diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml
index 7dcd868..a888cec 100644
--- a/.github/workflows/build_and_test.yml
+++ b/.github/workflows/build_and_test.yml
@@ -38,21 +38,6 @@ jobs:
         run: |
           ln -s ~/kraken2_db_8 kraken2_db
 
-      - name: make sylph db # Needed so tests can run quickly
-        run: |
-          cd ~
-          if [ ! -d "gatekeeper_sylph_test_data" ]; then
-            mkdir gatekeeper_sylph_test_data
-            cp /mnt/portal-sp3dev-knowledge/sylph/gtdb-r220-c1000-dbv1.syldb gatekeeper_sylph_test_data
-            cp /mnt/portal-sp3dev-knowledge/sylph/virus_imgvr_c200_v0.3.0.syldb gatekeeper_sylph_test_data
-            cp /mnt/portal-sp3dev-knowledge/sylph/fungi-refseq-2024-07-25-c200-v0.3.syldb gatekeeper_sylph_test_data
-            cp /mnt/portal-sp3dev-knowledge/sylph/*.tsv* gatekeeper_sylph_test_data
-          fi
-
-      - name: symlink sylph db
-        run: |
-          ln -s ~/gatekeeper_sylph_test_data sylph_dbs
-
       # Run pytest in container to use conda environment
       - name: pytest in docker
         run: |
diff --git a/.gitignore b/.gitignore
index 4143746..7483ef2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -22,8 +22,6 @@ kraken2_db*
 results
 report*.html
 
-sylph_dbs
-
 # Python
 *__pycache__
 
diff --git a/CHANGELOG.md b/CHANGELOG.md
index db8c17e..0ac5c0d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,8 +1,6 @@
 ## New
 
-- Code for generating sylph databases has been altered to incorporate ani_groups (based on taxid). This is only set for groups, not singletons
-- when making sylph databases the taxonomy tsv now have a header and gets the ani_group column
-- code for making virus sylph db now filters for human viruses
+- Remove Sylph
 
 ## 2.4.0
 
diff --git a/README.md b/README.md
index d5cb55d..ef78ade 100644
--- a/README.md
+++ b/README.md
@@ -6,7 +6,6 @@ This pipeline should be used to perform check quality and trimming in sequence d
 * Nextflow (tested on version 23.04)
 * dependencies in [env.yml](env.yml)
 * Kraken2 [Standard dataset](https://benlangmead.github.io/aws-indexes/k2) (tested with Standard-8 from 2023/06/05).
-* For sylph: pre-built indexes and associated metadata.
 
 ## Running Pipeline ##
 Parameters:
@@ -14,11 +13,9 @@ Parameters:
 - **input_dir** = A directory containing input fastq.gz files
 - **seq_platform** = Sequencing platform `illumina` or `ont`
 - **kraken2_db_path** = Path to the kraken2 dataset
-- **workflow** = `sylph`, `flu`, or `myco`. `speciated` is deprecated.
+- **workflow** = `flu`, or `myco`. `speciated` is deprecated.
 - **mem_map** (Optional) = Use Kraken 2 memory mapping (requires preloading kraken2 db `cp -r <path_to_kraken2_db> /dev/shm`) `true` or `false`
 - **publish_dir** (Optional) If set will output files to directory provided.
-- **sylph_dbs** = Path to sylph database(s). See [here](https://github.com/bluenote-1577/sylph/wiki/Pre%E2%80%90built-databases)
-- **sylph_db_taxonomy_files** = Path taxonomy file(s) for sylph db. Should be tsv (optionally gzipped)
 
 See parameters with:
 ```bash
@@ -56,56 +53,6 @@ cp -r kraken_index /dev/shm/
 kraken2 --db /dev/shm/kraken_index --memory-mapping ...
 ```
 
-## Sylph
-
-Sylph is a k-mer based classification system that processes all the reads in one go, rather than classifying per read.
-It can accept multiple databases, so to incorporate fungi or viruses an extra database can be provided rather than needing to rebuild a single db.
-To use multiple databases it is easiest to set it in the `nextflow.config`:
-```bash
-params {
-  sylph_dbs = ["knowledge_bucket/sylph/refseq_bacteria_2025-08-04/refseq_bacteria_db_c200.syldb",
-              "knowledge_bucket/sylph/refseq_fungi_2025-08-04/refseq_fungi_db_c200.syldb",
-              "knowledge_bucket/sylph/refseq_viral_2025-08-04/refseq_viral_db_c100.syldb"]
-  sylph_db_taxonomy_files = ["knowledge_bucket/sylph/refseq_bacteria_2025-08-04/taxonomy.tsv.gz",
-                       "knowledge_bucket/sylph/refseq_fungi_2025-08-04/taxonomy.tsv.gz",
-                       "knowledge_bucket/sylph/refseq_viral_2025-08-04/taxonomy.tsv.gz"]
-}
-```
-
-The taxonomy file needs to fit the format required for [sylph-tax](https://sylph-docs.github.io/sylph-tax-custom-taxonomies/).
-As such it must be a two column TSV where the first column if the name of the fasta file, and the second column is the taxonomy string.
-From testing:
-- Can add a header without causing issues
-- Can add additional columns
-
-The taxonomy format for sylph-tax is the same as provided in the downloads from [GTDB](https://data.gtdb.aau.ecogenomic.org/releases/release226/226.0/)
-
-### Parameters
-There are two parameters used in the Sylph process:
-- `sylph_query_ani_threshold`: sets the minimum ani threshold from the query step. Sylph authors recommend 90.
-- `sylph_profile_ani_threshold`: sets the minimum ani threshold from the profile step. Sylph authors recommend 95.
-
-### Databases for use
-Preference is to go with NCBI over GTDB as it is more familiar to clinical users (Though GTDB likely works better).
-Likewise with viruses the focus should be on human pathogenic viruses rather than phages etc.
-
-In the knowledge bucket there are a variety of sylph databates.
-To use one in this pipeline requires the database itself plus a tsv with the taxonomy metadata.
-
-See [sylph_references](sylph_references/README.md) for details of creating databases from RefSeq (NCBI).
-
-Note: For database to be used in competitive mapping downstream it also requires a folder of the reference genomes to make a manifest from.
-As such the pre-built Sylph dbs are less useful except for GTDB which matches certain releases.
-
-### Data for tests
-Sylph tests expect a folder `sylph_dbs` containing the sylph [pre-built databases](https://github.com/bluenote-1577/sylph/wiki/Pre%E2%80%90built-databases) for testing.
-These are included in the knowledge bucket in the sylph directory. Specifically uses:
-- `gtdb-r220-c1000-dbv1.syldb` and `gtdb_r220_metadata.tsv.gz`
-- `virus_imgvr_c200_v0.3.0.syldb` and `virus_imgvr_4.1_metadata.tsv.gz`
-
-The c1000 means that the k-mers are sampled every 1000bp making it smaller than c200, and so useful for testing.
-The metadata/taxonomy file can be optionally gzipped.
-
 
 ## Development/Install
 The python side of this repo forms a python project.
diff --git a/env.yml b/env.yml
index e5c9c77..bc08a2a 100644
--- a/env.yml
+++ b/env.yml
@@ -11,5 +11,3 @@ dependencies:
 - just=1.40.0
 - bracken=2.9
 - pytest=8.3.2
-- sylph=0.8.0
-- sylph-tax=1.1.2
diff --git a/main.nf b/main.nf
index 8ff1eb2..4db0431 100644
--- a/main.nf
+++ b/main.nf
@@ -4,7 +4,6 @@ include { fastp } from './process/quality_check.nf'
 include { kraken2 ; summarise_taxa ; bracken_summarise_taxa } from './process/kraken2.nf'
 include { filter_myco ; filter_flu } from './process/filter_reads.nf'
 include { has_enough_reads } from './process/has_enough_reads.nf'
-include { sylph } from './process/sylph.nf'
 
 // Parameters
 params.input_paired_suffix = "*_{1,2}.fastq.gz"
@@ -15,8 +14,6 @@ params.gatekeeper_illumina_min_num_reads = 10000
 params.gatekeeper_ont_min_num_reads = 1000
 params.gatekeeper_confidence_threshold = 0.00
 params.gatekeeper_taxa_summary_threshold = 0.5
-params.sylph_query_ani_threshold = 90
-params.sylph_profile_ani_threshold = 95
 
 workflow {
     if (params.help) {
@@ -27,12 +24,10 @@ workflow {
 
             Parameters:
             ------------------------------------------------------------------------
-            --workflow    workflow to run: speciate, myco, sylph, speciate_detailed
+            --workflow    workflow to run: speciate, myco, speciate_detailed
             --input_dir    Path to directory containing input fastq files
             --seq_platform    sequencing platform: illumina or ont
             --kraken2_db_path   Path to the kraken dataset directory
-            --sylph_db    Path to the sylph database
-            --sylph_db_taxonomy    Path to the sylph database taxonomy metadata
 
             Optional:
             --mem_map    If 'true' use memory mapping for kraken2. See README for details
@@ -43,12 +38,12 @@ workflow {
     }
 
     if (params.seq_platform == 'ont') {
-        input_files = Channel.fromPath("${params.input_dir}/${params.input_single_suffix}", checkIfExists: true)
+        input_files = channel.fromPath("${params.input_dir}/${params.input_single_suffix}", checkIfExists: true)
             .ifEmpty { error("cannot find any reads matching ${params.input_single_suffix} in ${params.input_dir}") }
             .map { it -> tuple(it.simpleName, it) }
     }
     else if (params.seq_platform == 'illumina') {
-        input_files = Channel.fromFilePairs(
+        input_files = channel.fromFilePairs(
                 "${params.input_dir}/${params.input_paired_suffix}",
                 flat: false,
                 checkIfExists: true,
@@ -57,12 +52,12 @@ workflow {
             .ifEmpty { error("cannot find any reads matching ${params.input_paired_suffix} in ${params.input_dir}") }
     }
 
-    kraken2_db_path = Channel.fromPath(params.kraken2_db_path).first()
+    kraken2_db_path = channel.fromPath(params.kraken2_db_path).first()
 
     check_seq_platform(params.seq_platform, input_files)
 
     if (params.workflow == 'speciate') {
-        log.info("Speciate workflow is deprecated, consider sylph instead")
+        log.info("Speciate workflow is deprecated, consider sylph instead within competitive mapping")
         gatekeeper_speciate(input_files, kraken2_db_path, params.seq_platform)
     }
     else if (params.workflow == 'myco') {
@@ -71,9 +66,6 @@ workflow {
     else if (params.workflow == 'flu') {
         gatekeeper_flu(input_files, kraken2_db_path, params.seq_platform)
     }
-    else if (params.workflow == 'sylph') {
-        gatekeeper_sylph(input_files, params.sylph_dbs, params.sylph_db_taxonomy_files, params.seq_platform)
-    }
     else {
         error("Invalid workflow: ${params.workflow}")
     }
@@ -169,28 +161,6 @@ workflow gatekeeper_flu {
     gatekeeper_report = filter_flu.out.gatekeeper_report_json
 }
 
-workflow gatekeeper_sylph {
-    take:
-    fastq_files
-    sylph_dbs
-    sylph_db_taxonomy_files
-    seq_platform
-
-    main:
-    sylph(
-        fastq_files,
-        sylph_dbs,
-        sylph_db_taxonomy_files,
-        seq_platform,
-        params.sylph_query_ani_threshold,
-        params.sylph_profile_ani_threshold,
-    )
-
-    emit:
-    sylph_query = sylph.out.sylph_query
-    sylph_report = sylph.out.sylph_report
-    taxonomy_report = sylph.out.taxonomy_report
-}
 
 def check_seq_platform(seq_platform, fastq_files) {
     def seq_platforms = ['ont', 'illumina']
diff --git a/minimal_files.txt b/minimal_files.txt
index eb7e7af..b50571c 100644
--- a/minimal_files.txt
+++ b/minimal_files.txt
@@ -7,5 +7,3 @@ process/templates/filter_myco.sh
 process/templates/filter_flu.sh
 process/templates/run_fastp.sh
 process/templates/run_kraken.sh
-process/sylph.nf
-process/templates/run_sylph.sh
diff --git a/process/sylph.nf b/process/sylph.nf
deleted file mode 100644
index 76de1b4..0000000
--- a/process/sylph.nf
+++ /dev/null
@@ -1,36 +0,0 @@
-process sylph {
-    publishDir "${params.publish_dir}", enabled: params.publish_dir != "", mode: "copy", saveAs: { filename -> sample_name + "_" + filename }
-    maxRetries 5
-
-    container {
-        params.test_container_gatekeeper == "" ? params.container_prefix + '/gpas/gatekeeper_pipeline:37bfc21' : params.test_container_gatekeeper
-    }
-    cpus 4
-    memory { 14.GB * task.attempt }
-
-    pod label: "name", value: "gatekeeper_pipeline:sylph"
-    pod label: "sample_id", value: "${params.sample_id}"
-    pod label: "run_id", value: "${params.run_id}"
-
-    input:
-    tuple val(sample_name), path(fqs)
-    // Use fixed name to avoid name conflicts.
-    // Can use multiple databases
-    path "database??.syldb"
-    path "taxonomies?/*"
-    val seq_platform
-    val query_ani_threshold
-    val profile_ani_threshold
-
-    output:
-    tuple val(sample_name), path(sylph_query), emit: sylph_query
-    tuple val(sample_name), path(sylph_report), emit: sylph_report
-    tuple val(sample_name), path(taxonomy_report), emit: taxonomy_report
-
-    script:
-    sylph_query = "sylph_query.tsv"
-    sylph_report = "sylph_report.tsv"
-    taxonomy_report = "taxonomy_report.tsv"
-
-    template('run_sylph.sh')
-}
diff --git a/process/templates/run_sylph.sh b/process/templates/run_sylph.sh
deleted file mode 100644
index 965a50f..0000000
--- a/process/templates/run_sylph.sh
+++ /dev/null
@@ -1,34 +0,0 @@
-
-if [ $seq_platform == 'ont' ]
-then
-    sylph sketch -t ${task.cpus} -c 100 -r $fqs
-elif [ $seq_platform == 'illumina' ]
-then
-    sylph sketch -t ${task.cpus} -c 100 \
-        -1 ${fqs[0]} -2 ${fqs[1]}
-fi
-# either way a file ending .sylsp is created
-
-sylph query -t ${task.cpus} -m ${query_ani_threshold} \
-    -o ${sylph_query} database*.syldb *.sylsp
-
-sylph profile -u -t ${task.cpus} -m ${profile_ani_threshold} \
-    -o ${sylph_report} database*.syldb *.sylsp
-
-
-if [[ \$(wc -l <${sylph_report}) -le 1 ]]
-then
-    echo "Sylph failed to generate a profile report"
-    echo "Generating a dummy taxonomy report"
-    if [ $seq_platform == 'ont' ]
-    then
-        echo -e "#SampleID\t${fqs}" > ${taxonomy_report}
-    elif [ $seq_platform == 'illumina' ]
-    then
-        echo -e "#SampleID\t${fqs[0]}" > ${taxonomy_report}
-    fi
-    echo -e "clade_name\trelative_abundance\tsequence_abundance\tANI (if strain-level)\tCoverage (if strain-level)" >> ${taxonomy_report}
-else
-    sylph-tax taxprof ${sylph_report} -t taxonomies*/* -o taxo_
-    cat taxo_* > ${taxonomy_report}
-fi
diff --git a/pyproject.toml b/pyproject.toml
index 62135af..66c4a28 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -55,5 +55,4 @@ version_files = [
     "process/kraken2.nf",
     "process/quality_check.nf",
     "process/filter_reads.nf",
-    "process/sylph.nf",
 ]
diff --git a/sylph_references/.gitignore b/sylph_references/.gitignore
deleted file mode 100644
index 6744e18..0000000
--- a/sylph_references/.gitignore
+++ /dev/null
@@ -1,14 +0,0 @@
-assembly_summary_refseq.txt
-ncbi_taxonomy/
-virushostdb.daily.tsv
-
-*download/
-*download.sh
-*metadata.csv
-*rsync_file_list.txt
-*taxonomy.tsv
-*taxonomy.tsv.gz
-*ani_edge_list.tsv
-*.syldb
-*genome_paths.tsv
-genomes/
diff --git a/sylph_references/README.md b/sylph_references/README.md
deleted file mode 100644
index 4428e76..0000000
--- a/sylph_references/README.md
+++ /dev/null
@@ -1,120 +0,0 @@
-# Making Reference databases for Sylph
-
-## Currently available databases
-These are available in the sp3dev knowledge bucket
-
-Sylph pre built (options)[https://github.com/bluenote-1577/sylph/wiki/Pre%E2%80%90built-databases]:
-- GTDB-220 release from 24/04/24 using c200 or c1000 `gtdb-r220-c200-dbv1.syldb`
-- RefSeq fungi from 25/07/24 using c200 `fungi-refseq-2024-07-25-c200-v0.3.syldb`
-- IMG/VR4.1 high-confidence vOTU reps using c200 `virus_imgvr_c200_v0.3.0.syldb`
-
-RefSeq databases built on 4/8/2025 using method below.
-
-TODO: Look into IMG/VR4.1 for making custom viral database
-
----
-
-## Dependencies:
-```bash
-conda env create -f env.yml
-conda activate ncbi_refseq
-```
-
-## Components of a database
-- a folder called `genomes` containing all the ref fastas
-- A file called `genome_paths.tsv` with paths to the genomes based on their filenames
-- a `.syldb` which is used by sylph and built from the genomes
-- `taxonomy.tsv` is a table going from ref file name to taxonomy
-- `metadata.csv` has the metadata for chosen genomes. The parts used by comp mapping is `accession`, `taxonomy`, `ani_group`. So the name used for the reference will be the species in the taxonomy column.
-
-## Walk through making databases
-This walks through the steps to produce sylph databases from NCBI.
-Note that it takes some time to download all the references!
-
-To make reference we need:
-- The list of reference genomes [assembly_summary_refseq.tsv](https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/).
-- The taxonomy [taxdump.tar.gz](https://ftp.ncbi.nih.gov/pub/taxonomy/). This should be extracted to a folder.
-Both of these are updated regularly, so note when they were collected and aim to be at the same time.
-- Viral-host database file [virushostdb.daily.tsv](https://www.genome.jp/ftp/db/virushostdb/). Only human viruses will be used.
-
-```bash
-wget https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/assembly_summary_refseq.txt
-# equivalently
-wget https://ftp.ncbi.nlm.nih.gov/genomes/refseq/assembly_summary_refseq.txt
-
-# For explanations
-wget https://ftp.ncbi.nlm.nih.gov/genomes/README_assembly_summary.txt
-
-mkdir ncbi_taxonomy
-wget https://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz
-tar -xvf taxdump.tar.gz -C ncbi_taxonomy
-rm taxdump.tar.gz
-
-wget https://www.genome.jp/ftp/db/virushostdb/virushostdb.daily.tsv
-```
-
-### Selecting reference genomes
-
-The reference genomes can then be selected:
-```bash
-python3 select_references.py assembly_summary_refseq.txt ncbi_taxonomy virushostdb.daily.tsv
-```
-
-For each group (bacteria/archaea, fungi, viral) it will produce a folder containing:
-- csv with metadata on all the references
-- a file to download all genomes
-- a taxonomy file used by sylph to produce taxonomy summary.
-
-Note: some references do not seem to have a taxonomy, this seems to be for very recently published refs.
-You may need to manually set these. Look online for that reference and fill in the taxonomy value accordingly. Or try again tomorrow.
-
-### Downloading reference genomes
-
-You can then download the samples (likely with screen) using:
-```bash
-cd refseq_bacteria
-mkdir -p genomes
-rsync -avP --files-from=rsync_file_list.txt rsync://ftp.ncbi.nlm.nih.gov/genomes ./genomes
-```
-
-This runs a single rsync command for all the files. You should just be able to run it again if connection drops (etc).
-
-At this point you should have a directory with all the reference genomes
-
-### Making resources for species identification pipeline
-To make the sylph database. Can lower c to make more sensitive (suggested for viruses is c=100)
-```bash
-find genomes -type f > sylph_file_list.txt
-sylph sketch -l sylph_file_list.txt -o refseq_bacteria_db -t 30 -c 200
-rm sylph_file_list.txt
-```
-to produce refseq_bacteria_db.syldb
-
-The `taxonomy.tsv` acts as the metadata for sylph. Can be gzipped to be smaller:
-```bash
-gzip -c taxonomy.tsv > taxonomy.tsv.gz
-```
-
-Will also require a `genome_paths.tsv` which is used by dynamic competitive mapping:
-```bash
-find genomes -type f | while read file_path; do
-    file_name=$(basename $file_path)
-    dir=$(dirname $file_path)
-    echo -e "$file_name\t$dir/" >> genome_paths.tsv
-done
-```
-
-
-### Making ANI groups
-
-Assign genomes to ANI groups. This adds "ani_group" and "in_group" to the metadata csv.
-```bash
-cd refseq_bacteria
-python3 ../assign_ani_groups.py -g genomes -m metadata.csv -t taxonomy.tsv --cpus 16 --ani_threshold 97
-```
-This also produces `ani_edge_list.tsv` which has the actual distances.
-
-The ani_groups are based on the lowest taxid within each group.
-If taxid's are not present than just uses row index.
-An ani group is only given if there is more than one genome in the group.
-Both metadata.csv and taxonomy.tsv get the ani_group column added.
diff --git a/sylph_references/assign_ani_groups.py b/sylph_references/assign_ani_groups.py
deleted file mode 100644
index 39fbb9b..0000000
--- a/sylph_references/assign_ani_groups.py
+++ /dev/null
@@ -1,129 +0,0 @@
-import argparse
-import os
-import subprocess
-from pathlib import Path
-
-import networkx as nx
-import pandas as pd
-
-
-def set_ani_distances(
-    genome_dir: str,
-    metadata: pd.DataFrame,
-    ani_threshold: float,
-    cpus: int,
-) -> pd.DataFrame:
-    """Get ANI distances between genomes using skani"""
-    with open("tmp_file_list.txt", "w", encoding="utf-8") as f:
-        for file in Path(genome_dir).rglob("*.fna.gz"):
-            f.write(str(file) + "\n")
-
-    command = (
-        f"skani triangle -E -t {cpus} --medium -l tmp_file_list.txt > ani_edge_list.tsv"
-    )
-    subprocess.run(command, shell=True, check=True)
-    ani_df = pd.read_csv("ani_edge_list.tsv", sep="\t")
-    os.remove("tmp_file_list.txt")
-
-    # filter ANI dataframe based on threshold
-    ani_df = ani_df[ani_df["ANI"] >= ani_threshold]
-
-    # get assembly accessions from file paths
-    ani_df["Ref"] = (
-        ani_df["Ref_file"].str.replace("_genomic.fna.gz", "").str.split("/").str[-1]
-    )
-    ani_df["Query"] = (
-        ani_df["Query_file"].str.replace("_genomic.fna.gz", "").str.split("/").str[-1]
-    )
-
-    # Ensure that both Ref and Query are in metadata
-    ani_df = ani_df[
-        ani_df["Ref"].isin(metadata["accession"])
-        & ani_df["Query"].isin(metadata["accession"])
-    ]
-
-    # build graph from filtered data
-    graph = nx.from_pandas_edgelist(ani_df, "Ref", "Query")
-
-    # Set initial ani_group as taxid (or row index if no taxid)
-    if "taxid" in metadata.columns:
-        metadata["ani_group"] = metadata["taxid"]
-    else:
-        metadata["ani_group"] = metadata.index
-    metadata["in_group"] = False
-
-    # Assign ani_group based on connected components
-    for component in nx.connected_components(graph):
-        if len(component) <= 1:
-            continue
-        ani_group = min(
-            metadata.loc[metadata["accession"].isin(component), "ani_group"]
-        )
-        metadata.loc[metadata["accession"].isin(component), "ani_group"] = ani_group
-        metadata.loc[metadata["accession"].isin(component), "in_group"] = True
-
-    # If not in a group set ani_group to nan
-    metadata["ani_group"] = metadata["ani_group"].astype("Int64")
-    metadata.loc[~metadata["in_group"], "ani_group"] = pd.NA
-
-    front_cols = ["accession", "ani_group", "in_group"]
-    metadata = metadata[
-        front_cols + [col for col in metadata.columns if col not in front_cols]
-    ]
-
-    # sort by ani_group and accession
-    metadata.sort_values(by=["ani_group", "accession"], inplace=True)
-
-    return metadata
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Run skani triangle to create ani groups."
-    )
-    parser.add_argument(
-        "-g",
-        "--genome_dir",
-        required=True,
-        help="Directory containing gzipped fasta files",
-    )
-    parser.add_argument(
-        "-m", "--metadata", required=True, help="CSV file with metadata"
-    )
-    parser.add_argument(
-        "-t", "--taxonomy", required=True, help="TSV file with taxonomy"
-    )
-    parser.add_argument(
-        "-c", "--cpus", type=int, default=8, help="Number of CPUs to use for skani"
-    )
-    parser.add_argument(
-        "-a",
-        "--ani_threshold",
-        type=float,
-        default=95,
-        help="ANI threshold for filtering (default: 95)",
-    )
-    args = parser.parse_args()
-
-    metadata = pd.read_csv(args.metadata)
-
-    metadata = set_ani_distances(
-        genome_dir=args.genome_dir,
-        metadata=metadata,
-        ani_threshold=args.ani_threshold,
-        cpus=args.cpus,
-    )
-
-    metadata.to_csv(args.metadata, index=False)
-
-    taxonomy = pd.read_csv(args.taxonomy, sep="\t", usecols=["accession", "taxonomy"])
-    taxonomy = taxonomy.merge(
-        metadata[["accession", "ani_group"]], on="accession", how="left"
-    )
-    taxonomy.to_csv(args.taxonomy, sep="\t", index=False)
-
-    print("ANI groups assigned and metadata updated.")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/sylph_references/check_for_missing.py b/sylph_references/check_for_missing.py
deleted file mode 100644
index f43955b..0000000
--- a/sylph_references/check_for_missing.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import argparse
-import os
-
-import pandas as pd
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Check for missing genome files.")
-    parser.add_argument("input_dir", help="Directory containing .fna.gz files")
-    parser.add_argument("input_csv", help="CSV file with accession column")
-    args = parser.parse_args()
-
-    df = pd.read_csv(args.input_csv)
-    if "assembly_accession" not in df.columns:
-        print("Error: 'assembly_accession' column not found in CSV.")
-        return
-
-    missing = []
-    for accession in df["assembly_accession"]:
-        filename = f"{accession}_genomic.fna.gz"
-        filepath = os.path.join(args.input_dir, filename)
-        if not os.path.isfile(filepath):
-            missing.append(accession)
-
-    if not missing:
-        print("All genome files are present.")
-
-    missing_df = df[df["assembly_accession"].isin(missing)]
-    missing_df.to_csv("missing_genomes.csv", index=False)
-    print(
-        f"Missing genome files saved to 'missing_genomes.csv'. Found {len(missing)} missing files."
-    )
-
-
-if __name__ == "__main__":
-    main()
diff --git a/sylph_references/env.yml b/sylph_references/env.yml
deleted file mode 100644
index dc5fb75..0000000
--- a/sylph_references/env.yml
+++ /dev/null
@@ -1,14 +0,0 @@
-name: ncbi_refseq
-channels:
- - conda-forge
- - bioconda
- - defaults
-dependencies:
-  - "python>=3.11,<4.0"
-  - pandas>=2.2.0
-  - sylph=0.8.0
-  - skani
-  - pip
-  - pip:
-      - git+https://github.com/GlobalPathogenAnalysisService/kraken2_analysis.git
-      - networkx[default]
diff --git a/sylph_references/make_dbs.sh b/sylph_references/make_dbs.sh
deleted file mode 100644
index c739235..0000000
--- a/sylph_references/make_dbs.sh
+++ /dev/null
@@ -1,30 +0,0 @@
-# Script for doing the steps from downloading refs onwards
-
-threads=100
-
-for group in fungi bacteria viral
-do
-    cd refseq_${group}
-    mkdir -p genomes
-    rsync -avP --files-from=rsync_file_list.txt rsync://ftp.ncbi.nlm.nih.gov/genomes ./genomes
-
-    c=200
-    if [ "$group" == "viral" ]; then
-        c=100
-    fi
-    find genomes -type f > sylph_file_list.txt
-    sylph sketch -l sylph_file_list.txt -o refseq_${group}_db -t ${threads} -c ${c}
-    rm sylph_file_list.txt
-
-    gzip -c taxonomy.tsv > taxonomy.tsv.gz
-
-    find genomes -type f | while read file_path; do
-        file_name=$(basename $file_path)
-        dir=$(dirname $file_path)
-        echo -e "$file_name\t$dir/" >> genome_paths.tsv
-    done
-
-    python3 ../assign_ani_groups.py -g genomes/ -m metadata.csv --cpus ${threads} -a 97
-
-    cd ..
-done
diff --git a/sylph_references/select_references.py b/sylph_references/select_references.py
deleted file mode 100644
index 7dcea86..0000000
--- a/sylph_references/select_references.py
+++ /dev/null
@@ -1,209 +0,0 @@
-import argparse
-import os
-
-import pandas as pd
-from k2_analysis.kraken_tree import Tree, ncbi_taxonomy_to_tree
-
-PROVIDED_COLS = [
-    "assembly_accession",
-    "bioproject",
-    "biosample",
-    "wgs_master",
-    "refseq_category",
-    "taxid",
-    "species_taxid",
-    "organism_name",
-    "infraspecific_name",
-    "isolate",
-    "version_status",
-    "assembly_level",
-    "release_type",
-    "genome_rep",
-    "seq_rel_date",
-    "asm_name",
-    "asm_submitter",
-    "gbrs_paired_asm",
-    "paired_asm_comp",
-    "ftp_path",
-    "excluded_from_refseq",
-    "relation_to_type_material",
-    "asm_not_live_date",
-    "assembly_type",
-    "group",
-    "genome_size",
-    "genome_size_ungapped",
-    "gc_percent",
-    "replicon_count",
-    "scaffold_count",
-    "contig_count",
-    "annotation_provider",
-    "annotation_name",
-    "annotation_date",
-    "total_gene_count",
-    "protein_coding_gene_count",
-    "non_coding_gene_count",
-    "pubmed_id",
-]
-
-SELECTED_COLS = [
-    "assembly_accession",
-    "bioproject",
-    "biosample",
-    "refseq_category",
-    "taxid",
-    "species_taxid",
-    "organism_name",
-    "isolate",
-    "version_status",
-    "assembly_level",
-    "genome_rep",
-    "relation_to_type_material",
-    "group",
-    "genome_size",
-    "contig_count",
-    "annotation_provider",
-    "ftp_path",
-]
-
-LEVEL_CODES = {
-    "superkingdom": "d",
-    "phylum": "p",
-    "class": "c",
-    "order": "o",
-    "family": "f",
-    "genus": "g",
-    "species": "s",
-}
-
-
-def get_taxonomy(node: Tree | None) -> list[str]:
-    if node is None:
-        return ["unknown_taxa"]
-
-    if node.level_code in ["R"] or node.name == "cellular organisms":
-        return []
-
-    level_code = LEVEL_CODES.get(node.level_code, "x")
-
-    taxa_string = level_code + "__" + str(node.name)
-    return get_taxonomy(node.parent) + [taxa_string]
-
-
-def main():
-    # parse arguments
-    parser = argparse.ArgumentParser(
-        description="Select reference genomes from refseq metadata"
-    )
-    parser.add_argument("metadata", type=str, help="Path to the metadata file")
-    parser.add_argument(
-        "ncbi_taxonomy_dir",
-        type=str,
-        help="Path to directory with names.dmp and nodes.dmp",
-    )
-    parser.add_argument(
-        "virushostdb",
-        type=str,
-        help="Path to the viral-host database file (virushostdb.daily.tsv)",
-    )
-    args = parser.parse_args()
-
-    df = pd.read_csv(
-        args.metadata, sep="\t", skiprows=2, names=PROVIDED_COLS, usecols=SELECTED_COLS
-    )
-
-    print("groups: ", df["group"].unique())
-
-    df = df[df["group"].isin(["bacteria", "archaea", "fungi", "viral"])]
-    df = df[df["version_status"] == "latest"]
-    refs = df[
-        (df["refseq_category"] == "reference genome") | (df["group"] == "viral")
-    ].copy()
-
-    missing_ftp = refs[refs["ftp_path"].isna()]
-    if not missing_ftp.empty:
-        print(
-            f"Warning: {len(missing_ftp)} samples have no ftp_path and will be excluded from the download list"
-        )
-        missing_ftp.to_csv("missing_ftp.csv", index=False)
-        print("Missing ftp paths saved to missing_ftp.csv")
-
-        refs = refs[~refs["ftp_path"].isna()]
-
-    def get_rsync_path(ftp_path):
-        accession = ftp_path.split("/")[-1]
-        return f"{ftp_path.replace('https://ftp.ncbi.nlm.nih.gov/genomes/', '')}/{accession}_genomic.fna.gz"
-
-    refs["rsync_path"] = refs.apply(
-        lambda row: get_rsync_path(row["ftp_path"]),
-        axis=1,
-    )
-
-    refs["accession"] = refs["ftp_path"].str.split("/").str[-1]
-    refs = refs[["accession"] + [c for c in refs.columns if c not in ["accession"]]]
-
-    taxonomy = ncbi_taxonomy_to_tree(
-        f"{args.ncbi_taxonomy_dir}/nodes.dmp", f"{args.ncbi_taxonomy_dir}/names.dmp"
-    )
-    taxa_to_node = {taxon.taxid: taxon for taxon in taxonomy.to_list()}
-    print("Taxonomy loaded")
-    refs["taxonomy"] = refs["taxid"].apply(
-        lambda x: ";".join(get_taxonomy(taxa_to_node.get(x, None)))
-    )
-
-    unknown_taxa = refs[refs["taxonomy"] == "unknown_taxa"]
-    if not unknown_taxa.empty:
-        print(
-            f"Warning: {len(unknown_taxa)} samples have no taxonomy please set manually."
-        )
-        unknown_taxa.to_csv("unknown_taxa.csv", index=False)
-        print("Unknown taxa saved to unknown_taxa.csv")
-
-    def save_outputs(df_to_save: pd.DataFrame, prefix: str):
-        os.makedirs(f"refseq_{prefix}", exist_ok=True)
-        df_to_save.drop(columns=["rsync_path", "ftp_path"], inplace=False).to_csv(
-            f"refseq_{prefix}/metadata.csv", index=False
-        )
-
-        df_to_save[["rsync_path"]].to_csv(
-            f"refseq_{prefix}/rsync_file_list.txt", index=False, header=False
-        )
-
-        df_to_save[["accession", "taxonomy"]].to_csv(
-            f"refseq_{prefix}/taxonomy.tsv", sep="\t", index=False, header=True
-        )
-
-    bacteria = refs[refs["group"].isin(["bacteria", "archaea"])]
-    save_outputs(bacteria, "bacteria")
-
-    fungi = refs[refs["group"].isin(["fungi"])]
-    save_outputs(fungi, "fungi")
-
-    ## Viruses
-
-    viralhostdb = pd.read_csv(
-        args.virushostdb,
-        sep="\t",
-        usecols=["virus tax id", "virus name", "refseq id", "DISEASE", "host tax id"],
-    )
-    viralhostdb = viralhostdb[
-        viralhostdb["host tax id"] == 9606
-    ]  # Filter for human hosts
-    viralhostdb.rename(
-        columns={
-            "virus tax id": "taxid",
-            "virus name": "virus_name",
-            "refseq id": "refseq_ids",
-            "DISEASE": "disease",
-        },
-        inplace=True,
-    )
-    viralhostdb.drop(columns=["host tax id"], inplace=True)
-
-    # viruses are do not have refseq category
-    viral = refs[refs["group"].isin(["viral"])]
-    viral = viral.merge(viralhostdb, on="taxid", how="inner")
-    save_outputs(viral, "viral")
-
-
-if __name__ == "__main__":
-    main()
diff --git a/tests/nextflow/samples/clinic/sylph_report.tsv b/tests/nextflow/samples/clinic/sylph_report.tsv
deleted file mode 100644
index 09d632d..0000000
--- a/tests/nextflow/samples/clinic/sylph_report.tsv
+++ /dev/null
@@ -1,4 +0,0 @@
-Sample_file	Genome_file	Taxonomic_abundance	Sequence_abundance	Adjusted_ANI	True_cov	ANI_5-95_percentile	Eff_lambda	Lambda_5-95_percentile	Median_cov	Mean_cov_geq1	Containment_ind	Naive_ANI	kmers_reassigned	Contig_name
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/002/086/515/GCF_002086515.1_genomic.fna.gz	97.6912	97.1919	99.99	47.385	NA-NA	HIGH	NA-NA	36	36.637	4279/4287	99.99	0	NZ_MVHH01000001.1 Mycolicibacter arupensis strain DSM 44942 Mycobacterium_arupense_DSM44942_contig1, whole genome shotgun sequence
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/025/215/495/GCF_025215495.1_genomic.fna.gz	1.6754	1.4966	99.68	0.813	99.39-99.92	0.617	0.56-0.69	1	1.346	1600/3773	97.27	47	NZ_CP104302.1 Mycolicibacterium brumae strain ATCC 51384 chromosome, complete genome
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/000/195/955/GCF_000195955.2_genomic.fna.gz	0.6334	0.6258	99.55	0.307	98.94-100.06	0.233	0.20-0.28	1	1.129	785/4253	94.70	9	NC_000962.3 Mycobacterium tuberculosis H37Rv, complete genome
diff --git a/tests/nextflow/samples/clinic/sylph_taxonomy_report.tsv b/tests/nextflow/samples/clinic/sylph_taxonomy_report.tsv
deleted file mode 100644
index 64e4b23..0000000
--- a/tests/nextflow/samples/clinic/sylph_taxonomy_report.tsv
+++ /dev/null
@@ -1,14 +0,0 @@
-#SampleID	test_clinic_sample_1.fastq.gz	Taxonomies_used:['taxonomies1/gtdb_r220_metadata.tsv.gz']
-clade_name	relative_abundance	sequence_abundance	ANI (if strain-level)	 Coverage (if strain-level)
-d__Bacteria	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium	99.99999999999999	99.3143	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium arupense	97.6912	97.1919	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium brumae	1.6754	1.4966	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis	0.6334	0.6258	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium arupense|t__GCF_002086515.1	97.6912	97.1919	99.99	47.385
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium brumae|t__GCF_025215495.1	1.6754	1.4966	99.68	0.813
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis|t__GCF_000195955.2	0.6334	0.6258	99.55	0.307
diff --git a/tests/nextflow/samples/clinic/with_virus_sylph_report.tsv b/tests/nextflow/samples/clinic/with_virus_sylph_report.tsv
deleted file mode 100644
index 7b6939f..0000000
--- a/tests/nextflow/samples/clinic/with_virus_sylph_report.tsv
+++ /dev/null
@@ -1,7 +0,0 @@
-Sample_file	Genome_file	Taxonomic_abundance	Sequence_abundance	Adjusted_ANI	True_cov	ANI_5-95_percentile	Eff_lambda	Lambda_5-95_percentile	Median_cov	Mean_cov_geq1	Containment_ind	Naive_ANI	kmers_reassigned	Contig_name
-test_clinic_sample_1.fastq.gz	imgvr_reps.fna	26.0540	0.4168	100.00	50.018	NA-NA	HIGH	NA-NA	38	37.136	81/81	100.00	0	IMGVR_UViG_3300048835_000078|3300048835|Ga0498919_0008194
-test_clinic_sample_1.fastq.gz	imgvr_reps.fna	24.6828	1.0613	98.55	47.385	NA-NA	HIGH	NA-NA	36	36.156	141/222	98.55	81	IMGVR_UViG_2636415716_000002|2636415716|2636450064|114-49182
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/002/086/515/GCF_002086515.1_genomic.fna.gz	24.6828	96.0894	99.95	47.385	NA-NA	HIGH	NA-NA	36	36.668	4223/4287	99.95	56	NZ_MVHH01000001.1 Mycolicibacter arupensis strain DSM 44942 Mycobacterium_arupense_DSM44942_contig1, whole genome shotgun sequence
-test_clinic_sample_1.fastq.gz	imgvr_reps.fna	23.9971	0.3342	100.00	46.069	NA-NA	HIGH	NA-NA	35	35.463	67/67	100.00	0	IMGVR_UViG_2636415716_000003|2636415716|2636450084|42096-57988
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/025/215/495/GCF_025215495.1_genomic.fna.gz	0.4233	1.4796	99.68	0.813	99.39-99.92	0.617	0.56-0.69	1	1.346	1600/3773	97.27	47	NZ_CP104302.1 Mycolicibacterium brumae strain ATCC 51384 chromosome, complete genome
-test_clinic_sample_1.fastq.gz	gtdb_genomes_reps_r220/database/GCF/000/195/955/GCF_000195955.2_genomic.fna.gz	0.1600	0.6187	99.55	0.307	98.94-100.06	0.233	0.20-0.28	1	1.129	785/4253	94.70	9	NC_000962.3 Mycobacterium tuberculosis H37Rv, complete genome
diff --git a/tests/nextflow/samples/clinic/with_virus_sylph_taxonomy_report.tsv b/tests/nextflow/samples/clinic/with_virus_sylph_taxonomy_report.tsv
deleted file mode 100644
index 55a22b0..0000000
--- a/tests/nextflow/samples/clinic/with_virus_sylph_taxonomy_report.tsv
+++ /dev/null
@@ -1,25 +0,0 @@
-#SampleID	test_clinic_sample_1.fastq.gz	Taxonomies_used:['taxonomies1/gtdb_r220_metadata.tsv.gz', 'taxonomies2/virus_imgvr_4.1_metadata.tsv.gz']
-clade_name	relative_abundance	sequence_abundance	ANI (if strain-level)	 Coverage (if strain-level)
-r__Duplodnaviria	74.7339	1.8123	NA	NA
-d__Bacteria	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes|	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes||	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium	25.2661	98.1877	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes|||	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium arupense	24.6828	96.0894	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium brumae	0.4233	1.4796	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis	0.16	0.6187	NA	NA
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes||||	74.7339	1.8123	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium arupense|t__GCF_002086515.1	24.6828	96.0894	99.95	47.385
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium brumae|t__GCF_025215495.1	0.4233	1.4796	99.68	0.813
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis|t__GCF_000195955.2	0.16	0.6187	99.55	0.307
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes|||||t__IMGVR_UViG_3300048835_000078	26.054	0.4168	100.0	50.018
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes|||||t__IMGVR_UViG_2636415716_000002	24.6828	1.0613	98.55	47.385
-r__Duplodnaviria|k__Heunggongvirae|p__Uroviricota|c__Caudoviricetes|||||t__IMGVR_UViG_2636415716_000003	23.9971	0.3342	100.0	46.069
diff --git a/tests/nextflow/samples/ont_full/sylph_report.tsv b/tests/nextflow/samples/ont_full/sylph_report.tsv
deleted file mode 100644
index be08132..0000000
--- a/tests/nextflow/samples/ont_full/sylph_report.tsv
+++ /dev/null
@@ -1,2 +0,0 @@
-Sample_file	Genome_file	Taxonomic_abundance	Sequence_abundance	Adjusted_ANI	True_cov	ANI_5-95_percentile	Eff_lambda	Lambda_5-95_percentile	Median_cov	Mean_cov_geq1	Containment_ind	Naive_ANI	kmers_reassigned	Contig_name
-reads.fastq.gz	gtdb_genomes_reps_r220/database/GCF/000/195/955/GCF_000195955.2_genomic.fna.gz	100.0000	96.3226	99.96	15.070	NA-NA	HIGH	NA-NA	9	9.079	4196/4253	99.96	0	NC_000962.3 Mycobacterium tuberculosis H37Rv, complete genome
diff --git a/tests/nextflow/samples/ont_full/sylph_taxonomy_report.tsv b/tests/nextflow/samples/ont_full/sylph_taxonomy_report.tsv
deleted file mode 100644
index 9da3f8c..0000000
--- a/tests/nextflow/samples/ont_full/sylph_taxonomy_report.tsv
+++ /dev/null
@@ -1,10 +0,0 @@
-#SampleID	reads.fastq.gz	Taxonomies_used:['taxonomies1/gtdb_r220_metadata.tsv.gz']
-clade_name	relative_abundance	sequence_abundance	ANI (if strain-level)	 Coverage (if strain-level)
-d__Bacteria	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis	100.0	96.3226	NA	NA
-d__Bacteria|p__Actinomycetota|c__Actinomycetes|o__Mycobacteriales|f__Mycobacteriaceae|g__Mycobacterium|s__Mycobacterium tuberculosis|t__GCF_000195955.2	100.0	96.3226	99.96	15.07
diff --git a/tests/nextflow/sylph.nf.test b/tests/nextflow/sylph.nf.test
deleted file mode 100644
index 8e1122b..0000000
--- a/tests/nextflow/sylph.nf.test
+++ /dev/null
@@ -1,175 +0,0 @@
-nextflow_process {
-    name "Test Process Sylph"
-    script "process/sylph.nf"
-    process "sylph"
-
-    test("Illumina - sylph should run on a sample") {
-        tag 'illumina'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', [file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_1.fastq.gz"), file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_2.fastq.gz")]]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb")]
-                input[2] = [file("$projectDir/sylph_dbs/gtdb_r220_metadata.tsv.gz")]
-                input[3] = 'illumina'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/clinic/sylph_report.tsv").md5)
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/clinic/sylph_taxonomy_report.tsv").md5)
-            }
-        }
-    }
-
-    test("Illumina - sylph should run with edited taxonomy metadata") {
-        tag 'illumina'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', [file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_1.fastq.gz"), file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_2.fastq.gz")]]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb")]
-                input[2] = [file("$projectDir/tests/nextflow/other_files/myco_taxonomy_edited.gz")]
-                input[3] = 'illumina'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/clinic/sylph_report.tsv").md5)
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-                assert path(get(1)).readLines().drop(1) == path("$projectDir/tests/nextflow/samples/clinic/sylph_taxonomy_report.tsv").readLines().drop(1)
-            }
-        }
-    }
-
-    test("Illumina - sylph should run on an empty sample") {
-        tag 'illumina'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', [file("$projectDir/tests/nextflow/samples/empty_samples/reads_1.fastq.gz"), file("$projectDir/tests/nextflow/samples/empty_samples/reads_2.fastq.gz")]]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb")]
-                input[2] = [file("$projectDir/sylph_dbs/gtdb_r220_metadata.tsv.gz")]
-                input[3] = 'illumina'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-            }
-        }
-    }
-
-    test("Illumina - sylph should run on multiple dbs") {
-        tag 'illumina'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', [file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_1.fastq.gz"), file("$projectDir/tests/nextflow/samples/clinic/test_clinic_sample_2.fastq.gz")]]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb"), file("$projectDir/sylph_dbs/virus_imgvr_c200_v0.3.0.syldb")]
-                input[2] = [file("$projectDir/sylph_dbs/gtdb_r220_metadata.tsv.gz"), file("$projectDir/sylph_dbs/virus_imgvr_4.1_metadata.tsv.gz")]
-                input[3] = 'illumina'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/clinic/with_virus_sylph_report.tsv").md5)
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/clinic/with_virus_sylph_taxonomy_report.tsv").md5)
-            }
-        }
-    }
-
-    test("ONT - should run on a sample") {
-        tag 'ont'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', file("$projectDir/tests/nextflow/samples/ont_full/reads.fastq.gz")]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb")]
-                input[2] = [file("$projectDir/sylph_dbs/gtdb_r220_metadata.tsv.gz")]
-                input[3] = 'ont'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/ont_full/sylph_report.tsv").md5)
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-                assert (path(get(1)).md5 == path("$projectDir/tests/nextflow/samples/ont_full/sylph_taxonomy_report.tsv").md5)
-            }
-        }
-    }
-
-    test("ONT - sylph should run on an empty sample") {
-        tag 'ont'
-        when {
-            process{
-                """
-                input[0] = ['sample_test', file("$projectDir/tests/nextflow/samples/empty_samples/reads_1.fastq.gz")]
-                input[1] = [file("$projectDir/sylph_dbs/gtdb-r220-c1000-dbv1.syldb")]
-                input[2] = [file("$projectDir/sylph_dbs/gtdb_r220_metadata.tsv.gz")]
-                input[3] = 'ont'
-                input[4] = 90
-                input[5] = 95
-                """
-            }
-        }
-
-        then {
-            assert process.success
-
-            with(process.out.sylph_report.get(0)) {
-                assert get(1).contains("sylph_report.tsv")
-            }
-            with(process.out.taxonomy_report.get(0)) {
-                assert get(1).contains("taxonomy_report.tsv")
-            }
-        }
-    }
-}