zhongwei/gh-brunoasm-my-claude-skills-bioinfo-skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Zhongwei Li
2025-11-29 18:02:37 +08:00
commit c1d9dee646
38 changed files with 11210 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
skills/phylo_from_buscos/.skillignore Normal file
View File

@@ -0,0 +1,12 @@
# Exclude development materials from skill packaging
info_to_craft_skill/
# Exclude GitHub documentation (not needed in skill package)
README.md
# Exclude local settings
.claude/
# Exclude git files
.git/
.gitignore

99
skills/phylo_from_buscos/README.md Normal file
View File

@@ -0,0 +1,99 @@
# BUSCO-based Phylogenomics Skill
A Claude Code skills for phylogenomic analyses, created by Bruno de Medeiros (Field Museum) based on code initially written by Paul Frandsen (Brigham Young University)
It generate a complete phylogenetic workflow from genome assemblies using BUSCO/compleasm-based single-copy orthologs.
**Features:**
- Supports local genome files and NCBI accessions (BioProjects/Assemblies)
- Generates scheduler-specific scripts (SLURM, PBS, cloud, local)
- Uses modern tools (compleasm, MAFFT, IQ-TREE, ASTRAL)
- Multiple alignment trimming options
- Both concatenation and coalescent approaches
- Quality control with recommendations
- Writes a draft methods paragraph describing the pipeline for publications
**Use when you need to:**
- Build phylogenetic trees from multiple genome assemblies
- Extract and align single-copy orthologs across genomes
- Download genomes from NCBI by accession
- Generate ready-to-run scripts for your computing environment
## Installation
See README on the repository root folder for plugin installation.
## Usage
Once installed, simply describe your phylogenomics task:
```
I need to generate a phylogeny from 20 genome assemblies on a SLURM cluster
```
Claude Code will automatically activate the appropriate skill and guide you through the workflow.
## Workflow Overview
The complete phylogenomics pipeline:
1. **Input Preparation** - Download NCBI genomes if needed
2. **Ortholog Identification** - Run compleasm/BUSCO on all genomes
3. **Quality Control** - Assess genome completeness with recommendations
4. **Ortholog Extraction** - Generate per-locus unaligned FASTA files
5. **Alignment** - Align orthologs with MAFFT
6. **Trimming** - Remove poorly aligned regions (Aliscore/ALICUT, trimAl, BMGE, ClipKit)
7. **Concatenation** - Build supermatrix with partition scheme
8. **Phylogenetic Inference** - Generate ML concatenated tree (IQ-TREE), gene trees, and coalescent species tree (ASTRAL)
## Requirements
Claude Code is better than the web interface, since Claude will then help you install all requirements.
The skill generates scripts that install and use:
- **compleasm** or BUSCO - ortholog detection
- **MAFFT** - multiple sequence alignment
- **Aliscore/ALICUT, trimAl, BMGE, or ClipKit** - alignment trimming
- **FASconCAT** - alignment concatenation
- **IQ-TREE** - maximum likelihood phylogenetic inference
- **ASTRAL** - coalescent species tree estimation
- **NCBI Datasets CLI** - genome download (if using NCBI accessions)
## Computing Environments
The skill supports multiple computing environments:
- **SLURM clusters** - generates SBATCH array jobs
- **PBS/Torque clusters** - generates PBS array jobs
- **Local machines** - sequential execution scripts
## Attribution
Created by **Bruno de Medeiros** (Curator of Pollinating Insects, Field Museum) based on phylogenomics tutorials by **Paul Frandsen** (Brigham Young University).
## Citation
If you use this skill for published research, please cite this website and also:
- **compleasm**: Huang, N., & Li, H. (2023). compleasm: a faster and more accurate reimplementation of BUSCO. *Bioinformatics*, 39(10), btad595.
- **MAFFT**: Katoh, K., & Standley, D. M. (2013). MAFFT multiple sequence alignment software version 7. *Molecular Biology and Evolution*, 30(4), 772-780.
- **IQ-TREE**: Minh, B. Q., et al. (2020). IQ-TREE 2: New models and efficient methods for phylogenetic inference. *Molecular Biology and Evolution*, 37(5), 1530-1534.
- **ASTRAL**: Zhang, C., et al. (2018). ASTRAL-III: polynomial time species tree reconstruction. *BMC Bioinformatics*, 19(6), 153.
Plus any trimming tool you use (Aliscore/ALICUT, trimAl, BMGE, or ClipKit).
## License
MIT License - see individual tool licenses for software dependencies.
## Support
For issues or questions:
- Open an issue in this repository
- Contact Bruno de Medeiros at the Field Museum (bdemedeiros@fieldmuseum.org)
## Acknowledgments
Special thanks to Paul Frandsen (BYU) for creating the excellent phylogenomics tutorials that form the foundation of this skill.

757
skills/phylo_from_buscos/SKILL.md Normal file
View File

@@ -0,0 +1,757 @@
---
name: busco-phylogeny
description: Generate phylogenies from genome assemblies using BUSCO/compleasm-based single-copy orthologs with scheduler-aware workflow generation
---
# BUSCO-based Phylogenomics Workflow Generator
This skill provides phylogenomics expertise for generating comprehensive, scheduler-aware workflows for phylogenetic inference from genome assemblies using single-copy orthologs.
## Purpose
This skill helps users generate phylogenies from genome assemblies by:
1. Handling mixed input (local files and NCBI accessions)
2. Creating scheduler-specific scripts (SLURM, PBS, cloud, local)
3. Setting up complete workflows from raw genomes to final trees
4. Providing quality control and recommendations
5. Supporting flexible software management (bioconda, Docker, custom)
## Available Resources
The skill provides access to these bundled resources:
### Scripts (`scripts/`)
- **`query_ncbi_assemblies.py`** - Query NCBI for available genome assemblies by taxon name (new!)
- **`download_ncbi_genomes.py`** - Download genomes from NCBI using BioProjects or Assembly accessions
- **`rename_genomes.py`** - Rename genome files with meaningful sample names (important!)
- **`generate_qc_report.sh`** - Generate quality control reports from compleasm results
- **`extract_orthologs.sh`** - Extract and reorganize single-copy orthologs
- **`run_aliscore.sh`** - Wrapper for Aliscore to identify randomly similar sequences (RSS)
- **`run_alicut.sh`** - Wrapper for ALICUT to remove RSS positions from alignments
- **`run_aliscore_alicut_batch.sh`** - Batch process all alignments through Aliscore + ALICUT
- **`convert_fasconcat_to_partition.py`** - Convert FASconCAT output to IQ-TREE partition format
- **`predownloaded_aliscore_alicut/`** - Pre-tested Aliscore and ALICUT Perl scripts
### Templates (`templates/`)
- **`slurm/`** - SLURM job scheduler templates
- **`pbs/`** - PBS/Torque job scheduler templates
- **`local/`** - Local machine templates (with GNU parallel)
- **`README.md`** - Complete template documentation
### References (`references/`)
- **`REFERENCE.md`** - Detailed technical reference including:
- Sample naming best practices
- BUSCO lineage datasets (complete list)
- Resource recommendations (memory, CPUs, walltime)
- Detailed step-by-step implementation guides
- Quality control guidelines
- Aliscore/ALICUT detailed guide
- Tool citations and download links
- Software installation guide
- Common issues and troubleshooting
## Workflow Overview
The complete phylogenomics pipeline follows this sequence:
**Input Preparation** → **Ortholog Identification** → **Quality Control** → **Ortholog Extraction** → **Alignment** → **Trimming** → **Concatenation** → **Phylogenetic Inference**
## Initial User Questions
When a user requests phylogeny generation, gather the following information systematically:
### Step 1: Detect Computing Environment
Before asking questions, attempt to detect the local computing environment:
```bash
# Check for job schedulers
command -v sbatch >/dev/null 2>&1 # SLURM
command -v qsub >/dev/null 2>&1 # PBS/Torque
command -v parallel >/dev/null 2>&1 # GNU parallel
```
Report findings to the user, then confirm: **"I detected [X] on this machine. Will you be running the scripts here or on a different system?"**
### Required Information
Ask these questions to gather essential workflow parameters:
1. **Computing Environment**
- Where will these scripts run? (SLURM cluster, PBS/Torque cluster, Cloud computing, Local machine)
2. **Input Data**
- Local genome files, NCBI accessions, or both?
- If NCBI: Do you already have Assembly accessions (GCA_*/GCF_*) or BioProject accessions (PRJNA*/PRJEB*/PRJDA*)?
- If user doesn't have accessions: Offer to help find assemblies using `query_ncbi_assemblies.py` (see "STEP 0A: Query NCBI for Assemblies" below)
- If local files: What are the file paths?
3. **Taxonomic Scope & Dataset Details**
- What taxonomic group? (determines BUSCO lineage dataset)
- How many taxa/genomes will be analyzed?
- What is the approximate phylogenetic breadth? (species-level, genus-level, family-level, order-level, etc.)
- See `references/REFERENCE.md` for complete lineage list
4. **Environment Management**
- Use unified conda environment (default, recommended), or separate environments per tool?
5. **Resource Constraints**
- How many CPU cores/threads to use in total? (Ask user to specify, do not auto-detect)
- Available memory (RAM) per node/machine?
- Maximum walltime for jobs?
- See `references/REFERENCE.md` for resource recommendations
6. **Parallelization Strategy**
Ask the user how they want to handle parallel processing:
- **For job schedulers (SLURM/PBS)**:
- Use array jobs for parallel steps? (Recommended: Yes)
- Which steps to parallelize? (Steps 2, 5, 6, 8C recommended)
- **For local machines**:
- Use GNU parallel for parallel steps? (requires `parallel` installed)
- How many concurrent jobs?
- **For all systems**:
- Optimize for maximum throughput or simplicity?
7. **Scheduler-Specific Configuration** (if using SLURM or PBS)
- Account/Username for compute time charges
- Partition/Queue to submit jobs to
- Email notifications? (address and when: START, END, FAIL, ALL)
- Job dependencies? (Recommended: Yes for linear workflow)
- Output log directory? (Default: `logs/`)
8. **Alignment Trimming Preference**
- Aliscore/ALICUT (traditional, thorough), trimAl (fast), BMGE (entropy-based), or ClipKit (modern)?
9. **Substitution Model Selection** (for IQ-TREE phylogenetic inference)
**Context needed**: Taxonomic breadth, number of taxa, evolutionary rates
**Action**: Fetch IQ-TREE model documentation and suggest appropriate amino acid substitution models based on dataset characteristics.
Use the substitution model recommendation system (see "Substitution Model Recommendation" section below).
10. **Educational Goals**
- Are you learning bioinformatics and would you like comprehensive explanations of each workflow step?
- If yes: After completing each major workflow stage, offer to explain what the step accomplishes, why certain choices were made, and what best practices are being followed.
- Store this preference to use throughout the workflow.
---
## Recommended Directory Structure
Organize analyses with dedicated folders for each pipeline step:
```
project_name/
├── logs/ # All log files
├── 00_genomes/ # Input genome assemblies
├── 01_busco_results/ # BUSCO/compleasm outputs
├── 02_qc/ # Quality control reports
├── 03_extracted_orthologs/ # Extracted single-copy orthologs
├── 04_alignments/ # Multiple sequence alignments
├── 05_trimmed/ # Trimmed alignments
├── 06_concatenation/ # Supermatrix and partition files
├── 07_partition_search/ # Partition model selection
├── 08_concatenated_tree/ # Concatenated ML tree
├── 09_gene_trees/ # Individual gene trees
├── 10_species_tree/ # ASTRAL species tree
└── scripts/ # All analysis scripts
```
**Benefits**: Easy debugging, clear workflow progression, reproducibility, prevents root directory clutter.
---
## Template System
This skill uses a template-based system to reduce token usage and improve maintainability. Script templates are stored in the `templates/` directory and organized by computing environment.
### How to Use Templates
When generating scripts for users:
1. **Read the appropriate template** for their computing environment:
```
Read("templates/slurm/02_compleasm_first.job")
```
2. **Replace placeholders** with user-specific values:
- `TOTAL_THREADS` → e.g., `64`
- `THREADS_PER_JOB` → e.g., `16`
- `NUM_GENOMES` → e.g., `20`
- `NUM_LOCI` → e.g., `2795`
- `LINEAGE` → e.g., `insecta_odb10`
- `MODEL_SET` → e.g., `LG,WAG,JTT,Q.pfam`
3. **Present the customized script** to the user with setup instructions
### Available Templates
Key templates by workflow step:
- **Step 0 (setup)**: Environment setup script in `references/REFERENCE.md`
- **Step 2 (compleasm)**: `02_compleasm_first`, `02_compleasm_parallel`
- **Step 8A (partition search)**: `08a_partition_search`
- **Step 8C (gene trees)**: `08c_gene_trees_array`, `08c_gene_trees_parallel`, `08c_gene_trees_serial`
See `templates/README.md` for complete template documentation.
---
## Substitution Model Recommendation
When asked about substitution model selection (Question 9), use this systematic approach:
### Step 1: Fetch IQ-TREE Documentation
Use WebFetch to retrieve current model information:
```
WebFetch(url="https://iqtree.github.io/doc/Substitution-Models",
prompt="Extract all amino acid substitution models with descriptions and usage guidelines")
```
### Step 2: Analyze Dataset Characteristics
Consider these factors from user responses:
- **Taxonomic Scope**: Species/genus (shallow) vs. family/order (moderate) vs. class/phylum+ (deep)
- **Number of Taxa**: <20 (small), 20-50 (medium), >50 (large)
- **Evolutionary Rates**: Fast-evolving, moderate, or slow-evolving
- **Sequence Type**: Nuclear proteins, mitochondrial, or chloroplast
### Step 3: Recommend Models
Provide 3-5 appropriate models based on dataset characteristics. For detailed model recommendation matrices and taxonomically-targeted models, see `references/REFERENCE.md` section "Substitution Model Recommendation".
**General recommendations**:
- **Nuclear proteins (most common)**: LG, WAG, JTT, Q.pfam
- **Mitochondrial**: mtREV, mtZOA, mtMAM, mtART, mtVer, mtInv
- **Chloroplast**: cpREV
- **Taxonomically-targeted**: Q.bird, Q.mammal, Q.insect, Q.plant, Q.yeast (when applicable)
### Step 4: Present Recommendations
Format recommendations with justifications and explain how models will be used in IQ-TREE steps 8A and 8C.
### Step 5: Store Model Set
Store the final comma-separated model list (e.g., "LG,WAG,JTT,Q.pfam") for use in Step 8 template placeholders.
---
## Workflow Implementation
Once required information is gathered, guide the user through these steps. For each step, use templates where available and refer to `references/REFERENCE.md` for detailed implementation.
### STEP 0: Environment Setup
**ALWAYS start by generating a setup script** for the user's environment.
Use the unified conda environment setup script from `references/REFERENCE.md` (Section: "Software Installation Guide"). This creates a single conda environment with all necessary tools:
- compleasm, MAFFT, trimming tools (trimAl, ClipKit, BMGE)
- IQ-TREE, ASTRAL, Perl with BioPerl, GNU parallel
- Downloads and installs Aliscore/ALICUT Perl scripts
**Key points**:
- Users choose between mamba (faster) or conda
- Users choose between predownloaded Aliscore/ALICUT scripts (tested) or latest from GitHub
- All subsequent steps use `conda activate phylo` (the unified environment)
See `references/REFERENCE.md` for the complete setup script template.
---
### STEP 0A: Query NCBI for Assemblies (Optional)
**Use this step when**: User wants to use NCBI data but doesn't have specific assembly accessions yet.
This optional preliminary step helps users discover available genome assemblies by taxon name before proceeding with the main workflow.
#### When to Offer This Step
Offer this step when:
- User wants to analyze genomes from NCBI
- User doesn't have specific Assembly or BioProject accessions
- User mentions a taxonomic group (e.g., "I want to build a phylogeny for beetles")
#### Workflow
1. **Ask for focal taxon**: Request the taxonomic group of interest
- Examples: "Coleoptera", "Drosophila", "Apis mellifera"
- Can be at any taxonomic level (order, family, genus, species)
2. **Query NCBI using the script**: Use `scripts/query_ncbi_assemblies.py` to search for assemblies
```bash
# Basic query (returns 20 results by default)
python scripts/query_ncbi_assemblies.py --taxon "Coleoptera"
# Query with more results
python scripts/query_ncbi_assemblies.py --taxon "Drosophila" --max-results 50
# Query for RefSeq assemblies only (higher quality, GCF_* accessions)
python scripts/query_ncbi_assemblies.py --taxon "Apis" --refseq-only
# Save accessions to file for later download
python scripts/query_ncbi_assemblies.py --taxon "Coleoptera" --save assembly_accessions.txt
```
3. **Present results to user**: The script displays:
- Assembly accession (GCA_* or GCF_*)
- Organism name
- Assembly level (Chromosome, Scaffold, Contig)
- Assembly name
4. **Help user select assemblies**: Ask user which assemblies they want to include
- Consider assembly level (Chromosome > Scaffold > Contig)
- Consider phylogenetic breadth (species coverage)
- Consider data quality (RefSeq > GenBank when available)
5. **Collect selected accessions**: Compile the list of chosen assembly accessions
6. **Proceed to STEP 1**: Use the selected accessions with `download_ncbi_genomes.py`
#### Tips for Assembly Selection
- **Assembly Level**: Chromosome-level assemblies are most complete, followed by Scaffold, then Contig
- **RefSeq vs GenBank**: RefSeq (GCF_*) assemblies undergo additional curation; GenBank (GCA_*) are submitter-provided
- **Taxonomic Sampling**: For phylogenetics, aim for representative sampling across the taxonomic group
- **Quality over Quantity**: Better to have 20 high-quality assemblies than 100 poor-quality ones
---
### STEP 1: Download NCBI Genomes (if applicable)
If user provided NCBI accessions, use `scripts/download_ncbi_genomes.py`:
**For BioProjects**:
```bash
python scripts/download_ncbi_genomes.py --bioprojects PRJNA12345 -o genomes.zip
unzip genomes.zip
```
**For Assembly Accessions**:
```bash
python scripts/download_ncbi_genomes.py --assemblies GCA_123456789.1 -o genomes.zip
unzip genomes.zip
```
**IMPORTANT**: After download, genomes must be renamed with meaningful sample names (format: `[ACCESSION]_[SPECIES_NAME]`). Sample names appear in final phylogenetic trees.
Generate a script that:
1. Finds all downloaded FASTA files in ncbi_dataset directory structure
2. Moves/renames files to main genomes directory with meaningful names
3. Includes any local genome files
4. Creates final genome_list.txt with ALL genomes (local + downloaded)
See `references/REFERENCE.md` section "Sample Naming Best Practices" for detailed guidelines.
---
### STEP 2: Ortholog Identification with compleasm
Activate the unified environment and run compleasm on all genomes to identify single-copy orthologs.
**Key considerations**:
- First genome must run alone to download lineage database
- Remaining genomes can run in parallel
- Thread allocation: Miniprot scales well up to ~16-32 threads per genome
**Threading guidelines**: See `references/REFERENCE.md` for recommended thread allocation table.
**Generate scripts using templates**:
- **SLURM**: Read templates `02_compleasm_first.job` and `02_compleasm_parallel.job`
- **PBS**: Read templates `02_compleasm_first.job` and `02_compleasm_parallel.job`
- **Local**: Read templates `02_compleasm_first.sh` and `02_compleasm_parallel.sh`
Replace placeholders: `TOTAL_THREADS`, `THREADS_PER_JOB`, `NUM_GENOMES`, `LINEAGE`
For detailed implementation examples, see `references/REFERENCE.md` section "Ortholog Identification Implementation".
---
### STEP 3: Quality Control
After compleasm completes, generate QC report using `scripts/generate_qc_report.sh`:
```bash
bash scripts/generate_qc_report.sh qc_report.csv
```
Provide interpretation:
- **>95% complete**: Excellent, retain
- **90-95% complete**: Good, retain
- **85-90% complete**: Acceptable, case-by-case
- **70-85% complete**: Questionable, consider excluding
- **<70% complete**: Poor, recommend excluding
See `references/REFERENCE.md` section "Quality Control Guidelines" for detailed assessment criteria.
---
### STEP 4: Ortholog Extraction
Use `scripts/extract_orthologs.sh` to extract single-copy orthologs:
```bash
bash scripts/extract_orthologs.sh LINEAGE_NAME
```
This generates per-locus unaligned FASTA files in `single_copy_orthologs/unaligned_aa/`.
---
### STEP 5: Alignment with MAFFT
Activate the unified environment (`conda activate phylo`) which contains MAFFT.
Create locus list, then generate alignment scripts:
```bash
cd single_copy_orthologs/unaligned_aa
ls *.fas > locus_names.txt
num_loci=$(wc -l < locus_names.txt)
```
**Generate scheduler-specific scripts**:
- **SLURM/PBS**: Array job with one task per locus
- **Local**: Sequential processing or GNU parallel
For detailed script templates, see `references/REFERENCE.md` section "Alignment Implementation".
---
### STEP 6: Alignment Trimming
Based on user's preference, provide appropriate trimming method. All tools are available in the unified conda environment.
**Options**:
- **trimAl**: Fast (`-automated1`), recommended for large datasets
- **ClipKit**: Modern, fast (default smart-gap mode)
- **BMGE**: Entropy-based (`-t AA`)
- **Aliscore/ALICUT**: Traditional, thorough (recommended for phylogenomics)
**For Aliscore/ALICUT**:
- Perl scripts were installed in STEP 0
- Use `scripts/run_aliscore_alicut_batch.sh` for batch processing
- Or use array jobs with `scripts/run_aliscore.sh` and `scripts/run_alicut.sh`
- Always use `-N` flag for amino acid sequences
**Generate scripts** using scheduler-appropriate templates (array jobs for SLURM/PBS, parallel or serial for local).
For detailed implementation of each trimming method, see `references/REFERENCE.md` section "Alignment Trimming Implementation".
---
### STEP 7: Concatenation and Partition Definition
Download FASconCAT-G (Perl script) and run concatenation:
```bash
conda activate phylo # Has Perl installed
wget https://raw.githubusercontent.com/PatrickKueck/FASconCAT-G/master/FASconCAT-G_v1.06.1.pl -O FASconCAT-G.pl
chmod +x FASconCAT-G.pl
cd trimmed_aa
perl ../FASconCAT-G.pl -s -i
```
Convert to IQ-TREE format using `scripts/convert_fasconcat_to_partition.py`:
```bash
python ../scripts/convert_fasconcat_to_partition.py FcC_info.xls partition_def.txt
```
Outputs: `FcC_supermatrix.fas`, `FcC_info.xls`, `partition_def.txt`
---
### STEP 8: Phylogenetic Inference
IQ-TREE is already installed in the unified environment. Activate with `conda activate phylo`.
#### Part 8A: Partition Model Selection
Use the substitution models selected during initial setup (Question 9).
**Generate script using templates**:
- Read appropriate template: `templates/[slurm|pbs|local]/08a_partition_search.[job|sh]`
- Replace `MODEL_SET` placeholder with user's selected models (e.g., "LG,WAG,JTT,Q.pfam")
For detailed implementation, see `references/REFERENCE.md` section "Partition Model Selection Implementation".
#### Part 8B: Concatenated ML Tree
Run IQ-TREE using the best partition scheme from Part 8A:
```bash
iqtree -s FcC_supermatrix.fas -spp partition_search.best_scheme.nex \
-nt 18 -safe -pre concatenated_ML_tree -bb 1000 -bnni
```
Output: `concatenated_ML_tree.treefile`
#### Part 8C: Individual Gene Trees
Estimate gene trees for coalescent-based species tree inference.
**Generate scripts using templates**:
- **SLURM/PBS**: Read `08c_gene_trees_array.job` template
- **Local**: Read `08c_gene_trees_parallel.sh` or `08c_gene_trees_serial.sh` template
- Replace `NUM_LOCI` placeholder
For detailed implementation, see `references/REFERENCE.md` section "Gene Trees Implementation".
#### Part 8D: ASTRAL Species Tree
ASTRAL is already installed in the unified conda environment.
```bash
conda activate phylo
# Concatenate all gene trees
cat trimmed_aa/*.treefile > all_gene_trees.tre
# Run ASTRAL
astral -i all_gene_trees.tre -o astral_species_tree.tre
```
Output: `astral_species_tree.tre`
---
### STEP 9: Generate Methods Paragraph
**ALWAYS generate a methods paragraph** to help users write their publication methods section.
Create `METHODS_PARAGRAPH.md` file with:
- Customized text based on tools and parameters used
- Complete citations for all software
- Placeholders for user-specific values (genome count, loci count, thresholds)
- Instructions for adapting to journal requirements
For the complete methods paragraph template, see `references/REFERENCE.md` section "Methods Paragraph Template".
Pre-fill known values when possible:
- Number of genomes
- BUSCO lineage
- Trimming method used
- Substitution models tested
---
## Final Outputs Summary
Provide users with a summary of outputs:
**Phylogenetic Results**:
1. `concatenated_ML_tree.treefile` - ML tree from concatenated supermatrix
2. `astral_species_tree.tre` - Coalescent species tree
3. `*.treefile` - Individual gene trees
**Data and Quality Control**:
4. `qc_report.csv` - Genome quality statistics
5. `FcC_supermatrix.fas` - Concatenated alignment
6. `partition_search.best_scheme.nex` - Selected partitioning scheme
**Publication Materials**:
7. `METHODS_PARAGRAPH.md` - Ready-to-use methods section with citations
**Visualization tools**: FigTree, iTOL, ggtree (R), ete3/toytree (Python)
---
## Script Validation
**ALWAYS perform validation checks** after generating scripts but before presenting them to the user. This ensures script accuracy, consistency, and proper resource allocation.
### Validation Workflow
For each generated script, perform these validation checks in order:
#### 1. Program Option Verification
**Purpose**: Detect hallucinated or incorrect command-line options that may cause scripts to fail.
**Procedure**:
1. **Extract all command invocations** from the generated script (e.g., `compleasm run`, `iqtree -s`, `mafft --auto`)
2. **Compare against reference sources**:
- First check: Compare against corresponding template in `templates/` directory
- Second check: Compare against examples in `references/REFERENCE.md`
- Third check: If options differ significantly or are uncertain, perform web search for official documentation
3. **Common tools to validate**:
- `compleasm run` - Check `-a`, `-o`, `-l`, `-t` options
- `iqtree` - Verify `-s`, `-p`, `-m`, `-bb`, `-alrt`, `-nt`, `-safe` options
- `mafft` - Check `--auto`, `--thread`, `--reorder` options
- `astral` - Verify `-i`, `-o` options
- Trimming tools (`trimal`, `clipkit`, `BMGE.jar`) - Validate options
**Action on issues**:
- If incorrect options found: Inform user of the issue and ask if they want you to correct it
- If uncertain: Ask user to verify with tool documentation before proceeding
#### 2. Pipeline Continuity Verification
**Purpose**: Ensure outputs from one step correctly feed into inputs of subsequent steps.
**Procedure**:
1. **Map input/output relationships**:
- Step 2 output (`01_busco_results/*_compleasm/`) → Step 3 input (QC script)
- Step 3 output (`single_copy_orthologs/`) → Step 5 input (MAFFT)
- Step 5 output (`04_alignments/*.fas`) → Step 6 input (trimming)
- Step 6 output (`05_trimmed/*.fas`) → Step 7 input (FASconCAT-G)
- Step 7 output (`FcC_supermatrix.fas`, partition file) → Step 8A input (IQ-TREE)
- Step 8C output (`*.treefile`) → Step 8D input (ASTRAL)
2. **Check for consistency**:
- File path references match across scripts
- Directory structure follows recommended layout
- Glob patterns correctly match expected files
- Required intermediate files are generated before being used
**Action on issues**:
- If path mismatches found: Inform user and ask if they want you to correct them
- If directory structure inconsistent: Suggest corrections aligned with recommended structure
#### 3. Resource Compatibility Check
**Purpose**: Ensure allocated computational resources are appropriate for the task.
**Procedure**:
1. **Verify resource allocations** against recommendations in `references/REFERENCE.md`:
- **Memory allocation**: Check if memory per CPU (typically 6GB for compleasm, 2-4GB for others) is adequate
- **Thread allocation**: Verify thread counts are reasonable for the number of genomes/loci
- **Walltime**: Ensure walltime is sufficient based on dataset size guidelines
- **Parallelization**: Check that threads per job × concurrent jobs ≤ total threads
2. **Common issues to check**:
- Compleasm: First job needs full thread allocation (downloads database)
- IQ-TREE: `-nt` should match allocated CPUs
- Gene trees: Ensure enough threads per tree × concurrent trees ≤ total available
- Memory: Concatenated tree inference may need 8-16GB per CPU for large datasets
3. **Validate against user-specified constraints**:
- Total CPUs specified by user
- Available memory per node
- Maximum walltime limits
- Scheduler-specific limits (if mentioned)
**Action on issues**:
- If resource allocation issues found: Inform user and suggest corrections with justification
- If uncertain about adequacy: Ask user about typical job performance in their environment
### Validation Reporting
After completing all validation checks:
1. **If all checks pass**: Inform user briefly: "Scripts validated successfully - options, pipeline flow, and resources verified."
2. **If issues found**: Present a structured report:
```
**Validation Results**
⚠️ Issues found during validation:
1. [Issue category]: [Description]
- Current: [What was generated]
- Suggested: [Recommended fix]
- Reason: [Why this is an issue]
Would you like me to apply these corrections?
```
3. **Always ask before correcting**: Never silently fix issues - always get user confirmation before applying changes.
4. **Document corrections**: If corrections are applied, explain what was changed and why.
---
## Communication Guidelines
- **Always start with STEP 0**: Generate the unified environment setup script
- **Always end with STEP 9**: Generate the customized methods paragraph
- **Always validate scripts**: Perform validation checks before presenting scripts to users
- **Use unified environment by default**: All scripts should use `conda activate phylo`
- **Always ask about CPU allocation**: Never auto-detect cores, always ask user
- **Recommend optimized workflows**: For users with adequate resources, recommend optimized parallel approaches over simple serial approaches
- **Be clear and pedagogical**: Explain why each step is necessary
- **Provide educational explanations when requested**: If user answered yes to educational goals (question 10):
- After completing each major workflow stage, ask: "Would you like me to explain this step?"
- If yes, provide moderate-length explanation (1-2 paragraphs) covering:
- What the step accomplishes biologically and computationally
- Significant choices made and their rationale
- Best practices being followed in the workflow
- Examples of "major workflow stages": STEP 0 (setup), STEP 1 (download), STEP 2 (BUSCO), STEP 3 (QC), STEP 5 (alignment), STEP 6 (trimming), STEP 7 (concatenation), STEP 8 (phylogenetic inference)
- **Provide complete, ready-to-run scripts**: Users should copy-paste and run
- **Adapt to user's environment**: Always generate scheduler-specific scripts
- **Reference supporting files**: Direct users to `references/REFERENCE.md` for details
- **Use helper scripts**: Leverage provided scripts in `scripts/` directory
- **Include error checking**: Add file existence checks and informative error messages
- **Be encouraging**: Phylogenomics is complex; maintain supportive tone
---
## Important Notes
### Mandatory Steps
1. **STEP 0 is mandatory**: Always generate the environment setup script first
2. **STEP 9 is mandatory**: Always generate the methods paragraph file at the end
### Template Usage (IMPORTANT!)
3. **Prefer templates over inline code**: Use `templates/` directory for major scripts
4. **Template workflow**:
- Read: `Read("templates/slurm/02_compleasm_first.job")`
- Replace placeholders: `TOTAL_THREADS`, `LINEAGE`, `NUM_GENOMES`, `MODEL_SET`, etc.
- Present customized script to user
5. **Available templates**: See `templates/README.md` for complete list
6. **Benefits**: Reduces token usage, easier maintenance, consistent structure
### Script Generation
7. **Always adapt scripts** to user's scheduler (SLURM/PBS/local)
8. **Replace all placeholders** before presenting scripts
9. **Never auto-detect CPU cores**: Always ask user to specify
10. **Provide parallelization options**: For each parallelizable step, offer array job, parallel, and serial options
11. **Scheduler-specific configuration**: For SLURM/PBS, always ask about account, partition, email, etc.
### Parallelization Strategy
12. **Ask about preferences**: Let user choose between throughput optimization vs. simplicity
13. **Compleasm optimization**: For ≥2 genomes and ≥16 cores, recommend two-phase approach
14. **Use threading guidelines**: Refer to `references/REFERENCE.md` for thread allocation recommendations
15. **Parallelizable steps**: Steps 2 (compleasm), 5 (MAFFT), 6 (trimming), 8C (gene trees)
### Substitution Model Selection
16. **Always recommend models**: Use the systematic model recommendation process
17. **Fetch current documentation**: Use WebFetch to get IQ-TREE model information
18. **Replace MODEL_SET placeholder**: In Step 8A templates with comma-separated list
19. **Taxonomically-targeted models**: Suggest Q.bird, Q.mammal, Q.insect, Q.plant when applicable
### Reference Material
20. **Direct users to references/REFERENCE.md** for:
- Detailed implementation guides
- BUSCO lineage datasets (complete list)
- Resource recommendations (memory, CPUs, walltime tables)
- Sample naming best practices
- Quality control assessment criteria
- Aliscore/ALICUT detailed guide and parameters
- Tool citations with DOIs
- Software installation instructions
- Common issues and troubleshooting
---
## Attribution
This skill was created by **Bruno de Medeiros** (Curator of Pollinating Insects, Field Museum) based on phylogenomics tutorials by **Paul Frandsen** (Brigham Young University).
## Workflow Entry Point
When a user requests phylogeny generation:
1. Gather required information using the "Initial User Questions" section
2. Generate STEP 0 setup script from `references/REFERENCE.MD`
3. If user needs help finding NCBI assemblies, perform STEP 0A using `query_ncbi_assemblies.py`
4. Proceed step-by-step through workflow (STEPS 1-8), using templates and referring to `references/REFERENCE.md` for detailed implementation
5. All workflow scripts should use the unified conda environment (`conda activate phylo`)
6. Validate all generated scripts before presenting to user (see "Script Validation" section)
7. Generate STEP 9 methods paragraph from template in `references/REFERENCE.md`
8. Provide final outputs summary

2225
skills/phylo_from_buscos/references/REFERENCE.md Normal file
View File

File diff suppressed because it is too large Load Diff

63
skills/phylo_from_buscos/scripts/convert_fasconcat_to_partition.py Executable file
View File

@@ -0,0 +1,63 @@
#!/usr/bin/env python3
"""
Convert FASconCAT info file to IQ-TREE partition format
Usage:
python convert_fasconcat_to_partition.py FcC_info.xls [output_file.txt]
Author: Bruno de Medeiros (Field Museum)
Based on tutorials by Paul Frandsen (BYU)
"""
import sys
def convert_fcc_to_partition(fcc_file, output_file="partition_def.txt"):
"""
Convert FASconCAT info file to IQ-TREE partition format
Args:
fcc_file: Path to FcC_info.xls file from FASconCAT
output_file: Path to output partition definition file
"""
try:
with open(fcc_file, 'r') as f:
lines = f.readlines()
except FileNotFoundError:
print(f"Error: File '{fcc_file}' not found")
sys.exit(1)
partitions_written = 0
with open(output_file, 'w') as out:
# Skip first two header lines (FASconCAT INFO and column headers)
for line in lines[2:]:
line = line.strip()
if line:
parts = line.split('\t')
if len(parts) >= 3:
locus = parts[0]
start = parts[1]
end = parts[2]
out.write(f"AA, {locus} = {start}-{end}\n")
partitions_written += 1
print(f"Partition file created: {output_file}")
print(f"Number of partitions: {partitions_written}")
def main():
if len(sys.argv) < 2:
print("Usage: python convert_fasconcat_to_partition.py FcC_info.xls [output_file.txt]")
print("\nConverts FASconCAT info file to IQ-TREE partition format")
sys.exit(1)
fcc_file = sys.argv[1]
output_file = sys.argv[2] if len(sys.argv) > 2 else "partition_def.txt"
convert_fcc_to_partition(fcc_file, output_file)
if __name__ == "__main__":
main()

133
skills/phylo_from_buscos/scripts/download_ncbi_genomes.py Executable file
View File

@@ -0,0 +1,133 @@
#!/usr/bin/env python3
"""
Download genomes from NCBI using BioProject or Assembly accessions
Usage:
python download_ncbi_genomes.py --bioprojects PRJNA12345 PRJEB67890
python download_ncbi_genomes.py --assemblies GCA_123456789.1 GCF_987654321.1
Requires: ncbi-datasets-pylib (pip install ncbi-datasets-pylib)
Author: Bruno de Medeiros (Field Museum)
Based on tutorials by Paul Frandsen (BYU)
"""
import argparse
import sys
import subprocess
def download_using_cli(accessions, output_file="genomes.zip"):
"""
Download genomes using NCBI datasets CLI
Args:
accessions: List of BioProject or Assembly accessions
output_file: Name of output zip file
"""
cmd = ["datasets", "download", "genome", "accession"] + accessions + ["--filename", output_file]
print(f"Running: {' '.join(cmd)}")
print("")
try:
result = subprocess.run(cmd, check=True, capture_output=True, text=True)
print(result.stdout)
print(f"\nDownload complete: {output_file}")
print("Extract with: unzip " + output_file)
return True
except subprocess.CalledProcessError as e:
print(f"Error downloading genomes: {e}", file=sys.stderr)
print(e.stderr, file=sys.stderr)
return False
except FileNotFoundError:
print("Error: 'datasets' command not found", file=sys.stderr)
print("Install with: conda install -c conda-forge ncbi-datasets-cli", file=sys.stderr)
return False
def get_bioproject_assemblies(bioprojects):
"""
Get assembly accessions for given BioProjects using Python API
Args:
bioprojects: List of BioProject accessions
Returns:
List of tuples (assembly_accession, organism_name)
"""
try:
from ncbi.datasets.metadata.genome import get_assembly_metadata_by_bioproject_accessions
except ImportError:
print("Error: ncbi-datasets-pylib not installed", file=sys.stderr)
print("Install with: pip install ncbi-datasets-pylib", file=sys.stderr)
sys.exit(1)
assemblies = []
print(f"Fetching assembly information for {len(bioprojects)} BioProject(s)...")
print("")
for assembly in get_assembly_metadata_by_bioproject_accessions(bioprojects):
acc = assembly.accession
name = assembly.organism.organism_name
assemblies.append((acc, name))
print(f" {name}: {acc}")
print(f"\nFound {len(assemblies)} assemblies")
return assemblies
def main():
parser = argparse.ArgumentParser(
description="Download genomes from NCBI using BioProject or Assembly accessions"
)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument(
"--bioprojects",
nargs="+",
help="BioProject accessions (e.g., PRJNA12345 PRJEB67890)"
)
group.add_argument(
"--assemblies",
nargs="+",
help="Assembly accessions (e.g., GCA_123456789.1 GCF_987654321.1)"
)
parser.add_argument(
"-o", "--output",
default="genomes.zip",
help="Output zip file name (default: genomes.zip)"
)
parser.add_argument(
"--list-only",
action="store_true",
help="List assemblies without downloading (BioProject mode only)"
)
args = parser.parse_args()
if args.bioprojects:
assemblies = get_bioproject_assemblies(args.bioprojects)
if args.list_only:
print("\nAssembly accessions (use with --assemblies to download):")
for acc, name in assemblies:
print(acc)
return
# Download assemblies
assembly_accs = [acc for acc, name in assemblies]
success = download_using_cli(assembly_accs, args.output)
elif args.assemblies:
success = download_using_cli(args.assemblies, args.output)
sys.exit(0 if success else 1)
if __name__ == "__main__":
main()

88
skills/phylo_from_buscos/scripts/extract_orthologs.sh Executable file
View File

@@ -0,0 +1,88 @@
#!/bin/bash
# Extract and reorganize single-copy orthologs from compleasm output
#
# Usage: bash extract_orthologs.sh LINEAGE_NAME
# Example: bash extract_orthologs.sh metazoa
#
# Author: Bruno de Medeiros (Field Museum)
# Based on tutorials by Paul Frandsen (BYU)
if [ $# -lt 1 ]; then
echo "Usage: bash extract_orthologs.sh LINEAGE_NAME"
echo " Example: bash extract_orthologs.sh metazoa"
exit 1
fi
LINEAGE="$1"
echo "Extracting single-copy orthologs for lineage: ${LINEAGE}"
# Create directory for ortholog FASTA files
mkdir -p single_copy_orthologs
# Copy gene_marker.fasta files and rename by species
count=0
for dir in 01_busco_results/*_compleasm; do
if [ ! -d "${dir}" ]; then
continue
fi
genome=$(basename "${dir}" _compleasm)
# Auto-detect the OrthoDB version (odb10, odb11, odb12, etc.)
odb_dirs=("${dir}/${LINEAGE}_odb"*)
if [ -d "${odb_dirs[0]}" ]; then
marker_file="${odb_dirs[0]}/gene_marker.fasta"
else
echo " Warning: No OrthoDB directory found for ${genome}" >&2
continue
fi
if [ -f "${marker_file}" ]; then
cp "${marker_file}" "single_copy_orthologs/${genome}.fasta"
echo " Extracted: ${genome}"
count=$((count + 1))
else
echo " Warning: Marker file not found for ${genome}" >&2
fi
done
if [ ${count} -eq 0 ]; then
echo "Error: No gene_marker.fasta files found. Check lineage name." >&2
exit 1
fi
echo "Extracted ${count} genomes"
echo ""
echo "Now generating per-locus unaligned FASTA files..."
cd single_copy_orthologs || exit 1
mkdir -p unaligned_aa
cd unaligned_aa || exit 1
# AWK script to split by ortholog ID
awk 'BEGIN{RS=">"; FS="\n"} {
if (NF > 1) {
split($1, b, "_");
fnme = b[1] ".fas";
n = split(FILENAME, a, "/");
species = a[length(a)];
gsub(".fasta", "", species);
print ">" species "\n" $2 >> fnme;
close(fnme);
}
}' ../*.fasta
# Fix headers
if [[ "$OSTYPE" == "darwin"* ]]; then
# macOS
sed -i '' -e 's/.fasta//g' *.fas
else
# Linux
sed -i -e 's/.fasta//g' *.fas
fi
num_loci=$(ls -1 *.fas 2>/dev/null | wc -l)
echo "Unaligned ortholog files generated: ${num_loci} loci"
echo ""
echo "Output directory: single_copy_orthologs/unaligned_aa/"

59
skills/phylo_from_buscos/scripts/generate_qc_report.sh Executable file
View File

@@ -0,0 +1,59 @@
#!/bin/bash
# Quality control report generator for compleasm results
#
# Usage: bash generate_qc_report.sh [output_file.csv]
#
# Author: Bruno de Medeiros (Field Museum)
# Based on tutorials by Paul Frandsen (BYU)
OUTPUT_FILE="${1:-qc_report.csv}"
echo "Genome,Complete_SCO,Fragmented,Duplicated,Missing,Completeness(%)" > "${OUTPUT_FILE}"
count=0
for dir in 01_busco_results/*_compleasm; do
if [ ! -d "${dir}" ]; then
continue
fi
genome=$(basename "${dir}" _compleasm)
summary="${dir}/summary.txt"
if [ -f "${summary}" ]; then
# Parse completeness statistics from compleasm format
# compleasm uses: S: (single-copy), D: (duplicated), F: (fragmented), M: (missing)
# Format: "S:80.93%, 2283" where we need the count (2283)
complete=$(grep "^S:" "${summary}" | awk -F',' '{print $2}' | tr -d ' ')
duplicated=$(grep "^D:" "${summary}" | awk -F',' '{print $2}' | tr -d ' ')
fragmented=$(grep "^F:" "${summary}" | awk -F',' '{print $2}' | tr -d ' ')
missing=$(grep "^M:" "${summary}" | awk -F',' '{print $2}' | tr -d ' ')
# Check if all values were successfully extracted
if [ -z "${complete}" ] || [ -z "${fragmented}" ] || [ -z "${missing}" ]; then
echo "Warning: Could not parse statistics for ${genome}" >&2
continue
fi
# Calculate completeness percentage (Complete / Total * 100)
total=$((complete + duplicated + fragmented + missing))
if command -v bc &> /dev/null; then
completeness=$(echo "scale=2; (${complete} + ${duplicated}) / ${total} * 100" | bc)
else
# Fallback if bc not available
completeness=$(awk "BEGIN {printf \"%.2f\", (${complete} + ${duplicated}) / ${total} * 100}")
fi
echo "${genome},${complete},${fragmented},${duplicated},${missing},${completeness}" >> "${OUTPUT_FILE}"
count=$((count + 1))
else
echo "Warning: Summary file not found for ${genome}" >&2
fi
done
if [ ${count} -eq 0 ]; then
echo "Error: No compleasm output directories found (*_compleasm)" >&2
exit 1
fi
echo "QC report generated: ${OUTPUT_FILE}"
echo "Genomes analyzed: ${count}"

742
skills/phylo_from_buscos/scripts/predownloaded_aliscore_alicut/ALICUT_V2.31.pl Executable file
View File

@@ -0,0 +1,742 @@
#!/usr/bin/perl
use strict ;
use File::Copy ;
use Tie::File ;
use Fcntl ;
use Term::Cap ;
use Term::ANSIColor qw(:constants);
use Getopt::Std ;
# updated on 13th february , 2009 by patrick k<>ck
# updated on 2nd april , 2009 by patrick k<>ck
# updated on 15th june , 2009 by patrick k<>ck
# updated on 26th july , 2009 by patrick k<>ck
# updated on 7th september, 2011 by patrick k<>ck (alicut v2.3)
# updated on 22.2.2017, by patrick k<>ck (alicut v2.31) -> correction of initial warning due to line 547, changed some terminal prints, argv handling commands
my @answer_remain_stems = ( 'no', 'yes' ) ;
my @answer_codons = ( 'no', 'yes' ) ;
my @answer_third_pos = ( 'no', 'yes' ) ;
&argv_handling ( \@answer_remain_stems, \@answer_codons, \@answer_third_pos ) ;
&menu ( \@answer_remain_stems, \@answer_codons, \@answer_third_pos ) ;
sub argv_handling{
my $aref_remain_stems = $_[0] ;
my $aref_codons = $_[1] ;
my $aref_third_pos = $_[2] ;
my ( $commandline ) = join "", @ARGV ;
$commandline =~ s/ |\s+// ;
my @commands = split "-", $commandline ;
shift @commands ;
for my $single_command ( sort @commands ){
if ( $single_command =~ /^r$/i ) { @$aref_remain_stems = ( reverse @$aref_remain_stems) }
elsif ( $single_command =~ /^c$/i ) { @$aref_codons = ( reverse @$aref_codons ) }
elsif ( $single_command =~ /^3$/i ) { @$aref_third_pos = ( reverse @$aref_third_pos ) }
elsif ( $single_command =~ /^h$/i ) { &help }
elsif ( $single_command =~ /^p$/i ) { &preface }
elsif ( $single_command =~ /^s$/i ) {
&header ;
&commands( \$aref_remain_stems->[0], \$aref_codons->[0], \$aref_third_pos->[0]) ;
&start (\$aref_remain_stems->[0], \$aref_codons->[0], \$aref_third_pos->[0])
}
else { print "\n\t!COMMAND-ERROR!: unknown command \"-", $single_command, "\"\n" }
}
&menu ( \@$aref_remain_stems, \@$aref_codons, \@$aref_third_pos)
}
sub header{
printf "\n%68s\n", "------------------------------------------------------------" ;
printf "%49s\n" , "Welcome to ALICUT V2.31 !" ;
printf "%60s\n" , "a Perlscript to cut ALISCORE identified RSS" ;
printf "%57s\n" , "written by Patrick Kueck (ZFMK, Bonn)" ;
printf "%68s\n\n", "------------------------------------------------------------" ;
}
sub commands{
my $sref_rem_stems = $_[0] ;
my $sref_reo_codon = $_[1] ;
my $sref_th_posit = $_[2] ;
print "\n\t------------------------------------------------------------" ;
print "\n\tRemain Stem Position :\t", $$sref_rem_stems ;
print "\n\tRemove Codon :\t", $$sref_reo_codon ;
print "\n\tRemove 3rd Position :\t", $$sref_th_posit ;
print "\n\t------------------------------------------------------------\n" ;
}
sub help{
print
<<info;
-------------------------------------------------------------------
-------------------------------------------------------------------
General Information and Usage:
-------------------------------
ALICUT V2.31 removes ALISCORE identified RSS positions
in given FASTA file(s) which are listed in the FASTA file cor-
responding ALISCORE "List" outfile(s). If structure sequences
are implemented, ALICUT V2.3 automatically replaces brackets
of non rss positions by dots when they are paired with rss
identified positions.
Start ALICUT under default
-------------------------------------------------------------------
To remove all ALISCORE identified RSS positions:
Type <s> return (via Menu) or
Type <perl ALICUT_V2.3.pl -s> <enter> (via command line)
R-Option (Remain Stems)
-------------------------------------------------------------------
To remain all stem positions of identified rss within FASTA file(s):
Type <r> <return> <s> <enter> (via Menu)
Type <perl ALICUT_V2.3.pl -r -s> <enter> (via command line)
C-Option (Remove Codon)
-------------------------------------------------------------------
To translate ALISCORE identified RSS positions of amino-acid data
into nucleotide triplet positions before exclusion of randomised
sequence sections:
Type <c> return <s> return (via Menu) or
Type <perl ALICUT_V2.3.pl -c -s> <enter> (via command line)
Note:
This option is only useful if you have analysed amino-acid
data, but wish to exclude nucleotide positions from the amino-acid
data corresponding nucleotide data.
Be aware, that the name of the nucleotide data file has to be named
equal to the ALISCORE analysed amino-acid data file. The C-option
can not be applied on amino-acid sequences. Otherwise, ALICUT
excludes the original ALISCORE identified sequence sections.
3-Option (Remove 3rd position)
-------------------------------------------------------------------
To remove ALISCORE identified RSS only if its sequence position is
up to amultiple of 3:
Type <3> <return> <s> <return> (via Menu)
Type <perl ALICUT_V2.3.pl -3 -s> <enter> (via command line)
Note:
The 3-Option can be combined with the C-option. In this case,
positions of the ALISCORE "List" outfile(s) are translated into
codon positions from which only the 3rd positions are excluded.
The 3-Option can only be applied on nucleotide data. Otherwise,
ALICUT excludes the original ALISCORE identified sequence sections.
ALICUT IN and OUT files
-------------------------------------------------------------------
ALICUT V2.3 needs the original ALISCORE FASTA infile(s) and "List"
outfile(s) in the same folder as ALICUT V2.3.
The "List" outfile(s) must contain the identified RSS positions
in one single line, separated by whitespace.
e.g. 1 3 5 6 8 9 10 11 123 127 10000 10001
ALICUT V2.0 can handle unlimited FASTA files in one single run.
The sole condition is that the Prefix of the ALISCORE "List"
outfile(s) are identic with the associated FASTA infile(s).
ALICUT V2.3 first searches for the ALISCORE "List" outfile(s),
removes the Suffix "_List_random.txt" and searches for the
"List" associated FASTA file(s).
e.g. COI.fas_List_random.txt (ALISCORE "List" outfile)
COI.fas (Associated FASTA infile)
If both files are detected, ALICUT V2.3 excludes the RSS identified
positions of the "List" file(s) in the associated
FASTA file(s) and saves the changes in a new FASTA outfile,
named "ALICUT_FASTAinputname.fas".
Under the C- and 3-Option, removed sequence positions differ from
the original "List" position numbers. Under both options, ALICUT
prints the actually removed positions in separate "ALICUT_LIST"
outfile(s).
ALICUT V2.3 generates also an info file "ALICUT_info". This file
informs about the number and percentage of removed positions, number
of single sequences, single parameter settings, and sequence states
of each restricted FASTA file.
If structure sequences are identified by ALICUT, ALICUT generates
structure info file(s) which lists remaining stem pairs and loop
positions, as well as percentages of both structure elements.
-------------------------------------------------------------------
-------------------------------------------------------------------
info
;
print "\tBACK to ALICUT MAIN-Menu:\t\t type <return>\n" ;
print "\n\t------------------------------------------------------------\n\t" ;
chomp ( my $answer_xy = <STDIN> );
&menu ;
}
sub preface{
print
<<preface
--------------------FASconCAT PREFACE---------------------
Version : 2.31
Language : PERL
Last Update : 22nd February, 2017
Author : Patrick Kueck, ZFMK Bonn GERMANY
e-mail : patrick_kueck\@web.de
Homepage : http://www.zfmk.de
This program is free software; you can whitedistribute it
and/or modify it under the terms of the GNU General Public
License as published by the Free Software Foundation ;
either version 2 of the License, or (at your option) any
later version.
This program is distributed in the hope that it will be
useful, but WITHOUT ANY WARRANTY; without even the
implied warranty of MERCHANTABILITY or FITNESS FOR A
PARTICULAR PURPOSE. See the GNU General Public License for
more details.
You should have received a copy of the GNU General Public
License along with this program; if not, write to the Free
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139,
USA.
For further free downloadable programs visit:
www.zfmk.de/web/Forschung/Abteilungen/AG_Wgele/index.en.html
------------------------------------------------------------
preface
;
print "\tBACK to ALICUT MAIN-Menu:\t\t type <return>\n" ;
print "\n\t------------------------------------------------------------\n\t" ;
chomp ( my $answer_xy = <STDIN> );
&menu;
}
sub menu{
my $aref_remain_stems = $_[0] ;
my $aref_remove_codon = $_[1] ;
my $aref_third_posit = $_[2] ;
&header ;
print "\n\tSTART ALICUT:\t\ttype <s> <return>" ;
print "\n\tQUIT ALICUT:\t\ttype <q> <return>" ;
print "\n\tREMAIN STEMS:\t\ttype <r> <return>" ;
print "\n\tREMOVE CODON:\t\ttype <c> <return>" ;
print "\n\tREMOVE 3rd:\t\ttype <3> <return>" ;
print "\n\tHELP:\t\t\ttype <h> <return>" ;
print "\n\tPREFACE:\t\ttype <p> <return>" ;
&commands ( \$aref_remain_stems->[0], \$aref_remove_codon->[0], \$aref_third_posit->[0] );
my $answer_opening = &commandline ;
until ( $answer_opening =~ /^s$|^r$|^c$|^p$|^h$|^1$|^2$|^q$|^3$/i ){
print "\n\t!COMMAND-ERROR!: unknown command \"$answer_opening\"!\n" ;
$answer_opening = &commandline ;
}
$answer_opening =~ /^s$/i and do { &start ( \$aref_remain_stems->[0], \$aref_remove_codon->[0], \$aref_third_posit->[0] ) } ;
$answer_opening =~ /^r$/i and do { @$aref_remain_stems = (reverse @$aref_remain_stems ); &menu } ;
$answer_opening =~ /^c$/i and do { @$aref_remove_codon = (reverse @$aref_remove_codon ); &menu } ;
$answer_opening =~ /^3$/i and do { @$aref_third_posit = (reverse @$aref_third_posit ); &menu } ;
$answer_opening =~ /^q$/i and do { exit } ;
$answer_opening =~ /^h$/i and do { &help } ;
$answer_opening =~ /^1$/ and do { &error1 } ;
$answer_opening =~ /^2$/ and do { &error2 } ;
$answer_opening =~ /^p$/i and do { &preface }
}
sub start{
my $sref_stems_remain = $_[0] ;
my $sref_codon_remove = $_[1] ;
my $sref_third_remove = $_[2] ;
my $j = 0 ;
open OUTinfo, ">>ALICUT_info.xls" ;
print OUTinfo "\nUsed List File\tUsed Fasta file\tremove triplets\tremove 3rd position\tnumber taxa\tbp before\tbp after\tremaining bp [%]\tsequence type\n" ;
# Read IN of all List_random.txt files within the same folder as ALICUT and handle it
READING:
foreach my $file ( <*List_*.txt> ) {
# Set counter +1
$j++;
# Read in of the ALISCORE-list outfile
&tie_linefeeds ( \$file ) ;
( open IN, "<$file" ) or die "n\t!FILE-ERROR!: Can not open listfile $file!\n" ;
my $line = <IN> ; chomp $line ;
# check for correct aliscore list format
unless ( $line =~ /^(\d+ )+\d+$|^\d+$/ ) { warn "\t!FILE-WARN!: $file has no ALISCORE list format!\n" ; next READING }
# Total number of randomized identified positions
my @cut_positions = split " ", $line ; close IN ;
# "filename.fas_List_random.txt" to "filename.fas"
( my $file_fasta = $file ) =~ s/_List_.+// ;
# Read in of the original ALISCORE fasta infile which belongs to the listfile
&tie_linefeeds ( \$file_fasta ) ;
( open INfas, "<$file_fasta" ) or warn "\t!FILE-WARN!: Can not find $file_fasta!\n" and next READING ;
chomp ( my @inputfile = <INfas> ) ; close INfas ;
warn "\t!FILE-WARN!: File $file_fasta is empty!\n" if 0 == @inputfile and next READING ;
# Handle the FASTA file in the way that sequencename and sequence alternate in each line
@inputfile = fas_bearbeiten ( @inputfile ) ;
# Generate a hash: key=>taxon, value => sequenz
my %sequence = @inputfile ;
my @values = values %sequence ;
# Determine basepositions before und after cut. Output of cuttings as total number and in percent
my $number_sequences = keys %sequence ;
my $number_characters_before = length $values[0] ;
# Check for correct FASTA format and handling of structure sequence
my $sequence_state = 'nt' ;
SEQUENCE_CHECK:
for my $raw_taxon ( keys %sequence ){
# if whitespace are between ">" and the next sign within a sequence name, delete these whitespaces
$raw_taxon =~ s/^\>\s*/\>/g ;
# if whitespaces between last sign and newline in sequence name, delete these whitespaces
$raw_taxon =~ s/\s*$//g ;
die "\n\t!FILE-ERROR!: $raw_taxon in $file_fasta is not in FASTA format!\n" if $raw_taxon !~ /^\>/ ;
die "\n\t!FILE-ERROR!: Sequence name missing in $file_fasta!\n" if $raw_taxon =~ /^\>$/ ;
die "\n\t!FILE-ERROR!: Sequence name $raw_taxon in $file_fasta involves forbidden signs!\n" if $raw_taxon !~ /\w/ ;
die "\n\t!FILE-ERROR!: Sequences of $file_fasta have no equal length!\n" if length $sequence{$raw_taxon} != $number_characters_before ;
die "\n\t!FILE-ERROR!: Sequence missing in $file_fasta!\n" if $sequence{$raw_taxon} =~ /^\n$|^$/ ;
die "\n\t!FILE-ERROR!: Sequence length in $file_fasta is too short to cut all positions!\n" if $number_characters_before < $cut_positions[ $#cut_positions ] ;
# Structure handling
if ( $sequence{$raw_taxon} =~ /.*\(.*\).*/ ){
$sequence{$raw_taxon} =~ s/-/./g ;
my @strc_elements = split "" , $sequence{$raw_taxon} ;
for my $str_sign ( @strc_elements ){
unless ( $str_sign =~ /\(|\)|\./ ){ die "\n\t!FILE-ERROR!: Structure string of $file_fasta involves forbidden signs in $raw_taxon!\n" }
}
my $structurestring = $sequence{$raw_taxon} ;
$structurestring =~ s/-/./g ;
$sequence{$raw_taxon} = &structure_handling ( \$structurestring, \$$sref_stems_remain, \@cut_positions, \$file_fasta ); next SEQUENCE_CHECK ;
}
# Check for correct sequence states
$sequence{$raw_taxon} =~ s/(\w+)/\U$1/ig ;
my @seq_elements = split "" , $sequence{$raw_taxon} ;
for my $seq_sign ( @seq_elements ){
unless ( $seq_sign =~ /A|C|G|T|U|-|N|Y|X|R|W|S|K|M|D|V|H|B|Q|E|I|L|F|P|\?/ ){ die "\n\t!FILE-ERROR!: Sequence of $file_fasta involves forbidden signs in $raw_taxon!\n" }
}
if ( $sequence{$raw_taxon} =~ /I|E|L|Q|F|P/ ) { $sequence_state = 'aa' }
}
# Translate cut positions
my @fasta_cut;
&translate_cut_positions( \$$sref_codon_remove, \$$sref_third_remove, \@cut_positions, \$number_characters_before, \@fasta_cut, \$sequence_state, \$file_fasta );
# Calculate percent of remaining positions
my $number_cut_positions = @cut_positions ;
my $number_characters_after = $number_characters_before-$number_cut_positions ;
my $percent_left = sprintf "%.1f", ( $number_characters_after / $number_characters_before ) * 100 ;
$percent_left =~ s/\./,/g ;
# Assume uncut positions to $final and print out to ALICUT_$file_fasta
if ( $$sref_codon_remove =~ /yes/ && $$sref_third_remove =~ /yes/ ){ open OUT, ">ALICUT_codon_3rd_$file_fasta" }
elsif ( $$sref_codon_remove =~ /yes/ && $$sref_third_remove =~ /no/ ){ open OUT, ">ALICUT_codon_$file_fasta" }
elsif ( $$sref_codon_remove =~ /no/ && $$sref_third_remove =~ /yes/ ){ open OUT, ">ALICUT_3rd_$file_fasta" }
else { open OUT, ">ALICUT_$file_fasta" }
for ( keys %sequence ){
my @bases = split "", $sequence{$_} ;
my @final = map { $bases[$_] } @fasta_cut ;
my $final = $_."\n".( join "", @final )."\n" ;
print OUT "$final" ;
}
close OUT;
# Print Out of extra infos to ALICUT_info
print OUTinfo "$file\t$file_fasta\t$$sref_codon_remove\t$$sref_third_remove\t$number_sequences\t$number_characters_before\t$number_characters_after\t$percent_left\t$sequence_state\n" ;
print "\tDone : $file cut to ALICUT_$file_fasta\n"
}
close OUTinfo ;
# Print OUT number of right handled FASTA files in relation to total number of files
printf "\n%68s\n", "------------------------------------------------------------" ;
printf "%42s\n", "$j FASTA file(s) correctly handled!" ;
printf "%57s\n", "Further infos are printed out in Alicut_info.txt!" ;
printf "\n%63s\n", "ALICUT V2.0 Finished! Thank you and good bye!" ;
printf "%68s\n", "------------------------------------------------------------" ;
&set_timer ;
exit ;
sub tie_linefeeds{
my $sref_filename = $_[0] ;
( open IN , "<$$sref_filename" ) or warn "\tError: can not open $$sref_filename!\n" and next READING ;
(tie ( my @data, 'Tie::File', $$sref_filename )) ;
warn "\t!FILE-WARN!: $$sref_filename is empty!\n" and next READING if 0 == @data ;
map { s/\r\n/\n/g } @data ;
map { s/\r/\n/g } @data ;
untie @data ; close IN ;
}
sub set_timer{
my ( $user, $system, $cuser, $csystem ) = times ;
print <<TIME;
*** time used: $user sec ***
TIME
}
sub translate_cut_positions {
my $sref_command_codon_remove = $_[0] ;
my $sref_command_third_remove = $_[1] ;
my $aref_cut_positions = $_[2] ;
my $sref_number_characters = $_[3] ;
my $aref_remaining_positions = $_[4] ;
my $sref_sequence_state = $_[5] ;
my $sref_filename = $_[6] ;
# Translate identified RSS aminoacid positions to nucleotide triplet positions
if ( $$sref_command_codon_remove =~ /yes/ && $$sref_command_third_remove =~ /no/){
unless ( $$sref_sequence_state =~ /aa/ ){
my @fasta_old = @$aref_cut_positions ; @$aref_cut_positions = ();
for my $number( @fasta_old ){
my $newno1 = ($number*3)-2;
my $newno2 = $newno1+1;
my $newno3 = $newno2+1;
push @$aref_cut_positions, ( $newno1, $newno2, $newno3 )
}
my $string_cutnumbers = join " ", @$aref_cut_positions ;
open OUTnewcut, ">ALICUT_cut_positions_codon.txt" or die "\n\t!FILE-ERROR!: Can not open File ALICUT_cut_positions_codon.txt" ;
print OUTnewcut $string_cutnumbers ; close OUTnewcut ;
}
else { warn "\n\t!FILE-WARN!: $$sref_filename include aa sequences!\n\tCodon positions not translated!" }
}
# Translate identified RSS aminoacid positions to nucleotide triplet positions, but remove only third position
elsif ( $$sref_command_codon_remove =~ /yes/ && $$sref_command_third_remove =~ /yes/){
unless ( $$sref_sequence_state =~ /aa/ ){
my @fasta_old = @$aref_cut_positions ; @$aref_cut_positions = ();
for my $number( @fasta_old ){
push @$aref_cut_positions, ($number*3)
}
my $string_cutnumbers = join " ", @$aref_cut_positions ;
open OUTnewcut, ">ALICUT_cut_positions_codon_3rd.txt" or die "\n\t!FILE-ERROR!: Can not open File ALICUT_cut_positions_codon_3rd.txt" ;
print OUTnewcut $string_cutnumbers ; close OUTnewcut ;
}
else { warn "\n\t!FILE-WARN!: $$sref_filename include aa sequences!\n\tCodon positions not translated!\n\t3rd codon position not removed!" }
}
# Remove only identified RSS if third position of original sequence
elsif ( $$sref_command_codon_remove =~ /no/ && $$sref_command_third_remove =~ /yes/){
unless ( $$sref_sequence_state =~ /aa/ ){
my @fasta_old = @$aref_cut_positions ; @$aref_cut_positions = ();
for my $number( @fasta_old ){
if ( $number % 3 == 0 ){ push @$aref_cut_positions, $number }
}
my $string_cutnumbers = join " ", @$aref_cut_positions ;
open OUTnewcut, ">ALICUT_cut_positions_3rd.txt" or die "\n\t!FILE-ERROR!: Can not open File ALICUT_cut_positions_3rd.txt" ;
print OUTnewcut $string_cutnumbers ; close OUTnewcut
}
else { warn "\n\t!FILE-WARN!: $$sref_filename include aa sequences!\n\tNot only 3rd codon position removed!" }
}
# Examine remaining positions
my ( %seen, @zahlenreihe ) ;
for ( 1 .. $$sref_number_characters ) { push @zahlenreihe, $_-1 }
for my $value ( @$aref_cut_positions ){ $seen{$value-1}++ }
for ( @zahlenreihe ){ unless ( $seen{$_} ){ push @$aref_remaining_positions, $_ } }
}
}
sub fas_bearbeiten{
my @infile = @_ ;
grep s/(\>.*)/$1\t/, @infile ;
grep s/ //g, @infile ;
grep s/\n//g, @infile ;
grep s/\t/\n/g, @infile ;
grep s/\>/\n\>/g, @infile ;
my $string = join "", @infile ;
@infile = split "\n", $string ;
shift @infile ;
return @infile ;
}
sub structure_handling{
my $sref_string = $_[0] ;
my $sref_answer_remain = $_[1] ;
my $aref_cut_positions = $_[2] ;
my $sref_filename = $_[3] ;
my (
@pair_infos ,
@forward ,
@structurestring ,
@loops ,
@pairs ,
%structure_of_position ,
%seen_struc
);
# Stem assignment
my @structures = split "", $$sref_string ;
my $i = 0 ;
CHECKING:
for ( @structures ){ $i++ ;
SWITCH:
$structure_of_position{$i} = $_ ;
if ( $_ =~ /\(/ ){ push @forward, $i and next CHECKING }
if ( $_ =~ /\)/ ){ my $pair_1 = pop @forward; push @pairs, ( $pair_1, $i ); push @pair_infos, ( $pair_1.":".$i ); next CHECKING }
if ( $_ =~ /\./ ){ push @loops, $i and next CHECKING }
}
@pair_infos = reverse @pair_infos ;
# Generate listfiles for structure_info file
my $pairlist = join "\n\t\t\t\t\t", @pair_infos ;
my $looplist = join "\n\t\t\t\t\t", @loops ;
# Number and proportion of stem and loop positions for structure info file
my $N_total = @structures ;
my $N_stems = @pair_infos ;
my $N_loops = $N_total - ( $N_stems * 2 ) ;
my $P_loops = ( $N_loops / $N_total ) * 100 ;
my $P_stems = 100 - $P_loops ;
# Open structure info outfile
open OUTstruc, ">ALICUT_Struc_info_${$sref_filename}.txt" ;
# Print out
print OUTstruc "\nOriginal structure information identified in $$sref_filename:\n\n" ;
print OUTstruc "- Number of characters:\t\t\t$N_total\n" ;
print OUTstruc "- Number of single loop characters:\t$N_loops [$P_stems %]\n" ;
print OUTstruc "- Number of paired stem characters:\t$N_stems [$P_loops %]\n" ;
print OUTstruc "\n- Paired stem positions:\t\t$pairlist\n\n" ;
print OUTstruc "\n- Loop positions:\t\t\t$looplist\n" ;
close OUTstruc;
if ( $$sref_answer_remain =~ /yes/i ){
my @cut_positions2 = ();
# Remain rss identified stem positions within the MSA
for ( @pairs ){ $seen_struc{$_} = 1 }
for ( @$aref_cut_positions ){ unless ( $seen_struc{$_} ){ push @cut_positions2, $_ } }
@$aref_cut_positions = @cut_positions2 ;
}
else{
my %pair = @pairs;
# Replace paired structure positions of rss identified positions by dots
for my $bp_for ( keys %pair ){
for my $rss ( @$aref_cut_positions ){
if ( $bp_for == $rss ){ $structure_of_position{$pair{$bp_for}} = "." ; last }
if ( $pair{$bp_for} == $rss ){ $structure_of_position{$bp_for} = "." ; last }
}
}
}
for ( my $k=1; $k<=@structures-1; $k++ ){ push @structurestring, $structure_of_position{$k} }
my $structure_string_neu = join "", @structurestring ;
return $structure_string_neu ;
}
sub commandline{
print "\n\tCOMMAND:\t " ;
chomp ( my $sub_answer_opening = <STDIN> );
print "\n\t------------------------------------------------------------\n" ;
return $sub_answer_opening;
}

1271
skills/phylo_from_buscos/scripts/predownloaded_aliscore_alicut/Aliscore.02.2.pl Executable file
View File

File diff suppressed because it is too large Load Diff

2081
skills/phylo_from_buscos/scripts/predownloaded_aliscore_alicut/Aliscore_module.pm Executable file
View File

File diff suppressed because it is too large Load Diff

174
skills/phylo_from_buscos/scripts/query_ncbi_assemblies.py Executable file
View File

@@ -0,0 +1,174 @@
#!/usr/bin/env python3
"""
Query NCBI for available genome assemblies by taxon name
Usage:
python query_ncbi_assemblies.py --taxon "Coleoptera"
python query_ncbi_assemblies.py --taxon "Drosophila" --max-results 50
python query_ncbi_assemblies.py --taxon "Apis" --refseq-only
Requires: ncbi-datasets-pylib (pip install ncbi-datasets-pylib)
Author: Bruno de Medeiros (Field Museum)
"""
import argparse
import sys
def query_assemblies_by_taxon(taxon, max_results=20, refseq_only=False):
"""
Query NCBI for genome assemblies of a given taxon
Args:
taxon: Taxon name (e.g., "Coleoptera", "Drosophila melanogaster")
max_results: Maximum number of results to return
refseq_only: If True, only return RefSeq assemblies (GCF_*)
Returns:
List of dictionaries with assembly information
"""
try:
from ncbi.datasets import GenomeApi
from ncbi.datasets.openapi import ApiClient, ApiException
except ImportError:
print("Error: ncbi-datasets-pylib not installed", file=sys.stderr)
print("Install with: pip install ncbi-datasets-pylib", file=sys.stderr)
sys.exit(1)
assemblies = []
print(f"Querying NCBI for '{taxon}' genome assemblies...")
print(f"(Limiting to {max_results} results)")
if refseq_only:
print("(RefSeq assemblies only)")
print("")
try:
with ApiClient() as api_client:
api = GenomeApi(api_client)
# Query genome assemblies for the taxon
genome_summary = api.genome_summary_by_taxon(
taxon=taxon,
limit=str(max_results),
filters_refseq_only=refseq_only
)
if not genome_summary.reports:
print(f"No assemblies found for taxon '{taxon}'")
return []
for report in genome_summary.reports:
assembly_info = {
'accession': report.accession,
'organism': report.organism.organism_name,
'assembly_level': report.assembly_info.assembly_level,
'assembly_name': report.assembly_info.assembly_name,
'submission_date': report.assembly_info.release_date if hasattr(report.assembly_info, 'release_date') else 'N/A'
}
assemblies.append(assembly_info)
except ApiException as e:
print(f"Error querying NCBI: {e}", file=sys.stderr)
sys.exit(1)
except Exception as e:
print(f"Unexpected error: {e}", file=sys.stderr)
sys.exit(1)
return assemblies
def format_table(assemblies):
"""
Format assemblies as a readable table
Args:
assemblies: List of assembly dictionaries
"""
if not assemblies:
return
print(f"Found {len(assemblies)} assemblies:\n")
# Print header
print(f"{'#':<4} {'Accession':<20} {'Organism':<40} {'Level':<15} {'Assembly Name':<30}")
print("-" * 110)
# Print data rows
for i, asm in enumerate(assemblies, 1):
organism = asm['organism'][:38] + '..' if len(asm['organism']) > 40 else asm['organism']
assembly_name = asm['assembly_name'][:28] + '..' if len(asm['assembly_name']) > 30 else asm['assembly_name']
print(f"{i:<4} {asm['accession']:<20} {organism:<40} {asm['assembly_level']:<15} {assembly_name:<30}")
print("")
def save_accessions(assemblies, output_file):
"""
Save assembly accessions to a file
Args:
assemblies: List of assembly dictionaries
output_file: Output file path
"""
with open(output_file, 'w') as f:
for asm in assemblies:
f.write(f"{asm['accession']}\n")
print(f"Accessions saved to: {output_file}")
print(f"You can download these assemblies using:")
print(f" python download_ncbi_genomes.py --assemblies $(cat {output_file})")
def main():
parser = argparse.ArgumentParser(
description="Query NCBI for available genome assemblies by taxon name",
epilog="Example: python query_ncbi_assemblies.py --taxon 'Coleoptera' --max-results 50"
)
parser.add_argument(
"--taxon",
required=True,
help="Taxon name (e.g., 'Coleoptera', 'Drosophila melanogaster')"
)
parser.add_argument(
"--max-results",
type=int,
default=20,
help="Maximum number of results to return (default: 20)"
)
parser.add_argument(
"--refseq-only",
action="store_true",
help="Only return RefSeq assemblies (GCF_* accessions)"
)
parser.add_argument(
"--save",
metavar="FILE",
help="Save accessions to a file for later download"
)
args = parser.parse_args()
# Query NCBI
assemblies = query_assemblies_by_taxon(
taxon=args.taxon,
max_results=args.max_results,
refseq_only=args.refseq_only
)
# Display results
format_table(assemblies)
# Save if requested
if args.save and assemblies:
save_accessions(assemblies, args.save)
if __name__ == "__main__":
main()

240
skills/phylo_from_buscos/scripts/rename_genomes.py Executable file
View File

@@ -0,0 +1,240 @@
#!/usr/bin/env python3
"""
Rename genome files with clean, meaningful sample names for phylogenomics
This script helps create a mapping between genome files (often with cryptic
accession numbers) and clean species/sample names that will appear in the
final phylogenetic tree.
Usage:
# Interactive mode - prompts for names
python rename_genomes.py --interactive genome1.fasta genome2.fasta
# From mapping file (TSV: old_name<TAB>new_name)
python rename_genomes.py --mapping samples.tsv
# Create template mapping file
python rename_genomes.py --create-template *.fasta > samples.tsv
Author: Bruno de Medeiros (Field Museum)
Based on tutorials by Paul Frandsen (BYU)
"""
import argparse
import os
import sys
import shutil
from pathlib import Path
def sanitize_name(name):
"""
Sanitize a name to be phylogenomics-safe
- Replace spaces with underscores
- Remove special characters
- Keep only alphanumeric, underscore, hyphen
"""
# Replace spaces with underscores
name = name.replace(' ', '_')
# Remove special characters except underscore and hyphen
name = ''.join(c for c in name if c.isalnum() or c in '_-')
return name
def create_template(genome_files, output=sys.stdout):
"""Create a template mapping file"""
output.write("# Sample mapping file\n")
output.write("# Format: original_filename<TAB>new_sample_name\n")
output.write("# Edit the second column with meaningful species/sample names\n")
output.write("# Recommended format: [ACCESSION]_[NAME] (e.g., GCA000123456_Penstemon_eatonii)\n")
output.write("# This keeps accession for traceability while having readable names in trees\n")
output.write("# Names should contain only letters, numbers, underscores, and hyphens\n")
output.write("#\n")
for gfile in genome_files:
basename = Path(gfile).stem # Remove extension
output.write(f"{gfile}\t{basename}\n")
def read_mapping(mapping_file):
"""Read mapping from TSV file"""
mapping = {}
with open(mapping_file, 'r') as f:
for line in f:
line = line.strip()
# Skip comments and empty lines
if not line or line.startswith('#'):
continue
parts = line.split('\t')
if len(parts) != 2:
print(f"Warning: Skipping invalid line: {line}", file=sys.stderr)
continue
old_name, new_name = parts
new_name = sanitize_name(new_name)
mapping[old_name] = new_name
return mapping
def interactive_rename(genome_files):
"""Interactively ask for new names"""
mapping = {}
print("Enter new sample names for each genome file.")
print("Press Enter to keep the current name.")
print("Names will be sanitized (spaces→underscores, special chars removed)\n")
for gfile in genome_files:
current_name = Path(gfile).stem
new_name = input(f"{gfile} → [{current_name}]: ").strip()
if not new_name:
new_name = current_name
new_name = sanitize_name(new_name)
mapping[gfile] = new_name
print(f" Will rename to: {new_name}.fasta\n")
return mapping
def rename_files(mapping, dry_run=False, backup=True):
"""Rename genome files according to mapping"""
renamed = []
errors = []
for old_file, new_name in mapping.items():
if not os.path.exists(old_file):
errors.append(f"File not found: {old_file}")
continue
# Get extension from original file
ext = Path(old_file).suffix
if not ext:
ext = '.fasta'
new_file = f"{new_name}{ext}"
# Check if target exists
if os.path.exists(new_file) and new_file != old_file:
errors.append(f"Target exists: {new_file}")
continue
# Skip if names are the same
if old_file == new_file:
print(f"Skip (no change): {old_file}")
continue
if dry_run:
print(f"[DRY RUN] Would rename: {old_file} → {new_file}")
else:
# Backup if requested
if backup:
backup_file = f"{old_file}.backup"
shutil.copy2(old_file, backup_file)
print(f"Backup created: {backup_file}")
# Rename
shutil.move(old_file, new_file)
print(f"Renamed: {old_file} → {new_file}")
renamed.append((old_file, new_file))
return renamed, errors
def main():
parser = argparse.ArgumentParser(
description="Rename genome files with meaningful sample names for phylogenomics",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
# Create template mapping file
python rename_genomes.py --create-template *.fasta > samples.tsv
# Edit samples.tsv, then apply mapping
python rename_genomes.py --mapping samples.tsv
# Interactive renaming
python rename_genomes.py --interactive genome1.fasta genome2.fasta
# Dry run (preview changes)
python rename_genomes.py --mapping samples.tsv --dry-run
"""
)
group = parser.add_mutually_exclusive_group(required=True)
group.add_argument(
'--create-template',
nargs='+',
metavar='GENOME',
help='Create a template mapping file from genome files'
)
group.add_argument(
'--mapping',
metavar='FILE',
help='TSV file with mapping (old_name<TAB>new_name)'
)
group.add_argument(
'--interactive',
nargs='+',
metavar='GENOME',
help='Interactively rename genome files'
)
parser.add_argument(
'--dry-run',
action='store_true',
help='Show what would be renamed without actually renaming'
)
parser.add_argument(
'--no-backup',
action='store_true',
help='Do not create backup files'
)
args = parser.parse_args()
# Create template
if args.create_template:
create_template(args.create_template)
return
# Interactive mode
if args.interactive:
mapping = interactive_rename(args.interactive)
# Mapping file mode
elif args.mapping:
mapping = read_mapping(args.mapping)
else:
parser.error("No mode specified")
if not mapping:
print("No files to rename", file=sys.stderr)
return
# Perform renaming
renamed, errors = rename_files(
mapping,
dry_run=args.dry_run,
backup=not args.no_backup
)
# Summary
print("\n" + "="*60)
if args.dry_run:
print("DRY RUN - No files were actually renamed")
else:
print(f"Successfully renamed {len(renamed)} file(s)")
if errors:
print(f"\nErrors ({len(errors)}):")
for error in errors:
print(f" - {error}")
sys.exit(1)
if __name__ == "__main__":
main()

247
skills/phylo_from_buscos/scripts/run_alicut.sh Executable file
View File

@@ -0,0 +1,247 @@
#!/bin/bash
# run_alicut.sh
# Wrapper script for running ALICUT to remove Aliscore-identified RSS positions
# Removes randomly similar sequence sections from alignments
#
# Usage:
# bash run_alicut.sh [aliscore_dir] [options]
#
# Options:
# -r Remain stem positions (for RNA secondary structures)
# -c Remove codon (translate AA positions to nucleotide triplets)
# -3 Remove only 3rd codon positions
# -s Silent mode (non-interactive, use defaults)
#
# Requirements:
# - ALICUT_V2.31.pl in PATH or same directory
# - Perl with File::Copy, Tie::File, Term::Cap modules
# - Aliscore output directory with *_List_*.txt and original .fas file
set -euo pipefail
# Script directory
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# Check for ALICUT script
if command -v ALICUT_V2.31.pl &> /dev/null; then
ALICUT_SCRIPT="ALICUT_V2.31.pl"
elif [ -f "${SCRIPT_DIR}/ALICUT_V2.31.pl" ]; then
ALICUT_SCRIPT="${SCRIPT_DIR}/ALICUT_V2.31.pl"
elif [ -f "./ALICUT_V2.31.pl" ]; then
ALICUT_SCRIPT="./ALICUT_V2.31.pl"
else
echo "ERROR: ALICUT_V2.31.pl not found in PATH, script directory, or current directory"
echo "Please download from: https://www.zfmk.de/en/research/research-centres-and-groups/alicut"
exit 1
fi
# Function to display usage
usage() {
cat <<EOF
Usage: $0 [aliscore_dir] [options]
Run ALICUT to remove Aliscore-identified randomly similar sequence sections.
Arguments:
aliscore_dir Directory containing Aliscore output files
Options:
-r Remain stem positions in RNA secondary structure alignments
-c Remove entire codon (translates AA RSS positions to nt triplets)
-3 Remove only 3rd codon position of identified RSS
-s Silent/scripted mode (non-interactive, use defaults)
-h Display this help message
Input Requirements:
The aliscore_dir must contain:
- Original FASTA alignment file (*.fas)
- Aliscore List file (*_List_random.txt or *_List_*.txt)
Examples:
# Basic usage (interactive mode)
bash run_alicut.sh aliscore_alignment1
# Silent mode with defaults
bash run_alicut.sh aliscore_alignment1 -s
# Remain RNA stem positions
bash run_alicut.sh aliscore_16S -r -s
# Remove entire codons (for back-translation)
bash run_alicut.sh aliscore_protein1 -c -s
# Process all Aliscore output directories
for dir in aliscore_*/; do
bash run_alicut.sh "\${dir}" -s
done
Output Files (in aliscore_dir):
- ALICUT_[alignment].fas : Trimmed alignment
- ALICUT_info.xls : Statistics (taxa, positions removed, etc.)
- ALICUT_Struc_info_*.txt : Structure information (if RNA detected)
Citation:
Kück P, Meusemann K, Dambach J, Thormann B, von Reumont BM, Wägele JW,
Misof B (2010) Parametric and non-parametric masking of randomness in
sequence alignments can be improved and leads to better resolved trees.
Front Zool 7:10. doi: 10.1186/1742-9994-7-10
EOF
exit 0
}
# Parse command line arguments
ALISCORE_DIR=""
ALICUT_OPTS=""
SILENT_MODE=false
if [ $# -eq 0 ]; then
usage
fi
ALISCORE_DIR="$1"
shift
# Validate directory exists
if [ ! -d "${ALISCORE_DIR}" ]; then
echo "ERROR: Aliscore directory not found: ${ALISCORE_DIR}"
exit 1
fi
# Parse ALICUT options
while [ $# -gt 0 ]; do
case "$1" in
-h|--help)
usage
;;
-r)
ALICUT_OPTS="${ALICUT_OPTS} -r"
shift
;;
-c)
ALICUT_OPTS="${ALICUT_OPTS} -c"
shift
;;
-3)
ALICUT_OPTS="${ALICUT_OPTS} -3"
shift
;;
-s|--silent)
SILENT_MODE=true
ALICUT_OPTS="${ALICUT_OPTS} -s"
shift
;;
*)
echo "ERROR: Unknown option: $1"
usage
;;
esac
done
# Change to Aliscore output directory
cd "${ALISCORE_DIR}"
echo "Processing Aliscore output in: ${ALISCORE_DIR}"
# Find List file
LIST_FILE=$(ls *_List_*.txt 2>/dev/null | head -n 1)
if [ -z "${LIST_FILE}" ]; then
echo "ERROR: No Aliscore List file found (*_List_*.txt)"
echo "Make sure Aliscore completed successfully"
exit 1
fi
echo "Found List file: ${LIST_FILE}"
# Find original FASTA file
FASTA_FILE=$(find . -maxdepth 1 \( -name "*.fas" -o -name "*.fasta" \) -type f | head -n 1 | sed 's|^\./||')
if [ -z "${FASTA_FILE}" ]; then
echo "ERROR: No FASTA alignment file found (*.fas or *.fasta)"
echo "ALICUT requires the original alignment file in the same directory as List file"
exit 1
fi
echo "Found FASTA file: ${FASTA_FILE}"
# Check if List file contains RSS positions
RSS_COUNT=$(wc -w < "${LIST_FILE}" || echo "0")
if [ "${RSS_COUNT}" -eq 0 ]; then
echo "WARNING: List file is empty (no RSS positions identified)"
echo "Aliscore found no randomly similar sequences to remove"
echo "Skipping ALICUT - alignment is already clean"
# Create a symbolic link to indicate no trimming was needed
ln -sf "${FASTA_FILE}" "ALICUT_${FASTA_FILE}"
echo "Created symbolic link: ALICUT_${FASTA_FILE} -> ${FASTA_FILE}"
cd ..
exit 0
fi
echo "Found ${RSS_COUNT} RSS positions to remove"
# Run ALICUT
echo ""
echo "Running ALICUT..."
echo "Options: ${ALICUT_OPTS}"
# Construct ALICUT command
ALICUT_CMD="perl ${ALICUT_SCRIPT} ${ALICUT_OPTS}"
if [ "${SILENT_MODE}" = true ]; then
echo "Command: ${ALICUT_CMD}"
eval ${ALICUT_CMD}
else
echo "Running ALICUT in interactive mode..."
echo "Press 's' and Enter to start with current options"
echo ""
perl "${ALICUT_SCRIPT}" ${ALICUT_OPTS}
fi
# Check if ALICUT completed successfully
if [ $? -eq 0 ]; then
echo ""
echo "ALICUT completed successfully"
# Find output file
OUTPUT_FILE=$(ls ALICUT_*.fas ALICUT_*.fasta 2>/dev/null | head -n 1)
if [ -n "${OUTPUT_FILE}" ]; then
echo ""
echo "Output files:"
ls -lh ALICUT_* 2>/dev/null
# Calculate and report trimming statistics (handle multi-line FASTA format)
if [ -f "${OUTPUT_FILE}" ]; then
ORIGINAL_LENGTH=$(awk '/^>/ {if (seq) {print seq; seq=""}; next} {seq = seq $0} END {if (seq) print seq}' "${FASTA_FILE}" | head -n 1 | wc -c)
TRIMMED_LENGTH=$(awk '/^>/ {if (seq) {print seq; seq=""}; next} {seq = seq $0} END {if (seq) print seq}' "${OUTPUT_FILE}" | head -n 1 | wc -c)
REMOVED_LENGTH=$((ORIGINAL_LENGTH - TRIMMED_LENGTH))
PERCENT_REMOVED=$(awk "BEGIN {printf \"%.1f\", (${REMOVED_LENGTH}/${ORIGINAL_LENGTH})*100}")
echo ""
echo "Trimming statistics:"
echo " Original length: ${ORIGINAL_LENGTH} bp"
echo " Trimmed length: ${TRIMMED_LENGTH} bp"
echo " Removed: ${REMOVED_LENGTH} bp (${PERCENT_REMOVED}%)"
fi
# Check for info file
if [ -f "ALICUT_info.xls" ]; then
echo ""
echo "Detailed statistics in: ALICUT_info.xls"
fi
else
echo "WARNING: Expected output file ALICUT_*.fas not found"
fi
else
echo "ERROR: ALICUT failed"
cd ..
exit 1
fi
# Return to parent directory
cd ..
echo ""
echo "Done: ${ALISCORE_DIR}"

248
skills/phylo_from_buscos/scripts/run_aliscore.sh Executable file
View File

@@ -0,0 +1,248 @@
#!/bin/bash
# run_aliscore.sh
# Wrapper script for running Aliscore on aligned sequences
# Identifies randomly similar sequence sections (RSS) in multiple sequence alignments
#
# Usage:
# bash run_aliscore.sh [alignment.fas] [options]
#
# Options:
# -w INT Window size (default: 4)
# -r INT Number of random pairs to compare (default: 4*N taxa)
# -N Treat gaps as ambiguous characters (recommended for amino acids)
# -t TREE Tree file in Newick format for guided comparisons
# -l LEVEL Node level for tree-based comparisons
# -o TAXA Comma-separated list of outgroup taxa
#
# Array job usage:
# Set SLURM_ARRAY_TASK_ID or PBS_ARRAYID environment variable
# Create locus_list.txt with one alignment file per line
#
# Requirements:
# - Aliscore.02.2.pl in PATH or same directory
# - Perl with Tie::File and Fcntl modules
set -euo pipefail
# Script directory
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# Check for Aliscore script
if command -v Aliscore.02.2.pl &> /dev/null; then
ALISCORE_SCRIPT="Aliscore.02.2.pl"
elif [ -f "${SCRIPT_DIR}/Aliscore.02.2.pl" ]; then
ALISCORE_SCRIPT="${SCRIPT_DIR}/Aliscore.02.2.pl"
elif [ -f "./Aliscore.02.2.pl" ]; then
ALISCORE_SCRIPT="./Aliscore.02.2.pl"
else
echo "ERROR: Aliscore.02.2.pl not found in PATH, script directory, or current directory"
echo "Please download from: https://www.zfmk.de/en/research/research-centres-and-groups/aliscore"
exit 1
fi
# Function to display usage
usage() {
cat <<EOF
Usage: $0 [alignment.fas] [options]
Run Aliscore to identify randomly similar sequence sections in alignments.
Options:
-d DIR Base output directory for all Aliscore results (default: aliscore_output)
-w INT Window size for sliding window analysis (default: 4)
-r INT Number of random sequence pairs to compare (default: 4*N taxa)
-N Treat gaps as ambiguous characters (recommended for amino acids)
-t FILE Tree file in Newick format for phylogeny-guided comparisons
-l LEVEL Node level limit for tree-based comparisons (default: all)
-o TAXA Comma-separated list of outgroup taxa for focused comparisons
-h Display this help message
Array Job Mode:
If SLURM_ARRAY_TASK_ID or PBS_ARRAYID is set, reads alignment from locus_list.txt
Create locus_list.txt with: ls *.fas > locus_list.txt
Examples:
# Basic run with defaults (outputs to aliscore_output/)
bash run_aliscore.sh alignment.fas
# Amino acid sequences with gaps as ambiguous
bash run_aliscore.sh protein_alignment.fas -N
# Custom output directory
bash run_aliscore.sh alignment.fas -d my_aliscore_results
# Custom window size and random pairs
bash run_aliscore.sh alignment.fas -w 6 -r 100
# Tree-guided analysis
bash run_aliscore.sh alignment.fas -t species.tre
# Array job on SLURM
ls aligned_aa/*.fas > locus_list.txt
sbatch --array=1-\$(wc -l < locus_list.txt) run_aliscore_array.job
Output Files (in aliscore_output/aliscore_[alignment]/):
- [alignment]_List_random.txt : Positions identified as RSS (for ALICUT)
- [alignment]_Profile_random.txt: Quality profile for each position
- [alignment].svg : Visual plot of scoring profiles
Citation:
Misof B, Misof K (2009) A Monte Carlo approach successfully identifies
randomness in multiple sequence alignments: a more objective means of data
exclusion. Syst Biol 58(1):21-34. doi: 10.1093/sysbio/syp006
EOF
exit 0
}
# Parse command line arguments
ALIGNMENT=""
ALISCORE_OPTS=""
BASE_OUTPUT_DIR="aliscore_output"
if [ $# -eq 0 ]; then
usage
fi
# Check for array job mode
ARRAY_MODE=false
ARRAY_ID=""
if [ -n "${SLURM_ARRAY_TASK_ID:-}" ]; then
ARRAY_MODE=true
ARRAY_ID="${SLURM_ARRAY_TASK_ID}"
elif [ -n "${PBS_ARRAYID:-}" ]; then
ARRAY_MODE=true
ARRAY_ID="${PBS_ARRAYID}"
fi
# If in array mode, get alignment from locus list
if [ "${ARRAY_MODE}" = true ]; then
if [ ! -f "locus_list.txt" ]; then
echo "ERROR: Array job mode requires locus_list.txt"
echo "Create with: ls *.fas > locus_list.txt"
exit 1
fi
ALIGNMENT=$(sed -n "${ARRAY_ID}p" locus_list.txt)
if [ -z "${ALIGNMENT}" ]; then
echo "ERROR: Could not read alignment for array index ${ARRAY_ID}"
exit 1
fi
echo "Array job ${ARRAY_ID}: Processing ${ALIGNMENT}"
# Remaining arguments are Aliscore options
shift $# # Clear positional parameters
set -- "$@" # Reset with remaining args
else
# First argument is alignment file
ALIGNMENT="$1"
shift
fi
# Validate alignment file exists
if [ ! -f "${ALIGNMENT}" ]; then
echo "ERROR: Alignment file not found: ${ALIGNMENT}"
exit 1
fi
# Parse Aliscore options
while [ $# -gt 0 ]; do
case "$1" in
-h|--help)
usage
;;
-d|--output-dir)
BASE_OUTPUT_DIR="$2"
shift 2
;;
-w)
ALISCORE_OPTS="${ALISCORE_OPTS} -w $2"
shift 2
;;
-r)
ALISCORE_OPTS="${ALISCORE_OPTS} -r $2"
shift 2
;;
-N)
ALISCORE_OPTS="${ALISCORE_OPTS} -N"
shift
;;
-t)
if [ ! -f "$2" ]; then
echo "ERROR: Tree file not found: $2"
exit 1
fi
ALISCORE_OPTS="${ALISCORE_OPTS} -t $2"
shift 2
;;
-l)
ALISCORE_OPTS="${ALISCORE_OPTS} -l $2"
shift 2
;;
-o)
ALISCORE_OPTS="${ALISCORE_OPTS} -o $2"
shift 2
;;
*)
echo "ERROR: Unknown option: $1"
usage
;;
esac
done
# Get alignment name without extension
ALIGNMENT_NAME=$(basename "${ALIGNMENT}" .fas)
ALIGNMENT_NAME=$(basename "${ALIGNMENT_NAME}" .fasta)
# Create base output directory and specific directory for this alignment
mkdir -p "${BASE_OUTPUT_DIR}"
OUTPUT_DIR="${BASE_OUTPUT_DIR}/aliscore_${ALIGNMENT_NAME}"
mkdir -p "${OUTPUT_DIR}"
# Copy alignment to output directory
cp "${ALIGNMENT}" "${OUTPUT_DIR}/"
# Change to output directory
cd "${OUTPUT_DIR}"
# Run Aliscore
echo "Running Aliscore on ${ALIGNMENT}..."
echo "Options: ${ALISCORE_OPTS}"
echo "Aliscore script: ${ALISCORE_SCRIPT}"
# Construct and run Aliscore command
ALISCORE_CMD="perl -I${SCRIPT_DIR} ${ALISCORE_SCRIPT} -i $(basename ${ALIGNMENT}) ${ALISCORE_OPTS}"
echo "Command: ${ALISCORE_CMD}"
eval ${ALISCORE_CMD}
# Check if Aliscore completed successfully
if [ $? -eq 0 ]; then
echo "Aliscore completed successfully for ${ALIGNMENT}"
# List output files
echo ""
echo "Output files in ${OUTPUT_DIR}:"
ls -lh *List*.txt *Profile*.txt *.svg 2>/dev/null || echo " (some expected files not generated)"
# Report RSS positions if found
if [ -f "$(basename ${ALIGNMENT})_List_random.txt" ]; then
RSS_COUNT=$(wc -w < "$(basename ${ALIGNMENT})_List_random.txt")
echo ""
echo "Identified ${RSS_COUNT} randomly similar sequence positions"
echo "See: ${OUTPUT_DIR}/$(basename ${ALIGNMENT})_List_random.txt"
fi
else
echo "ERROR: Aliscore failed for ${ALIGNMENT}"
cd ..
exit 1
fi
# Return to parent directory
cd ..
echo "Done: ${ALIGNMENT} -> ${OUTPUT_DIR}"

270
skills/phylo_from_buscos/scripts/run_aliscore_alicut_batch.sh Executable file
View File

@@ -0,0 +1,270 @@
#!/bin/bash
# run_aliscore_alicut_batch.sh
# Batch processing script for Aliscore + ALICUT alignment trimming
# Processes all alignments in a directory through both tools sequentially
#
# Usage:
# bash run_aliscore_alicut_batch.sh [alignment_dir] [options]
#
# This script:
# 1. Runs Aliscore on all alignments to identify RSS
# 2. Runs ALICUT on each Aliscore output to remove RSS
# 3. Collects trimmed alignments in output directory
#
# Requirements:
# - run_aliscore.sh and run_alicut.sh in same directory or PATH
# - Aliscore.02.2.pl and ALICUT_V2.31.pl available
set -euo pipefail
# Script directory
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# Function to display usage
usage() {
cat <<EOF
Usage: $0 [alignment_dir] [options]
Batch process multiple alignments through Aliscore and ALICUT.
Arguments:
alignment_dir Directory containing aligned FASTA files (*.fas)
Options:
-o DIR Output directory for trimmed alignments (default: aliscore_alicut_trimmed)
-d DIR Base directory for Aliscore outputs (default: aliscore_output)
-w INT Aliscore window size (default: 4)
-r INT Aliscore random pairs (default: 4*N)
-N Aliscore: treat gaps as ambiguous (recommended for AA)
--remain-stems ALICUT: remain RNA stem positions
--remove-codon ALICUT: remove entire codons (for back-translation)
--remove-3rd ALICUT: remove only 3rd codon positions
-h Display this help message
Examples:
# Basic usage for amino acid alignments
bash run_aliscore_alicut_batch.sh aligned_aa/ -N
# Custom window size
bash run_aliscore_alicut_batch.sh aligned_aa/ -w 6 -N
# With RNA structure preservation
bash run_aliscore_alicut_batch.sh aligned_rrna/ --remain-stems
Output:
- aliscore_output/aliscore_[locus]/ : Individual Aliscore results per locus
- aliscore_alicut_trimmed/ : Final trimmed alignments
- aliscore_alicut_trimmed/trimming_summary.txt : Statistics for all loci
EOF
exit 0
}
# Default parameters
ALIGNMENT_DIR=""
OUTPUT_DIR="aliscore_alicut_trimmed"
ALISCORE_BASE_DIR="aliscore_output"
ALISCORE_OPTS=""
ALICUT_OPTS="-s" # Silent mode by default
if [ $# -eq 0 ]; then
usage
fi
ALIGNMENT_DIR="$1"
shift
# Validate alignment directory
if [ ! -d "${ALIGNMENT_DIR}" ]; then
echo "ERROR: Alignment directory not found: ${ALIGNMENT_DIR}"
exit 1
fi
# Parse options
while [ $# -gt 0 ]; do
case "$1" in
-h|--help)
usage
;;
-o|--output)
OUTPUT_DIR="$2"
shift 2
;;
-d|--aliscore-dir)
ALISCORE_BASE_DIR="$2"
shift 2
;;
-w)
ALISCORE_OPTS="${ALISCORE_OPTS} -w $2"
shift 2
;;
-r)
ALISCORE_OPTS="${ALISCORE_OPTS} -r $2"
shift 2
;;
-N)
ALISCORE_OPTS="${ALISCORE_OPTS} -N"
shift
;;
--remain-stems)
ALICUT_OPTS="${ALICUT_OPTS} -r"
shift
;;
--remove-codon)
ALICUT_OPTS="${ALICUT_OPTS} -c"
shift
;;
--remove-3rd)
ALICUT_OPTS="${ALICUT_OPTS} -3"
shift
;;
*)
echo "ERROR: Unknown option: $1"
usage
;;
esac
done
# Check for wrapper scripts
RUN_ALISCORE="${SCRIPT_DIR}/run_aliscore.sh"
RUN_ALICUT="${SCRIPT_DIR}/run_alicut.sh"
if [ ! -f "${RUN_ALISCORE}" ]; then
echo "ERROR: run_aliscore.sh not found: ${RUN_ALISCORE}"
exit 1
fi
if [ ! -f "${RUN_ALICUT}" ]; then
echo "ERROR: run_alicut.sh not found: ${RUN_ALICUT}"
exit 1
fi
# Create output directory
mkdir -p "${OUTPUT_DIR}"
# Find all FASTA files
ALIGNMENTS=($(find "${ALIGNMENT_DIR}" -maxdepth 1 -name "*.fas" -o -name "*.fasta"))
if [ ${#ALIGNMENTS[@]} -eq 0 ]; then
echo "ERROR: No FASTA files found in ${ALIGNMENT_DIR}"
exit 1
fi
echo "Found ${#ALIGNMENTS[@]} alignments to process"
echo "Aliscore options: ${ALISCORE_OPTS}"
echo "ALICUT options: ${ALICUT_OPTS}"
echo ""
# Initialize summary file
SUMMARY_FILE="${OUTPUT_DIR}/trimming_summary.txt"
echo -e "Locus\tOriginal_Length\tTrimmed_Length\tRemoved_Positions\tPercent_Removed\tRSS_Count" > "${SUMMARY_FILE}"
# Process each alignment
SUCCESS_COUNT=0
FAIL_COUNT=0
for ALIGNMENT in "${ALIGNMENTS[@]}"; do
LOCUS=$(basename "${ALIGNMENT}" .fas)
LOCUS=$(basename "${LOCUS}" .fasta)
echo "=========================================="
echo "Processing: ${LOCUS}"
echo "=========================================="
# Step 1: Run Aliscore
echo ""
echo "Step 1/2: Running Aliscore..."
if bash "${RUN_ALISCORE}" "${ALIGNMENT}" -d "${ALISCORE_BASE_DIR}" ${ALISCORE_OPTS}; then
echo "Aliscore completed for ${LOCUS}"
else
echo "ERROR: Aliscore failed for ${LOCUS}"
FAIL_COUNT=$((FAIL_COUNT + 1))
continue
fi
# Step 2: Run ALICUT
echo ""
echo "Step 2/2: Running ALICUT..."
ALISCORE_DIR="${ALISCORE_BASE_DIR}/aliscore_${LOCUS}"
if [ ! -d "${ALISCORE_DIR}" ]; then
echo "ERROR: Aliscore output directory not found: ${ALISCORE_DIR}"
FAIL_COUNT=$((FAIL_COUNT + 1))
continue
fi
if bash "${RUN_ALICUT}" "${ALISCORE_DIR}" ${ALICUT_OPTS}; then
echo "ALICUT completed for ${LOCUS}"
else
echo "ERROR: ALICUT failed for ${LOCUS}"
FAIL_COUNT=$((FAIL_COUNT + 1))
continue
fi
# Copy trimmed alignment to output directory
TRIMMED_FILE=$(find "${ALISCORE_DIR}" -name "ALICUT_*.fas" -o -name "ALICUT_*.fasta" | head -n 1)
if [ -n "${TRIMMED_FILE}" ] && [ -f "${TRIMMED_FILE}" ]; then
cp "${TRIMMED_FILE}" "${OUTPUT_DIR}/${LOCUS}_trimmed.fas"
echo "Trimmed alignment: ${OUTPUT_DIR}/${LOCUS}_trimmed.fas"
# Calculate statistics (handle multi-line FASTA format)
ORIGINAL_LENGTH=$(awk '/^>/ {if (seq) {print seq; seq=""}; next} {seq = seq $0} END {if (seq) print seq}' "${ALIGNMENT}" | head -n 1 | tr -d ' ' | wc -c)
TRIMMED_LENGTH=$(awk '/^>/ {if (seq) {print seq; seq=""}; next} {seq = seq $0} END {if (seq) print seq}' "${TRIMMED_FILE}" | head -n 1 | tr -d ' ' | wc -c)
REMOVED_LENGTH=$((ORIGINAL_LENGTH - TRIMMED_LENGTH))
PERCENT_REMOVED=$(awk "BEGIN {printf \"%.2f\", (${REMOVED_LENGTH}/${ORIGINAL_LENGTH})*100}")
# Count RSS positions
LIST_FILE=$(find "${ALISCORE_DIR}" -name "*_List_*.txt" | head -n 1)
RSS_COUNT=$(wc -w < "${LIST_FILE}" 2>/dev/null || echo "0")
# Append to summary
echo -e "${LOCUS}\t${ORIGINAL_LENGTH}\t${TRIMMED_LENGTH}\t${REMOVED_LENGTH}\t${PERCENT_REMOVED}\t${RSS_COUNT}" >> "${SUMMARY_FILE}"
SUCCESS_COUNT=$((SUCCESS_COUNT + 1))
else
echo "WARNING: Trimmed file not found for ${LOCUS}"
FAIL_COUNT=$((FAIL_COUNT + 1))
fi
echo ""
done
# Final report
echo "=========================================="
echo "BATCH PROCESSING COMPLETE"
echo "=========================================="
echo ""
echo "Successfully processed: ${SUCCESS_COUNT}/${#ALIGNMENTS[@]} alignments"
echo "Failed: ${FAIL_COUNT}/${#ALIGNMENTS[@]} alignments"
echo ""
echo "Output directory: ${OUTPUT_DIR}"
echo "Trimmed alignments: ${OUTPUT_DIR}/*_trimmed.fas"
echo "Summary statistics: ${SUMMARY_FILE}"
echo ""
# Display summary statistics
if [ ${SUCCESS_COUNT} -gt 0 ]; then
echo "Overall trimming statistics:"
awk 'NR>1 {
total_orig += $2;
total_trim += $3;
total_removed += $4;
count++
}
END {
if (count > 0) {
avg_removed = (total_removed / total_orig) * 100;
printf " Total positions before: %d\n", total_orig;
printf " Total positions after: %d\n", total_trim;
printf " Total removed: %d (%.2f%%)\n", total_removed, avg_removed;
printf " Average per locus: %.2f%% removed\n", avg_removed;
}
}' "${SUMMARY_FILE}"
fi
echo ""
echo "Done!"

125
skills/phylo_from_buscos/templates/README.md Normal file
View File

@@ -0,0 +1,125 @@
# Phylogenomics Workflow Templates
This directory contains template scripts for running the phylogenomics pipeline across different computing environments.
## Directory Structure
```
templates/
├── slurm/ # SLURM job scheduler templates
├── pbs/ # PBS/Torque job scheduler templates
└── local/ # Local machine templates (with GNU parallel support)
```
## Template Naming Convention
Templates follow a consistent naming pattern: `NN_step_name[_variant].ext`
- `NN`: Step number (e.g., `02` for compleasm, `08a` for partition search)
- `step_name`: Descriptive name of the pipeline step
- `_variant`: Optional variant (e.g., `_first`, `_parallel`, `_serial`)
- `.ext`: File extension (`.job` for schedulers, `.sh` for local scripts)
## Available Templates
### Step 2: Ortholog Identification (compleasm)
**SLURM:**
- `02_compleasm_first.job` - Process first genome to download lineage database
- `02_compleasm_parallel.job` - Array job for remaining genomes
**PBS:**
- `02_compleasm_first.job` - Process first genome to download lineage database
- `02_compleasm_parallel.job` - Array job for remaining genomes
**Local:**
- `02_compleasm_first.sh` - Process first genome to download lineage database
- `02_compleasm_parallel.sh` - GNU parallel for remaining genomes
### Step 8A: Partition Model Selection
**SLURM:**
- `08a_partition_search.job` - IQ-TREE partition model search with TESTMERGEONLY
**PBS:**
- `08a_partition_search.job` - IQ-TREE partition model search with TESTMERGEONLY
**Local:**
- `08a_partition_search.sh` - IQ-TREE partition model search with TESTMERGEONLY
### Step 8C: Individual Gene Trees
**SLURM:**
- `08c_gene_trees_array.job` - Array job for parallel gene tree estimation
**PBS:**
- `08c_gene_trees_array.job` - Array job for parallel gene tree estimation
**Local:**
- `08c_gene_trees_parallel.sh` - GNU parallel for gene tree estimation
- `08c_gene_trees_serial.sh` - Serial processing (for debugging/limited resources)
## Placeholders
Templates contain placeholders that must be replaced with user-specific values:
| Placeholder | Description | Example |
|-------------|-------------|---------|
| `TOTAL_THREADS` | Total CPU cores available | `64` |
| `THREADS_PER_JOB` | Threads per concurrent job | `16` |
| `NUM_GENOMES` | Number of genomes in analysis | `20` |
| `NUM_LOCI` | Number of loci/alignments | `2795` |
| `LINEAGE` | BUSCO lineage dataset | `insecta_odb10` |
| `MODEL_SET` | Comma-separated substitution models | `LG,WAG,JTT,Q.pfam` |
## Usage
### For Claude (LLM)
When a user requests scripts for a specific computing environment:
1. **Read the appropriate template** using the Read tool
2. **Replace placeholders** with user-specified values
3. **Present the customized script** to the user
4. **Provide setup instructions** (e.g., how many genomes, how to calculate thread allocation)
Example:
```python
# Read template
template = Read("templates/slurm/02_compleasm_first.job")
# Replace placeholders
script = template.replace("TOTAL_THREADS", "64")
script = script.replace("LINEAGE", "insecta_odb10")
# Present to user
print(script)
```
### For Users
Templates are not meant to be used directly. Instead:
1. Follow the workflow in `SKILL.md`
2. Answer Claude's questions about your setup
3. Claude will fetch the appropriate template and customize it for you
4. Copy the customized script Claude provides
## Benefits of This Structure
1. **Reduced token usage**: Claude only reads templates when needed
2. **Easier maintenance**: Update one template file instead of multiple locations in SKILL.md
3. **Consistency**: All users get the same base template structure
4. **Clarity**: Separate files are easier to review than inline code
5. **Extensibility**: Easy to add new templates for additional tools or variants
## Adding New Templates
When adding new templates:
1. **Follow naming convention**: `NN_descriptive_name[_variant].ext`
2. **Include clear comments**: Explain what the script does
3. **Use consistent placeholders**: Match existing placeholder names
4. **Test thoroughly**: Ensure placeholders are complete and correct
5. **Update this README**: Add the new template to the "Available Templates" section
6. **Update SKILL.md**: Reference the new template in the appropriate workflow step

26
skills/phylo_from_buscos/templates/local/02_compleasm_first.sh Normal file
View File

@@ -0,0 +1,26 @@
#!/bin/bash
# run_compleasm_first.sh
source ~/.bashrc
conda activate phylo
# User-specified total CPU threads
TOTAL_THREADS=TOTAL_THREADS # Replace with total cores you want to use (e.g., 16, 32, 64)
echo "Processing first genome with ${TOTAL_THREADS} CPU threads to download lineage database..."
# Create output directory
mkdir -p 01_busco_results
# Process FIRST genome only
first_genome=$(head -n 1 genome_list.txt)
genome_name=$(basename ${first_genome} .fasta)
echo "Processing: ${genome_name}"
compleasm run \
-a ${first_genome} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t ${TOTAL_THREADS}
echo ""
echo "First genome complete! Lineage database is now cached."
echo "Now run the parallel script for remaining genomes: bash run_compleasm_parallel.sh"

33
skills/phylo_from_buscos/templates/local/02_compleasm_parallel.sh Normal file
View File

@@ -0,0 +1,33 @@
#!/bin/bash
# run_compleasm_parallel.sh
source ~/.bashrc
conda activate phylo
# Threading configuration (adjust based on your system)
TOTAL_THREADS=TOTAL_THREADS # Total cores to use (e.g., 64)
THREADS_PER_JOB=THREADS_PER_JOB # Threads per genome (e.g., 16)
CONCURRENT_JOBS=$((TOTAL_THREADS / THREADS_PER_JOB)) # Calculated automatically
echo "Configuration:"
echo " Total threads: ${TOTAL_THREADS}"
echo " Threads per genome: ${THREADS_PER_JOB}"
echo " Concurrent genomes: ${CONCURRENT_JOBS}"
echo ""
# Create output directory
mkdir -p 01_busco_results
# Process remaining genomes (skip first one) in parallel
tail -n +2 genome_list.txt | parallel -j ${CONCURRENT_JOBS} '
genome_name=$(basename {} .fasta)
echo "Processing ${genome_name} with THREADS_PER_JOB threads..."
compleasm run \
-a {} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t THREADS_PER_JOB
'
echo ""
echo "All genomes processed!"

20
skills/phylo_from_buscos/templates/local/08a_partition_search.sh Normal file
View File

@@ -0,0 +1,20 @@
#!/bin/bash
source ~/.bashrc
conda activate phylo
cd 06_concatenation
iqtree \
-s FcC_supermatrix.fas \
-spp partition_def.txt \
-nt 18 \
-safe \
-pre partition_search \
-m TESTMERGEONLY \
-mset MODEL_SET \
-msub nuclear \
-rcluster 10 \
-bb 1000 \
-alrt 1000
echo "Partition search complete! Best scheme: partition_search.best_scheme.nex"

17
skills/phylo_from_buscos/templates/local/08c_gene_trees_parallel.sh Normal file
View File

@@ -0,0 +1,17 @@
#!/bin/bash
source ~/.bashrc
conda activate phylo
cd trimmed_aa
# Create list of alignments
ls *_trimmed.fas > locus_alignments.txt
# Run IQ-TREE in parallel (adjust -j for number of concurrent jobs)
cat locus_alignments.txt | parallel -j 4 '
prefix=$(basename {} _trimmed.fas)
iqtree -s {} -m MFP -bb 1000 -bnni -czb -pre ${prefix} -nt 1
echo "Tree complete: ${prefix}"
'
echo "All gene trees complete!"

13
skills/phylo_from_buscos/templates/local/08c_gene_trees_serial.sh Normal file
View File

@@ -0,0 +1,13 @@
#!/bin/bash
source ~/.bashrc
conda activate phylo
cd trimmed_aa
for locus in *_trimmed.fas; do
prefix=$(basename ${locus} _trimmed.fas)
echo "Processing ${prefix}..."
iqtree -s ${locus} -m MFP -bb 1000 -bnni -czb -pre ${prefix} -nt 1
done
echo "All gene trees complete!"

27
skills/phylo_from_buscos/templates/pbs/02_compleasm_first.job Normal file
View File

@@ -0,0 +1,27 @@
#!/bin/bash
#PBS -N compleasm_first
#PBS -l nodes=1:ppn=TOTAL_THREADS # Replace with total available CPUs (e.g., 64)
#PBS -l mem=384gb # Adjust based on ppn × 6GB
#PBS -l walltime=24:00:00
cd $PBS_O_WORKDIR
source ~/.bashrc
conda activate phylo
mkdir -p logs
mkdir -p 01_busco_results
# Process FIRST genome only (downloads lineage database)
first_genome=$(head -n 1 genome_list.txt)
genome_name=$(basename ${first_genome} .fasta)
echo "Processing first genome: ${genome_name} with $PBS_NUM_PPN threads..."
echo "This will download the BUSCO lineage database for subsequent runs."
compleasm run \
-a ${first_genome} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t $PBS_NUM_PPN
echo "First genome complete! Lineage database is now cached."
echo "Submit the parallel job for remaining genomes: qsub run_compleasm_parallel.job"

24
skills/phylo_from_buscos/templates/pbs/02_compleasm_parallel.job Normal file
View File

@@ -0,0 +1,24 @@
#!/bin/bash
#PBS -N compleasm_parallel
#PBS -t 2-NUM_GENOMES # Start from genome 2 (first genome already processed)
#PBS -l nodes=1:ppn=THREADS_PER_JOB # e.g., 16 for 64-core system
#PBS -l mem=96gb # Adjust based on ppn × 6GB
#PBS -l walltime=48:00:00
cd $PBS_O_WORKDIR
source ~/.bashrc
conda activate phylo
mkdir -p 01_busco_results
# Get genome for this array task
genome=$(sed -n "${PBS_ARRAYID}p" genome_list.txt)
genome_name=$(basename ${genome} .fasta)
echo "Processing ${genome_name} with $PBS_NUM_PPN threads..."
compleasm run \
-a ${genome} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t $PBS_NUM_PPN

22
skills/phylo_from_buscos/templates/pbs/08a_partition_search.job Normal file
View File

@@ -0,0 +1,22 @@
#!/bin/bash
#PBS -N iqtree_partition
#PBS -l nodes=1:ppn=18
#PBS -l mem=72gb
#PBS -l walltime=72:00:00
cd $PBS_O_WORKDIR/06_concatenation
source ~/.bashrc
conda activate phylo
iqtree \
-s FcC_supermatrix.fas \
-spp partition_def.txt \
-nt 18 \
-safe \
-pre partition_search \
-m TESTMERGEONLY \
-mset MODEL_SET \
-msub nuclear \
-rcluster 10 \
-bb 1000 \
-alrt 1000

26
skills/phylo_from_buscos/templates/pbs/08c_gene_trees_array.job Normal file
View File

@@ -0,0 +1,26 @@
#!/bin/bash
#PBS -N iqtree_genes
#PBS -t 1-NUM_LOCI
#PBS -l nodes=1:ppn=1
#PBS -l mem=4gb
#PBS -l walltime=2:00:00
cd $PBS_O_WORKDIR/trimmed_aa
source ~/.bashrc
conda activate phylo
# Create list of alignments if not present
if [ ! -f locus_alignments.txt ]; then
ls *_trimmed.fas > locus_alignments.txt
fi
locus=$(sed -n "${PBS_ARRAYID}p" locus_alignments.txt)
iqtree \
-s ${locus} \
-m MFP \
-bb 1000 \
-bnni \
-czb \
-pre $(basename ${locus} _trimmed.fas) \
-nt 1

28
skills/phylo_from_buscos/templates/slurm/02_compleasm_first.job Normal file
View File

@@ -0,0 +1,28 @@
#!/bin/bash
#SBATCH --job-name=compleasm_first
#SBATCH --cpus-per-task=TOTAL_THREADS # Replace with total available CPUs (e.g., 64)
#SBATCH --mem-per-cpu=6G
#SBATCH --time=24:00:00
#SBATCH --output=logs/compleasm_first.%j.out
#SBATCH --error=logs/compleasm_first.%j.err
source ~/.bashrc
conda activate phylo
mkdir -p logs
mkdir -p 01_busco_results
# Process FIRST genome only (downloads lineage database)
first_genome=$(head -n 1 genome_list.txt)
genome_name=$(basename ${first_genome} .fasta)
echo "Processing first genome: ${genome_name} with ${SLURM_CPUS_PER_TASK} threads..."
echo "This will download the BUSCO lineage database for subsequent runs."
compleasm run \
-a ${first_genome} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t ${SLURM_CPUS_PER_TASK}
echo "First genome complete! Lineage database is now cached."
echo "Submit the parallel job for remaining genomes: sbatch run_compleasm_parallel.job"

25
skills/phylo_from_buscos/templates/slurm/02_compleasm_parallel.job Normal file
View File

@@ -0,0 +1,25 @@
#!/bin/bash
#SBATCH --job-name=compleasm_parallel
#SBATCH --array=2-NUM_GENOMES # Start from genome 2 (first genome already processed)
#SBATCH --cpus-per-task=THREADS_PER_JOB # e.g., 16 for 64-core system with 4 concurrent jobs
#SBATCH --mem-per-cpu=6G
#SBATCH --time=48:00:00
#SBATCH --output=logs/compleasm.%A_%a.out
#SBATCH --error=logs/compleasm.%A_%a.err
source ~/.bashrc
conda activate phylo
mkdir -p 01_busco_results
# Get genome for this array task (skipping the first one)
genome=$(sed -n "${SLURM_ARRAY_TASK_ID}p" genome_list.txt)
genome_name=$(basename ${genome} .fasta)
echo "Processing ${genome_name} with ${SLURM_CPUS_PER_TASK} threads..."
compleasm run \
-a ${genome} \
-o 01_busco_results/${genome_name}_compleasm \
-l LINEAGE \
-t ${SLURM_CPUS_PER_TASK}

27
skills/phylo_from_buscos/templates/slurm/08a_partition_search.job Normal file
View File

@@ -0,0 +1,27 @@
#!/bin/bash
#SBATCH --job-name=iqtree_partition
#SBATCH --cpus-per-task=18
#SBATCH --mem-per-cpu=4G
#SBATCH --time=72:00:00
#SBATCH --output=logs/partition_search.out
#SBATCH --error=logs/partition_search.err
source ~/.bashrc
conda activate phylo
cd 06_concatenation # Use organized directory structure
iqtree \
-s FcC_supermatrix.fas \
-spp partition_def.txt \
-nt ${SLURM_CPUS_PER_TASK} \
-safe \
-pre partition_search \
-m TESTMERGEONLY \
-mset MODEL_SET \
-msub nuclear \
-rcluster 10 \
-bb 1000 \
-alrt 1000
# Output: partition_search.best_scheme.nex

28
skills/phylo_from_buscos/templates/slurm/08c_gene_trees_array.job Normal file
View File

@@ -0,0 +1,28 @@
#!/bin/bash
#SBATCH --job-name=iqtree_genes
#SBATCH --array=1-NUM_LOCI
#SBATCH --cpus-per-task=1
#SBATCH --mem-per-cpu=4G
#SBATCH --time=2:00:00
#SBATCH --output=logs/%A_%a.genetree.out
source ~/.bashrc
conda activate phylo
cd trimmed_aa
# Create list of alignments if not present
if [ ! -f locus_alignments.txt ]; then
ls *_trimmed.fas > locus_alignments.txt
fi
locus=$(sed -n "${SLURM_ARRAY_TASK_ID}p" locus_alignments.txt)
iqtree \
-s ${locus} \
-m MFP \
-bb 1000 \
-bnni \
-czb \
-pre $(basename ${locus} _trimmed.fas) \
-nt 1