A systematic study of key elements underlying molecular property prediction.

Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4200 models on SMILES sequences and 8400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.

An integrated LSTM-HeteroRGNN model for interpretable opioid overdose risk prediction.

Opioid overdose (OD) has become a leading cause of accidental death in the United States, and overdose deaths reached a record high during the COVID-19 pandemic. Combating the opioid crisis requires targeting high-need populations by identifying individuals at risk of OD. While deep learning emerges as a powerful method for building predictive models using large scale electronic health records (EHR), it is challenged by the complex intrinsic relationships among EHR data. Further, its utility is limited by the lack of clinically meaningful explainability, which is necessary for making informed clinical or policy decisions using such models. In this paper, we present LIGHTED, an integrated deep learning model combining long short term memory (LSTM) and graph neural networks (GNN) to predict patients' OD risk. The LIGHTED model can incorporate the temporal effects of disease progression and the knowledge learned from interactions among clinical features. We evaluated the model using Cerner's Health Facts database with over 5 million patients. Our experiments demonstrated that the model outperforms traditional machine learning methods and other deep learning models. We also proposed a novel interpretability method by exploiting embeddings provided by GNNs to cluster patients and EHR features respectively, and conducted qualitative feature cluster analysis for clinical interpretations. Our study shows that LIGHTED can take advantage of longitudinal EHR data and the intrinsic graph structure of EHRs among patients to provide effective and interpretable OD risk predictions that may potentially improve clinical decision support.

Artificial intelligence in drug discovery: applications and techniques.

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in many drug discovery applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e. molecular property prediction and molecule generation. We then present common data resources, molecule representations and benchmark platforms. As a major part of the survey, AI techniques are dissected into model architectures and learning paradigms. To reflect the technical development of AI in drug discovery over the years, the surveyed works are organized chronologically. We expect that this survey provides a comprehensive review on AI in drug discovery. We also provide a GitHub repository with a collection of papers (and codes, if applicable) as a learning resource, which is regularly updated.

A Large-Scale Observational Study on the Temporal Trends and Risk Factors of Opioid Overdose: Real-World Evidence for Better Opioids.

BACKGROUND: The USA is in the midst of an opioid overdose epidemic. To address the epidemic, we conducted a large-scale population study on opioid overdose. OBJECTIVES: The primary objective of this study was to evaluate the temporal trends and risk factors of inpatient opioid overdose. Based on its patterns, the secondary objective was to examine the innate properties of opioid analgesics underlying reduced overdose effects. METHODS: A retrospective cross-sectional study was conducted based on a large-scale inpatient electronic health records database, Cerner Health Facts®, with (1) inclusion criteria for participants as patients admitted between 1 January, 2009 and 31 December, 2017 and (2) measurements as opioid overdose prevalence by year, demographics, and prescription opioid exposures. RESULTS: A total of 4,720,041 patients with 7,339,480 inpatient encounters were retrieved from Cerner Health Facts®. Among them, 30.2% patients were aged 65+ years, 57.0% female, 70.1% Caucasian, 42.3% single, 32.0% from the South, and 80.8% in an urban area. From 2009 to 2017, annual opioid overdose prevalence per 1000 patients significantly increased from 3.7 to 11.9 with an adjusted odds ratio (aOR): 1.16, 95% confidence interval (CI) 1.15-1.16. Compared to the major demographic counterparts, being in (1) age group: 41-50 years (overall aOR 1.36, 95% CI 1.31-1.40) or 51-64 years (overall aOR 1.35, 95% CI 1.32-1.39), (2) marital status: divorced (overall aOR 1.19, 95% CI 1.15-1.23), and (3) census region: West (overall aOR 1.32, 95% CI 1.28-1.36) were significantly associated with a higher odds of opioid overdose. Prescription opioid exposures were also associated with an increased odds of opioid overdose, such as meperidine (overall aOR 1.09, 95% CI 1.06-1.13) and tramadol (overall aOR 2.20, 95% CI 2.14-2.27). Examination on the relationships between opioid analgesic properties and their association strengths, aORs, and opioid overdose showed that lower aOR values were significantly associated with (1) high molecular weight, (2) non-interaction with multi-drug resistance protein 1 or interaction with cytochrome P450 3A4, and (3) non-interaction with the delta opioid receptor or kappa opioid receptor. CONCLUSIONS: The significant increasing trends of opioid overdose at the inpatient care setting from 2009 to 2017 suggested an ongoing need for efforts to combat the opioid overdose epidemic in the USA. Risk factors associated with opioid overdose included patient demographics and prescription opioid exposures. Moreover, there are physicochemical, pharmacokinetic, and pharmacodynamic properties underlying reduced overdose effects, which can be utilized to develop better opioids.

Identifying risk of opioid use disorder for patients taking opioid medications with deep learning.

OBJECTIVE: The United States is experiencing an opioid epidemic. In recent years, there were more than 10 million opioid misusers aged 12 years or older annually. Identifying patients at high risk of opioid use disorder (OUD) can help to make early clinical interventions to reduce the risk of OUD. Our goal is to develop and evaluate models to predict OUD for patients on opioid medications using electronic health records and deep learning methods. The resulting models help us to better understand OUD, providing new insights on the opioid epidemic. Further, these models provide a foundation for clinical tools to predict OUD before it occurs, permitting early interventions. METHODS: Electronic health records of patients who have been prescribed with medications containing active opioid ingredients were extracted from Cerner's Health Facts database for encounters between January 1, 2008, and December 31, 2017. Long short-term memory models were applied to predict OUD risk based on five recent prior encounters before the target encounter and compared with logistic regression, random forest, decision tree, and dense neural network. Prediction performance was assessed using F1 score, precision, recall, and area under the receiver-operating characteristic curve. RESULTS: The long short-term memory (LSTM) model provided promising prediction results which outperformed other methods, with an F1 score of 0.8023 (about 0.016 higher than dense neural network (DNN)) and an area under the receiver-operating characteristic curve (AUROC) of 0.9369 (about 0.145 higher than DNN). CONCLUSIONS: LSTM-based sequential deep learning models can accurately predict OUD using a patient's history of electronic health records, with minimal prior domain knowledge. This tool has the potential to improve clinical decision support for early intervention and prevention to combat the opioid epidemic.

Predicting opioid overdose risk of patients with opioid prescriptions using electronic health records based on temporal deep learning.

The US is experiencing an opioid epidemic, and opioid overdose is causing more than 100 deaths per day. Early identification of patients at high risk of Opioid Overdose (OD) can help to make targeted preventative interventions. We aim to build a deep learning model that can predict the patients at high risk for opioid overdose and identify most relevant features. The study included the information of 5,231,614 patients from the Health Facts database with at least one opioid prescription between January 1, 2008 and December 31, 2017. Potential predictors (n = 1185) were extracted to build a feature matrix for prediction. Long Short-Term Memory (LSTM) based models were built to predict overdose risk in the next hospital visit. Prediction performance was compared with other machine learning methods assessed using machine learning metrics. Our sequential deep learning models built upon LSTM outperformed the other methods on opioid overdose prediction. LSTM with attention mechanism achieved the highest F-1 score (F-1 score: 0.7815, AUCROC: 0.8449). The model is also able to reveal top ranked predictive features by permutation important method, including medications and vital signs. This study demonstrates that a temporal deep learning based predictive model can achieve promising results on identifying risk of opioid overdose of patients using the history of electronic health records. It provides an alternative informatics-based approach to improving clinical decision support for possible early detection and intervention to reduce opioid overdose.

Detecting Miscoded Diabetes Diagnosis Codes in Electronic Health Records for Quality Improvement: Temporal Deep Learning Approach.

BACKGROUND: Diabetes affects more than 30 million patients across the United States. With such a large disease burden, even a small error in classification can be significant. Currently billing codes, assigned at the time of a medical encounter, are the "gold standard" reflecting the actual diseases present in an individual, and thus in aggregate reflect disease prevalence in the population. These codes are generated by highly trained coders and by health care providers but are not always accurate. OBJECTIVE: This work provides a scalable deep learning methodology to more accurately classify individuals with diabetes across multiple health care systems. METHODS: We leveraged a long short-term memory-dense neural network (LSTM-DNN) model to identify patients with or without diabetes using data from 5 acute care facilities with 187,187 patients and 275,407 encounters, incorporating data elements including laboratory test results, diagnostic/procedure codes, medications, demographic data, and admission information. Furthermore, a blinded physician panel reviewed discordant cases, providing an estimate of the total impact on the population. RESULTS: When predicting the documented diagnosis of diabetes, our model achieved an 84% F1 score, 96% area under the curve-receiver operating characteristic curve, and 91% average precision on a heterogeneous data set from 5 distinct health facilities. However, in 81% of cases where the model disagreed with the documented phenotype, a blinded physician panel agreed with the model. Taken together, this suggests that 4.3% of our studied population have either missing or improper diabetes diagnosis. CONCLUSIONS: This study demonstrates that deep learning methods can improve clinical phenotyping even when patient data are noisy, sparse, and heterogeneous.

An Informatics-based Approach to Identify Key Pharmacological Components in Drug-Drug Interactions.

Drug-drug interactions (DDI) can cause severe adverse drug reactions and pose a major challenge to medication therapy. Recently, informatics-based approaches are emerging for DDI studies. In this paper, we aim to identify key pharmacological components in DDI based on large-scale data from DrugBank, a comprehensive DDI database. With pharmacological components as features, logistic regression is used to perform DDI classification with a focus on searching for most predictive features, a process of identifying key pharmacological components. Using univariate feature selection with chi-squared statistic as the ranking criteria, our study reveals that top 10% features can achieve comparable classification performance compared to that using all features. The top 10% features are identified to be key pharmacological components. Furthermore, their importance is quantified by feature coefficients in the classifier, which measures the DDI potential and provides a novel perspective to evaluate pharmacological components.

In silico drug absorption tract: An agent-based biomimetic model for human oral drug absorption.

BACKGROUND: An agent-based modeling approach has been suggested as an alternative to traditional, equation-based modeling methods for describing oral drug absorption. It enables researchers to gain a better understanding of the pharmacokinetic (PK) mechanisms of a drug. This project demonstrates that a biomimetic agent-based model can adequately describe the absorption and disposition kinetics both of midazolam and clonazepam. METHODS: An agent-based biomimetic model, in silico drug absorption tract (ISDAT), was built to mimic oral drug absorption in humans. The model consisted of distinct spaces, membranes, and metabolic enzymes, and it was altogether representative of human physiology relating to oral drug absorption. Simulated experiments were run with the model, and the results were compared to the referent data from clinical equivalence trials. Acceptable similarity was verified by pre-specified criteria, which included 1) qualitative visual matching between the clinical and simulated concentration-time profiles, 2) quantitative similarity indices, namely, weighted root mean squared error (RMSE), and weighted mean absolute percentage error (MAPE) and 3) descriptive similarity which requires less than 25% difference between key PK parameters calculated by the clinical and the simulated concentration-time profiles. The model and its parameters were iteratively refined until all similarity criteria were met. Furthermore, simulated PK experiments were conducted to predict bioavailability (F). For better visualization, a graphical user interface for the model was developed and a video is available in Supporting Information. RESULTS: Simulation results satisfied all three levels of similarity criteria for both drugs. The weighted RMSE was 0.51 and 0.92, and the weighted MAPE was 5.99% and 8.43% for midazolam and clonazepam, respectively. Calculated PK parameter values, including area under the curve (AUC), peak plasma drug concentration (Cmax), time to reach Cmax (Tmax), terminal elimination rate constant (Kel), terminal elimination half life (T1/2), apparent oral clearance (CL/F), and apparent volume of distribution (V/F), were reasonable compared to the referent values. The predicted absolute oral bioavailability (F) was 44% for midazolam (literature reported value, 31-72%) and 93% (literature reported value, ≥ 90%) for clonazepam. CONCLUSION: The ISDAT met all the pre-specified similarity criteria for both midazolam and clonazepam, and demonstrated its ability to describe absorption kinetics of both drugs. Therefore, the validated ISDAT can be a promising platform for further research into the use of similar in silico models for drug absorption kinetics.

Robust and Fast Decoding of High-Capacity Color QR Codes for Mobile Applications.

The use of color in QR codes brings extra data capacity, but also inflicts tremendous challenges on the decoding process due to chromatic distortion-cross-channel color interference and illumination variation. Particularly, we further discover a new type of chromatic distortion in high-density color QR codes-cross-module color interference-caused by the high density which also makes the geometric distortion correction more challenging. To address these problems, we propose two approaches, LSVM-CMI and QDA-CMI, which jointly model these different types of chromatic distortion. Extended from SVM and QDA, respectively, both LSVM-CMI and QDA-CMI optimize over a particular objective function and learn a color classifier. Furthermore, a robust geometric transformation method and several pipeline refinements are proposed to boost the decoding performance for mobile applications. We put forth and implement a framework for high-capacity color QR codes equipped with our methods, called HiQ. To evaluate the performance of HiQ, we collect a challenging large-scale color QR code dataset, CUHK-CQRC, which consists of 5390 high-density color QR code samples. The comparison with the baseline method [2] on CUHK-CQRC shows that HiQ at least outperforms [2] by 188% in decoding success rate and 60% in bit error rate. Our implementation of HiQ in iOS and Android also demonstrates the effectiveness of our framework in real-world applications.

Self-Stabilized Precipitation Polymerization and Its Application.

An effective, value-added use of the large amounts of olefinic compounds produced in the processing of petroleum, aside from ethylene and propylene, has been a long outstanding challenge. Here, we developed a novel heterogeneous polymerization method, beyond emulsion/dispersion/suspension, termed self-stabilized precipitation (2SP) polymerization, which involves the nucleation and growth of nanoparticles (NPs) of a well-defined size without the use of any stabilizers and multifunctional monomers (crosslinker). This technique leads to two revolutionary advances: (1) the generation of functional copolymer particles from single olefinic monomer or complex olefinic mixtures (including C4/C5/C9 fractions) in large quantities, which open a new way to transform huge amount of unused olefinic compounds in C4/C5/C9 fractions into valuable copolymers, and (2) the resultant polymeric NPs possess a self-limiting size and narrow size distribution, therefore being one of the most simple, efficient, and green strategies to produce uniform, size-tunable, and functional polymeric nanoparticles. More importantly, the separation of the NPs from the reaction medium is simple and the supernatant liquid can be reused; hence this new synthetic strategy has great potential for industrial production.

A Review of Food-Drug Interactions on Oral Drug Absorption.

Food effect, also known as food-drug interactions, is a common phenomenon associated with orally administered medications and can be defined as changes in absorption rate or absorption extent. The mechanisms of food effect and their consequences can involve multiple factors, including human post-prandial physiology, properties of the drug, and how the drug is administered. Therefore, it is essential to have a thorough understanding of these mechanisms when recommending whether a specific drug should be taken with or without food. Food-drug interactions can be clinically relevant, especially when they must be avoided to prevent undesirable effects or exploited to optimize medication therapy. This review conducts a literature search that examined studies on food effect. We summarized the literature and identified and discussed common food effect mechanisms. Furthermore, we highlighted drugs that have a clinically significant food effect and discussed the corresponding mechanisms. In addition, this review analyzes the effects of high-fat food or standard meals on the oral drug absorption rate and absorption extent for 229 drugs based on the Biopharmaceutics Drug Disposition Classification System and demonstrates an association between Biopharmaceutics Drug Disposition Classification System class and food effect.

An Agent-Based Approach to Dynamically Represent the Pharmacokinetic Properties of Baicalein.

Baicalein, a typical flavonoid presented in Scutellariae radix, exhibits a unique metabolic profile during first-pass metabolism: parallel glucuronidation and sulfation pathways, with possible substrate inhibition in both pathways. In this project, we aimed to construct an agent-based model to dynamically represent baicalein pharmacokinetics and to verify the substrate inhibition hypothesis. The model consisted of three 3D spaces and two membranes: apical space (S1), intracellular space (S2), basolateral space (S3), apical membrane (M1), and basolateral membrane (M2). In silico enzymes (UDP-glucuronosyltransferases (UGTs) and sulfotransferases (SULTs)) and binder components were placed in S2. The model was then executed to simulate one-pass metabolism experiments of baicalein. With the implementation of a two-site enzyme design, the simulated results captured the preset qualitative and quantitative features of the wet-lab observations. The feasible parameter set showed that substrate inhibition happened in both conjugation pathways of baicalein. The simulation results suggested that the sulfation pathway was dominant at low concentrations and that SULT was more inclined to substrate inhibition than UGT. Cross-model validation was satisfactory. Our findings were consistent with a previously reported catenary model. We conclude that the mechanisms represented by our model are plausible. Our novel modeling approach could dynamically represent the metabolic pathways of baicalein in a Caco-2 system.

An extremely simple and effective strategy to tailor the surface performance of inorganic substrates by two new photochemical reactions.

This article reports on a new sequential strategy to fabricate monolayer functional organosilane films on inorganic substrate surfaces, and subsequently, to pattern them by two new photochemical reactions. (1) By using UV light (254 nm) plus dimethylformamide (DMF), a functional silane monolayer film could be fabricated quickly (within minutes) under ambient temperature. (2) The organic groups of the formed films became decomposed in a few minutes with UV irradiation coupled with a water solution of ammonium persulfate (APS). (3) When two photochemical reactions were sequentially combined, a high-quality patterned functional surface could be obtained thanks to the photomask.