11 Hits in 3.4 sec

SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties [article]

Garrett B. Goh, Nathan O. Hodas, Charles Siegel, Abhinav Vishnu
2018 arXiv   pre-print
Using Bayesian optimization methods to tune the network architecture, we show that an optimized SMILES2vec model can serve as a general-purpose neural network for predicting distinct chemical properties  ...  In this work, we develop SMILES2vec, a deep RNN that automatically learns features from SMILES to predict chemical properties, without the need for additional explicit feature engineering.  ...  CONCLUSION In this paper, we develop SMILES2vec, the rst general-purpose deep neural network that uses chemical text data (SMILES) for predicting chemical property, with an explanation mask that improves  ... 
arXiv:1712.02034v2 fatcat:zgbcrunn7jhqda3inwnohapp5q

CheMixNet: Mixed DNN Architectures for Predicting Chemical Properties using Multiple Molecular Representations [article]

Arindam Paul, Dipendra Jha, Reda Al-Bahrani, Wei-keng Liao, Alok Choudhary, Ankit Agrawal
2018 arXiv   pre-print
In this work, we present CheMixNet -- a set of neural networks for predicting chemical properties from a mixture of features learned from the two molecular representations -- SMILES as sequences and molecular  ...  There exist several predictive models for learning chemical properties based on either SMILES or molecular fingerprints.  ...  Department of Commerce, National Institute of Standards and Technology as part of the Center for Hierarchical Materials Design (CHiMaD).  ... 
arXiv:1811.08283v2 fatcat:zigst4l7szhf5dzophrqmcqt2m

Explanatory Masks for Neural Network Interpretability [article]

Lawrence Phillips, Garrett Goh, Nathan Hodas
2019 arXiv   pre-print
Neural network interpretability is a vital component for applications across a wide variety of domains.  ...  We demonstrate the applicability of our method for image classification with CNNs, sentiment analysis with RNNs, and chemical property prediction with mixed CNN/RNN architectures.  ...  In this work, we explore an alternate method for generating such an explanatory mask.  ... 
arXiv:1911.06876v1 fatcat:64vng2uqfzc5jliw6wgd7u3mau

Transfer Learning Using Ensemble Neural Networks for Organic Solar Cell Screening [article]

Arindam Paul, Dipendra Jha, Reda Al-Bahrani, Wei-keng Liao, Alok Choudhary, Ankit Agrawal
2019 arXiv   pre-print
In this work, we present an ensemble deep neural network architecture, called SINet, which harnesses both the SMILES and InChI molecular representations to predict HOMO values and leverage the potential  ...  However, generating candidate chemical compounds for solar cells is a time-consuming process requiring thousands of hours of laboratory analysis.  ...  [34] developed an RNN neural network architecture SMILES2vec trained on SMILES for predicting chemical properties across different datasets.  ... 
arXiv:1903.03178v4 fatcat:66pvwlh6fvad5migqsxffdfezm

Artificial Intelligence in Drug Discovery: Applications and Techniques [article]

Jianyuan Deng, Zhibo Yang, Iwao Ojima, Dimitris Samaras, Fusheng Wang
2021 arXiv   pre-print
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 expect that this survey will serve as a guide for researchers who are interested in working at the interface of artificial intelligence and drug discovery.  ...  The neural networks templates are from Visuals by ( Supporting Information Available AI Drug Discovery  ... 
arXiv:2106.05386v4 fatcat:w2at5y5jyffrxiejsupmwiimhq

Comprehensive Survey of Recent Drug Discovery Using Deep Learning

Jintae Kim, Sera Park, Dongbo Min, Wankyu Kim
2021 International Journal of Molecular Sciences  
The two major challenges are prediction of interactions between drugs and druggable targets and generation of novel molecular structures suitable for a target of interest.  ...  Therefore, we reviewed recent deep-learning applications in drug–target interaction (DTI) prediction and de novo drug design.  ...  Therefore, we summarized the recent works using deep neural networks as prediction models for the DTIs.  ... 
doi:10.3390/ijms22189983 pmid:34576146 pmcid:PMC8470987 fatcat:yji6q3cf4fb7ha6m6f5bxcvamq

Exploring chemical space using natural language processing methodologies for drug discovery

Hakime Öztürk, Arzucan Özgür, Philippe Schwaller, Teodoro Laino, Elif Ozkirimli
2020 Drug Discovery Today  
molecular properties or to design novel molecules.  ...  Text-based representations of chemicals and proteins can be thought of as unstructured languages codified by humans to describe domain-specific knowledge.  ...  [75, 94, 95, 96, 150] VAE-types molecule generation [35, 103, 104] GAN molecule generation [109, 151] Deep Neural Network (DNN) [152] An artificial neural network (ANN) witha large number of  ... 
doi:10.1016/j.drudis.2020.01.020 pmid:32027969 fatcat:5dhdhn5pxrffnegbqf73cym3kq

Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition [article]

Sebastian Raschka, Benjamin Kaufman
2020 arXiv   pre-print
However, an equal focus of this review is on the discussion of machine learning-based technology that has been applied to ligand discovery in general and has the potential to pave the way for successful  ...  When applied to various scientific domains that are concerned with the processing of non-tabular data, for example, image or text, deep learning has been shown to outperform not only conventional machine  ...  Acknowledgements Support for this work was provided by the Office of the Vice Chancellor for Research and Graduate Education at the University of Wisconsin-Madison with funding from the Wisconsin Alumni  ... 
arXiv:2001.06545v3 fatcat:e5f4v3fnyvdwtliftwia6rwyc4

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Rohan Gupta, Devesh Srivastava, Mehar Sahu, Swati Tiwari, Rashmi K Ambasta, Pravir Kumar
2021 Molecular diversity  
The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms  ...  Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists.  ...  Acknowledgements We would like to thank the senior management of Delhi Technological University for their constant support and guidance.  ... 
doi:10.1007/s11030-021-10217-3 pmid:33844136 pmcid:PMC8040371 fatcat:yltthjorrvfrjgyrnszpxgpb2q

Efficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees [article]

Abdul Karim, Avinash Mishra, M A Hakim Newton, Abdul Sattar
2019 arXiv   pre-print
Our model needs only a minute on a single CPU for its training while existing methods using deep neural networks need about 10 min on NVidia Tesla K40 GPU.  ...  Toxicity prediction of chemical compounds is a grand challenge.  ...  ■ ACKNOWLEDGMENTS The authors acknowledge support from the Institute for Integrated and Intelligent Systems, Griffith University and the Department of Biotechnology (DBT), India for the award of an  ... 
arXiv:1901.09240v1 fatcat:aasoji5dlzbrxgg7mgsy6luoka

Gene expression based inference of drug resistance in cancer [article]

Smriti Chawla, Anja Rockstroh, Melanie Lehman, Ellca Rather, Atishay Jain, Anuneet Anand, Apoorva Gupta, Namrata Bhattacharya, Sarita Poonia, Priyadarshini Rai, Nirjhar Das, Angshul Majumdar (+5 others)
2021 bioRxiv   pre-print
Recently, the availability of large-scale drug screening datasets has provided an opportunity for predicting appropriate patient-tailored therapies by employing machine learning approaches.  ...  Inter and intra-tumoral heterogeneity are major stumbling blocks in the treatment of cancer and are responsible for imparting differential drug responses in cancer patients.  ...  A deep neural network (DNN) was trained using the Keras platform.  ... 
doi:10.1101/2021.11.17.468905 fatcat:ox3bezun5baafjewvljhfyz5py