distance matrices compatible with scikit-learn
- Ordination results visualizable with matplotlib/seaborn/plotly
- Works seamlessly with QIIME 2 artifacts (BIOM, trees, distance matrices)
Common Workflows
- Microbiome diversity analysis: Read BIOM table → Calculate alpha/beta diversity → Ordination (PCoA) → Statistical testing (PERMANOVA)
- Phylogenetic analysis: Read sequences → Align → Build distance matrix → Construct tree → Calculate phylogenetic distances
- Sequence processing: Read FASTQ → Quality filter → Trim/clean → Find motifs → Translate → Write FASTA
- Comparative genomics: Read sequences → Pairwise alignment → Calculate distances → Build tree → Analyze clades
Reference Documentation
For detailed API information, parameter specifications, and advanced usage examples, refer to references/api_reference.md which contains comprehensive documentation on:
- Complete method signatures and parameters for all capabilities
- Extended code examples for complex workflows
- Troubleshooting common issues
- Performance optimization tips
- Integration patterns with other libraries
Additional Resources
1---2author: luo-kai3name: scikit-bio-24description: Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.5license: BSD-3-Clause license6metadata:7 source: https://skillmd.com/skills/luokai0/scikit-bio-28 skill-author: K-Dense Inc.9---1011# scikit-bio1213## Overview1415scikit-bio is a comprehensive Python library for working with biological data. Apply this skill for bioinformatics analyses spanning sequence manipulation, alignment, phylogenetics, microbial ecology, and multivariate statistics.1617## When to Use This Skill1819This skill should be used when the user:20- Works with biological sequences (DNA, RNA, protein)21- Needs to read/write biological file formats (FASTA, FASTQ, GenBank, Newick, BIOM, etc.)22- Performs sequence alignments or searches for motifs23- Constructs or analyzes phylogenetic trees24- Calculates diversity metrics (alpha/beta diversity, UniFrac distances)25- Performs ordination analysis (PCoA, CCA, RDA)26- Runs statistical tests on biological/ecological data (PERMANOVA, ANOSIM, Mantel)27- Analyzes microbiome or community ecology data28- Works with protein embeddings from language models29- Needs to manipulate biological data tables3031## Core Capabilities3233### 1. Sequence Manipulation3435Work with biological sequences using specialized classes for DNA, RNA, and protein data.3637**Key operations:**38- Read/write sequences from FASTA, FASTQ, GenBank, EMBL formats39- Sequence slicing, concatenation, and searching40- Reverse complement, transcription (DNA→RNA), and translation (RNA→protein)41- Find motifs and patterns using regex42- Calculate distances (Hamming, k-mer based)43- Handle sequence quality scores and metadata4445**Common patterns:**46```python47import skbio4849# Read sequences from file50seq = skbio.DNA.read('input.fasta')5152# Sequence operations53rc = seq.reverse_complement()54rna = seq.transcribe()55protein = rna.translate()5657# Find motifs58motif_positions = seq.find_with_regex('ATG[ACGT]{3}')5960# Check for properties61has_degens = seq.has_degenerates()62seq_no_gaps = seq.degap()63```6465**Important notes:**66- Use `DNA`, `RNA`, `Protein` classes for grammared sequences with validation67- Use `Sequence` class for generic sequences without alphabet restrictions68- Quality scores automatically loaded from FASTQ files into positional metadata69- Metadata types: sequence-level (ID, description), positional (per-base), interval (regions/features)7071### 2. Sequence Alignment7273Perform pairwise and multiple sequence alignments using dynamic programming algorithms.7475**Key capabilities:**76- Global alignment (Needleman-Wunsch with semi-global variant)77- Local alignment (Smith-Waterman)78- Configurable scoring schemes (match/mismatch, gap penalties, substitution matrices)79- CIGAR string conversion80- Multiple sequence alignment storage and manipulation with `TabularMSA`8182**Common patterns:**83```python84from skbio.alignment import local_pairwise_align_ssw, TabularMSA8586# Pairwise alignment87alignment = local_pairwise_align_ssw(seq1, seq2)8889# Access aligned sequences90msa = alignment.aligned_sequences9192# Read multiple alignment from file93msa = TabularMSA.read('alignment.fasta', constructor=skbio.DNA)9495# Calculate consensus96consensus = msa.consensus()97```9899**Important notes:**100- Use `local_pairwise_align_ssw` for local alignments (faster, SSW-based)101- Use `StripedSmithWaterman` for protein alignments102- Affine gap penalties recommended for biological sequences103- Can convert between scikit-bio, BioPython, and Biotite alignment formats104105### 3. Phylogenetic Trees106107Construct, manipulate, and analyze phylogenetic trees representing evolutionary relationships.108109**Key capabilities:**110- Tree construction from distance matrices (UPGMA, WPGMA, Neighbor Joining, GME, BME)111- Tree manipulation (pruning, rerooting, traversal)112- Distance calculations (patristic, cophenetic, Robinson-Foulds)113- ASCII visualization114- Newick format I/O115116**Common patterns:**117```python118from skbio import TreeNode119from skbio.tree import nj120121# Read tree from file122tree = TreeNode.read('tree.nwk')123124# Construct tree from distance matrix125tree = nj(distance_matrix)126127# Tree operations128subtree = tree.shear(['taxon1', 'taxon2', 'taxon3'])129tips = [node for node in tree.tips()]130lca = tree.lowest_common_ancestor(['taxon1', 'taxon2'])131132# Calculate distances133patristic_dist = tree.find('taxon1').distance(tree.find('taxon2'))134cophenetic_matrix = tree.cophenetic_matrix()135136# Compare trees137rf_distance = tree.robinson_foulds(other_tree)138```139140**Important notes:**141- Use `nj()` for neighbor joining (classic phylogenetic method)142- Use `upgma()` for UPGMA (assumes molecular clock)143- GME and BME are highly scalable for large trees144- Trees can be rooted or unrooted; some metrics require specific rooting145146### 4. Diversity Analysis147148Calculate alpha and beta diversity metrics for microbial ecology and community analysis.149150**Key capabilities:**151- Alpha diversity: richness, Shannon entropy, Simpson index, Faith's PD, Pielou's evenness152- Beta diversity: Bray-Curtis, Jaccard, weighted/unweighted UniFrac, Euclidean distances153- Phylogenetic diversity metrics (require tree input)154- Rarefaction and subsampling155- Integration with ordination and statistical tests156157**Common patterns:**158```python159from skbio.diversity import alpha_diversity, beta_diversity160import skbio161162# Alpha diversity163alpha = alpha_diversity('shannon', counts_matrix, ids=sample_ids)164faith_pd = alpha_diversity('faith_pd', counts_matrix, ids=sample_ids,165 tree=tree, otu_ids=feature_ids)166167# Beta diversity168bc_dm = beta_diversity('braycurtis', counts_matrix, ids=sample_ids)169unifrac_dm = beta_diversity('unweighted_unifrac', counts_matrix,170 ids=sample_ids, tree=tree, otu_ids=feature_ids)171172# Get available metrics173from skbio.diversity import get_alpha_diversity_metrics174print(get_alpha_diversity_metrics())175```176177**Important notes:**178- Counts must be integers representing abundances, not relative frequencies179- Phylogenetic metrics (Faith's PD, UniFrac) require tree and OTU ID mapping180- Use `partial_beta_diversity()` for computing specific sample pairs only181- Alpha diversity returns Series, beta diversity returns DistanceMatrix182183### 5. Ordination Methods184185Reduce high-dimensional biological data to visualizable lower-dimensional spaces.186187**Key capabilities:**188- PCoA (Principal Coordinate Analysis) from distance matrices189- CA (Correspondence Analysis) for contingency tables190- CCA (Canonical Correspondence Analysis) with environmental constraints191- RDA (Redundancy Analysis) for linear relationships192- Biplot projection for feature interpretation193194**Common patterns:**195```python196from skbio.stats.ordination import pcoa, cca197198# PCoA from distance matrix199pcoa_results = pcoa(distance_matrix)200pc1 = pcoa_results.samples['PC1']201pc2 = pcoa_results.samples['PC2']202203# CCA with environmental variables204cca_results = cca(species_matrix, environmental_matrix)205206# Save/load ordination results207pcoa_results.write('ordination.txt')208results = skbio.OrdinationResults.read('ordination.txt')209```210211**Important notes:**212- PCoA works with any distance/dissimilarity matrix213- CCA reveals environmental drivers of community composition214- Ordination results include eigenvalues, proportion explained, and sample/feature coordinates215- Results integrate with plotting libraries (matplotlib, seaborn, plotly)216217### 6. Statistical Testing218219Perform hypothesis tests specific to ecological and biological data.220221**Key capabilities:**222- PERMANOVA: test group differences using distance matrices223- ANOSIM: alternative test for group differences224- PERMDISP: test homogeneity of group dispersions225- Mantel test: correlation between distance matrices226- Bioenv: find environmental variables correlated with distances227228**Common patterns:**229```python230from skbio.stats.distance import permanova, anosim, mantel231232# Test if groups differ significantly233permanova_results = permanova(distance_matrix, grouping, permutations=999)234print(f"p-value: {permanova_results['p-value']}")235236# ANOSIM test237anosim_results = anosim(distance_matrix, grouping, permutations=999)238239# Mantel test between two distance matrices240mantel_results = mantel(dm1, dm2, method='pearson', permutations=999)241print(f"Correlation: {mantel_results[0]}, p-value: {mantel_results[1]}")242```243244**Important notes:**245- Permutation tests provide non-parametric significance testing246- Use 999+ permutations for robust p-values247- PERMANOVA sensitive to dispersion differences; pair with PERMDISP248- Mantel tests assess matrix correlation (e.g., geographic vs genetic distance)249250### 7. File I/O and Format Conversion251252Read and write 19+ biological file formats with automatic format detection.253254**Supported formats:**255- Sequences: FASTA, FASTQ, GenBank, EMBL, QSeq256- Alignments: Clustal, PHYLIP, Stockholm257- Trees: Newick258- Tables: BIOM (HDF5 and JSON)259- Distances: delimited square matrices260- Analysis: BLAST+6/7, GFF3, Ordination results261- Metadata: TSV/CSV with validation262263**Common patterns:**264```python265import skbio266267# Read with automatic format detection268seq = skbio.DNA.read('file.fasta', format='fasta')269tree = skbio.TreeNode.read('tree.nwk')270271# Write to file272seq.write('output.fasta', format='fasta')273274# Generator for large files (memory efficient)275for seq in skbio.io.read('large.fasta', format='fasta', constructor=skbio.DNA):276 process(seq)277278# Convert formats279seqs = list(skbio.io.read('input.fastq', format='fastq', constructor=skbio.DNA))280skbio.io.write(seqs, format='fasta', into='output.fasta')281```282283**Important notes:**284- Use generators for large files to avoid memory issues285- Format can be auto-detected when `into` parameter specified286- Some objects can be written to multiple formats287- Support for stdin/stdout piping with `verify=False`288289### 8. Distance Matrices290291Create and manipulate distance/dissimilarity matrices with statistical methods.292293**Key capabilities:**294- Store symmetric (DistanceMatrix) or asymmetric (DissimilarityMatrix) data295- ID-based indexing and slicing296- Integration with diversity, ordination, and statistical tests297- Read/write delimited text format298299**Common patterns:**300```python301from skbio import DistanceMatrix302import numpy as np303304# Create from array305data = np.array([[0, 1, 2], [1, 0, 3], [2, 3, 0]])306dm = DistanceMatrix(data, ids=['A', 'B', 'C'])307308# Access distances309dist_ab = dm['A', 'B']310row_a = dm['A']311312# Read from file313dm = DistanceMatrix.read('distances.txt')314315# Use in downstream analyses316pcoa_results = pcoa(dm)317permanova_results = permanova(dm, grouping)318```319320**Important notes:**321- DistanceMatrix enforces symmetry and zero diagonal322- DissimilarityMatrix allows asymmetric values323- IDs enable integration with metadata and biological knowledge324- Compatible with pandas, numpy, and scikit-learn325326### 9. Biological Tables327328Work with feature tables (OTU/ASV tables) common in microbiome research.329330**Key capabilities:**331- BIOM format I/O (HDF5 and JSON)332- Integration with pandas, polars, AnnData, numpy333- Data augmentation techniques (phylomix, mixup, compositional methods)334- Sample/feature filtering and normalization335- Metadata integration336337**Common patterns:**338```python339from skbio import Table340341# Read BIOM table342table = Table.read('table.biom')343344# Access data345sample_ids = table.ids(axis='sample')346feature_ids = table.ids(axis='observation')347counts = table.matrix_data348349# Filter350filtered = table.filter(sample_ids_to_keep, axis='sample')351352# Convert to/from pandas353df = table.to_dataframe()354table = Table.from_dataframe(df)355```356357**Important notes:**358- BIOM tables are standard in QIIME 2 workflows359- Rows typically represent samples, columns represent features (OTUs/ASVs)360- Supports sparse and dense representations361- Output format configurable (pandas/polars/numpy)362363### 10. Protein Embeddings364365Work with protein language model embeddings for downstream analysis.366367**Key capabilities:**368- Store embeddings from protein language models (ESM, ProtTrans, etc.)369- Convert embeddings to distance matrices370- Generate ordination objects for visualization371- Export to numpy/pandas for ML workflows372373**Common patterns:**374```python375from skbio.embedding import ProteinEmbedding, ProteinVector376377# Create embedding from array378embedding = ProteinEmbedding(embedding_array, sequence_ids)379380# Convert to distance matrix for analysis381dm = embedding.to_distances(metric='euclidean')382383# PCoA visualization of embedding space384pcoa_results = embedding.to_ordination(metric='euclidean', method='pcoa')385386# Export for machine learning387array = embedding.to_array()388df = embedding.to_dataframe()389```390391**Important notes:**392- Embeddings bridge protein language models with traditional bioinformatics393- Compatible with scikit-bio's distance/ordination/statistics ecosystem394- SequenceEmbedding and ProteinEmbedding provide specialized functionality395- Useful for sequence clustering, classification, and visualization396397## Best Practices398399### Installation400```bash401uv pip install scikit-bio402```403404### Performance Considerations405- Use generators for large sequence files to minimize memory usage406- For massive phylogenetic trees, prefer GME or BME over NJ407- Beta diversity calculations can be parallelized with `partial_beta_diversity()`408- BIOM format (HDF5) more efficient than JSON for large tables409410### Integration with Ecosystem411- Sequences interoperate with Biopython via standard formats412- Tables integrate with pandas, polars, and AnnData413- Distance matrices compatible with scikit-learn414- Ordination results visualizable with matplotlib/seaborn/plotly415- Works seamlessly with QIIME 2 artifacts (BIOM, trees, distance matrices)416417### Common Workflows4181. **Microbiome diversity analysis**: Read BIOM table → Calculate alpha/beta diversity → Ordination (PCoA) → Statistical testing (PERMANOVA)4192. **Phylogenetic analysis**: Read sequences → Align → Build distance matrix → Construct tree → Calculate phylogenetic distances4203. **Sequence processing**: Read FASTQ → Quality filter → Trim/clean → Find motifs → Translate → Write FASTA4214. **Comparative genomics**: Read sequences → Pairwise alignment → Calculate distances → Build tree → Analyze clades422423## Reference Documentation424425For detailed API information, parameter specifications, and advanced usage examples, refer to `references/api_reference.md` which contains comprehensive documentation on:426- Complete method signatures and parameters for all capabilities427- Extended code examples for complex workflows428- Troubleshooting common issues429- Performance optimization tips430- Integration patterns with other libraries431432## Additional Resources433434- Official documentation: https://scikit.bio/docs/latest/435- GitHub repository: https://github.com/scikit-bio/scikit-bio436- Forum support: https://forum.qiime2.org (scikit-bio is part of QIIME 2 ecosystem)437