Merge pull request #38 from brianloyal/main

v1.13.0

Author: brianloyal

.gitlab-ci.yml

@@ -33,7 +33,7 @@ cfn-lint:
     - pip install -U cfn-lint
     - pip freeze
   script:
-    - cfn-lint -I infrastructure/cloudformation/*cfn*.yaml -i W3002
+    - cfn-lint -I infrastructure/cloudformation/*cfn*.yaml -i W3002 -i E1019 -i W1031
 
 cfn-nag:
   image:

CHANGELOG.md

@@ -7,11 +7,25 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [1.13.0] - 2025-03-14
+
+### 1.13.0 Update
+
+- Remove CodeCommit dependency
+
+### 1.13.0 Fixed
+
+- Resolve various cfn-lint issues
+- Update OpenFold dockerfile
+
+---
+
 ## [1.12.7] - 2024-03-14
 
 ### 1.12.7 Fixed
 
 - Updated S3 location for reference data
+- Added missing script to download ESM parameters
 
 ---
 

README.md

@@ -13,12 +13,10 @@
     4.2. [AlphaFold](#42-alphafold)  
     4.3. [OpenFold](#43-openfold)  
     4.4. [OmegaFold](#44-omegafold)  
-    4.5. [RFDesign](#45-rfdesign)  
-    4.6. [ESMFold](#46-esmfold)  
-    4.7. [ProteinMPNN](#47-proteinmpnn)  
-    4.8. [DiffDock](#48-diffdock)  
-    4.9. [RFDiffusion](#49-rfdiffusion)  
-    4.10. [NextFlow](#410-nextflow)  
+    4.5. [ESMFold](#46-esmfold)  
+    4.6. [ProteinMPNN](#47-proteinmpnn)  
+    4.7. [DiffDock](#48-diffdock)  
+    4.8. [RFDiffusion](#49-rfdiffusion)  
 5. [Architecture Details](#5-architecture-details)  
     5.1. [Stack Creation Details](#51-stack-creation-details)  
     5.2. [Cost](#52-cost)  
@@ -179,29 +177,7 @@ The OmegaFold citation is
 }
 ```
 
-### 4.5. RFDesign
-
-Commit [bba6992283de63faba6ff727bb4bc68327a5356c](https://github.com/RosettaCommons/RFDesign/commit/bba6992283de63faba6ff727bb4bc68327a5356c) from November 21, 2022.
-
-Please visit [https://github.com/RosettaCommons/RFDesign](https://github.com/RosettaCommons/RFDesign) for more information about the RFDesign hallucinate and inpainting algorithms.
-
-The RFDesign citation is
-
-```text
-@article{RFDesign,
-  author = {Jue Wang, Sidney Lisanza, David Juergens, Doug Tischer, Ivan Anishchenko, Minkyung Baek, Joseph L. Watson, Jung Ho Chun, Lukas F. Milles, Justas Dauparas, Marc Expòsit, Wei Yang, Amijai Saragovi, Sergey Ovchinnikov, and David Baker},
-  title = {Deep learning methods for designing proteins scaffolding functional sites},
-  elocation-id = {2021.11.10.468128},
-  year = {2022},
-  doi = {10.1101/2021.11.10.468128},
-  publisher = {bioRxiv},
-  URL = {https://www.biorxiv.org/content/early/2022/07/22/2022.07.21.500999},
-  eprint = {https://www.biorxiv.org/content/10.1101/2021.11.10.468128v2.full.pdf},
-  journal = {bioRxiv}
-}
-```
-
-### 4.6. ESMFold
+### 4.5. ESMFold
 
 Commit [74d25cba46a7fd9a9f557ff41ed1d8e9f131aac3](https://github.com/facebookresearch/esm/commit/74d25cba46a7fd9a9f557ff41ed1d8e9f131aac3) from November 26, 2023.
 
@@ -219,7 +195,7 @@ The ESMFold citation is
 }
 ```
 
-### 4.7. ProteinMPNN
+### 4.6. ProteinMPNN
 
 Commit [be1d37b6699dcd2283ab5b6fc8cc88774e2c80e9](https://github.com/dauparas/ProteinMPNN/commit/be1d37b6699dcd2283ab5b6fc8cc88774e2c80e9) from March 24, 2023.
 
@@ -240,7 +216,7 @@ The ProteinMPNN citation is
 }
 ```
 
-### 4.8. DiffDock
+### 4.7. DiffDock
 
 Commit [3c3c728cf2e444cf8df45b58067604d982159471](https://github.com/gcorso/DiffDock/commit/3c3c728cf2e444cf8df45b58067604d982159471) from March 27, 2023.
 
@@ -257,7 +233,7 @@ The DiffDock citation is
 }
 ```
 
-### 4.9. RFDiffusion
+### 4.8. RFDiffusion
 
 Commit [5606075d45bd23aa60785024b203ed6b0f6d2cd0](https://github.com/RosettaCommons/RFdiffusion/commit/5606075d45bd23aa60785024b203ed6b0f6d2cd0) from June 28, 2023.
 
@@ -276,10 +252,6 @@ The RFDiffusion citation is
 }
 ```
 
-### 4.10. NextFlow
-
-Please visit [https://www.nextflow.io](https://www.nextflow.io) for more information about the RFDiffusion algorithm. For a fully-managed NextFlow solution, you may also be interested in [Amazon Omics Workflows](https://docs.aws.amazon.com/omics/latest/dev/workflows.html).
-
 -----
 
 ## 5. Architecture Details

infrastructure/cloudformation/batch-protein-folding-cfn-container.yaml

@@ -9,21 +9,14 @@ Parameters:
     Description: Name of the application, if applicable
     Type: String
     Default: "Unknown"
-  Environment:
-    Description: Leave this as "main" unless you are testing a pre-release versions of this architecture.
-    Type: String
-    Default: main
-    AllowedValues:
-      - main
-      - dev     
   DownloadFsxData:
     Description: Automatically populate FSx for Lustre file system with model parameters and sequence databases?
     Type: String
     Default: "Y"
     AllowedValues: [Y, N]
   CodeRepoS3BucketName:
     Description: S3 Bucket Name to retrieve code zip
-    Type: String    
+    Type: String
     Default: "aws-hcls-ml"
   S3BucketARN:
     Description: S3 Bucket ARN
@@ -35,41 +28,12 @@ Parameters:
 
 Conditions:
   DownloadFsxDataCondition:
-    "Fn::Equals": [Ref: "DownloadFsxData", "Y"] 
+    "Fn::Equals": [Ref: "DownloadFsxData", "Y"]
 
 Resources:
-
   ##################################################
   # Container Services
   ##################################################
-  CodeRepository:
-    Type: AWS::CodeCommit::Repository
-    Properties:
-      Code:
-        BranchName: "main"
-        S3:
-          Bucket: !Ref CodeRepoS3BucketName
-          Key: !Sub "${Environment}/batch-protein-folding.zip"
-      RepositoryDescription: Code for running batch protein folding on AWS
-      RepositoryName:
-        !Join [
-          "-",
-          [
-            "batch-protein-folding",
-            "code-repo",
-            !Select [
-              4,
-              !Split ["-", !Select [2, !Split ["/", !Ref "AWS::StackId"]]],
-            ],
-          ],
-        ]
-      Tags:
-        - Key: Application
-          Value: !Ref ApplicationName
-        - Key: StackId
-          Value: !Ref AWS::StackId
-        - Key: SolutionId
-          Value: SO9164
 
   DownloadContainerRegistry:
     Type: AWS::ECR::Repository
@@ -82,9 +46,9 @@ Resources:
         - Key: Application
           Value: !Ref ApplicationName
         - Key: StackId
-          Value: !Ref "AWS::StackId"    
+          Value: !Ref "AWS::StackId"
         - Key: SolutionId
-          Value: SO9164 
+          Value: SO9164
 
   CodeBuildRole:
     Type: AWS::IAM::Role
@@ -126,29 +90,18 @@ Resources:
                       ["arn:aws:s3:::codepipeline", !Ref "AWS::Region", "*"],
                     ]
                   - !Sub "${S3BucketARN}*"
-                  - !Sub "arn:aws:s3:::${CodeRepoS3BucketName}/*"
               - Effect: Allow
                 Action:
                   - s3:GetObject
                   - s3:GetObjectVersion
                   - s3:GetBucketAcl
                   - s3:GetBucketLocation
+                  - s3:ListBucket
+                  - s3:ListBucketVersions
                 Resource:
-                  - !Sub "arn:aws:s3:::${CodeRepoS3BucketName}*"                  
-              - Effect: Allow
-                Action:
-                  - codecommit:GitPull
-                Resource:
-                  - Fn::Join:
-                      [
-                        ":",
-                        [
-                          "arn:aws:codecommit",
-                          !Ref "AWS::Region",
-                          !Ref "AWS::AccountId",
-                          !GetAtt CodeRepository.Name,
-                        ],
-                      ]
+                  - !Sub "arn:aws:s3:::${CodeRepoS3BucketName}"
+                  - !Sub "arn:aws:s3:::${CodeRepoS3BucketName}/*"
+
               - Effect: Allow
                 Action:
                   - codebuild:CreateReportGroup
@@ -251,7 +204,7 @@ Resources:
               - Effect: Allow
                 Action:
                   - codebuild:StartBuild
-                Resource: "*"          
+                Resource: "*"
       ManagedPolicyArns:
         - "arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole"
 
@@ -304,11 +257,11 @@ Resources:
         - Key: StackId
           Value: !Ref "AWS::StackId"
         - Key: SolutionId
-          Value: SO9164      
+          Value: SO9164
 
   ##################################################
   # Delete container repo on stack deletion
-  ##################################################  
+  ##################################################
   DeleteContainerRepoLambdaExecutionRole:
     Type: AWS::IAM::Role
     Properties:
@@ -326,10 +279,10 @@ Resources:
           PolicyDocument:
             Version: "2012-10-17"
             Statement:
-            - Effect: Allow
-              Action:
-                - ecr:DeleteRepository
-              Resource: "*"
+              - Effect: Allow
+                Action:
+                  - ecr:DeleteRepository
+                Resource: "*"
       ManagedPolicyArns:
         - "arn:aws:iam::aws:policy/service-role/AWSLambdaBasicExecutionRole"
         - "arn:aws:iam::aws:policy/service-role/AWSLambdaVPCAccessExecutionRole"
@@ -380,7 +333,7 @@ Resources:
       Role:
         Fn::GetAtt: DeleteContainerRepoLambdaExecutionRole.Arn
       Runtime: python3.10
-      Timeout: 10     
+      Timeout: 10
       Tags:
         - Key: Application
           Value: !Ref ApplicationName
@@ -389,9 +342,9 @@ Resources:
         - Key: SolutionId
           Value: SO9164
 
-##################################################
-# Create Download Container
-##################################################  
+  ##################################################
+  # Create Download Container
+  ##################################################
 
   CodeBuildProjectDownload:
     Type: AWS::CodeBuild::Project
@@ -406,32 +359,30 @@ Resources:
           - Name: IMAGE_TAG
             Value: latest
           - Name: IMAGE_REPO_NAME
-            Value: !Ref DownloadContainerRegistry            
+            Value: !Ref DownloadContainerRegistry
           - Name: ACCOUNT_ID
             Value: !Ref "AWS::AccountId"
           - Name: BUILD_CONTEXT
-            Value: infrastructure/docker/download        
+            Value: infrastructure/docker/download
           - Name: WAIT_CONDITION_HANDLE
-            Value: !Ref CodeBuildWaitHandle                     
+            Value: !Ref CodeBuildWaitHandle
         Image: aws/codebuild/standard:6.0
         ImagePullCredentialsType: CODEBUILD
         PrivilegedMode: true
         Type: LINUX_CONTAINER
       ResourceAccessRole: !GetAtt CodeBuildRole.Arn
       ServiceRole: !GetAtt CodeBuildRole.Arn
       Source:
-        BuildSpec: infrastructure/docker/download/buildspec_with_wait.yaml        
-        GitCloneDepth: 1
-        Location: !GetAtt CodeRepository.CloneUrlHttp
-        Type: CODECOMMIT
-      SourceVersion: refs/heads/main
+        BuildSpec: infrastructure/docker/buildspec.yaml
+        Location: !Sub "${CodeRepoS3BucketName}/main/batch-protein-folding.zip"
+        Type: S3
       Tags:
         - Key: Application
           Value: !Ref ApplicationName
         - Key: StackId
-          Value: !Ref "AWS::StackId"        
+          Value: !Ref "AWS::StackId"
         - Key: SolutionId
-          Value: SO9164                  
+          Value: SO9164
 
   StartDownloadContainerBuild:
     Type: Custom::ResourceForBuildingContainer
@@ -449,7 +400,7 @@ Resources:
   CodeBuildWaitCondition:
     Type: AWS::CloudFormation::WaitCondition
     Condition: DownloadFsxDataCondition
-    DependsOn: 
+    DependsOn:
       - CodeBuildProjectDownload
     Properties:
       Handle: !Ref CodeBuildWaitHandle
@@ -462,13 +413,9 @@ Resources:
       ServiceToken:
         Fn::GetAtt: DeleteContainerRepoLambda.Arn
       ContainerRepo:
-        Ref: DownloadContainerRegistry           
+        Ref: DownloadContainerRegistry
 
 Outputs:
-  CodeRepositoryURI:
-    Description: Code repository URI
-    Value:
-      Fn::GetAtt: CodeRepository.CloneUrlHttp
   CodeBuildEncryptionKey:
     Description: Encryption key for CodeBuild jobs
     Value:
@@ -480,16 +427,16 @@ Outputs:
   StartCodeBuildLambdaArn:
     Description: Lambda function for building container repos
     Value:
-      Fn::GetAtt: StartCodeBuildLambda.Arn      
+      Fn::GetAtt: StartCodeBuildLambda.Arn
   DeleteContainerRepoLambdaArn:
     Description: Lambda function for deleting container repos
     Value:
-      Fn::GetAtt: DeleteContainerRepoLambda.Arn      
+      Fn::GetAtt: DeleteContainerRepoLambda.Arn
   DownloadContainerRegistryURI:
     Description: URI of the download container
     Value:
-      Fn::GetAtt: DownloadContainerRegistry.RepositoryUri   
+      Fn::GetAtt: DownloadContainerRegistry.RepositoryUri
   DownloadContainerRegistryName:
     Description: Name of the download container repository
     Value:
-      Ref: DownloadContainerRegistry        
+      Ref: DownloadContainerRegistry

infrastructure/cloudformation/batch-protein-folding-cfn-download.yaml

@@ -81,7 +81,6 @@ Resources:
                           "/scripts/download_uniprot.sh",                          
                           "/scripts/download_uniref90.sh",
                           "/scripts/download_omegafold_params.sh",
-                          "/scripts/download_rfdesign_params.sh",
                           "/scripts/download_diffdock_params.sh",
                           "/scripts/download_rfdiffusion_params.sh"
                       ]