pone.0241728.g001.tif (475.22 kB)
PharmaNet workflow.
figure
posted on 2021-04-26, 17:30 authored by Paola Ruiz Puentes, Natalia Valderrama, Cristina González, Laura Daza, Carolina Muñoz-Camargo, Juan C. Cruz, Pablo ArbeláezFor each molecule we compute a raw molecular image with nxm dimensions, where n is the number of unique atoms and bonds and m is the molecules’ maximum length. A convolutional encoder produces a fingerprint molecular image that is then analyzed globally by an RNN to predict scores for each of the targets in the AD Dataset.
History
Usage metrics
Categories
Keywords
ROC-AUCnovel drug candidateSMILES representationUSD 2.6molecule predictionsequence analysisFDARecurrent Neural Networksfeature extractiontest PharmaNetsilico approachespayback timesReceiver Operating Characteristic curvedetection problemRNNCHEMBL dataanticancer treatmentsactivity predictionimagePCDH 17 pathway102 targetsMolecule Target predictionnovel pharmaceuticalsFPPSfarnesyl pyrophosphate synthaseDUD-E databaseinvestmentcell receptorssilico toxicity predictionperformanceNAP curvePharmaceutical discoveryconvolutional encoder processesmachine learning-based algorithmNormalized Average PrecisionRecurrent Neural Network
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC