Add Boltz

CHANGELOG.md

@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[PR ##205](https://github.com/nf-core/proteinfold/pull/205)] - Change input schema from `sequence,fasta` to `id,fasta`.
 - [[PR #210](https://github.com/nf-core/proteinfold/pull/210)]- Moving post-processing logic to a subworkflow, change wave images pointing to oras to point to https and refactor module to match nf-core folder structure.
 - [[#214](https://github.com/nf-core/proteinfold/issues/214)]- Fix colabfold image to run in cpus after [#188](https://github.com/nf-core/proteinfold/issues/188) fix.
+- [[#229](https://github.com/nf-core/proteinfold/issues/229)]- Add Boltz pipeline [PR #230](https://github.com/nf-core/proteinfold/pull/230).
 
 ## [[1.1.1](https://github.com/nf-core/proteinfold/releases/tag/1.1.1)] - 2025-07-30
 

conf/dbs.config

@@ -21,6 +21,8 @@ params {
     pdb_seqres_link          = 'https://files.wwpdb.org/pub/pdb/derived_data/pdb_seqres.txt'
     uniprot_sprot_link       = 'https://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz'
     uniprot_trembl_link      = 'https://ftp.ebi.ac.uk/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz'
+    boltz_ccd_link           = 'https://huggingface.co/boltz-community/boltz-1/resolve/main/ccd.pkl'
+    boltz_model_link         = 'https://huggingface.co/boltz-community/boltz-1/resolve/main/boltz1.ckpt'
 
     // Alphafold paths
     bfd_path                 = "${params.alphafold2_db}/bfd/*"

main.nf

@@ -27,6 +27,10 @@ if (params.mode.toLowerCase().split(",").contains("esmfold")) {
     include { PREPARE_ESMFOLD_DBS } from './subworkflows/local/prepare_esmfold_dbs'
     include { ESMFOLD             } from './workflows/esmfold'
 }
+if (params.mode.toLowerCase().split(",").contains("boltz")) {
+    include { PREPARE_BOLTZ_DBS } from './subworkflows/local/prepare_boltz_dbs'
+    include { BOLTZ } from './workflows/boltz'
+}
 
 include { PIPELINE_INITIALISATION          } from './subworkflows/local/utils_nfcore_proteinfold_pipeline'
 include { PIPELINE_COMPLETION              } from './subworkflows/local/utils_nfcore_proteinfold_pipeline'
@@ -205,6 +209,37 @@ workflow NFCORE_PROTEINFOLD {
         ch_report_input           = ch_report_input.mix(ESMFOLD.out.pdb_msa)
     }
 
+    //
+    // WORKFLOW: Run Boltz
+    //
+    if (params.mode.toLowerCase().split(",").contains("boltz")) {
+        PREPARE_BOLTZ_DBS(
+            params.boltz_ccd_path,
+            params.boltz_model_path,
+            params.boltz_ccd_link,
+            params.boltz_model_link
+        )
+        ch_versions = ch_versions.mix(PREPARE_BOLTZ_DBS.out.versions)
+
+        BOLTZ(
+            ch_samplesheet,
+            ch_versions,
+            PREPARE_BOLTZ_DBS.out.boltz_ccd,
+            PREPARE_BOLTZ_DBS.out.boltz_model
+        )
+        ch_versions = ch_versions.mix(BOLTZ.out.versions)
+        ch_report_input = ch_report_input.mix(
+            BOLTZ
+                .out
+                .msa
+                .join(BOLTZ.out.structures)
+                .join(BOLTZ.out.confidence)
+                .join(BOLTZ.out.plddt)
+                .map { it[0]["model"] = "boltz"; it }
+        )
+
+    }
+
     //
     // POST PROCESSING: generate visualisation reports
     //

modules/local/create_samplesheet/main.nf

@@ -0,0 +1,29 @@
+process CREATE_SAMPLESHEET_YAML {
+    tag "$meta.id"
+    label 'process_single'
+
+    container 'docker://nbtmsh/samplesheet-utils'
+
+    input:
+    tuple val(meta), path(samplesheet)
+
+    output:
+    tuple val(meta), path("*.yaml"), emit: samplesheet
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    """
+    create-samplesheet \\
+        --directory ./ \\
+        --yaml \
+        --output-file \$(sample-name --sanitise --index 0 ./*.fasta).yaml
+    """
+
+    stub:
+    """
+    echo "" > samplesheet.yaml
+    """
+}
+

modules/local/run_boltz/main.nf

@@ -0,0 +1,25 @@
+/*
+ * Run Alphafold2
+ */
+process RUN_BOLTZ {
+    tag "$meta.id"
+    label 'process_medium'
+
+    container "docker.io/nbtmsh/boltz:0.1.2"
+
+    input:
+    tuple val(meta), path(fasta)
+    path ('boltz1_conf.ckpt')
+    path ('ccd.pkl')
+
+    output:
+    path ("boltz_results_${fasta.baseName}/processed/msa/*.npz"), emit: msa
+    path ("boltz_results_${fasta.baseName}/processed/structures/*.npz"), emit: structures
+    path ("boltz_results_${fasta.baseName}/predictions/${fasta.baseName}/confidence*.json"), emit: confidence
+    path ("boltz_results_${fasta.baseName}/predictions/${fasta.baseName}/plddt_*.npz"), emit: plddt
+
+    script:
+    """
+    /opt/miniforge/envs/boltz/bin/boltz predict --use_msa_server --accelerator gpu "./${fasta.name}" --cache ./
+    """
+}

nextflow.config

@@ -47,6 +47,14 @@ params {
     uniref90_path               = null
     pdb_seqres_path             = null
     uniprot_path                = null
+
+	// Boltz links
+    boltz_ccd_link           = null
+    boltz_model_link         = null
+
+	// Boltz parameters
+    boltz_ccd_path              = null
+    boltz_model_path            = null
 
     // Colabfold parameters
     colabfold_server            = "webserver"

nextflow_schema.json

@@ -296,6 +296,35 @@
                 }
             }
         },
+        "boltz_options": {
+            "title": "Boltz DBs and model paths options",
+            "type": "object",
+            "fa_icon": "fas fa-database",
+            "description": "Paths used to provide model paths and weight paths to Boltz",
+
+            "properties": {
+                "boltz_ccd_link": {
+                    "type": "string",
+                    "description": "Link to download CCD file",
+                    "icon": "fas fa-link"
+                },
+                "boltz_model_link": {
+                    "type": "string",
+                    "description": "Link to download model file",
+                    "icon": "fas fa-link"
+                },
+                "boltz_ccd_path": {
+                    "type": "string",
+                    "description": "Path to CCD path",
+                    "icon": "fas folder-open"
+                },
+                "boltz_model_path": {
+                    "type": "string",
+                    "description": "Path to Model path",
+                    "icon": "fas folder-open"
+                }
+            }
+        },
         "alphafold2_dbs_and_parameters_link_options": {
             "title": "Alphafold2 DBs and parameters links options",
             "type": "object",

subworkflows/local/prepare_boltz_dbs.nf

@@ -0,0 +1,49 @@
+//
+// Download the files required for Boltz
+//
+
+include {
+          ARIA2 as ARIA2_BOLTZ_CCD
+          ARIA2 as ARIA2_BOLTZ_MODEL } from '../../modules/nf-core/aria2/main'
+
+workflow PREPARE_BOLTZ_DBS {
+    // TODO: Implement
+    take:
+    boltz_ccd
+    boltz_model
+    boltz_ccd_link
+    boltz_model_link
+
+    main:
+    ch_versions     = Channel.empty() 
+
+    if (boltz_ccd) {
+        ch_boltz_ccd = Channel.value(file(boltz_ccd))
+        ch_boltz_model = Channel.value(file(boltz_model))
+    } else {
+        ARIA2_BOLTZ_CCD(
+            [
+                [:],
+                boltz_ccd_link
+            ]
+        )
+        ch_boltz_ccd = ARIA2_BOLTZ_CCD.out.downloaded_file.map{ it[1] }
+        ch_versions = ch_versions.mix(ARIA2_BOLTZ_CCD.out.versions)
+
+        ARIA2_BOLTZ_MODEL(
+            [
+                [:],
+                boltz_model_link
+            ]
+        )
+        ch_boltz_model = ARIA2_BOLTZ_MODEL.out.downloaded_file.map{ it[1] }
+        ch_versions = ch_versions.mix(ARIA2_BOLTZ_MODEL.out.versions)
+    }
+
+    emit:
+    boltz_ccd    = ch_boltz_ccd
+    boltz_model  = ch_boltz_model
+    versions     = ch_versions
+}
+
+

workflows/boltz.nf

@@ -0,0 +1,75 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    IMPORT LOCAL MODULES/SUBWORKFLOWS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+//
+// MODULE: Loaded from modules/local/
+//
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    IMPORT NF-CORE MODULES/SUBWORKFLOWS
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+//
+// MODULE: Installed directly from nf-core/modules
+//
+include { MULTIQC } from '../modules/nf-core/multiqc/main'
+include { CREATE_SAMPLESHEET_YAML } from '../modules/local/create_samplesheet'
+
+//
+// SUBWORKFLOW: Consisting entirely of nf-core/modules
+//
+include { paramsSummaryMap       } from 'plugin/nf-schema'
+include { paramsSummaryMultiqc   } from '../subworkflows/nf-core/utils_nfcore_pipeline'
+include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pipeline'
+include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_proteinfold_pipeline'
+
+//
+// MODULE: Boltz
+//
+include { RUN_BOLTZ } from '../modules/local/run_boltz'
+
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    RUN MAIN WORKFLOW
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/
+
+workflow BOLTZ {
+
+    take:
+    ch_samplesheet  // channel: samplesheet read from --input
+    ch_versions     // channel: [ path(versions.yml) ]
+    ch_boltz_ccd    // channel: [ path(boltz_ccd) ]
+    ch_boltz_model  // channel: [ path(model) ]
+
+    main:
+    ch_multiqc_files = Channel.empty()
+    // CREATE_SAMPLESHEET_YAML
+    CREATE_SAMPLESHEET_YAML(
+        ch_samplesheet
+    )
+
+    // RUN_BOLTZ 
+    RUN_BOLTZ(
+        CREATE_SAMPLESHEET_YAML.out.samplesheet,
+        ch_boltz_model,
+        ch_boltz_ccd
+    )
+
+    emit:
+    versions   = ch_versions
+    msa        = RUN_BOLTZ.out.msa
+    structures = RUN_BOLTZ.out.structures
+    confidence = RUN_BOLTZ.out.confidence
+    plddt      = RUN_BOLTZ.out.plddt
+} 
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    THE END
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+*/