Configure foldseek pipeline for WES execution

- Update container image to harbor.cluster.omic.ai/omic/foldseek:latest
- Update default paths to /omic/eureka/foldseek/ PVC mount paths
- Add k8s profile with eureka-pvc storage
- Remove stageInMode copy and containerOptions for k8s compatibility
- Update params.json defaults to s3://omic/eureka/foldseek/ paths

main.nf

@@ -2,9 +2,9 @@
 
 nextflow.enable.dsl=2
 
-params.query = '/mnt/OmicNAS/private/old/olamide/foldseek/input/1CRN.pdb'
+params.query = '/omic/eureka/foldseek/input/1CRN.pdb'
-params.target = '/mnt/OmicNAS/private/old/olamide/foldseek/input/'
+params.target = '/omic/eureka/foldseek/input/'
-params.outdir = '/mnt/OmicNAS/private/old/olamide/foldseek/output/'
+params.outdir = '/omic/eureka/foldseek/output'
 params.mode = 'search'
 params.sensitivity = 9.5
 params.evalue = 0.001
@@ -14,10 +14,8 @@ params.coverage = 0.0
 params.format_output = 'query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits'
 
 process FOLDSEEK_SEARCH {
-    container 'foldseek:latest'
+    container 'harbor.cluster.omic.ai/omic/foldseek:latest'
-    containerOptions '-v /mnt:/mnt'
     publishDir params.outdir, mode: 'copy'
-    stageInMode 'copy'
 
     input:
         path query
@@ -47,10 +45,8 @@ process FOLDSEEK_SEARCH {
 }
 
 process FOLDSEEK_CLUSTER {
-    container 'foldseek:latest'
+    container 'harbor.cluster.omic.ai/omic/foldseek:latest'
-    containerOptions '-v /mnt:/mnt'
     publishDir params.outdir, mode: 'copy'
-    stageInMode 'copy'
 
     input:
         path structures
@@ -77,10 +73,8 @@ process FOLDSEEK_CLUSTER {
         """
 }
 process FOLDSEEK_MULTIMER_SEARCH {
-    container 'foldseek:latest'
+    container 'harbor.cluster.omic.ai/omic/foldseek:latest'
-    containerOptions '-v /mnt:/mnt'
     publishDir params.outdir, mode: 'copy'
-    stageInMode 'copy'
 
     input:
         path query
@@ -107,10 +101,8 @@ process FOLDSEEK_MULTIMER_SEARCH {
 }
 
 process FOLDSEEK_CREATEDB {
-    container 'foldseek:latest'
+    container 'harbor.cluster.omic.ai/omic/foldseek:latest'
-    containerOptions '-v /mnt:/mnt'
     publishDir params.outdir, mode: 'copy'
-    stageInMode 'copy'
 
     input:
         path structures

nextflow.config

@@ -1,18 +1,15 @@
-// Manifest for Nextflow metadata
 manifest {
-    name = 'Foldseek-Nextflow'
+    name = 'foldseek'
-    author = 'Generated from Foldseek repository'
+    author = 'Olamide'
-    homePage = 'https://github.com/steineggerlab/foldseek'
     description = 'Nextflow pipeline for Foldseek - Fast protein structure search and clustering'
     mainScript = 'main.nf'
     version = '1.0.0'
 }
 
-// Global default parameters
 params {
-    query = "/mnt/OmicNAS/private/old/olamide/foldseek/input/1CRN.pdb"
+    query = "/omic/eureka/foldseek/input/1CRN.pdb"
-    target = "/mnt/OmicNAS/private/old/olamide/foldseek/input/"
+    target = "/omic/eureka/foldseek/input/"
-    outdir = "/mnt/OmicNAS/private/old/olamide/foldseek/output"
+    outdir = "/omic/eureka/foldseek/output"
     mode = "search"
     sensitivity = 9.5
     evalue = 0.001
@@ -22,22 +19,30 @@ params {
     format_output = "query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits"
 }
 
-// Container configurations
 docker {
     enabled = true
-    runOptions = '-v /mnt:/mnt'
 }
 
-// Process configurations
 process {
+    container = 'harbor.cluster.omic.ai/omic/foldseek:latest'
     cpus = 4
     memory = '16 GB'
 }
 
-// Execution configurations
+profiles {
-executor {
+    standard {
-    $local {
+        docker {
-        cpus = 8
+            temp = 'auto'
-        memory = '32 GB'
+        }
+    }
+
+    k8s {
+        process {
+            executor = 'k8s'
+        }
+        k8s {
+            storageClaimName = 'eureka-pvc'
+            storageMountPath = '/omic/eureka'
+        }
     }
 }

params.json

@@ -0,0 +1,169 @@
+{
+    "params": {
+        "query": {
+            "type": "file",
+            "description": "Path to input protein structure files (PDB/mmCIF format)",
+            "default": "s3://omic/eureka/foldseek/input/1CRN.pdb",
+            "required": true,
+            "pipeline_io": "input",
+            "var_name": "params.query",
+            "examples": [
+                "s3://omic/eureka/foldseek/input/1CRN.pdb",
+                "s3://omic/eureka/foldseek/input/*.pdb"
+            ],
+            "pattern": ".*\\.(pdb|cif|mmcif)(\\.gz)?$",
+            "enum": [],
+            "validation": {},
+            "notes": "Can be a single PDB/mmCIF file or a pattern to match multiple files. Supports gzipped files."
+        },
+        "target": {
+            "type": "file",
+            "description": "Path to target database or directory for structure search",
+            "default": "s3://omic/eureka/foldseek/input/",
+            "required": true,
+            "pipeline_io": "input",
+            "var_name": "params.target",
+            "examples": [
+                "s3://omic/eureka/foldseek/input/",
+                "s3://omic/eureka/foldseek/databases/"
+            ],
+            "pattern": ".*",
+            "enum": [],
+            "validation": {},
+            "notes": "Can be a Foldseek database or a directory containing structure files."
+        },
+        "outdir": {
+            "type": "folder",
+            "description": "Directory for Foldseek output results",
+            "default": "s3://omic/eureka/foldseek/output",
+            "required": true,
+            "pipeline_io": "output",
+            "var_name": "params.outdir",
+            "examples": [
+                "s3://omic/eureka/foldseek/output"
+            ],
+            "pattern": ".*",
+            "enum": [],
+            "validation": {},
+            "notes": "Directory where all output files will be stored. Will be created if it doesn't exist."
+        },
+        "mode": {
+            "type": "string",
+            "description": "Operation mode for Foldseek pipeline",
+            "default": "search",
+            "required": true,
+            "pipeline_io": "parameter",
+            "var_name": "params.mode",
+            "examples": [
+                "search",
+                "cluster",
+                "multimersearch",
+                "createdb"
+            ],
+            "pattern": "^(search|cluster|multimersearch|createdb)$",
+            "enum": ["search", "cluster", "multimersearch", "createdb"],
+            "validation": {},
+            "notes": "search: structure search, cluster: clustering, multimersearch: complex search, createdb: create database"
+        },
+        "sensitivity": {
+            "type": "number",
+            "description": "Search sensitivity (higher = more sensitive but slower)",
+            "default": 9.5,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.sensitivity",
+            "examples": [
+                7.5,
+                9.5
+            ],
+            "pattern": "^[0-9]+(\\.[0-9]+)?$",
+            "enum": [],
+            "validation": {},
+            "notes": "Fast: 7.5, Default: 9.5. Range: 1.0 to 15.0"
+        },
+        "evalue": {
+            "type": "number",
+            "description": "E-value threshold for reporting matches",
+            "default": 0.001,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.evalue",
+            "examples": [
+                0.001,
+                0.01,
+                10
+            ],
+            "pattern": "^[0-9]+(\\.[0-9]+)?([eE][+-]?[0-9]+)?$",
+            "enum": [],
+            "validation": {},
+            "notes": "Lower values are more stringent. Default: 0.001"
+        },
+        "threads": {
+            "type": "integer",
+            "description": "Number of CPU threads to use",
+            "default": 4,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.threads",
+            "examples": [
+                4,
+                8,
+                16
+            ],
+            "pattern": "^[0-9]+$",
+            "enum": [],
+            "validation": {},
+            "notes": "More threads improve speed for larger searches."
+        },
+        "alignment_type": {
+            "type": "integer",
+            "description": "Type of structural alignment algorithm",
+            "default": 2,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.alignment_type",
+            "examples": [
+                0,
+                1,
+                2
+            ],
+            "pattern": "^[0-3]$",
+            "enum": [0, 1, 2, 3],
+            "validation": {},
+            "notes": "0: 3Di only, 1: TMalign (global), 2: 3Di+AA (default), 3: LoLalign"
+        },
+        "coverage": {
+            "type": "number",
+            "description": "Minimum fraction of aligned residues",
+            "default": 0.0,
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.coverage",
+            "examples": [
+                0.0,
+                0.5,
+                0.8
+            ],
+            "pattern": "^[0-1](\\.[0-9]+)?$",
+            "enum": [],
+            "validation": {},
+            "notes": "Range: 0.0 to 1.0. Higher values produce more global alignments."
+        },
+        "format_output": {
+            "type": "string",
+            "description": "Output format columns (comma-separated)",
+            "default": "query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits",
+            "required": false,
+            "pipeline_io": "parameter",
+            "var_name": "params.format_output",
+            "examples": [
+                "query,target,fident,evalue,bits",
+                "query,target,alntmscore,qtmscore,ttmscore"
+            ],
+            "pattern": ".*",
+            "enum": [],
+            "validation": {},
+            "notes": "Available columns: query, target, fident, alnlen, mismatch, gapopen, qstart, qend, tstart, tend, evalue, bits, alntmscore, qtmscore, ttmscore, lddt, prob"
+        }
+    }
+}