restructure to workspace

.github/workflows/rust.yml

@@ -4,13 +4,13 @@ on:
   push:
     branches: ['master']
     paths:
-      - 'src/**'
-      - 'tests/**'
+      - 'tf-binding-rs/**'
+      - 'motif-scanner/**'
   pull_request:
     branches: ['master']
     paths:
-      - 'src/**'
-      - 'tests/**'
+      - 'tf-binding-rs/**'
+      - 'motif-scanner/**'
 
 env:
   CARGO_TERM_COLOR: always
@@ -22,6 +22,6 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Build
-        run: cargo build --verbose
+        run: cargo build --workspace --verbose
       - name: Run tests
-        run: cargo test --verbose
+        run: cargo test --workspace --verbose

.gitignore

@@ -1,4 +1,5 @@
 /target
-/Cargo.lock
+/*/target
+Cargo.lock
 *.py
 /.vscode

Cargo.toml

@@ -1,16 +1,6 @@
-[package]
-name = "tf-binding-rs"
-version = "0.1.4"
-edition = "2021"
-description = "Fast transcription factor binding site prediction and FASTA manipulation in Rust"
-license = "MIT"
-
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[dependencies]
-ndarray = "0.16.1"
-polars = { version = "0.44.2", features = ["lazy", "dtype-struct", "log"] }
-serde = { version = "1.0.215", features = ["derive"] }
-thiserror = "2.0.3"
-statrs = "0.17.1"
-phf = {version = "0.11.2", features = ["macros"]}
+[workspace]
+resolver = "2"
+members = [
+    "tf-binding-rs",
+    "motif-scanner"
+]

motif-scanner/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "motif-scanner"
+version = "0.1.0"
+edition = "2021"
+description = "Command line tool for scanning DNA sequences for transcription factor binding sites"
+authors = ["Jiayu Huang <[email protected]>"]
+license = "MIT"
+
+[dependencies]
+tf-binding-rs = { path = "../tf-binding-rs" }
+clap = { version = "4.5.21", features = ["derive"] }

motif-scanner/src/main.rs

@@ -0,0 +1,3 @@
+fn main() {
+    println!("Hello, world!");
+}

readme.md

@@ -1,113 +1,76 @@
-# tf-binding-rs (In Development)
+# TF Binding Analysis Tools
+
+This workspace contains tools for analyzing transcription factor (TF) binding sites in DNA sequences:
+
+- **[tf-binding-rs](tf-binding-rs/)**: A Rust library for TF binding site prediction and sequence analysis
+- **[motif-scanner](motif-scanner/)**: A command-line tool for scanning DNA sequences for TF binding sites
+
+## 🧬 tf-binding-rs
 
 [<img alt="github" src="https://img.shields.io/badge/github-peter6866/tf--binding--rs-8da0cb?style=for-the-badge&labelColor=555555&logo=github" height="20">](https://github.com/peter6866/tf-binding-rs)
 [<img alt="crates.io" src="https://img.shields.io/crates/v/tf-binding-rs.svg?style=for-the-badge&color=fc8d62&logo=rust" height="20">](https://crates.io/crates/tf-binding-rs)
 
-A Rust library for predicting transcription factor (TF) binding site occupancy in DNA sequences. This toolkit provides efficient implementations for:
+A Rust library providing efficient implementations for:
 
 - FASTA file manipulation and sequence processing
-- Position Weight Matrix (PWM) handling and Energy Weight Matrix (EWM) conversion
-- TF binding site occupancy prediction using statistical thermodynamics
-- Binding energy landscape and occupancy probability calculations
+- Position Weight Matrix (PWM) handling
+- Energy Weight Matrix (EWM) conversion
+- TF binding site occupancy prediction
 - Multi-TF occupancy analysis
 
-## Features
-
-- 🧬 Fast FASTA file reading and writing
-- 📊 PWM/EWM-based binding site analysis
-- 🔍 Efficient sequence scanning with energy matrices
-- 📈 Occupancy landscape calculation for multiple TFs
-- 🧮 Statistical thermodynamics-based predictions
-
-## Installation
-
-Add this to your `Cargo.toml`:
-
-```toml
-[dependencies]
-tf-binding-rs = "0.1.1"
-```
-
-Or install using cargo:
-
-```bash
-cargo add tf-binding-rs
-```
-
-## Examples
-
-### Reading FASTA Files
-
 ```rust
-use tf_binding_rs::fasta;
+use tf_binding_rs::occupancy;
 
 fn main() -> Result<(), Box<dyn std::error::Error>> {
-    // Read sequences from a FASTA file
-    let sequences = fasta::read_fasta("path/to/sequences.fasta")?;
-
-    // Print sequence information
-    println!("Number of sequences: {}", sequences.height());
-
-    // Calculate GC content
-    let gc_stats = fasta::gc_content(&sequences)?;
-    println!("GC content analysis: {:?}", gc_stats);
-
+    let ewms = occupancy::read_pwm_to_ewm("motifs.meme")?;
+    let sequence = "ATCGATCGTAGCTACGT";
+    let landscape = occupancy::total_landscape(sequence, &ewms, -3.0)?;
+    println!("Binding landscape:\n{}", landscape);
     Ok(())
 }
 ```
 
-### Working with PWM Files
-
-```rust
-use tf_binding_rs::occupancy;
+## 🔍 motif-scanner
 
-fn main() -> Result<(), Box<dyn std::error::Error>> {
-    // Read PWM motifs from MEME format file
-    let pwm_collection = occupancy::read_pwm_files("path/to/motifs.meme")?;
+A command-line tool for scanning DNA sequences and predicting TF binding sites. Features:
 
-    // Process each motif
-    for (motif_id, pwm) in pwm_collection {
-        println!("Processing motif: {}", motif_id);
-        println!("Matrix dimensions: {:?}", pwm.shape());
-    }
+- Batch processing of sequence files
+- Occupancy score calculation
+- Multiple output formats (CSV, Parquet)
+- Filtering by occupancy threshold
 
-    Ok(())
-}
+```bash
+motif-scanner input.csv motifs.meme output.csv --cutoff 0.2 --mu 9.0
 ```
 
-### Working with PWMs and Energy Matrices
-
-```rust
-use tf_binding_rs::occupancy;
+## Installation
 
-fn main() -> Result<(), Box<dyn std::error::Error>> {
-    // Read PWMs and convert to Energy Weight Matrices
-    let ewm_collection = occupancy::read_pwm_to_ewm("path/to/motifs.meme")?;
+### From Source
 
-    // Calculate binding landscape for a sequence
-    let sequence = "ATCGATCGTAGCTACGT";
-    let mu = -3.0; // chemical potential
+```bash
+# Clone the repository
+git clone https://github.com/peter6866/tf-binding-rs
+cd tf-binding-rs
 
-    // Get occupancy predictions for all TFs
-    let occupancy_landscape = occupancy::total_landscape(
-        &sequence,
-        &ewm_collection,
-        mu
-    )?;
+# Build both the library and the scanner
+cargo build --release --workspace
 
-    println!("Occupancy predictions:\n{}", occupancy_landscape);
-    Ok(())
-}
+# Install the motif-scanner binary
+cargo install --path motif-scanner
 ```
 
-## Use Cases
+### From crates.io
+
+```bash
+# Install just the motif-scanner tool
+cargo install motif-scanner
 
-- Genomic sequence analysis
-- TF binding site prediction and quantification
-- Multi-factor binding landscape analysis
-- Regulatory sequence characterization
-- Statistical thermodynamics of protein-DNA interactions
+# For library usage, add to your Cargo.toml:
+[dependencies]
+tf-binding-rs = "0.1.4"
+```
 
 ## Documentation
 
-For detailed API documentation, visit [docs.rs/tf-binding-rs](https://docs.rs/tf-binding-rs)
+- [tf-binding-rs API Documentation](https://docs.rs/tf-binding-rs)
+- [motif-scanner Usage Guide](motif-scanner/README.md)

tf-binding-rs/Cargo.toml

@@ -0,0 +1,15 @@
+[package]
+name = "tf-binding-rs"
+version = "0.1.4"
+edition = "2021"
+description = "Fast transcription factor binding site prediction and FASTA manipulation in Rust"
+license = "MIT"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+ndarray = "0.16.1"
+polars = { version = "0.44.2", features = ["lazy", "dtype-struct", "log"] }
+thiserror = "2.0.3"
+statrs = "0.17.1"
+phf = {version = "0.11.2", features = ["macros"]}

tf-binding-rs/readme.md

@@ -0,0 +1,113 @@
+# tf-binding-rs (In Development)
+
+[<img alt="github" src="https://img.shields.io/badge/github-peter6866/tf--binding--rs-8da0cb?style=for-the-badge&labelColor=555555&logo=github" height="20">](https://github.com/peter6866/tf-binding-rs)
+[<img alt="crates.io" src="https://img.shields.io/crates/v/tf-binding-rs.svg?style=for-the-badge&color=fc8d62&logo=rust" height="20">](https://crates.io/crates/tf-binding-rs)
+
+A Rust library for predicting transcription factor (TF) binding site occupancy in DNA sequences. This toolkit provides efficient implementations for:
+
+- FASTA file manipulation and sequence processing
+- Position Weight Matrix (PWM) handling and Energy Weight Matrix (EWM) conversion
+- TF binding site occupancy prediction using statistical thermodynamics
+- Binding energy landscape and occupancy probability calculations
+- Multi-TF occupancy analysis
+
+## Features
+
+- 🧬 Fast FASTA file reading and writing
+- 📊 PWM/EWM-based binding site analysis
+- 🔍 Efficient sequence scanning with energy matrices
+- 📈 Occupancy landscape calculation for multiple TFs
+- 🧮 Statistical thermodynamics-based predictions
+
+## Installation
+
+Add this to your `Cargo.toml`:
+
+```toml
+[dependencies]
+tf-binding-rs = "0.1.1"
+```
+
+Or install using cargo:
+
+```bash
+cargo add tf-binding-rs
+```
+
+## Examples
+
+### Reading FASTA Files
+
+```rust
+use tf_binding_rs::fasta;
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    // Read sequences from a FASTA file
+    let sequences = fasta::read_fasta("path/to/sequences.fasta")?;
+
+    // Print sequence information
+    println!("Number of sequences: {}", sequences.height());
+
+    // Calculate GC content
+    let gc_stats = fasta::gc_content(&sequences)?;
+    println!("GC content analysis: {:?}", gc_stats);
+
+    Ok(())
+}
+```
+
+### Working with PWM Files
+
+```rust
+use tf_binding_rs::occupancy;
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    // Read PWM motifs from MEME format file
+    let pwm_collection = occupancy::read_pwm_files("path/to/motifs.meme")?;
+
+    // Process each motif
+    for (motif_id, pwm) in pwm_collection {
+        println!("Processing motif: {}", motif_id);
+        println!("Matrix dimensions: {:?}", pwm.shape());
+    }
+
+    Ok(())
+}
+```
+
+### Working with PWMs and Energy Matrices
+
+```rust
+use tf_binding_rs::occupancy;
+
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    // Read PWMs and convert to Energy Weight Matrices
+    let ewm_collection = occupancy::read_pwm_to_ewm("path/to/motifs.meme")?;
+
+    // Calculate binding landscape for a sequence
+    let sequence = "ATCGATCGTAGCTACGT";
+    let mu = -3.0; // chemical potential
+
+    // Get occupancy predictions for all TFs
+    let occupancy_landscape = occupancy::total_landscape(
+        &sequence,
+        &ewm_collection,
+        mu
+    )?;
+
+    println!("Occupancy predictions:\n{}", occupancy_landscape);
+    Ok(())
+}
+```
+
+## Use Cases
+
+- Genomic sequence analysis
+- TF binding site prediction and quantification
+- Multi-factor binding landscape analysis
+- Regulatory sequence characterization
+- Statistical thermodynamics of protein-DNA interactions
+
+## Documentation
+
+For detailed API documentation, visit [docs.rs/tf-binding-rs](https://docs.rs/tf-binding-rs)

src/occupancy.rs → tf-binding-rs/src/occupancy.rs

@@ -4,7 +4,6 @@ use crate::types::*;
 use polars::lazy::dsl::*;
 use polars::prelude::*;
 use std::collections::HashMap;
-use std::fmt::format;
 use std::fs::File;
 use std::io::{BufRead, BufReader};
 use std::iter::Peekable;