Current and Future Roles of Artificial Intelligence in Medicinal Chemistry Synthesis

Struble, Thomas J.; Álvarez, Juan Carlos; Brown, Scott P.; Chytil, Milan; Cisar, Justin S.; DesJarlais, Renée L.; Engkvist, Ola; Frank, Scott A.; Greve, Daniel R.; Griffin, Daniel J.; Hou, Xinjun; Johannes, Jeffrey W.; Kreatsoulas, Constantine; Lahue, Brian R.; Mathea, Miriam; Mogk, Georg; Nicolaou, Christos A.; Palmer, Andrew; Price, Daniel J.; Robinson, Richard I.; Salentin, Sebastian; Li, Xing; Jaakkola, Tommi S.; Green, William; Barzilay, Regina; Coley, Connor W.; Jensen, Klavs F.

doi:10.1021/acs.jmedchem.9b02120

Cited by 181 publications

(128 citation statements)

References 79 publications

Supporting

Mentioning

120

Contrasting

Unclassified

Order By: Relevance

“…This makes it suitable for the in silico filtering of large compound libraries, and has been demonstrated by Gao and Coley for the case of generated compounds. 11 However, despite the vast amount of progress that has contributed to making the prediction of full synthetic routes computationally tractable, 6,[12][13][14] to the extent that some predictions may be made within a minute. 5,6 The scale at which predictions must be conducted for large compound libraries consisting of several million or even billions of compounds can still be limiting.…”

Section: Figure 1: Example Of a Virtual Screening (Vs) Workflow The mentioning

confidence: 99%

“…4,5 The question as to which molecule to make and how to make it, is at the center of chemical discovery programs across academia and a range of industries, ranging from agrochemicals to pharmaceuticals. 6 Typically virtual screening (VS) workflows have been used to decide which compounds to make, starting from generated, enumerated, commercial or public datasets which are then filtered using a variety of statistical and physics based modelling until the search space is refined (Figure 1). [7][8][9][10] The question and decision of how to make a given set of compounds is left to a team of chemists at the end of the VS workflow, prior to synthesis in the laboratory.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

Thakkar

Chadimova

Bjerrum

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

<p>Computer aided synthesis planning (CASP) is part of a suite of artificial intelligence (AI) based tools that are able to propose synthesis to a wide range of compounds. However, at present they are too slow to be used to screen the synthetic feasibility of millions of generated or enumerated compounds before identification of potential bioactivity by virtual screening (VS) workflows. Herein we report a machine learning (ML) based method capable of classifying whether a synthetic route can be identified for a particular compound or not by the CASP tool AiZynthFinder. The resulting ML models return a retrosynthetic accessibility score (RAscore) of any molecule of interest, and computes 4,500 times faster than retrosynthetic analysis performed by the underlying CASP tool. The RAscore should be useful for the pre-screening millions of virtual molecules from enumerated databases or generative models for synthetic accessibility and produce higher quality databases for virtual screening of biological activity. </p>

show abstract

Section: Figure 1: Example Of a Virtual Screening (Vs) Workflow The mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

Thakkar

Chadimova

Bjerrum

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Depending on the constraints that users set for the retrosynthesis search, such as search time and number of single-step expansions allowed per intermediate, a successful retrosynthetic search could result in thousands of potential retrosynthesis pathways. For example, the open-source program, ASKCOS 5,17,18 , gave a total of 1,498 different retrosynthesis pathways for hydroxychloroquine with only 30 seconds search time on a 20-core workstation.…”

Section: Introductionmentioning

confidence: 99%

Evaluating and clustering retrosynthesis pathways with learned strategy

Guan

Verma

et al. 2021

Chem. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, with the rapid development of deep learning technology, arti cial intelligence (AI) and machine learning (ML) have been used to handle with a variety of problems [14], ranging from computer vision, gaming, high-energy physics, drug-design [15] and bioinformatics [16]. Besides, many deep learning methods are also applied to the eld of medical image [17] analysis, but to building deep a neural network model by using lab items and vitals is relatively limited.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Prediction of AKI Among Middle-Aged and Older in ICU: A Retrospective and Machine Learning Study

Wang¹,

Deng²,

Zhang³

et al. 2020

Preprint

View full text Add to dashboard Cite

BackgroundAcute Kidney Injury (AKI), a major public health problem，is responsible for two-thirds of intensive care unit patients’ cost, and aging is an independent risk factor for AKI and its associated mortality and morbidity. The early recognition of AKI helps ICU caregivers to guide fluid treatment and titrate the dosing of the nephrotoxic drug. Therefore, it is desirable to build models to predict their position. The study is to build models based machine learning to predict AKI stage after 24 hours and 48 hours among middle-aged and older patients respectively in ICU. Methods and FindingsWe used two real-world databases to build and test models. The Medical Information Mart for Intensive Care (MIMIC-III v1.4) database for training, funded by National Institutes of Health (NIIH) built by the Computational Physiology Laboratory of MIT, Beth Israel Dikon Medical Center, and Philips Medical. The eICU Collaborative Research Database (eICU-CRD v 2.0) for the test is open-access, de-identified data sets of patients admitted to ICUs. 26316 patients in the overall cohort were generally older (median age ranging from 57 to 79) and 54% were male. Here we present three models, using the support vector machine (SVM), Long short-term memory (LSTM), and convolutional LSTM ConvLSTM respectively. the ConvLSTM model had the best performance in the test data set, and it has good ability and surpasses any previous model to predict whether older patients have AKI or not. The area under the receiver operating characteristic curve (AUC) of 24-hour prediction AKI is 99.79%, 48-hours AKI 99.43% during the hospital. we demonstrate that deep learning can handle lots of variables which may be predictors and that the algorithm achieved robust and excellent performance.ConclusionsTo our knowledge, this study is the first to use large-scale data collected from electronic health record（EHR）to prove the contribution of big data and deep learning methods to the real-time prediction of AKI prognosis in middle-aged and elderly patients. The model performance is better than any previous models. This work provides novel evidence to change clinical practice and precise personalized interventions.

show abstract

Current and Future Roles of Artificial Intelligence in Medicinal Chemistry Synthesis

Cited by 181 publications

References 79 publications

Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

Retrosynthetic Accessibility Score (RAscore) - Rapid Machine Learned Synthesizability Classification from AI Driven Retrosynthetic Planning

Evaluating and clustering retrosynthesis pathways with learned strategy

Real-Time Prediction of AKI Among Middle-Aged and Older in ICU: A Retrospective and Machine Learning Study

Contact Info

Product

Resources

About