Dataset Information

Prediction of Organic Reaction Outcomes Using Machine Learning.

ABSTRACT: Computer assistance in synthesis design has existed for over 40 years, yet retrosynthesis planning software has struggled to achieve widespread adoption. One critical challenge in developing high-quality pathway suggestions is that proposed reaction steps often fail when attempted in the laboratory, despite initially seeming viable. The true measure of success for any synthesis program is whether the predicted outcome matches what is observed experimentally. We report a model framework for anticipating reaction outcomes that combines the traditional use of reaction templates with the flexibility in pattern recognition afforded by neural networks. Using 15?000 experimental reaction records from granted United States patents, a model is trained to select the major (recorded) product by ranking a self-generated list of candidates where one candidate is known to be the major product. Candidate reactions are represented using a unique edit-based representation that emphasizes the fundamental transformation from reactants to products, rather than the constituent molecules' overall structures. In a 5-fold cross-validation, the trained model assigns the major product rank 1 in 71.8% of cases, rank ?3 in 86.7% of cases, and rank ?5 in 90.8% of cases.

SUBMITTER: Coley CW

PROVIDER: S-EPMC5445544 | biostudies-literature | 2017 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Organic Reaction Outcomes Using Machine Learning.

Coley Connor W CW Barzilay Regina R Jaakkola Tommi S TS Green William H WH Jensen Klavs F KF

ACS central science 20170418 5

Computer assistance in synthesis design has existed for over 40 years, yet retrosynthesis planning software has struggled to achieve widespread adoption. One critical challenge in developing high-quality pathway suggestions is that proposed reaction steps often fail when attempted in the laboratory, despite initially seeming viable. The true measure of success for any synthesis program is whether the predicted outcome matches what is observed experimentally. We report a model framework for antic ...[more]

PMID: 28573205

Similar Datasets

Project description:BackgroundDevelopment of emergency department (ED) triage systems that accurately differentiate and prioritize critically ill from stable patients remains challenging. We used machine learning models to predict clinical outcomes, and then compared their performance with that of a conventional approach-the Emergency Severity Index (ESI).MethodsUsing National Hospital and Ambulatory Medical Care Survey (NHAMCS) ED data, from 2007 through 2015, we identified all adult patients (aged ≥ 18 years). In the randomly sampled training set (70%), using routinely available triage data as predictors (e.g., demographics, triage vital signs, chief complaints, comorbidities), we developed four machine learning models: Lasso regression, random forest, gradient boosted decision tree, and deep neural network. As the reference model, we constructed a logistic regression model using the five-level ESI data. The clinical outcomes were critical care (admission to intensive care unit or in-hospital death) and hospitalization (direct hospital admission or transfer). In the test set (the remaining 30%), we measured the predictive performance, including area under the receiver-operating-characteristics curve (AUC) and net benefit (decision curves) for each model.ResultsOf 135,470 eligible ED visits, 2.1% had critical care outcome and 16.2% had hospitalization outcome. In the critical care outcome prediction, all four machine learning models outperformed the reference model (e.g., AUC, 0.86 [95%CI 0.85-0.87] in the deep neural network vs 0.74 [95%CI 0.72-0.75] in the reference model), with less under-triaged patients in ESI triage levels 3 to 5 (urgent to non-urgent). Likewise, in the hospitalization outcome prediction, all machine learning models outperformed the reference model (e.g., AUC, 0.82 [95%CI 0.82-0.83] in the deep neural network vs 0.69 [95%CI 0.68-0.69] in the reference model) with less over-triages in ESI triage levels 1 to 3 (immediate to urgent). In the decision curve analysis, all machine learning models consistently achieved a greater net benefit-a larger number of appropriate triages considering a trade-off with over-triages-across the range of clinical thresholds.ConclusionsCompared to the conventional approach, the machine learning models demonstrated a superior performance to predict critical care and hospitalization outcomes. The application of modern machine learning models may enhance clinicians' triage decision making, thereby achieving better clinical care and optimal resource utilization.

Project description:BACKGROUND:Prognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission. METHODS AND FINDINGS:This study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission improved the maximum AUC to 0.895 (σ = 0.008). Beyond the second day, predictive ability declined. CONCLUSION:This has implications for decision making in intensive care and provides a justification for time-limited trials of ICU therapy; the assessment of prognosis over more than one day may be a valuable strategy as new information on the second day helps to differentiate outcomes. New ML models based on trend data beyond the first day could greatly improve upon current risk stratification tools.

Project description:ObjectiveThe management of cardiogenic shock (CS) in the elderly remains a major clinical challenge. Existing clinical prediction models have not performed well in assessing the prognosis of elderly patients with CS. This study aims to build a predictive model, which could better predict the 30-day mortality of elderly patients with CS.MethodsWe extracted data from the Medical Information Mart for Intensive Care III version 1.4 (MIMIC-III) as the training set and the data of validation sets were collected from the Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University. Three models, including the cox regression model, the Least Absolute Shrinkage and Selection Operator (LASSO) regression model, and the CoxBoost model, were established using the training set. Through the comparison of area under the receiver operating characteristic (ROC) curve (AUC), C index, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and median improvement in risk score, the best model was selected. Then for external validation, compared the best model with the simplified acute physiology score II (SAPSII) and the CardShock risk score.ResultsA total of 919 patients were included in the study, of which 804 patients were in the training set and 115 patients were in the verification set. Using the training set, we built three models: the cox regression model including 6 predictors, the LASSO regression model including 4 predictors, and the CoxBoost model including 16 predictors. Among them, the CoxBoost model had good discrimination [AUC: 0.730; C index: 0.6958 (0.6657, 0.7259)]. Compared with the CoxBoost model, the NRI, IDI, and median improvement in risk score of other models were all<0. In the validation set, the CoxBoost model was also well-discriminated [AUC: 0.770; C index: 0.7713 (0.6751, 0.8675)]. Compared with the CoxBoost model, the NRI, IDI, and median improvement in risk score of SAPS II and the CardShock risk score were all < 0. And we constructed a dynamic nomogram to visually display the model.ConclusionIn conclusion, this study showed that in predicting the 30-day mortality of elderly CS patients, the CoxBoost model was superior to the Cox regression model, LASSO regression model, SAPS II, and the CardShock risk score.

Dataset Information

Prediction of Organic Reaction Outcomes Using Machine Learning.

Publications

Prediction of Organic Reaction Outcomes Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets