PINNED: Identifying Characteristics of Druggable Human Proteins Using an Interpretable Neural Network DOI Creative Commons
Michael Cunningham,

Danielle Pins,

Zoltán Dezső

et al.

Published: March 30, 2023

The identification of human proteins that are amenable to pharmacologic modulation without significant off-target effects remains an important unsolved challenge. Computational methods have been devised identify features which distinguish between “druggable” and “undruggable” proteins, finding protein sequence, tissue cellular localization, biological role, position in the protein-protein interaction network all discriminant factors. However, many prior efforts automate assessment druggability suffer from low performance or poor interpretability. We developed a neural network-based machine learning model capable generating sub-scores based on each four distinct categories, combining them form overall score. achieves excellent separating drugged undrugged proteome, with area under receiver operating characteristic (AUC) 0.95. Our use multiple allows potential targets interest contributors druggability, leading more interpretable holistic novel targets.

Language: Английский

Drug-Target Interactions Prediction Using Stacking Ensemble Learning Approach DOI

Viko Pradana Prasetyo,

Wiwik Anggraeni

2022 International Electronics Symposium (IES), Journal Year: 2024, Volume and Issue: 551, P. 681 - 686

Published: Aug. 6, 2024

Language: Английский

Citations

0
DrugProtAI: A guide to the future research of investigational target proteins DOI Open Access

Ankit Halder,

Sabyasachi Samantaray,

Sahil Barbade

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 8, 2024

Abstract Drug design and development are central to clinical research, yet ninety percent of drugs fail reach the clinic, often due inappropriate selection drug targets. Conventional methods for target identification lack precision sensitivity. While various computational tools have been developed predict druggability proteins, they focus on limited subsets human proteome or rely solely amino acid properties. To address challenge class imbalance between proteins with without approved drugs, we propose a novel Partitioning Method. We evaluated potential 20,273 reviewed which 2,636 drugs. Our comprehensive analysis 183 features, encompassing biophysical sequence-derived properties, achieved median AUC 0.86 in predictions. utilize SHAP (Shapley Additive Explanations) scores identify key predictors interpret their contribution druggability. 688 investigational from DrugBank ( https://go.drugbank.com/ ) using our tool, DrugProtAI https://drugprotai.pythonanywhere.com/ ). tool offers predictions access 2M+ publications targets effects, aiding development. believe that insights into will significantly advance propel field forward.

Language: Английский

Citations

0
Predicting cyclins based on key features and machine learning methods DOI

Chengyan Wu,

Zhi‐Xue Xu, Nan Li

et al.

Methods, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 1, 2024

Language: Английский

Citations

0
PINNED: Identifying Characteristics of Druggable Human Proteins Using an Interpretable Neural Network DOI Creative Commons
Michael Cunningham,

Danielle Pins,

Zoltán Dezső

et al.

Published: March 30, 2023

The identification of human proteins that are amenable to pharmacologic modulation without significant off-target effects remains an important unsolved challenge. Computational methods have been devised identify features which distinguish between “druggable” and “undruggable” proteins, finding protein sequence, tissue cellular localization, biological role, position in the protein-protein interaction network all discriminant factors. However, many prior efforts automate assessment druggability suffer from low performance or poor interpretability. We developed a neural network-based machine learning model capable generating sub-scores based on each four distinct categories, combining them form overall score. achieves excellent separating drugged undrugged proteome, with area under receiver operating characteristic (AUC) 0.95. Our use multiple allows potential targets interest contributors druggability, leading more interpretable holistic novel targets.

Language: Английский

Citations

0