0.14.0: optionally force --fasta output for fastq input

Author: bede

CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.14.0] - 2026-02-25
+
+### Added
+
+- `deacon filter` accepts `-f`/`--fasta` to force FASTA output regardless of input format.
+
 ## [0.13.2] - 2025-11-21
 
 ### Added

Cargo.lock

@@ -1,7 +1,7 @@
 [package]
 name = "deacon"
-version = "0.13.2"
-description = "Fast DNA search and [host] depletion using minimizers"
+version = "0.14.0"
+description = "Accelerated DNA sequence search and [host] depletion using minimizers"
 authors = ["Bede Constantinides <b@bede.im>"]
 edition = "2024"
 repository = "https://github.com/bede/deacon"

Cargo.toml

@@ -130,6 +130,9 @@ deacon filter -d -R panhuman-1.k31w15.idx reads.fq.gz > filt.fq
 # Only look for minimizer hits inside the first 1000bp per record
 deacon filter -d -p 1000 panhuman-1.k31w15.idx reads.fq.gz > filt.fq
 
+# Output FASTA regardless of input format (discards quality scores)
+deacon filter -d -f panhuman-1.k31w15.idx reads.fq.gz > filt.fa
+
 # Debug mode: see sequences with minimizer hits in stderr
 deacon filter -d --debug panhuman-1.k31w15.idx reads.fq.gz > filt.fq
 ```
@@ -193,6 +196,8 @@ Options:
           Replace sequence headers with incrementing numbers
       --rename-random
           Replace sequence headers with incrementing numbers and random suffixes
+  -f, --fasta
+          Output FASTA format regardless of input format
   -o, --output <OUTPUT>
           Path to output fastx file (stdout if not specified; detects .gz and .zst)
   -O, --output2 <OUTPUT2>

README.md

@@ -28,6 +28,7 @@ struct FilterProcessorConfig {
     deplete: bool,
     rename: bool,
     rename_random: bool,
+    output_fasta: bool,
     debug: bool,
 }
 
@@ -114,9 +115,10 @@ fn format_record_to_buffer<R: Record>(
     counter: u64,
     rename: bool,
     rename_random: bool,
+    output_fasta: bool,
     buffer: &mut Vec<u8>,
 ) -> Result<()> {
-    let is_fasta = record.qual().is_none();
+    let is_fasta = output_fasta || record.qual().is_none();
 
     // Header
     buffer.write_all(if is_fasta { b">" } else { b"@" })?;
@@ -290,6 +292,7 @@ struct FilterProcessor {
     deplete: bool,
     rename: bool,
     rename_random: bool,
+    output_fasta: bool,
     debug: bool,
 
     hasher: KmerHasher,
@@ -394,6 +397,7 @@ impl FilterProcessor {
             deplete: config.deplete,
             rename: config.rename,
             rename_random: config.rename_random,
+            output_fasta: config.output_fasta,
             debug: config.debug,
             hasher: KmerHasher::new(kmer_length as usize),
             local_buffer: Vec::with_capacity(DEFAULT_BUFFER_SIZE),
@@ -569,6 +573,7 @@ impl FilterProcessor {
             self.local_stats.output_seq_counter,
             self.rename,
             self.rename_random,
+            self.output_fasta,
             &mut self.local_buffer,
         )
     }
@@ -581,6 +586,7 @@ impl FilterProcessor {
             self.local_stats.output_seq_counter,
             self.rename,
             self.rename_random,
+            self.output_fasta,
             &mut self.local_buffer2,
         )
     }
@@ -928,6 +934,7 @@ pub fn run(config: &FilterConfig) -> Result<()> {
         deplete: config.deplete,
         rename: config.rename,
         rename_random: config.rename_random,
+        output_fasta: config.output_fasta,
         debug: config.debug,
     };
     let mut processor = FilterProcessor::new(

src/filter.rs

@@ -172,6 +172,9 @@ pub struct FilterConfig<'a> {
     /// Replace headers with sequential numbers followed by random u64 (1-12345, 2-67890, ...)
     pub rename_random: bool,
 
+    /// Force FASTA output (discards quality scores)
+    pub output_fasta: bool,
+
     /// Number of execution threads (0 = auto)
     pub threads: u16,
 
@@ -203,6 +206,7 @@ impl<'a> FilterConfig<'a> {
             deplete: false,
             rename: false,
             rename_random: false,
+            output_fasta: false,
             threads: 0,             // Use all available threads by default
             compression_level: 2,   // Default compression level
             compression_threads: 0, // Auto-calculate as ceil(total/2)

src/lib.rs

@@ -64,6 +64,10 @@ enum Commands {
         #[arg(long = "rename-random", default_value_t = false)]
         rename_random: bool,
 
+        /// Output FASTA format regardless of input format
+        #[arg(short = 'f', long = "fasta", default_value_t = false)]
+        output_fasta: bool,
+
         /// Path to output fastx file (stdout if not specified; detects .gz and .zst)
         #[arg(short = 'o', long = "output")]
         output: Option<PathBuf>,
@@ -420,6 +424,7 @@ fn process_command(command: &Commands) -> Result<(), anyhow::Error> {
             deplete,
             rename,
             rename_random,
+            output_fasta,
             threads,
             compression_level,
             compression_threads,
@@ -446,6 +451,7 @@ fn process_command(command: &Commands) -> Result<(), anyhow::Error> {
                 deplete: *deplete,
                 rename: *rename,
                 rename_random: *rename_random,
+                output_fasta: *output_fasta,
                 threads: *threads,
                 compression_level: *compression_level,
                 compression_threads: *compression_threads,

src/main.rs

@@ -283,6 +283,40 @@ fn test_filter_rename() {
     );
 }
 
+#[test]
+fn test_filter_fasta_flag() {
+    let temp_dir = tempdir().unwrap();
+    let fasta_path = temp_dir.path().join("ref.fasta");
+    let fastq_path = temp_dir.path().join("reads.fastq");
+    let bin_path = temp_dir.path().join("ref.bin");
+
+    create_test_fasta(&fasta_path);
+    create_test_fastq(&fastq_path);
+    build_index(&fasta_path, &bin_path);
+
+    let mut cmd = cargo::cargo_bin_cmd!("deacon");
+    let output = cmd
+        .arg("filter")
+        .arg("-f")
+        .arg("-a")
+        .arg("1")
+        .arg("-r")
+        .arg("0.0")
+        .arg(&bin_path)
+        .arg(&fastq_path)
+        .assert()
+        .success()
+        .get_output()
+        .stdout
+        .clone();
+
+    let output_str = std::str::from_utf8(&output).unwrap();
+    assert!(
+        output_str.starts_with('>'),
+        "FASTQ in with -f should gen FASTA out"
+    );
+}
+
 #[test]
 fn test_filter_min_matches() {
     let temp_dir = tempdir().unwrap();