Esm2 software for assistance #10041

chenwy804 · 2025-02-17T14:31:39Z

chenwy804
Feb 17, 2025

Hi Ahmet Sarıgün,
Because I use RTX 4090 to run CUDA, the PyTorch version must be 2.0.0 or higher. Therefore, I first installed OpenFold's 2.0.0 version according to OpenFold's requirements, and then used pip to install ESM related files

git clone -b pl_upgrades https://github.com/aqlaboratory/openfold.git
mamba env create -n openfold2 -f environment.yml
scripts/install_third_party_dependencies.sh
pip install "fair-esm[esmfold]"

I followed the relevant recommendations of OpenFold for testing, and in fact, I did pass all the tests:
scripts/run_unit_tests.sh

Here is my virtual environment software version：
name: openfold2
dependencies:

_libgcc_mutex=0.1=conda_forge
_openmp_mutex=4.5=2_kmp_llvm
absl-py=2.1.0=pyhd8ed1ab_1
alsa-lib=1.2.12=h4ab18f5_0
appdirs=1.4.4=pyhd8ed1ab_1
aria2=1.37.0=hbc8128a_2
aws-c-auth=0.7.26=hc36b679_2
aws-c-cal=0.7.4=h2abdd08_0
aws-c-common=0.9.27=h4bc722e_0
aws-c-compression=0.2.19=haa50ccc_0
aws-c-event-stream=0.4.3=h570d160_0
aws-c-http=0.8.8=h9b61739_1
aws-c-io=0.14.18=h49c7fd3_7
aws-c-mqtt=0.10.4=h5c8269d_18
aws-c-s3=0.6.4=h77088c0_11
aws-c-sdkutils=0.1.19=h038f3f9_2
aws-checksums=0.1.18=h038f3f9_10
awscli=2.22.15=py39hf3d152e_0
awscrt=0.21.2=py39h4a972c0_15
binutils=2.43=h4852527_2
binutils_impl_linux-64=2.43=h4bf12b8_2
binutils_linux-64=2.43=h4852527_2
biopython=1.84=py39hd3abc70_0
blas=2.129=openblas
blas-devel=3.9.0=29_h1ea3ea9_openblas
brotli-python=1.1.0=py39h3d6467e_1
bzip2=1.0.8=h4bc722e_7
c-ares=1.33.1=heb4867d_0
c-compiler=1.7.0=hd590300_1
ca-certificates=2025.1.31=hbcca054_0
cccl=2.5.0=h7ab4013_0
certifi=2025.1.31=pyhd8ed1ab_0
cffi=1.17.0=py39h49a4b6b_0
charset-normalizer=3.4.1=pyhd8ed1ab_0
click=8.1.8=pyh707e725_0
colorama=0.4.6=pyhd8ed1ab_1
contextlib2=21.6.0=pyhd8ed1ab_1
cryptography=43.0.0=py39h5c34e2d_0
cuda=12.6.0=ha804496_0
cuda-cccl=12.6.37=ha770c72_0
cuda-cccl_linux-64=12.6.37=ha770c72_0
cuda-command-line-tools=12.6.0=ha770c72_0
cuda-compiler=12.6.0=hbad6d8a_0
cuda-crt-dev_linux-64=12.6.20=ha770c72_0
cuda-crt-tools=12.6.20=ha770c72_0
cuda-cudart=12.6.37=he02047a_0
cuda-cudart-dev=12.6.37=he02047a_0
cuda-cudart-dev_linux-64=12.6.37=h85509e4_0
cuda-cudart-static=12.6.37=he02047a_0
cuda-cudart-static_linux-64=12.6.37=h85509e4_0
cuda-cudart_linux-64=12.6.37=h85509e4_0
cuda-cuobjdump=12.6.20=he02047a_0
cuda-cupti=12.6.37=he02047a_0
cuda-cupti-dev=12.6.37=he02047a_0
cuda-cuxxfilt=12.6.20=he02047a_0
cuda-driver-dev=12.6.37=he02047a_0
cuda-driver-dev_linux-64=12.6.77=h3f2d84a_0
cuda-gdb=12.6.37=hda18ab6_0
cuda-libraries=12.6.0=ha770c72_0
cuda-libraries-dev=12.6.0=ha770c72_0
cuda-nsight=12.6.20=ha770c72_0
cuda-nvcc=12.6.20=hcdd1206_0
cuda-nvcc-dev_linux-64=12.6.20=he91c749_0
cuda-nvcc-impl=12.6.20=h85509e4_0
cuda-nvcc-tools=12.6.20=he02047a_0
cuda-nvcc_linux-64=12.6.20=h8a487aa_0
cuda-nvdisasm=12.6.20=he02047a_0
cuda-nvml-dev=12.6.37=he02047a_0
cuda-nvprof=12.6.37=he02047a_1
cuda-nvprune=12.6.20=he02047a_0
cuda-nvrtc=12.6.20=he02047a_0
cuda-nvrtc-dev=12.6.20=he02047a_0
cuda-nvtx=12.6.37=he02047a_0
cuda-nvvm-dev_linux-64=12.6.20=ha770c72_0
cuda-nvvm-impl=12.6.20=he02047a_0
cuda-nvvm-tools=12.6.20=he02047a_0
cuda-nvvp=12.6.37=he02047a_0
cuda-opencl=12.6.37=he02047a_0
cuda-opencl-dev=12.6.37=he02047a_0
cuda-profiler-api=12.6.37=ha770c72_0
cuda-runtime=12.6.0=ha804496_0
cuda-sanitizer-api=12.6.34=he02047a_0
cuda-toolkit=12.6.0=ha804496_0
cuda-tools=12.6.0=ha770c72_0
cuda-version=12.6=h7480c83_3
cuda-visual-tools=12.6.0=ha770c72_0
cxx-compiler=1.7.0=h00ab1b0_1
dbus=1.13.6=h5008d03_3
distro=1.8.0=pyhd8ed1ab_0
docker-pycreds=0.4.0=py_0
docutils=0.19=py39hf3d152e_1
expat=2.6.2=h59595ed_0
font-ttf-dejavu-sans-mono=2.37=hab24e00_0
font-ttf-inconsolata=3.000=h77eed37_0
font-ttf-source-code-pro=2.038=h77eed37_0
font-ttf-ubuntu=0.83=h77eed37_3
fontconfig=2.14.2=h14ed4e7_0
fonts-conda-ecosystem=1=0
fonts-conda-forge=1=0
freetype=2.12.1=h267a509_2
gcc=12.4.0=h236703b_1
gcc_impl_linux-64=12.4.0=hb2e57f8_0
gcc_linux-64=12.4.0=h6b7512a_7
gds-tools=1.11.0.15=he02047a_0
git=2.46.0=pl5321hb5640b7_0
gitdb=4.0.12=pyhd8ed1ab_0
gitpython=3.1.44=pyhff2d567_0
gmp=6.3.0=hac33072_2
gxx=12.4.0=h236703b_1
gxx_impl_linux-64=12.4.0=h613a52c_0
gxx_linux-64=12.4.0=h8489865_7
hhsuite=3.3.0=py39pl5321h0dd7abe_12
hmmer=3.4=hdbdd923_2
icu=75.1=he02047a_0
idna=3.10=pyhd8ed1ab_1
ihm=1.3=py39hcd6043d_0
importlib-metadata=8.6.1=pyha770c72_0
jmespath=1.0.1=pyhd8ed1ab_1
kalign2=2.04=h031d066_7
kernel-headers_linux-64=3.10.0=he073ed8_18
keyutils=1.6.1=h166bdaf_0
krb5=1.21.3=h659f571_0
ld_impl_linux-64=2.43=h712a8e2_2
libabseil=20240116.2=cxx17_he02047a_1
libblas=3.9.0=29_h59b9bed_openblas
libcblas=3.9.0=29_he106b2a_openblas
libcublas=12.6.0.22=he02047a_0
libcublas-dev=12.6.0.22=he02047a_0
libcufft=11.2.6.28=he02047a_0
libcufft-dev=11.2.6.28=he02047a_0
libcufile=1.11.0.15=he02047a_0
libcufile-dev=1.11.0.15=he02047a_0
libcurand=10.3.7.37=he02047a_0
libcurand-dev=10.3.7.37=he02047a_0
libcurl=8.9.1=hdb1bdb2_0
libcusolver=11.6.4.38=he02047a_0
libcusolver-dev=11.6.4.38=he02047a_0
libcusparse=12.5.2.23=he02047a_0
libcusparse-dev=12.5.2.23=he02047a_0
libedit=3.1.20191231=he28a2e2_2
libev=4.33=hd590300_2
libexpat=2.6.2=h59595ed_0
libffi=3.4.2=h7f98852_5
libgcc=7.2.0=h69d50b8_2
libgcc-devel_linux-64=12.4.0=ha4f9413_100
libgcc-ng=14.1.0=h77fa898_0
libgfortran-ng=14.1.0=h69a702a_0
libgfortran5=14.1.0=hc5f4f2c_0
libglib=2.80.3=h315aac3_2
libgomp=14.1.0=h77fa898_0
libhwloc=2.11.1=default_hecaa2ac_1000
libiconv=1.17=hd590300_2
liblapack=3.9.0=29_h7ac8fdf_openblas
liblapacke=3.9.0=29_he2f377e_openblas
libnghttp2=1.58.0=h47da74e_1
libnpp=12.3.1.23=he02047a_0
libnpp-dev=12.3.1.23=he02047a_0
libnsl=2.0.1=hd590300_0
libnvfatbin=12.6.20=he02047a_0
libnvfatbin-dev=12.6.20=he02047a_0
libnvjitlink=12.6.20=he02047a_0
libnvjitlink-dev=12.6.20=he02047a_0
libnvjpeg=12.3.3.23=he02047a_0
libnvjpeg-dev=12.3.3.23=ha770c72_0
libopenblas=0.3.28=pthreads_h94d23a6_0
libpng=1.6.43=h2797004_0
libprotobuf=4.25.3=h08a7969_0
libsanitizer=12.4.0=h46f95d5_0
libsqlite=3.46.0=hde9e2c9_0
libssh2=1.11.0=h0841786_0
libstdcxx-devel_linux-64=12.4.0=ha4f9413_100
libstdcxx-ng=14.1.0=hc0a3c3a_0
libuuid=2.38.1=h0b41bf4_0
libxcb=1.16=hb9d3cd8_1
libxcrypt=4.4.36=hd590300_1
libxkbcommon=1.7.0=h2c5496b_1
libxkbfile=1.1.0=h166bdaf_1
libxml2=2.12.7=he7c6b58_4
libzlib=1.3.1=h4ab18f5_1
llvm-openmp=19.1.7=h024ca30_0
mkl=2024.2.2=ha957f24_16
ml-collections=0.1.1=pyhd8ed1ab_0
modelcif=0.7=pyhd8ed1ab_0
msgpack-python=1.0.8=py39h95fdab5_0
ncurses=6.5=he02047a_1
nsight-compute=2024.3.0.15=he3ecb2e_0
nspr=4.35=h27087fc_0
nss=3.103=h593d115_0
numpy=1.26.4=py39h474f0d3_0
ocl-icd=2.3.2=hd590300_1
ocl-icd-system=1.0.0=1
openblas=0.3.28=pthreads_h6ec200e_0
openmm=8.1.2=py39hb7c185c_2
openssl=3.3.1=hb9d3cd8_3
packaging=24.2=pyhd8ed1ab_2
pandas=2.2.2=py39hfc16268_1
pcre2=10.44=hba22ea6_2
pdbfixer=1.9=pyh1a96a4e_0
perl=5.32.1=7_hd590300_perl5
pip=25.0.1=pyh8b19718_0
platformdirs=4.3.6=pyhd8ed1ab_1
prompt-toolkit=3.0.38=pyha770c72_0
prompt_toolkit=3.0.38=hd8ed1ab_0
protobuf=4.25.3=py39h1be52a0_0
psutil=6.0.0=py39hd3abc70_0
pthread-stubs=0.4=h36c2ea0_1001
pycparser=2.22=pyh29332c3_1
pysocks=1.7.1=pyha55dd90_7
python=3.9.19=h0755675_0_cpython
python-dateutil=2.9.0=pyhd8ed1ab_0
python-tzdata=2025.1=pyhd8ed1ab_0
python_abi=3.9=5_cp39
pytz=2025.1=pyhd8ed1ab_0
pyyaml=5.4.1=py39hb9d737c_4
readline=8.2=h8228510_1
requests=2.32.3=pyhd8ed1ab_1
ruamel.yaml=0.17.21=py39h72bdee0_3
ruamel.yaml.clib=0.2.8=py39hd1e30aa_0
s2n=1.5.1=h3400bea_0
scipy=1.13.1=py39haf93ffa_0
sentry-sdk=2.21.0=pyhd8ed1ab_0
setproctitle=1.3.3=py39hd1e30aa_0
setuptools=59.5.0=py39hf3d152e_0
six=1.17.0=pyhd8ed1ab_0
smmap=5.0.0=pyhd8ed1ab_0
sysroot_linux-64=2.17=h0157908_18
tbb=2021.12.0=h434a139_3
tk=8.6.13=noxft_h4845f30_101
tqdm=4.62.2=pyhd8ed1ab_0
typing-extensions=4.12.2=hd8ed1ab_1
typing_extensions=4.12.2=pyha770c72_1
tzdata=2025a=h78e105d_0
urllib3=1.26.19=pyhd8ed1ab_0
wandb=0.16.6=pyhd8ed1ab_1
wayland=1.23.1=h3e06ad9_0
wcwidth=0.2.13=pyhd8ed1ab_1
wheel=0.45.1=pyhd8ed1ab_1
xcb-util=0.4.1=hb711507_2
xcb-util-cursor=0.1.4=h4ab18f5_2
xcb-util-image=0.4.0=hb711507_2
xcb-util-keysyms=0.4.1=hb711507_0
xcb-util-renderutil=0.3.10=hb711507_0
xcb-util-wm=0.4.2=hb711507_0
xkeyboard-config=2.42=h4ab18f5_0
xorg-compositeproto=0.4.2=h7f98852_1001
xorg-damageproto=1.2.1=h7f98852_1002
xorg-fixesproto=5.0=h7f98852_1002
xorg-inputproto=2.3.2=h7f98852_1002
xorg-kbproto=1.0.7=h7f98852_1002
xorg-libice=1.1.1=hd590300_0
xorg-libsm=1.2.4=h7391055_0
xorg-libx11=1.8.9=hb711507_1
xorg-libxau=1.0.11=hd590300_0
xorg-libxcomposite=0.4.6=h0b41bf4_1
xorg-libxdamage=1.1.5=h7f98852_1
xorg-libxdmcp=1.1.3=h7f98852_0
xorg-libxext=1.3.4=h0b41bf4_2
xorg-libxfixes=5.0.3=h7f98852_1004
xorg-libxi=1.7.10=h4bc722e_1
xorg-libxrandr=1.5.2=h7f98852_1
xorg-libxrender=0.9.11=hd590300_0
xorg-libxtst=1.2.5=h4bc722e_0
xorg-randrproto=1.5.0=h7f98852_1001
xorg-recordproto=1.14.2=h7f98852_1002
xorg-renderproto=0.11.1=h7f98852_1002
xorg-util-macros=1.19.3=h7f98852_0
xorg-xextproto=7.3.0=h0b41bf4_1003
xorg-xproto=7.0.31=h7f98852_1007
xz=5.2.6=h166bdaf_0
yaml=0.2.5=h7f98852_2
zipp=3.21.0=pyhd8ed1ab_1
zstd=1.5.6=ha6fb4c9_0
pip:
- aiohappyeyeballs==2.4.6
- aiohttp==3.11.12
- aiosignal==1.3.2
- annotated-types==0.7.0
- antlr4-python3-runtime==4.9.3
- async-timeout==5.0.1
- attrs==25.1.0
- cuda-bindings==12.8.0
- cuda-python==12.8.0
- deepspeed==0.16.3
- dllogger==1.0.0
- dm-tree==0.1.8
- einops==0.8.1
- fair-esm==2.0.0
- filelock==3.13.1
- flash-attn==2.6.3
- frozenlist==1.5.0
- fsspec==2024.6.1
- hjson==3.1.0
- jinja2==3.1.4
- lightning-utilities==0.12.0
- markupsafe==2.1.5
- mpmath==1.3.0
- multidict==6.1.0
- networkx==3.2.1
- ninja==1.11.1.3
- nvidia-cublas-cu12==12.6.4.1
- nvidia-cuda-cupti-cu12==12.6.80
- nvidia-cuda-nvrtc-cu12==12.6.77
- nvidia-cuda-runtime-cu12==12.6.77
- nvidia-cudnn-cu12==9.5.1.17
- nvidia-cufft-cu12==11.3.0.4
- nvidia-curand-cu12==10.3.7.77
- nvidia-cusolver-cu12==11.7.1.2
- nvidia-cusparse-cu12==12.5.4.2
- nvidia-cusparselt-cu12==0.6.3
- nvidia-cutlass==3.7.0.0
- nvidia-ml-py==12.570.86
- nvidia-nccl-cu12==2.21.5
- nvidia-nvjitlink-cu12==12.6.85
- nvidia-nvtx-cu12==12.6.77
- omegaconf==2.3.0
- openfold==2.0.0
- pillow==11.0.0
- propcache==0.2.1
- py-cpuinfo==9.0.0
- pydantic==2.10.6
- pydantic-core==2.27.2
- pydot==3.0.4
- pynvml==12.0.0
- pyparsing==3.2.1
- pytorch-lightning==2.5.0.post0
- sympy==1.13.1
- torch==2.6.0+cu126
- torchaudio==2.6.0+cu126
- torchmetrics==1.6.1
- torchvision==0.21.0+cu126
- treelib==1.7.0
- triton==3.2.0
- yarl==1.18.3
  variables:
  CUTLASS_PATH: /public/home/design1/software/openfold-2.0.0/cutlass
  KMP_AFFINITY: none
  prefix: /public/home/design1/miniconda3/envs/openfold2

Finally, when I ran the following command:model = esm.pretrained.esmfold_v1()
I encountered the following error：
[2025-02-17 22:18:38,434] [INFO] [real_accelerator.py:222:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Traceback (most recent call last):
File "/public/home/design1/data/cas12/esm_fold/download.py", line 7, in
model = esm.pretrained.esmfold_v1()
File "/public/home/design1/miniconda3/envs/openfold2/lib/python3.9/site-packages/esm/pretrained.py", line 420, in esmfold_v1
return esm.esmfold.v1.pretrained.esmfold_v1()
File "/public/home/design1/miniconda3/envs/openfold2/lib/python3.9/site-packages/esm/esmfold/v1/pretrained.py", line 54, in esmfold_v1
return _load_model("esmfold_3B_v1")
File "/public/home/design1/miniconda3/envs/openfold2/lib/python3.9/site-packages/esm/esmfold/v1/pretrained.py", line 29, in _load_model
raise RuntimeError(f"Keys '{', '.join(missing_essential_keys)}' are missing.")
RuntimeError: Keys 'trunk.structure_module.ipa.linear_kv_points.linear.weight, trunk.structure_module.ipa.linear_q_points.linear.bias, trunk.structure_module.ipa.linear_kv_points.linear.bias, trunk.structure_module.ipa.linear_q_points.linear.weight' are missing.

Thank you again for your help!

asarigun · 2025-02-18T15:25:16Z

asarigun
Feb 18, 2025

I've posted my solution to issues on my repository. You can check it out here: asarigun/esm#1 (comment)

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Esm2 software for assistance #10041

{{title}}

Replies: 1 comment

{{title}}

Select a reply

Esm2 software for assistance #10041

chenwy804 Feb 17, 2025

Replies: 1 comment

asarigun Feb 18, 2025

chenwy804
Feb 17, 2025

asarigun
Feb 18, 2025