Biology subjects

Norinder, U.

Publications and source records attributed to Norinder, U..

3 recordsLinked to original sources

bioRxiv2023

CPSign - Conformal Prediction for Cheminformatics Modeling

Conformal prediction has seen many applications in pharmaceutical science, being able to calibrate outputs of machine learning models and producing valid prediction intervals. We here present the open source software CPSign that is a complete implementation of conformal prediction for cheminformatics modeling. CPSign implements inductive and transductive conformal prediction for classification and regression, and probabilistic prediction with the Venn-ABERS methodology. The main chemical representation is signatures but other types of descriptors are also supported. The main modeling methodology is support vector machines (SVMs), but additional modeling methods are supported via an extension mechanism, e.g. DeepLearning4j models. We also describe features for visualizing results from conformal models including calibration and efficiency plots, as well as features to publish predictive models as REST services. We compare CPSign against other common cheminformatics modeling approaches including random forest, and a directed message-passing neural network. The results show that CPSign produces robust predictive performance with comparative predictive efficiency, with superior runtime and lower hardware requirements compared to neural network based models. CPSign has been used in several studies and is in production-use in multiple organizations. The ability to work directly with chemical input files, perform descriptor calculation and modeling with SVM in the conformal prediction framework, with a single software package having a low footprint and fast execution time makes CPSign a convenient and yet flexible package for training, deploying, and predicting on chemical data.

bioinformatics↗

bioRxiv2019

Deep Docking - a Deep Learning Approach for Virtual Screening of Big Chemical Datasets

Drug discovery is an extensive and rigorous process that requires up to 2 billion dollars of investments and more than ten years of research and development to bring a molecule "from bench to a bedside". While virtual screening can significantly enhance drug discovery workflow, it ultimately lags the current rate of expansion of chemical databases that already incorporate billions of purchasable compounds. This surge of available small molecules presents great opportunities for drug discovery but also demands for faster virtual screening methods and protocols. In order to address this challenge, we herein introduce Deep Docking (D2) - a novel deep learning-based approach which is suited for docking billions of molecular structures. The developed D2-platform utilizes quantitative structure-activity relationship (QSAR) based deep models trained on docking scores of subsets of a large chemical library (Big Base) to approximate the docking outcome for yet unprocessed molecular entries and to remove unfavorable structures in an iterative manner. We applied D2 to virtually screen 1.36 billion molecules form the ZINC15 library against 12 prominent target proteins, and demonstrated up to 100-fold chemical data reduction and 6,000-fold enrichment for top hits, without notable loss of well-docked entities. The developed D2 protocol can readily be used in conjunction with any docking program and was made publicly available.

bioinformatics↗

bioRxiv2017

Applying Mondrian Cross-Conformal Prediction to Estimate Prediction Confidence on Large Imbalanced Bioactivity Datasets

Conformal prediction has been proposed as a more rigorous way to define prediction confidence compared to other application domain concepts that have earlier been used for QSAR modelling. One main advantage of such a method is that it provides a prediction region potentially with multiple predicted labels, which contrasts to the single valued (regression) or single label (classification) output predictions by standard QSAR modelling algorithms. Standard conformal prediction might not be suitable for imbalanced datasets. Therefore, Mondrian cross-conformal prediction (MCCP) which combines the Mondrian inductive conformal prediction with cross-fold calibration sets has been introduced. In this study, the MCCP method was applied to 18 publicly available datasets that have various imbalance levels varying from 1:10 to 1:1000 (ratio of active/inactive compounds). Our results show that MCCP in general performed well on cheminformatics datasets with various imbalance levels. More importantly, the method not only provides confidence of prediction and prediction regions compared to standard machine learning methods, but also produces valid predictions for the minority class. In addition, a compound similarity based nonconformity measure was investigated. Our results demonstrate that although it gives valid predictions, its efficiency is much worse than nonconformity measures obtained from supervised learning.

pharmacology and toxicology↗