linadongxmu/gxle

Prediction of Binding Free Energy of Protein–Ligand Complexes with a Hybrid Molecular Mechanics/Generalized Born Surface Area and Machine Learning Method

gxle's Issues

Incompatibility error for model in GXLE.py

The version of scikit-learn for which the GXLE.pkl model was built seems not to be the 0.24.1version installed under the GXLE conda environment, so the GXLE.py script does not work showing the following error lines:

python3.9/site-packages/sklearn/base.py:347: InconsistentVersionWarning: Trying to unpickle estimator ExtraTreeRegressor from version 0.24.1 when using version 1.3.0. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
warnings.warn(
Traceback (most recent call last):
File "GXLE/application/for_model/GXLE.py", line 22, in
estimator=joblib.load("./GXLE.pkl")
File "python3.9/site-packages/joblib/numpy_pickle.py", line 658, in load
obj = _unpickle(fobj, filename, mmap_mode)
File "python3.9/site-packages/joblib/numpy_pickle.py", line 577, in _unpickle
obj = unpickler.load()
File "python3.9/pickle.py", line 1212, in load
dispatchkey[0]
File "python3.9/site-packages/joblib/numpy_pickle.py", line 402, in load_build
Unpickler.load_build(self)
File "python3.9/pickle.py", line 1717, in load_build
setstate(state)
File "sklearn/tree/_tree.pyx", line 714, in sklearn.tree._tree.Tree.setstate
File "sklearn/tree/_tree.pyx", line 1418, in sklearn.tree._tree._check_node_ndarray
ValueError: node array from the pickle has an incompatible dtype:

• expected: {'names': ['left_child', 'right_child', 'feature', 'threshold', 'impurity', 'n_node_samples', 'weighted_n_node_samples', 'missing_go_to_left'], 'formats': ['<i8', '<i8', '<i8', '<f8', '<f8', '<i8', '<f8', 'u1'], 'offsets': [0, 8, 16, 24, 32, 40, 48, 56], 'itemsize': 64}
• got : [('left_child', '<i8'), ('right_child', '<i8'), ('feature', '<i8'), ('threshold', '<f8'), ('impurity', '<f8'), ('n_node_samples', '<i8'), ('weighted_n_node_samples', '<f8')]

---

Thank you very much in advance for your reply.
Sincerely.

GXLE cannot be installed because of the X-Score inaccessibility

Hi,
First of all, thank you for freely making available to the scientific community the GXLE code. We are trying to install and testing it but with unsuccessful results because there is no way to download the X-Score from https://www.ics.uci.edu/~dock/manuals/xscore_1.2_manual.
Please, could you provide an alternative way to get such a requirement, e.g. including X-Score into the GXLE conda environmente or whatever any other fix you decide?
Thank you very much in advance for your reply.

Amber parameter errors about WAT atom types

Hi,
The GXLE code is unsuccessfully ending with teLeap errors about all O and H atoms from the WAT residues containing in the *_solv.pdb files. Cheking the leap.log file you can find lot of line errors as these ones:

amber/20.13-AmberTools-22.2/bin/teLeap: Error!
For atom (.R<WAT 20082>.A<O 1>) could not find vdW (or other) parameters for type (OW)

amber/20.13-AmberTools-22.2/bin/teLeap: Error!
For atom (.R<WAT 20082>.A<H1 2>) could not find vdW (or other) parameters for type (HW)

Please, could you figure out what the issue is? Thank you very much in advance for your reply.

No 'results.csv' file or directory

Whenever I run the GXLE.sh file, the following errors encounter -
mkdir: cannot create directory ‘xscore’: File exists
mkdir: cannot create directory ‘ligand’: File exists
GXLE.sh: line 4: bjobs: command not found
run_min2.sh: line 2: /home/mohon/.cshrc: No such file or directory
GXLE.sh: line 4: bjobs: command not found
run_gbsa.sh: line 3: /home/mohon/.cshrc: No such file or directory
ls: cannot access '*_FINAL_RESULTS_MMPBSA.dat': No such file or directory
hdac
xscore.sh: line 9: xscore: command not found
grep: xscore.log: No such file or directory
Traceback (most recent call last):
File "/home/mohon/GXLE/application/for_model/GXLE.py", line 12, in
x_test=transfer.fit_transform(x_test)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/utils/_set_output.py", line 157, in wrapped
data_to_wrap = f(self, X, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/base.py", line 916, in fit_transform
return self.fit(X, **fit_params).transform(X)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/preprocessing/_data.py", line 839, in fit
return self.partial_fit(X, y, sample_weight)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/base.py", line 1152, in wrapper
return fit_method(estimator, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/preprocessing/_data.py", line 875, in partial_fit
X = self._validate_data(
^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/base.py", line 605, in _validate_data
out = check_array(X, input_name="X", **check_params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mohon/anaconda3/envs/gxle/lib/python3.12/site-packages/sklearn/utils/validation.py", line 967, in check_array
raise ValueError(
ValueError: Found array with 0 sample(s) (shape=(0, 22)) while a minimum of 1 is required by StandardScaler.
cp: cannot stat 'results.csv': No such file or directory

Please help me with this issue.

running GXLE under Slurm instead of LSF

Hi,
To run the GXLE code we only have a HPC environment with SLURM as workload manager and Amber as a module loaded in that computing environment. We wonder whether you could guide us to the proper GXLE script files we can modify or delete in order to avoid both the bsub instructions and Amber environmental variables containing in the GXLE code.
Thank you very much in advance for your reply.

2fvd_ligand molecule error

Hi,
As you know, the 'run_tleap_min1.sh' script contain some tleap settings for a molecule labelled as "2fvd". Running GXLE using the example data one error about that molecule is showed in the leap.log file as follows:

PRL = loadmol2 1bcu_ligand.mol2_1
Loading Mol2 file: ./1bcu_ligand.mol2_1
Reading MOLECULE named PRL
loadamberparams 1bcu_ligand.frcmod
Loading parameters: ./1bcu_ligand.frcmod
Reading force field modification type file (frcmod)
Reading title:
Remark line goes here
loadamberparams 2fvd_ligand.frcmod
software/MPI/gcc/system/openmpi/4.0.5_ft3_cuda/amber/20.13-AmberTools-22.2/bin/teLeap: Fatal Error!
Could not open file 2fvd_ligand.frcmod: not found

What and where is "2fvd_ligand"?
Thank you very much in advance for your reply.

Floating-point warnings running GXLE

Hi,
We're running the example data for 20 hours so far and thousand of warning lines are persistently displaying about floating-point exceptions:
"Note: The following floating-point exceptions are signalling: IEEE_INVALID_FLAG"
Please, some remarks about that behaviour will be of helpful guide to go ahead. Thank you very much in advance for your reply.

endless while loops in some Default-AmberEnv scripts

The Default-AmberEnv scripts run_tleap_min1.sh, run_min2.sh, and run_gbsa.sh contain inside bjobmin() and bjobgbsa() functions endless "while true" loops causing never ending amber runnings.

.rst and _solv.inpcrd files are not found

Hi,
Using your .sh scripts from Default-AmberEnv and you example data, the tleap running is OK but both amber18-gpu.sh and amber18-min2.sh scripts show the following errors:

Unit 9 Error on OPEN: 1bcu_solv.inpcrd
Unit 9 Error on OPEN: 1bcu_wat_min1.rst

because the *.rst and *_solv.inpcrd files are not building by the GXLE code. Please. could you give us some clues to fix it?
Once again thank you very much in advance for your reply.