Deep-PK API


API - Documentation



Here we provide an API (Application Programming Interface) to help users in integrating Deep-PK into their research pipelines. In a nutshell, all predictive jobs submitted to Deep-PK's server are linked with a unique ID. This ID can be used to query the status of the job and to retrieve its results (after submission being processed).

Job Submission Via API


You should always use the following URL to submit your jobs via API

POST

Arguments:

  • Input - Provide query molecule(s) via the following options:
    • SMILES_string - Single SMILES string
    • SMILES_file - a list of SMILES string(s)
    • SDF_file - a list of SDF structure(s)
  • email (optional) - Email for contact when the job is finished
  • pred_type - The type of prediction to be done. Options are:
    • Absorption
    • Distribution
    • Metabolism
    • Excretion
    • ADMET (default)

Return:

  • job_id - ID used for uniquely identify each job

Examples (using curl):



curl  https://biosig.lab.uq.edu.au/deeppk/api/predict -X POST -i -F smiles="COC1=C(O)C=C2C(OC(=O)C=C2C2=CC(O)=C(O)C=C2)=C1" -F pred_type="admet"

curl  https://biosig.lab.uq.edu.au/deeppk/api/predict -X POST -i -F smiles_file=@deeppk_example.csv -F pred_type="admet"
            	
            

Examples (using python):

You can find the python sample code by clicking at: deeppk_api_smiles_post.py . If you want to use it, you can provide to run python the same parameters described for curl:


python deeppk_api_post.py --smiles "CN1C(=O)NC(=O)[C@](C)(C2=CCCCC2)C1=O"

python deeppk_api_post.py --smiles_file deeppk_example.csv   

            

Example of Response from the Deep-PK Server:



                HTTP/1.0 200 OK
                Content-Type: application/json
                Content-Length: 45                
                {
                    "job_id": "admet_1672109316.6310973"
                }
			

GET

Arguments:

  • job_id - ID used for uniquely identify each job.

Return:

For jobs still being processed or waiting on queue, the message below will be returned from querying the respective sample(s):


{
    "status": "running"
}
			

Examples (using curl):



curl  https://biosig.lab.uq.edu.au/deeppk/api/predict -X GET -F job_id="admet_1672107751.7206752"            	
            

Examples (using python):

You can find the python sample code by clicking at: deeppk_api_get.py . If you want to use it, you can retrieve your results in python using the same parameter described for curl:


python deeppk_api_get.py --job_id admet_1672107751.7206752               
            

Example of Response from the Deep-PK's Server:

After processed, users will get information for each predictive category chosen and its respective models. Information include the category of the model, the machine learning task, the unit, the processed SMILES, the prediction, the confidence score, and the interpretation for the prediction based on the confidence score.

Models are identified by molecule as users can submit a job containing several molecules at the same time into files (as shown bellow).


                "{"0":{"SMILES":"COC1=C(O)C=C2C(OC(=O)C=C2C2=CC(O)=C(O)C=C2)=C1"
                "Predictions_general_properties_bp":474.788
                "Probability_general_properties_bp":"-"
                "Interpretation_general_properties_bp":"BP<25: gas"
                "Predictions_general_properties_hydration_free_energy":-13.612
                "Probability_general_properties_hydration_free_energy":"-"
                "Interpretation_general_properties_hydration_free_energy":"None"
                "Predictions_general_properties_log_d_74":2.038
                "Probability_general_properties_log_d_74":"-"
                "Interpretation_general_properties_log_d_74":"Proper Value: 1 to 3 log mol/L"
                "Predictions_general_properties_log_p":2.577
                "Probability_general_properties_log_p":"-"
                "Interpretation_general_properties_log_p":"Proper Value: 0 to 3 log mol/L"
                "Predictions_general_properties_log_vp":-9.393
                "Probability_general_properties_log_vp":"-"
                "Interpretation_general_properties_log_vp":"Vapor (Gas) Phase: log vp < 4; Vapor and Particulate Phase: 5 =< log vp < 8; Solid Phase: log vp > 8 "
                "Predictions_general_properties_mp":262.762
                "Probability_general_properties_mp":"-"
                "Interpretation_general_properties_mp":"MP<25: liquid; MP>25:solid"
                "Predictions_general_properties_pka_acid":8.435
                "Probability_general_properties_pka_acid":"-"
                "Interpretation_general_properties_pka_acid":"None"
                "Predictions_general_properties_pka_basic":5.978
                "Probability_general_properties_pka_basic":"-"
                "Interpretation_general_properties_pka_basic":"None"
                "Predictions_absorption_caco_2":"Non-Permeable"
                "Probability_absorption_caco_2":0.002
                "Interpretation_absorption_caco_2":"High Non-Permeability"
                "Predictions_absorption_f20":"Bioavailable"
                "Probability_absorption_f20":0.808
                "Interpretation_absorption_f20":"Medium Bioavailability"
                "Predictions_absorption_f30":"Non-Bioavailable"
                "Probability_absorption_f30":0.333
                "Interpretation_absorption_f30":"Low Non-Bioavailability"
                "Predictions_absorption_hia":"Absorbed"
                "Probability_absorption_hia":0.864
                "Interpretation_absorption_hia":"High Absorption"
                "Predictions_absorption_log_s":-3.376
                "Probability_absorption_log_s":"-"
                "Interpretation_absorption_log_s":"Proper Value: -4 to 0.5 log mol/L"
                "Predictions_absorption_mdck_permeability":-4.689
                "Probability_absorption_mdck_permeability":"-"
                "Interpretation_absorption_mdck_permeability":"Proper Value:  > 2 x 10-6cm/s"
                "Predictions_absorption_ob":"Non-Bioavailable"
                "Probability_absorption_ob":0.208
                "Interpretation_absorption_ob":"Medium Non-Bioavailability"
                "Predictions_absorption_pgp_inhibitor":"Non-Inhibitor"
                "Probability_absorption_pgp_inhibitor":0.326
                "Interpretation_absorption_pgp_inhibitor":"Medium Non-Inhibition"
                "Predictions_absorption_pgp_substrate":"Non-Substrate"
                "Probability_absorption_pgp_substrate":0.03
                "Interpretation_absorption_pgp_substrate":"High Non-Substrative Activity"
                "Predictions_absorption_skin_permeability":"Non-Permeable"
                "Probability_absorption_skin_permeability":0.275
                "Interpretation_absorption_skin_permeability":"Medium Non-Permeability"
                "Predictions_distribution_bbb":"Non-Penetrating"
                "Probability_distribution_bbb":0.0
                "Interpretation_distribution_bbb":"High Non-Penetration"
                "Predictions_distribution_human_clinical_drugs_vdss":-0.04
                "Probability_distribution_human_clinical_drugs_vdss":"-"
                "Interpretation_distribution_human_clinical_drugs_vdss":"Low Value: < 0.71 L/kg (log VDss < -0.15); High Value > 2.81 L/kg (log VDss > 0.45)."
                "Predictions_distribution_ppb":85.573
                "Probability_distribution_ppb":"-"
                "Interpretation_distribution_ppb":"Proper Value: therapeutic index < 90 perc; Poor Value value > 90 perc"
                "Predictions_metabolism_bcrp":"Inhibitor"
                "Probability_metabolism_bcrp":0.68
                "Interpretation_metabolism_bcrp":"Medium Inhibition"
                "Predictions_metabolism_cyp1a2_inhibitor":"Inhibitor"
                "Probability_metabolism_cyp1a2_inhibitor":0.906
                "Interpretation_metabolism_cyp1a2_inhibitor":"High Inhibition"
                "Predictions_metabolism_cyp2c19_inhibitor":"Non-Inhibitor"
                "Probability_metabolism_cyp2c19_inhibitor":0.0
                "Interpretation_metabolism_cyp2c19_inhibitor":"High Non-Inhibition"
                "Predictions_metabolism_cyp2c9_inhibitor":"Non-Inhibitor"
                "Probability_metabolism_cyp2c9_inhibitor":0.0
                "Interpretation_metabolism_cyp2c9_inhibitor":"High Non-Inhibition"
                "Predictions_metabolism_cyp2c9_substrate":"Substrate"
                "Probability_metabolism_cyp2c9_substrate":0.984
                "Interpretation_metabolism_cyp2c9_substrate":"High Substrative"
                "Predictions_metabolism_cyp2d6_inhibitor":"Non-Inhibitor"
                "Probability_metabolism_cyp2d6_inhibitor":0.0
                "Interpretation_metabolism_cyp2d6_inhibitor":"High Non-Inhibition"
                "Predictions_metabolism_cyp2d6_substrate":"Non-Substrate"
                "Probability_metabolism_cyp2d6_substrate":0.035
                "Interpretation_metabolism_cyp2d6_substrate":"High Non-Substrative Activity"
                "Predictions_metabolism_cyp3a4_inhibitor":"Non-Inhibitor"
                "Probability_metabolism_cyp3a4_inhibitor":0.343
                "Interpretation_metabolism_cyp3a4_inhibitor":"Low Non-Inhibition"
                "Predictions_metabolism_cyp3a4_substrate":"Substrate"
                "Probability_metabolism_cyp3a4_substrate":0.603
                "Interpretation_metabolism_cyp3a4_substrate":"Low Substrative"
                "Predictions_metabolism_cyppro_iinh":0.476
                "Probability_metabolism_cyppro_iinh":"-"
                "Interpretation_metabolism_cyppro_iinh":"None"
                "Predictions_metabolism_cyppro_xi_cyp1a2":0.925
                "Probability_metabolism_cyppro_xi_cyp1a2":"-"
                "Interpretation_metabolism_cyppro_xi_cyp1a2":"None"
                "Predictions_metabolism_cyppro_xi_cyp2a9":0.603
                "Probability_metabolism_cyppro_xi_cyp2a9":"-"
                "Interpretation_metabolism_cyppro_xi_cyp2a9":"None"
                "Predictions_metabolism_cyppro_xi_cyp2c19":0.617
                "Probability_metabolism_cyppro_xi_cyp2c19":"-"
                "Interpretation_metabolism_cyppro_xi_cyp2c19":"None"
                "Predictions_metabolism_cyppro_xi_cyp2d6":0.378
                "Probability_metabolism_cyppro_xi_cyp2d6":"-"
                "Interpretation_metabolism_cyppro_xi_cyp2d6":"None"
                "Predictions_metabolism_oatp1b1":"Non-Inhibitor"
                "Probability_metabolism_oatp1b1":0.117
                "Interpretation_metabolism_oatp1b1":"High Non-Inhibition"
                "Predictions_metabolism_oatp1b3":"Non-Inhibitor"
                "Probability_metabolism_oatp1b3":0.114
                "Interpretation_metabolism_oatp1b3":"High Non-Inhibition"
                "Predictions_excretion_clearance":7.36
                "Probability_excretion_clearance":"-"
                "Interpretation_excretion_clearance":"None"
                "Predictions_excretion_oct2":"Non-Inhibitor"
                "Probability_excretion_oct2":0.0
                "Interpretation_excretion_oct2":"High Non-Inhibition"
                "Predictions_excretion_t05":"Half-life < 3hs"
                "Probability_excretion_t05":0.445
                "Interpretation_excretion_t05":"Low Probabilitity of Half-life < 3hs"}
            }"
			



UQ Logo
The University of Melbourne logo
Baker Logo
This material is Open Knowledge

Best viewed using Chrome on 1280x960 resolution and above