Code fix pip

[DaniDelHoyo]

The Pipy version of the code yields some coding errors in the python script (toxinpred2.py) when the input sequences is only 1, that I managed to fix with the following replacements. Please feel free to use them as you want.

Line 82: data_test = np.loadtxt(file_name, delimiter=',')
data_test = np.loadtxt(file_name, delimiter=',', ndmin=2)

Also, I have noticed that the way this code calculates the aac is way more inefficient than the same code for toxinpred3. So substituting the aac_comp function with the new toxinpred3 version accelerates the code remarkably.

There are probably other ways to fix it, I have seen other software of yours that have similar codes but that actually work.
Best wishes.

[raghavagps]

Thanks With regards and best wishes Raghava # ======================================================== # # Prof. Gajendra P. S. Raghava, Department of Computational Biology, # # Indraprastha Institute of Information Technology (IIIT), Okhla Phase III, # # New Delhi 110020 ; Phone:+91-11-26907444 # # ======================================================== # PS: Former Chief Scientist, CSIR-Institute of Microbial Technology, Chandigarh Web: http://webs.iiitd.edu.in/raghava/ GS: https://scholar.google.co.in/citations?user=XK5GUiYAAAAJ

…

On 23 Dec 2024, at 19:01, Daniel Del Hoyo Gomez ***@***.***> wrote: The Pipy version of the code yields some coding errors in the python script (toxinpred2.py) that I managed to fix with the following replacements. Please feel free to use them as you want. Line 87: y_p_score1=sess.run([label_name], {input_name: X_test.astype(numpy.float32)})[0] y_p_score1=sess.run([label_name], {input_name: [X_test.astype(numpy.float32)]})[0] Also, I have noticed that the way this code calculates the aac is way more inefficient than the same code for toxinpred3. So substituting the aac_comp function with the new toxinpred3 version accelerates the code remarkably. There are probably other ways to fix it, I have seen other software of yours that have similar codes but that actually work. Best wishes. — Reply to this email directly, view it on GitHub <#6>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AHNUVZKSGKUXXH5KIO6XA5L2HAGDTAVCNFSM6AAAAABUDCLPH6VHI2DSMVQWIX3LMV43ASLTON2WKOZSG42TMMBYGEZTOMY>. You are receiving this because you are subscribed to this thread.