hbusra / g4boost Goto Github PK

Please mention in the doc the required version of the packages,
i.e xgboost==1.4.2, pandas==?
install xgboost with:
pip install xgboost==1.4.2
Provided models G4Boost_classifier.json & G4Boost_regressor.json are built on 1.4.2 I had errors with xgboost==1.6
I could run the program with the following.
joblib 1.1.0
numpy 1.23.1
pandas 1.4.3
pip 22.2.2
python-dateutil 2.8.2
pytz 2022.2
scikit-learn 1.1.2
scipy 1.9.0
setuptools 64.0.2
six 1.16.0
threadpoolctl 3.1.0
wheel 0.37.1
xgboost 1.4.2

Hello

I am using the package to evaluate potential G4s.

Starting from a fasta file with an entry such as: GGTGGGTAGTTTGACTGGGGCGG

I analyze using
python3 G4Boost.py -f Sequences.fasta --maxloop 20 --minloop 0 --maxG 4 --minG 1 --loops 10 --noreverse --classifier G4Boost_classifier.json --regressor G4Boost_regressor.json

The result is a gff and a csv.
In the gff the results are:
Sequence_1 0 23 Sequence_1_0_23 23 + GGTGGGTAGTTTGACTGGGGCGG

In the csv however, the G4motif is modified and reduced, missing two Gs in the middle of the PQS (the motif goes form a length of 23 to 21).
GGTGGGTAGTTTGACTGGGGCGG --> GGtgGGtagtttgactGGcGG

Is this normal?
Why does this happen? It is changing the sequence.
Is there a way to obtain the G4-pred; G4-prob and mfe-pred of the entire imputed motif? (the 23 length motif and not the 21-long "modified" which is not really what i want to evaluate?)

Also, regarding G4-topology prediction, the algorithm is designed to give the Gs predicted to be part of G-runs (Gs in mayuscules), but not its actual predicted topology (parallel, antiparallel or hybrid), correct?

Thanks for the time

EBR

Trying to test the G4boost.py script with defaults and a single file test.fa with 'GGGAGGGTGGGAGGG' as its only contents and received the following:

Processing GGGAGGGTGGGAGGG
Starting stability prediction!

Traceback (most recent call last):
  File "/home/shared/G4Boost/G4Boost.py", line 252, in <module>
    regressor.load_model(args.regressor)
  File "/home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/sklearn.py", line 599, in load_model
    self.get_booster().load_model(fname)
  File "/home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/core.py", line 2170, in load_model
    self.handle, c_str(fname)))
  File "/home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/core.py", line 218, in _check_call
    raise XGBoostError(py_str(_LIB.XGBGetLastError()))
xgboost.core.XGBoostError: [16:09:15] ../src/common/io.cc:102: Opening G4Boost_regressor.json failed: No such file or directory
Stack trace:
  [bt] (0) /home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/lib/libxgboost.so(+0xc94ed) [0x7fcba139a4ed]
  [bt] (1) /home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/lib/libxgboost.so(+0xc9ada) [0x7fcba139aada]
  [bt] (2) /home/robert/tutorial-env/lib64/python3.6/site-packages/xgboost/lib/libxgboost.so(XGBoosterLoadModel+0x379) [0x7fcba136f9b9]
  [bt] (3) /lib64/libffi.so.6(ffi_call_unix64+0x4c) [0x7fcbeb921dcc]
  [bt] (4) /lib64/libffi.so.6(ffi_call+0x1f5) [0x7fcbeb9216f5]
  [bt] (5) /usr/lib64/python3.6/lib-dynload/_ctypes.cpython-36m-x86_64-linux-gnu.so(_ctypes_callproc+0x2a0) [0x7fcbebb34680]
  [bt] (6) /usr/lib64/python3.6/lib-dynload/_ctypes.cpython-36m-x86_64-linux-gnu.so(+0x97c6) [0x7fcbebb2d7c6]
  [bt] (7) /lib64/libpython3.6m.so.1.0(_PyObject_FastCallDict+0x90) [0x7fcc322eed20]
  [bt] (8) /lib64/libpython3.6m.so.1.0(+0x1522fc) [0x7fcc323982fc]

It seems to be looking for the file 'G4Boost_regressor.json' even though that should be an optional argument, correct?

I hope this message finds you well. Could you please share the Python script used for data preparation, along with the training data? Having access to these resources would greatly assist me in reproducing your code and analysis.

HI,

I am trying to run G4boost on a multifasta file, and it generates only the gff file and not the csv file.

Is G4Boost_v4.py the lastest version?