Related Experiment Video
Updated: Mar 16, 2026
Pharmacophore Modeling for Targets with Extensive Ligand Libraries: A Case Study on SARS-CoV-2 Mpro
Published on: September 26, 2025
Prediction of PARP Inhibition with Proteochemometric Modelling and Conformal Prediction
Isidro Cortés-Ciriano1, Andreas Bender2, Thérèse Malliavin3
1Institut Pasteur, Unité de Bioinformatique Structurale, CNRS UMR 3825, Département de Biologie, Structurale et Chimie, 25, rue du Dr Roux, 75015, Paris, France. isidro.cortes@pasteur.fr.
Abstract:
Poly(ADP-ribose) polymerases (PARPs) play a key role in DNA damage repair. PARP inhibitors act as chemo- and radio- sensitizers and thus potentiate the cytotoxicity of DNA damaging agents. Although PARP inhibitors are currently investigated as chemotherapeutic agents, their cross-reactivity with other members of the PARP family remains unclear. Here, we apply Proteochemometric Modelling (PCM) to model the activity of 181 compounds on 12 human PARPs. We demonstrate that PCM (R0 (2) test =0.65-0.69; RMSEtest =0.95-1.01 °C) displays higher performance on the test set (interpolation) than Family QSAR and Family QSAM (Tukey's HSD, α 0.05), and outperforms Inductive Transfer knowledge among targets (Tukey's HSD, α 0.05). We benchmark the predictive signal of 8 amino acid and 11 full-protein sequence descriptors, obtaining that all of them (except for SOCN) perform at the same level of statistical significance (Tukey's HSD, α 0.05). The extrapolation power of PCM to new compounds (RMSE=1.02±0.80 °C) and targets (RMSE=1.03±0.50 °C) is comparable to interpolation, although the extrapolation ability is not uniform across the chemical and the target space. For this reason, we also provide confidence intervals calculated with conformal prediction. In addition, we present the R package conformal, which permits the calculation of confidence intervals for regression and classification caret models.
Insights
Proteochemometric modelling (PCM) accurately predicts Poly(ADP-ribose) polymerase (PARP) inhibitor activity and cross-reactivity, outperforming other methods. This approach aids in developing new PARP-targeted cancer therapies.
Area of Science:
- Biochemistry
- Pharmacology
- Computational Chemistry
Background:
- Poly(ADP-ribose) polymerases (PARPs) are crucial for DNA repair.
- PARP inhibitors enhance chemotherapy and radiotherapy by increasing DNA damage cytotoxicity.
- The cross-reactivity of PARP inhibitors across the PARP family is not well understood.
Purpose of the Study:
- To apply Proteochemometric Modelling (PCM) to predict the activity of compounds against 12 human PARPs.
- To compare the performance of PCM with other modeling techniques like Family QSAR, Family QSAM, and Inductive Transfer.
- To evaluate the predictive power of various sequence descriptors and the extrapolation capabilities of PCM.
Main Methods:
- Proteochemometric Modelling (PCM) was used to analyze the activity of 181 compounds on 12 human PARPs.
- Performance was evaluated using metrics such as R-squared (R0^2) and Root Mean Squared Error (RMSE) on test sets.
- Statistical significance was assessed using Tukey's HSD test.
- Confidence intervals were calculated using conformal prediction, and an R package 'conformal' was developed.
Main Results:
- PCM demonstrated superior performance in predicting PARP inhibitor activity compared to Family QSAR, Family QSAM, and Inductive Transfer.
- Sequence descriptors, including amino acid and full-protein features, were benchmarked for their predictive signal.
- PCM showed comparable extrapolation power to interpolation for new compounds and targets, with confidence intervals provided via conformal prediction.
Conclusions:
- PCM is a robust method for modeling PARP inhibitor activity and cross-reactivity.
- The developed PCM approach and the 'conformal' R package can aid in the design and optimization of novel PARP inhibitors.
- Understanding cross-reactivity is essential for developing targeted cancer therapies with improved efficacy and reduced side effects.
Related Concept Videos
01:15Impact of Pharmacokinetic–Pharmacodynamic Models: Regulatory Decisions
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...