1. |
- Busch, Michael, et al.
(author)
-
How to Predict the p Ka of Any Compound in Any Solvent
- 2022
-
In: ACS Omega. - : American Chemical Society (ACS). - 2470-1343. ; 7:20, s. 17369-17383
-
Journal article (peer-reviewed)abstract
- Acid-base properties of molecules in nonaqueous solvents are of critical importance for almost all areas of chemistry. Despite this very high relevance, our knowledge is still mostly limited to the pKa of rather few compounds in the most common solvents, and a simple yet truly general computational procedure to predict pKa's of any compound in any solvent is still missing. In this contribution, we describe such a procedure. Our method requires only the experimental pKa of a reference compound in water and a few standard quantum-chemical calculations. This method is tested through computing the proton solvation energy in 39 solvents and by comparing the pKa of 142 simple compounds in 12 solvents. Our computations indicate that the method to compute the proton solvation energy is robust with respect to the detailed computational setup and the construction of the solvation model. The unscaled pKa's computed using an implicit solvation model on the other hand differ significantly from the experimental data. These differences are partly associated with the poor quality of the experimental data and the well-known shortcomings of implicit solvation models. General linear scaling relationships to correct this error are suggested for protic and aprotic media. Using these relationships, the deviations between experiment and computations drop to a level comparable to that observed in water, which highlights the efficiency of our method.
|
|
2. |
- Ahlberg, Ernst, et al.
(author)
-
Interpretation of Conformal Prediction Classification Models
- 2015
-
In: STATISTICAL LEARNING AND DATA SCIENCES. - Cham : Springer International Publishing. - 9783319170916 - 9783319170909 ; , s. 323-334
-
Conference paper (peer-reviewed)abstract
- We present a method for interpretation of conformal prediction models. The discrete gradient of the largest p-value is calculated with respect to object space. A criterion is applied to identify the most important component of the gradient and the corresponding part of the object is visualized. The method is exemplified with data from drug discovery relating chemical compounds to mutagenicity. Furthermore, a comparison is made to already established important subgraphs with respect to mutagenicity and this initial assessment shows very useful results with respect to interpretation of a conformal predictor.
|
|
3. |
- Ahlberg, Ernst, et al.
(author)
-
On the selection of relevant historical demand data for revenue management applied to transportation
- 2023
-
In: Journal of Revenue and Pricing Management. - : Springer. - 1476-6930 .- 1477-657X. ; 22:4, s. 266-275
-
Journal article (peer-reviewed)abstract
- The success of revenue management models depends to a large extent on the quality of historical data used to forecast future bookings. Several theoretical models and best practices of handing historical data have been developed over the years, that all rely on assumptions about underlying distribution and seasonality in the historical data. In this paper, we describe a novel method that compares the fingerprints of the departure to optimise and selects historical departures without making assumptions on data distribution or seasonality. By evaluating the method at the departure level and using the Nemenyi rank test, we show the method’s application in the ferry transportation business and discuss its advantages.
|
|
4. |
- Ahlberg, Ernst, et al.
(author)
-
Using conformal prediction to prioritize compound synthesis in drug discovery
- 2017
-
In: Proceedings of Machine Learning Research. - Stockholm : Machine Learning Research. ; , s. 174-184
-
Conference paper (peer-reviewed)abstract
- The choice of how much money and resources to spend to understand certain problems is of high interest in many areas. This work illustrates how computational models can be more tightly coupled with experiments to generate decision data at lower cost without reducing the quality of the decision. Several different strategies are explored to illustrate the trade off between lowering costs and quality in decisions.AUC is used as a performance metric and the number of objects that can be learnt from is constrained. Some of the strategies described reach AUC values over 0.9 and outperforms strategies that are more random. The strategies that use conformal predictor p-values show varying results, although some are top performing.The application studied is taken from the drug discovery process. In the early stages of this process compounds, that potentially could become marketed drugs, are being routinely tested in experimental assays to understand the distribution and interactions in humans.
|
|
5. |
- Ahlberg Helgee, Ernst, 1981
(author)
-
Improving Drug Discovery Decision Making using Machine Learning and Graph Theory in QSAR Modeling
- 2010
-
Doctoral thesis (other academic/artistic)abstract
- During the last decade non-linear machine-learning methods have gained popularity among QSAR modelers. The machine-learning algorithms generate highly accurate models at a cost of increased model complexity where simple interpretations, valid in the entire model domain, are rare. This thesis focuses on maximizing the amount of extracted knowledge from predictive QSAR models and data. This has been achieved by the development of a descriptor importance measure, a method for automated local optimization of compounds and a method for automated extraction of substructural alerts. Furthermore different QSAR modeling strategies have been evaluated with respect to predictivity, risks and information content. To test hypotheses and theories large scale simulations of known relations between activities and descriptors have been conducted. With the simulations it has been possible to study properties of methods,risks, implementations and errors in a controlled manner since the correct answer has been known. Simulation studies have been used in the development of the generally applicable descriptor importance measure and in the analysis of QSAR modeling strategies. The use of simulations is spread in many areas, but not that common in the computational chemistry community. The descriptor importance measure developed can be applied to any machine-learning method and validations using both real data and simulated data show that the descriptor importance measure is very accurate for non-linear methods. An automated method for local optimization of compounds was developed to partly replace manual searches made to optimize compounds. The local optimization of compounds make use of the information in available data and deterministically enumerates new compounds in a space spanned close to the compound of interest. This can be used as a starting point for further compound optimization and aids the chemist in finding new compounds. An other approach to guide chemists in the process of optimizing compounds is through substructural warnings. A fast method for significant substructure extraction has been developed that extracts significant substructures from data with respect to the activity of the compound. The method is at least on par with existing methods in terms of accuracy but is significantly less time consuming. Non-linear machine-learning methods have opened up new possibilities for QSAR modeling that changes the way chemical data can be handled by model algorithms. Therefore properties of Local and Global QSAR modeling strategies have been studied. The results show that Local models come with high risks and are less accurate compared to Global models. In summary this thesis shows that Global QSAR modeling strategies should be applied preferably using methods that are able to handle non-linear relationships. The developed methods can be interpreted easily and an extensive amount of information can be retrieved. For the methods to become easily available to a broader group of users packaging with an open-source chemical platform is needed.
|
|
6. |
- Arvidsson McShane, Staffan, 1990-
(author)
-
Confidence Predictions in Pharmaceutical Sciences
- 2023
-
Doctoral thesis (other academic/artistic)abstract
- The main focus of this thesis has been on Quantitative Structure Activity Relationship (QSAR) modeling using methods producing valid measures of uncertainty. The goal of QSAR is to prospectively predict the outcome from assays, such as ADMET (Absorption, Distribution, Metabolism, Excretion), toxicity and on- and off-target interactions, for novel compounds. QSAR modeling offers an appealing alternative to laboratory work, which is both costly and time-consuming, and can be applied earlier in the development process as candidate drugs can be tested in silico without requiring to synthesize them first. A common theme across the presented papers is the application of conformal and probabilistic prediction models, which are used in order to associate predictions with a level of their reliability – a desirable property that is essential in the stage of decision making. In Paper I we studied approaches on how to utilize biological assay data from legacy systems, in order to improve predictive models. This is otherwise problematic since mixing data from separate systems will cause issues for most machine learning algorithms. We demonstrated that old data could be used to augment the proper training set of a conformal predictor to yield more efficient predictions while preserving model calibration. In Paper II we studied a new approach of predicting metabolic transformations of small molecules based on transformations encoded in SMIRKS format. In this work use used the probabilistic Cross-Venn-ABERS predictor which overall worked well, but had difficulty in modeling the minority class of imbalanced datasets. In Paper III we studied metabolomics data from patients diagnosed with Multiple Sclerosis and found a set of 15 discriminatory metabolites that could be used to classify patients from a validation cohort into one of two sub types of the disease with high accuracy. We further demonstrated that conformal prediction could be useful for tracking the progression of the disease for individual patients, which we exemplified using data from a clinical trial. In Paper IV we introduced CPSign – a software for cheminformatics modeling using conformal and probabilistic methods. CPSign was compared against other regularly used methods for this task, using 32 benchmark datasets, demonstrating that CPSign produces predictive accuracy on par with the best performing methods.
|
|
7. |
- Arvidsson McShane, Staffan, 1990-, et al.
(author)
-
CPSign : Conformal Prediction for Cheminformatics Modeling
- 2024
-
In: Journal of Cheminformatics. - : BioMed Central (BMC). - 1758-2946. ; 16
-
Journal article (peer-reviewed)abstract
- 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. CPSign can be downloaded from GitHub at https://github.com/arosbio/cpsign.
|
|
8. |
- Arvidsson McShane, Staffan, et al.
(author)
-
Machine Learning Strategies When Transitioning between Biological Assays
- 2021
-
In: Journal of Chemical Information and Modeling. - : American Chemical Society (ACS). - 1549-9596 .- 1549-960X. ; 61:7, s. 3722-3733
-
Journal article (peer-reviewed)abstract
- Machine learning is widely used in drug development to predict activity in biological assays based on chemical structure. However, the process of transitioning from one experimental setup to another for the same biological endpoint has not been extensively studied. In a retrospective study, we here explore different modeling strategies of how to combine data from the old and new assays when training conformal prediction models using data from hERG and Na-v assays. We suggest to continuously monitor the validity and efficiency of models as more data is accumulated from the new assay and select a modeling strategy based on these metrics. In order to maximize the utility of data from the old assay, we propose a strategy that augments the proper training set of an inductive conformal predictor by adding data from the old assay but only having data from the new assay in the calibration set, which results in valid (well-calibrated) models with improved efficiency compared to other strategies. We study the results for varying sizes of new and old assays, allowing for discussion of different practical scenarios. We also conclude that our proposed assay transition strategy is more beneficial, and the value of data from the new assay is higher, for the harder case of regression compared to classification problems.
|
|
9. |
- Buendia, Ruben, et al.
(author)
-
Accurate Hit Estimation for Iterative Screening Using Venn-ABERS Predictors
- 2019
-
In: Journal of Chemical Information and Modeling. - : American Chemical Society (ACS). - 1549-9596 .- 1549-960X. ; 59:3, s. 1230-1237
-
Journal article (peer-reviewed)abstract
- Iterative screening has emerged as a promising approach to increase the efficiency of high-throughput screening (HTS) campaigns in drug discovery. By learning from a subset of the compound library, inferences on what compounds to screen next can be made by predictive models. One of the challenges of iterative screening is to decide how many iterations to perform. This is mainly related to difficulties in estimating the prospective hit rate in any given iteration. In this article, a novel method based on Venn - ABERS predictors is proposed. The method provides accurate estimates of the number of hits retrieved in any given iteration during an HTS campaign. The estimates provide the necessary information to support the decision on the number of iterations needed to maximize the screening outcome. Thus, this method offers a prospective screening strategy for early-stage drug discovery.
|
|
10. |
- Carlsson, Lars, et al.
(author)
-
Modifications to p-Values of conformal predictors
- 2015
-
In: Statistical learning and data sciences. - Cham : Springer. - 9783319170909 - 9783319170916 ; , s. 251-259
-
Conference paper (peer-reviewed)abstract
- The original definition of a p-value in a conformal predictor can sometimes lead to too conservative prediction regions when the number of training or calibration examples is small. The situation can be improved by using a modification to define an approximate p-value. Two modified p-values are presented that converges to the original p-value as the number of training or calibration examples goes to infinity. Numerical experiments empirically support the use of a p-value we call the interpolated p-value for conformal prediction. The interpolated p-value seems to be producing prediction sets that have an error rate which corresponds well to the prescribed significance level.
|
|