Skip to content

Commit

Permalink
Merge pull request #195 from JoseEspinosa/i188
Browse files Browse the repository at this point in the history
Fix colabfold image to run in gpu environments with new cuda drivers
  • Loading branch information
JoseEspinosa authored Oct 17, 2024
2 parents aebbd21 + 31ad0f4 commit bc823a1
Show file tree
Hide file tree
Showing 2 changed files with 8 additions and 7 deletions.
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- [[PR #178](https://github.com/nf-core/proteinfold/pull/178)] - Enable running multiple modes in parallel.
- [[#179](https://github.com/nf-core/proteinfold/issues/179)]- Produce an interactive html report for the predicted structures.
- [[#180](https://github.com/nf-core/proteinfold/issues/180)]- Implement Fooldseek.
- [[#188](https://github.com/nf-core/proteinfold/issues/188)]- Fix colabfold image to run in gpus.

## [[1.1.1](https://github.com/nf-core/proteinfold/releases/tag/1.1.1)] - 2025-07-30

Expand Down
14 changes: 7 additions & 7 deletions dockerfiles/Dockerfile_nfcore-proteinfold_colabfold
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
FROM nvidia/cuda:11.4.3-cudnn8-runtime-ubuntu18.04
FROM nvidia/cuda:12.6.2-cudnn-runtime-ubuntu24.04

LABEL authors="Athanasios Baltzis, Jose Espinosa-Carrasco, Leila Mansouri" \
title="nfcore/proteinfold_colabfold" \
Version="1.1.0" \
Version="1.2.0dev" \
description="Docker image containing all software requirements to run the COLABFOLD_BATCH module using the nf-core/proteinfold pipeline"

ENV PATH="/localcolabfold/colabfold-conda/bin:$PATH"
Expand All @@ -14,7 +14,7 @@ ENV PATH="/MMseqs2/build/bin:$PATH"
RUN apt-key adv --keyserver keyserver.ubuntu.com --recv-keys A4B469963BF863CC
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
build-essential \
cuda-command-line-tools-11-4 \
cuda-command-line-tools-12-6 \
git \
hmmer \
kalign \
Expand All @@ -25,13 +25,13 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y \
&& rm -rf /var/lib/apt/lists/*

RUN cd / \
&& wget https://raw.githubusercontent.com/YoshitakaMo/localcolabfold/82a3635/install_colabbatch_linux.sh \
&& wget https://raw.githubusercontent.com/YoshitakaMo/localcolabfold/07e87ed/install_colabbatch_linux.sh \
&& sed -i "/colabfold.download/d" install_colabbatch_linux.sh \
&& sed -i "s|cudatoolkit==.*\sopenmm|cudatoolkit==11.1.1 openmm|g" install_colabbatch_linux.sh \
&& bash install_colabbatch_linux.sh

RUN /localcolabfold/colabfold-conda/bin/python3.10 -m pip install tensorflow-cpu==2.11.0
## Updated
RUN /localcolabfold/colabfold-conda/bin/python3.10 -m pip install tensorflow-cpu==2.17.0

#Silence download of the AlphaFold2 params
# #Silence download of the AlphaFold2 params
RUN sed -i "s|download_alphafold_params(|#download_alphafold_params(|g" /localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py
RUN sed -i "s|if args\.num_models|#if args\.num_models|g" /localcolabfold/colabfold-conda/lib/python3.10/site-packages/colabfold/batch.py

0 comments on commit bc823a1

Please sign in to comment.