Dataset Information

DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets.

ABSTRACT: The druggability of targets is a crucial consideration in drug target selection. Here, we adopt a stochastic semi-supervised ML framework to develop DrugnomeAI, which estimates the druggability likelihood for every protein-coding gene in the human exome. DrugnomeAI integrates gene-level properties from 15 sources resulting in 324 features. The tool generates exome-wide predictions based on labelled sets of known drug targets (median AUC: 0.97), highlighting features from protein-protein interaction networks as top predictors. DrugnomeAI provides generic as well as specialised models stratified by disease type or drug therapeutic modality. The top-ranking DrugnomeAI genes were significantly enriched for genes previously selected for clinical development programs (p value < 1 × 10^-308) and for genes achieving genome-wide significance in phenome-wide association studies of 450 K UK Biobank exomes for binary (p value = 1.7 × 10^-5) and quantitative traits (p value = 1.6 × 10^-7). We accompany our method with a web application ( http://drugnomeai.public.cgr.astrazeneca.com ) to visualise the druggability predictions and the key features that define gene druggability, per disease type and modality.

SUBMITTER: Raies A

PROVIDER: S-EPMC9700683 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets.

Raies Arwa A Tulodziecka Ewa E Stainer James J Middleton Lawrence L Dhindsa Ryan S RS Hill Pamela P Engkvist Ola O Harper Andrew R AR Petrovski Slavé S Vitsios Dimitrios D

Communications biology 20221124 1

The druggability of targets is a crucial consideration in drug target selection. Here, we adopt a stochastic semi-supervised ML framework to develop DrugnomeAI, which estimates the druggability likelihood for every protein-coding gene in the human exome. DrugnomeAI integrates gene-level properties from 15 sources resulting in 324 features. The tool generates exome-wide predictions based on labelled sets of known drug targets (median AUC: 0.97), highlighting features from protein-protein interact ...[more]

PMID: 36434048

Similar Datasets

Project description:BackgroundSarcopenia presents a pressing public health concern due to its association with age-related muscle mass decline, strength loss and reduced physical performance, particularly in the growing older population. Given the absence of approved pharmacological therapies for sarcopenia, the need to discover effective pharmacological interventions has become critical.MethodsTo address this challenge and discover new therapies, we developed a novel Multi-Task Attention-aware method for Multi-Omics data (MTA-MO) to extract complex biological insights from various biomedical data sources, including transcriptome, methylome and genome data to identify drug targets and discover new therapies. Additionally, MTA-MO integrates human protein-protein interaction (PPI) networks and drug-target networks to improve target identification. The novel method is applied to a multi-omics dataset that included 1055 participants aged 20-50 (mean (± SD) age 36.88 (± 8.64)), comprising 37.82% African-American and 62.18% Caucasian/White individuals. Physical activity levels were self-reported and categorized into three groups: ≥ 3 times/week, < 3 times/week and no regular exercise. Mean (± SD) measures for grip strength, appendicular lean mass (ALM), exercise frequency and smoking status (no/yes, n (%)) were 38.72 (± 8.93) kg, 28.65 (± 4.63) kg, 4.31 (± 1.79) and 30.81%/69.19%, respectively. Significant differences (p < 0.05) were found between groups in age, ALM, smoking, and consumption of milk, alcohol, beer and wine.ResultsUsing the MTA-MO method, we identified 639 gene targets, and by analysing PPIs and querying public databases, we narrowed this list down to seven potential hub genes associated with sarcopenia (ESR1, ATM, CDC42, EP300, PIK3CA, EGF and PTK2B). These findings were further validated through diverse levels of pathobiological evidence associated with sarcopenia. Gene Ontology and KEGG pathways analysis highlighted five key functions and signalling pathways relevant to skeletal muscle. The interaction network analysis identified three transcriptional factors (GATA2, JUN and FOXC1) as the key transcriptional regulators of the seven potential genes. In silico analysis of 1940 drug candidates identified canagliflozin as a promising candidate for repurposing in sarcopenia, demonstrating the strongest binding affinity to the PTK2B protein (inhibition constant 6.97 μM). This binding is stabilized by hydrophobic bonds, Van der Waals forces, pi-alkyl interactions and pi-anion interactions around PTK2B's active residues, suggesting its potential as a therapeutic option.ConclusionsOur novel approach effectively integrates multi-omics data to identify potential treatments for sarcopenia. The findings suggest that canagliflozin could be a promising therapeutic candidate for sarcopenia.

Project description:BackgroundAccurate estimation of historical PM2.5 (particle matter with an aerodynamic diameter of less than 2.5μm) is critical and essential for environmental health risk assessment.ObjectivesThe aim of this study was to develop a multiple-level stacked ensemble machine learning framework for improving the estimation of the daily ground-level PM2.5 concentrations.MethodsAn innovative deep ensemble machine learning framework (DEML) was developed to estimate the daily PM2.5 concentrations. The framework has a three-stage structure: At the first stage, four base models [gradient boosting machine (GBM), support vector machine (SVM), random forest (RF), and eXtreme gradient boosting (XGBoost)] were used to generate a new data set of PM2.5 concentrations for training the next-stage learners. At the second stage, three meta-models [RF, XGBoost, and Generalized Linear Model (GLM)] were used to estimate PM2.5 concentrations using a combination of the original data set and the predictions from the first-stage models. At the third stage, a nonnegative least squares (NNLS) algorithm was employed to obtain the optimal weights for PM2.5 estimation. We took the data from 133 monitoring stations in Italy as an example to implement the DEML to predict daily PM2.5 at each 1km×1km grid cell from 2015 to 2019 across Italy. We evaluated the model performance by performing 10-fold cross-validation (CV) and compared it with five benchmark algorithms [GBM, SVM, RF, XGBoost, and Super Learner (SL)].ResultsThe results revealed that the PM2.5 prediction performance of DEML [coefficients of determination (R2)=0.87 and root mean square error (RMSE)=5.38μg/m3] was superior to any benchmark models (with R2 of 0.51, 0.76, 0.83, 0.70, and 0.83 for GBM, SVM, RF, XGBoost, and SL approach, respectively). DEML displayed reliable performance in capturing the spatiotemporal variations of PM2.5 in Italy.DiscussionThe proposed DEML framework achieved an outstanding performance in PM2.5 estimation, which could be used as a tool for more accurate environmental exposure assessment. https://doi.org/10.1289/EHP9752.

Dataset Information

DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets.

Publications

DrugnomeAI is an ensemble machine-learning framework for predicting druggability of candidate drug targets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets