where is the docked pose?

[mycode-bit]

Here me again, I got another question.

I am trying to repeat from your test_sets_pdb. But in the folder of test_sets_pdb/db5_equidock_results, I did not see docked complex structure. where is it?

in the folder of db5_test_random_transformed, there is one called complexes. If we are docking, why do we need the complex anyway.

Your help is greatly appreciated.

[octavian-ganea]

The ligand is docked to the bound receptor, so only the final ligand file is the output. See https://github.com/octavian-ganea/equidock_public/blob/main/src/inference_rigid.py#L136 .

The initial bound ligand is not needed for inference alone, I had it in the complexes folder for evaluation purposes only.

[mycode-bit]

thanks for your explanation. Now I got another error when I run inference_rigid.py. is that coming from dependency? I cannot figure out what is wrong. thanks in advance for help.

---

Parsing args Available GPUS:0 EQUIDOCK__drp_0.0#Wdec_0.0001#ITS_lw_10.0#Hdim_64#Nlay_5#shrdLay_F#SURFfs_F#ln_LN#lnX_0#Hnrm_0#NattH_50#skH_0.5#xConnI_0.0#LkySl_0.01#pokOTw_1.0#divXdist_F# [2022-03-07 07:24:44.417504] Model name ===> EQUIDOCK__drp_0.0#Wdec_0.0001#ITS_lw_10.0#Hdim_64#Nlay_5#shrdLay_F#SURFfs_F#ln_LN#lnX_0#Hnrm_0#NattH_50#skH_0.5#xConnI_0.0#LkySl_0.01#pokOTw_1.0#divXdist_F# checkpoint_filename = checkpts/oct20_Wdec_0.001#ITS_lw_10.0#Hdim_64#Nlay_5#shrdLay_T#ln_LN#lnX_0#Hnrm_0#NattH_50#skH_0.5#xConnI_0.0#LkySl_0.01#pokOTw_1.0#fine_F#/db5_model_best.pth [2022-03-07 07:24:44.484702] Number of parameters = 525,671 LN 0 0 10.0 divide_coors_dist = False inference on file = ./test_sets_pdb/db5_test_random_transformed/random_transformed/3SZK_l_b.pdb Traceback (most recent call last): File "src/inference_rigid.py", line 147, in main(args) File "src/inference_rigid.py", line 123, in main all_rotation_list, all_translation_list = model(batch_hetero_graph, epoch=0) File "/home/user/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/user/equidock_public-main/src/model/rigid_docking_model.py", line 647, in forward outputs = iegmn(batch_hetero_graph, epoch) File "/home/user/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/user/equidock_public-main/src/model/rigid_docking_model.py", line 490, in forward h_feats_receptor = layer(hetero_graph=batch_hetero_graph, File "/home/user/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/user/equidock_public-main/src/model/rigid_docking_model.py", line 274, in forward hetero_graph.update_all(fn.copy_edge('x_moment', 'm'), fn.mean('m', 'x_update'), File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/heterograph.py", line 4876, in update_all ndata = core.message_passing(g, message_func, reduce_func, apply_node_func) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/core.py", line 357, in message_passing ndata = invoke_gspmm(g, mfunc, rfunc) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/core.py", line 332, in invoke_gspmm z = op(graph, x) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/ops/spmm.py", line 191, in func return gspmm(g, 'copy_rhs', reduce_op, None, x) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/ops/spmm.py", line 75, in gspmm ret = gspmm_internal(g._graph, op, File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/backend/pytorch/sparse.py", line 757, in gspmm return GSpMM.apply(gidx, op, reduce_op, lhs_data, rhs_data) File "/home/user/anaconda3/lib/python3.8/site-packages/torch/cuda/amp/autocast_mode.py", line 94, in decorate_fwd return fwd(*args, **kwargs) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/backend/pytorch/sparse.py", line 126, in forward out, (argX, argY) = _gspmm(gidx, op, reduce_op, X, Y) File "/home/user/anaconda3/lib/python3.8/site-packages/dgl/sparse.py", line 228, in _gspmm _CAPI_DGLKernelSpMM(gidx, op, reduce_op, File "dgl/_ffi/_cython/./function.pxi", line 287, in dgl._ffi._cy3.core.FunctionBase.call File "dgl/_ffi/_cython/./function.pxi", line 232, in dgl._ffi._cy3.core.FuncCall File "dgl/_ffi/_cython/./base.pxi", line 155, in dgl._ffi._cy3.core.CALL dgl._ffi.base.DGLError: [07:24:49] /opt/dgl/src/array/cpu/./spmm_blocking_libxsmm.h:267: Failed to generate libxsmm kernel for the SpMM operation! Stack trace: [bt] (0) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(dmlc::LogMessageFatal::~LogMessageFatal()+0x4f) [0x7fdc8e6b743f] [bt] (1) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMRedopCsrOpt<int, float, dgl::aten::cpu::op::CopyRhs, dgl::aten::cpu::op::Add >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x3bc) [0x7fdc8e8e9d5c] [bt] (2) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMSumCsrLibxsmm<int, float, dgl::aten::cpu::op::CopyRhs >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x73) [0x7fdc8e8e9e03] [bt] (3) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(void dgl::aten::cpu::SpMMSumCsr<int, float, dgl::aten::cpu::op::CopyRhs >(dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray)+0x146) [0x7fdc8e915106] [bt] (4) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(void dgl::aten::SpMMCsr<1, int, 32>(std::string const&, std::string const&, dgl::BcastOff const&, dgl::aten::CSRMatrix const&, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, std::vector<dgl::runtime::NDArray, std::allocatordgl::runtime::NDArray >)+0xfeb) [0x7fdc8e921d2b] [bt] (5) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(dgl::aten::SpMM(std::string const&, std::string const&, std::shared_ptrdgl::BaseHeteroGraph, dgl::runtime::NDArray, dgl::runtime::NDArray, dgl::runtime::NDArray, std::vector<dgl::runtime::NDArray, std::allocatordgl::runtime::NDArray >)+0x1004) [0x7fdc8e95a8e4] [bt] (6) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(+0x46a098) [0x7fdc8e96f098] [bt] (7) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(+0x46a631) [0x7fdc8e96f631] [bt] (8) /home/user/anaconda3/lib/python3.8/site-packages/dgl/libdgl.so(DGLFuncCall+0x48) [0x7fdc8e9c28b8]

[octavian-ganea]

This looks like a DGL error. Do you have the same package versions as stated in our README ?

[mycode-bit]

now it is dgl 0.7, initially I installed 0.8, but now I downgraded to 0.7 again. error still shows up.

[octavian-ganea]

all packages need to be the same versions , not just DGL. Can you show your packages versions for those listed in the README ?

[octavian-ganea]

also, fyi, this code was not tested on Windows

[mycode-bit]

Here is the list, I guess rdkit does not match.

python==3.8.8 numpy==1.20.1 cuda==10.1 torch==1.10.2 dgl==0.7.0 biopandas==0.2.8 ot==0.7.0 rdkit==2019.09.3 dgllife==0.2.8 joblib==1.1.0

[octavian-ganea]

it really looks to me like a DGL error. Can you try testing the hetero_graph.update_all() function in a separate toy code ?