Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction.

Computer aided synthesis planning, suggesting synthetic routes for molecules of interest, is a rapidly growing field. The machine learning methods used are often dependent on access to large datasets for training, but finite experimental budgets limit how much data can be obtained from experiments. This suggests the use of schemes for data collection such as active learning, which identifies the data points of highest impact for model accuracy, and which has been used in recent studies with success. However, little has been done to explore the robustness of the methods predicting reaction yield when used together with active learning to reduce the amount of experimental data needed for training. This study aims to investigate the influence of machine learning algorithms and the number of initial data points on reaction yield prediction for two public high-throughput experimentation datasets. Our results show that active learning based on output margin reached a pre-defined AUROC faster than random sampling on both datasets. Analysis of feature importance of the trained machine learning models suggests active learning had a larger influence on the model accuracy when only a few features were important for the model prediction.

Uncertainty quantification in drug design.

Machine learning and artificial intelligence are increasingly being applied to the drug-design process as a result of the development of novel algorithms, growing access, the falling cost of computation and the development of novel technologies for generating chemically and biologically relevant data. There has been recent progress in fields such as molecular de novo generation, synthetic route prediction and, to some extent, property predictions. Despite this, most research in these fields has focused on improving the accuracy of the technologies, rather than on quantifying the uncertainty in the predictions. Uncertainty quantification will become a key component in autonomous decision making and will be crucial for integrating machine learning and chemistry automation to create an autonomous design-make-test-analyse cycle. This review covers the empirical, frequentist and Bayesian approaches to uncertainty quantification, and outlines how they can be used for drug design. We also outline the impact of uncertainty quantification on decision making.

Adherence to and persistence with zoledronic acid treatment for osteoporosis-reasons for early discontinuation.

This retrospective study reports 81% long-term (> 3 years) adherence to and 77% persistence with zoledronic acid (ZA) treatment in osteoporosis patients, with ZA being costfree for patients. Eight percent of patients discontinued treatment because of adverse events (AEs), with a tendency of higher discontinuation rate in older patients. PURPOSE: This study investigated (1) long-term adherence to and persistence with ZA treatment in a real-world setting, (2) extent to which an adverse reaction to ZA impacted on adherence and persistence, and (3) whether there were sex or age differences in patients that had early treatment termination (ETT) due to AEs and those who adhered to the regimen. METHODS: All patients treated with ZA at the Endocrinology Department at Linköping University Hospital, Linköping, Sweden between 2012 and 2017 were included. ETT was defined as < 3 ZA infusions, which was confirmed from patients' medical records. RESULTS: A total of 414 patients were treated with ZA, with 81% receiving > 3 ZA infusions. Three-year persistence was 77% for a treatment window of 365 days ± 90 days (75% with 365 days ± 60 days window). The most common reason for ETT was AEs (8%), followed by medical conditions (5%), biological aging (3%), and other (e.g., lost to follow-up [3%]). Most patients who discontinued treatment because of AEs reported symptoms of acute-phase reaction, and tended to be older than those who adhered to treatment (74 ± 9 vs 70 ± 13 years, p = 0.064). There was no difference in sex ratio between the 2 groups (85% vs 90% females, p = 0.367). CONCLUSION: Rates of long-term adherence to and persistence with ZA treatment were high with a pre-scheduled 3-year treatment regimen in the tax-financed Swedish healthcare system. AEs-mainly acute-phase reaction-were the most common reason for ETT, occurring in nearly 1 out of 10 patients.

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models.

Generative models are becoming a tool of choice for exploring the molecular space. These models learn on a large training dataset and produce novel molecular structures with similar properties. Generated structures can be utilized for virtual screening or training semi-supervized predictive models in the downstream tasks. While there are plenty of generative models, it is unclear how to compare and rank them. In this work, we introduce a benchmarking platform called Molecular Sets (MOSES) to standardize training and comparison of molecular generative models. MOSES provides training and testing datasets, and a set of metrics to evaluate the quality and diversity of generated structures. We have implemented and compared several molecular generation models and suggest to use our results as reference points for further advancements in generative chemistry research. The platform and source code are available at https://github.com/molecularsets/moses.

AI-assisted synthesis prediction.

Application of AI technologies in synthesis prediction has developed very rapidly in recent years. We attempt here to give a comprehensive summary on the latest advancement on retro-synthesis planning, forward synthesis prediction as well as quantum chemistry-based reaction prediction models. Besides an introduction on the AI/ML models for addressing various synthesis related problems, the sources of the reaction datasets used in model building is also covered. In addition to the predictive models, the robotics based high throughput experimentation technology will be another crucial factor for conducting synthesis in an automated fashion. Some state-of-the-art of high throughput experimentation practices carried out in the pharmaceutical industry are highlighted in this chapter to give the reader a sense of how future chemistry will be conducted to make compounds faster and cheaper.

A de novo molecular generation method using latent vector based generative adversarial network.

Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

Randomized SMILES strings improve the quality of molecular generative models.

Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million, 10,000 and 1000), with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations. To guide the benchmarks new metrics were developed that define how well a model has generalized the training set. The generated chemical space is evaluated with respect to its uniformity, closedness and completeness. Results show that models that use LSTM cells trained with 1 million randomized SMILES, a non-unique molecular string representation, are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space. Specifically, a model was trained with randomized SMILES that was able to generate almost all molecules from GDB-13 with a quasi-uniform probability. Models trained with smaller samples show an even bigger improvement when trained with randomized SMILES models. Additionally, models were trained on molecules obtained from ChEMBL and illustrate again that training with randomized SMILES lead to models having a better representation of the drug-like chemical space. Namely, the model trained with randomized SMILES was able to generate at least double the amount of unique molecules with the same distribution of properties comparing to one trained with canonical SMILES.