Dataset Information

Sun2017 - predictive and interpretable models for PAMPA permeability 7

ABSTRACT: Parallel Artificial Membrane Permeability is an in vitro surrogate to determine the permeability of drugs across cellular membranes. PAMPA at pH 7.4 was experimentally determined in a dataset of 5,473 unique compounds by the NIH-NCATS. 50% of the dataset was used to train a classifier (SVM) to predict the permeability of new compounds, and validated on the remaining 50% of the data, rendering an AUC = 0.88. The Peff was converted to logarithmic, log Peff value lower than 2.0 were considered to have low to moderate permeability, and those with a value higher than 2.5 were considered as high-permeability compounds. Model Type: Predictive machine learning model. Model Relevance: The model predicts a chemical compound as highly or low/moderate permeable. Model Encoded by: Pauline (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos9tyg

SUBMITTER: Zainab Ashimiyu-Abdusalam

PROVIDER: MODEL2404220001 | BioModels | 2024-04-23

REPOSITORIES: BioModels

ACCESS DATA

Publications

Highly predictive and interpretable models for PAMPA permeability.

Sun Hongmao H Nguyen Kimloan K Kerns Edward E Yan Zhengyin Z Yu Kyeong Ri KR Shah Pranav P Jadhav Ajit A Xu Xin X

Bioorganic & medicinal chemistry 20161231 3

Cell membrane permeability is an important determinant for oral absorption and bioavailability of a drug molecule. An in silico model predicting drug permeability is described, which is built based on a large permeability dataset of 7488 compound entries or 5435 structurally unique molecules measured by the same lab using parallel artificial membrane permeability assay (PAMPA). On the basis of customized molecular descriptors, the support vector regression (SVR) model trained with 4071 compounds ...[more]

PMID: 28082071

Similar Datasets

Project description:Chronic injury in kidney transplants remains a major cause of graft loss. The aim of this study was to identify a predictive gene set capable of classifying renal grafts at risk for progressive injury due to fibrosis.The Genomics of Chronic Allograft Rejection (GoCAR) study is a prospective, multicenter study. Biopsies obtained prospectively 3 months after transplantation from renal allograft recipients (n=159) with stable renal function were analyzed for gene expression by microarray. Genes were sought which correlated with subsequent 12-month Chronic Allograft Damage Index (CADI) but neither CADI in the 3 month biopsy nor other histological or clinical parameters. We identified a set of 13 genes that was independently predictive for the development of fi brosis at 1 year (ie, CADI-12 >=2). The gene set had high predictive capacity (area under the curve [AUC] 0·967), which was superior to that of baseline clinical variables (AUC 0·706) and clinical and pathological variables (AUC 0·806). Furthermore routine pathological variables were unable to identify which histologically normal allografts would progress to fi brosis (AUC 0·754), whereas the predictive gene set accurately discriminated between transplants at high and low risk of progression (AUC 0·916). The 13 genes also accurately predicted early allograft loss (AUC 0·842 at 2 years and 0·844 at 3 years). We validated the predictive value of this gene set in an independent cohort from the GoCAR study (n=45, AUC 0·866) and two independent, publically available expression datasets (n=282, AUC 0·831 and n=24, AUC 0·972). Biopsies obtained prospectively 3 months after transplantation from renal allograft recipients (n=159) with stable renal function were analyzed for gene expression by Affymetrix exon arrays. Genes that were specifically correlated with 12-month Chronic Allograft Damage Index (CADI) but neither CADI in the 3 month biopsy nor other histological or clinical parameters were identified by correlation analysis. The minimal geneset was further identified to predict the progressors/non progressors and validated by qPCR in an independent cohort and two public datasets. This dataset is part of the TransQST collection.

Project description:Recurrent venous thromboembolism (VTE) occurs infrequently following a provoked event but occurs in up to 30% of individuals following an initial unprovoked event. We studied 134 patients with VTE separated into 3 groups: (1) âlow-riskâ patients had â¥1 provoked VTE; (2) âmoderate-riskâ patients had no more than 1 unprovoked VTE; (3) âhigh-riskâ patients had â¥2 unprovoked VTE. 44 individuals with no history of VTE were enrolled as healthy controls. Consented individuals were enrolled at 4 medical centers in the US. Total RNA from whole blood was isolated and hybridized to Illumina HT-12 V4 Beadchips to assay whole genome expression. Using class prediction analysis, we distinguished high-risk patients from healthy controls with good receiver operating curve characteristics (AUC=0.88). We also distinguished high-risk from low-risk individuals, moderate-risk individuals from healthy controls, and low-risk individuals from healthy controls with AUCâs of 0.72, 0.77 and 0.72, respectively. Using differential expression analysis, we identified genes relevant to coagulation, immune response and vascular biology, such as SELP and CD46, which were differentially expressed in at least two comparisons. Neither approach distinguished the moderate-risk patients from the high-risk or low-risk groups. Gene expression profiles may provide insights into biological mechanisms associated with patients at risk for recurrent VTE. Prospective studies are needed to validate these findings. This study includes a total of 218 samples/individuals (in 5 groups; APS, high-risk VTE, moderate-risk VTE, low-risk VTE and healthy-controls). Samples in which the percent of probes present was 15% or less (n=51) were excluded leaving 167 samples. The data for these 167 samples were normalized together. However, this record represents the 132 individual samples in the following groups; high-risk (n=40); moderate-risk (n=33); low-risk (n=34); and healthy controls (n=25). The 35 samples in APS group are represented in GSE48001.

Dataset Information

Sun2017 - predictive and interpretable models for PAMPA permeability 7

Publications

Highly predictive and interpretable models for PAMPA permeability.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure