@datagrok/bio 2.11.30 → 2.11.33

package/files/tests/libraries/HELMmonomerSchema.json

@@ -0,0 +1,96 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "description": "HELM monomer JSON Schema draft v1",
+  "type": "object",
+  "properties": {
+    "symbol": {
+      "description": "Short name for the monomer. This will be displayed on the canvas.",
+	  "type": "string"
+    },
+    "name": {
+      "description": "Long name for the monomer. Generally an IUPAC or commonly used trivial chemical name.",
+	  "type": "string"
+    },
+    "molfile": {
+      "description": "Molfile with carriage returns escaped.", 
+	  "type": "string"
+    },
+    "author": {
+      "description": "Name of the person who entered the monomer information.",
+	  "type": "string"
+    },
+    "id": {
+      "description": "Unique ID for the monomer. There is no meaning associated with this ID value.",
+	  "type": "integer"
+    },
+    "rgroups": {
+      "description": "An array of the monomer R groups and required information.",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "id": {
+            "description": "meaningless identifier for the r group",
+            "type": "integer"
+          },
+          "alternateId": {
+            "description": "Descriptive ID for the R group consisting of the label and R group plus number",
+            "type": "string"
+          },
+          "label": {
+            "description": "R followed by an integer denoting the R group number",
+            "type": "string"
+          },
+          "capGroupName": {
+            "description": "A list of the atoms in the leaving group. This is descriptive, and exists to show the user the leaving group atoms",
+            "type": "string"
+          },
+          "capGroupSMILES": {
+            "description": "SMILES of the R group, uses atom mapping notation",
+            "type": "string"
+          }
+        },
+        "required": [
+          "alternateId",
+          "label",
+          "capGroupName",
+          "capGroupSMILES"
+        ]
+      }
+    },
+    "smiles": {
+      "description": "Canonical SMILES of the monomer including connection points.",
+      "type": "string"
+    },
+    "polymerType": {
+	   "description": "Type must be one of a fixed list of agreed polymer types.",
+	   "type": "string",
+	   "enum": ["RNA", "PEPTIDE", "CHEM"]
+    },
+    "naturalAnalog": {
+      "description": "Natural analogue of the monomer where available.",
+	  "type": "string"
+    },
+    "monomerType": {
+      "description": "Type of monomer from a fixed list of agreed monomer types.",
+	  "type": "string",
+	  "enum": ["Backbone", "Branch", "Terminal", "Undefined"]
+    },
+    "createDate": {
+      "description": "Date created.",
+	  "type": ["string", "null"]
+    }
+  },
+  "required": [
+    "symbol",
+    "name",
+    "molfile",
+    "author",
+    "id",
+    "rgroups",
+    "smiles",
+    "polymerType",
+    "monomerType",
+    "createDate"
+  ]
+}

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.11.30",
+  "version": "2.11.33",
   "description": "Bioinformatics support (import/export of sequences, conversion, visualization, analysis). [See more](https://github.com/datagrok-ai/public/blob/master/packages/Bio/README.md) for details.",
   "repository": {
     "type": "git",
@@ -34,11 +34,13 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.39.24",
+    "@datagrok-libraries/bio": "^5.39.25",
     "@datagrok-libraries/chem-meta": "^1.2.1",
-    "@datagrok-libraries/ml": "^6.4.7",
+    "@datagrok-libraries/ml": "^6.4.10",
     "@datagrok-libraries/tutorials": "^1.3.11",
-    "@datagrok-libraries/utils": "^4.1.43",
+    "ajv": "^8.12.0",
+    "ajv-errors": "^3.0.0",
+    "@datagrok-libraries/utils": "^4.1.44",
     "@datagrok-libraries/math": "^1.0.7",
     "cash-dom": "^8.0.0",
     "css-loader": "^6.7.3",
@@ -48,10 +50,13 @@
     "openchemlib": "6.0.1",
     "rxjs": "^6.5.5",
     "style-loader": "^3.3.1",
-    "wu": "latest",
-    "umap-js": "^1.3.3"
+    "umap-js": "^1.3.3",
+    "wu": "latest"
   },
   "devDependencies": {
+    "@datagrok/chem": "^1.8.11",
+    "@datagrok/dendrogram": "^1.2.22",
+    "@datagrok/helm": "^2.1.27",
     "@types/node": "^17.0.24",
     "@types/wu": "latest",
     "@typescript-eslint/eslint-plugin": "latest",
@@ -64,10 +69,7 @@
     "typescript": "^4.8.4",
     "webpack": "^5.76.3",
     "webpack-bundle-analyzer": "latest",
-    "webpack-cli": "^4.9.1",
-    "@datagrok/chem": "^1.8.11",
-    "@datagrok/helm": "^2.1.27",
-    "@datagrok/dendrogram": "^1.2.22"
+    "webpack-cli": "^4.9.1"
   },
   "scripts": {
     "link-api": "npm link datagrok-api",

package/scripts/sequence_generator.md

@@ -0,0 +1,48 @@
+# Sequence generator
+
+The utility generates clusters of macromolecule sequences to test SAR functionality. 
+Each cluster contains a randomly generated sequence motif.
+Each sequence has activity - a Gauss-distributed random value. 
+The utility can simulate activity cliffs - random changes in the conservative motif letters,
+leading to the significant change in the activity.
+Utility can simulate multiple experimental assays measuring activity, with different scales and noise levels.
+
+### Run options
+The utility can work in two modes:
+* Standalone command-line tool. Run the utility with `--help` key to get detailed help
+* Datagrok script. In this mode, Datagrok automatically generates utility UI.
+
+## Utility algorithm
+
+### Motif generation
+* Specify the sequence alphabet: DNA/RNA/Peptides/HELM file
+* Generate motif template
+  * Iterate through all positions in the motif
+  * With the probability `prob_any` it will be a non-conservative letter.
+    In this case, place the `?` code in this position.
+    The non-conservative letters can't reside on motif ends.
+  * Otherwise, generate a conservative letter
+    * Generate a random integer in range `[1-max_variants_cluster]` - the number of possible letters in this position.
+    * Randomly choose corresponding of letters from the alphabet.  
+* Generate cluster sequences by template
+  * Iterate through all motif template positions
+  * Take the letter from the list of allowed letters for the position
+* With the probability `cliff_probability` generate sequence cliff:
+  * Choose a conservative letters
+  * Mutate it to a random letter not present in the allowed template letters for this position.
+
+## Generation activities 
+
+The activity generation simulates experimental data from some real assay with noise and bias.
+* Generate random mean value for Gauss distribution for "ideal" activity generation. 
+    The `activity_range` parameter defines the range of ideal activities
+* Generate "ideal" activities from gauss distribution with sigma=1
+* Make activity cliffs for the of sequences:
+  * Calculate difference between generated activities
+  * Calculate `cliff_size` - random Gauss-distributed value   
+  * "Push apart" these values to ensure that the difference between them is 
+* Calculate "assay activities" for each assay
+  * Generate "noise" - Gauss-distributed value with a randomly chosen center    
+  * Calculate `real_activity = ideal_activity + noise*noise_level`
+    The `noise_level` is the ration of signal/noise for the assay
+  * Rescale the activity to fit in the requested assay scale