39 Hits in 8.6 sec

Towards Stacking Fault Energy Engineering in FCC High Entropy Alloys [article]

Tasneem Khan, Tanner Kirk, Guillermo Vazquez, Prashant Singh, A V Smirnov, Duane D Johnson, Khaleed Youssef, Raymundo Arroyave
2021 arXiv   pre-print
This efficient model along with a recently developed model to estimate intrinsic strength of fcc HEAs is used to explore the strength-SFE Pareto front, predicting new-candidate alloys with particularly  ...  The best-performing ML model is capable of accurately predicting the SFE of arbitrary compositions within this 7-element system.  ...  As the training set grows to contain most of the calculated data, the GPRs become overfit to the HT compositions during cross-validation.  ... 
arXiv:2111.03591v1 fatcat:vgx34nc3vvhs7hboty7jampbiq

Evolving scenario of big data and Artificial Intelligence (AI) in drug discovery

Manish Kumar Tripathi, Abhigyan Nath, Tej P. Singh, A. S. Ethayathulla, Punit Kaur
2021 Molecular diversity  
The present review summarizes the role of big data and AI techniques currently being implemented to satisfy the ever-increasing research demands in drug discovery pipelines.  ...  The development of deep learning neural networks and their variants with the corresponding increase in chemical data has resulted in a paradigm shift in information mining pertaining to the chemical space  ...  The limitations in addressing the large data set were overcome by the emergence of deep learning (DL) methods that could efficiently manage large data sets [35] .  ... 
doi:10.1007/s11030-021-10256-w pmid:34159484 pmcid:PMC8219515 fatcat:p3lsp57x6rbnxgxdu7y5dggdeu

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

Kevin Maik Jablonka, Daniele Ongari, Seyed Mohamad Moosavi, Berend Smit
2020 Chemical Reviews  
In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations.  ...  The first part of the review gives an introduction to the principles of big-data science.  ...  The task of the acquisition function is to balance exploration and exploitation, i.e., to choose a balanced ratio between points x where the surrogate model is uncertain (exploration) and points where  ... 
doi:10.1021/acs.chemrev.0c00004 pmid:32520531 pmcid:PMC7453404 fatcat:l2745cqxl5fcnnwty73j2ckkyq

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning [article]

Kevin Maik Jablonka, Daniele Ongari, Seyed Mohamad Moosavi, Berend Smit
2020 arXiv   pre-print
We emphasize the importance of data collection, methods to augment small data sets, how to select appropriate training sets.  ...  In particular, we review the different method to optimize the ML process and how to quantify the performance of the different methods.  ...  ) and by the NCCR-MARVEL, funded by the Swiss National Science Foundation.  ... 
arXiv:2001.06728v2 fatcat:cqtzxirbr5dkrplrwyo7yt7lze

Use of Recursion Forests in the Sequential Screening Process: Consensus Selection by Multiple Recursion Trees

A. Michiel van Rhee
2003 Journal of chemical information and computer sciences  
The application of Cheminformatics to High-Throughput Screening (HTS) data requires the use of robust modeling methods.  ...  Robust models must be able to accommodate false positive and false negative data yet retain good explanatory and predictive power.  ...  Laura Van Zant for helpful discussions and editorial assistance during the preparation of this manuscript and the reviewers for their thoughtful consideration and suggestions. REFERENCES AND NOTES (  ... 
doi:10.1021/ci034023j pmid:12767153 fatcat:t3kaqxw7obcpziejflhm7lztgi

Identification of Pathway-specific Protein Domain by Incorporating Hyperparameter Optimization Based on 2D Convolutional Neural Network

Ali Ghulam, Xiujuan Lei, Yuchen Zhang, Shi Cheng, Min Guo
2020 IEEE Access  
Therefore, the creation of an accurate method to predict its roles is a critical step toward human disease and pathways.  ...  The DDE model and DPC model of the PSSM feature profile input was associated with our proposed 2D-CNN method.  ...  Ali Ghulam wrote the initial manuscript. Yuchen Zhang helped design the method and the code. Shi Cheng and Min Guo revised the manuscript and polished the expression of English.  ... 
doi:10.1109/access.2020.3027887 fatcat:wujlmvavargxndutpwznacbmj4

Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry [article]

Prema Dhorma Lama, Surendra Kumar, Kang Kim, Sangjin Ahn, Mi-hyun Kim
2021 arXiv   pre-print
The molecular descriptors were verified by the statistical comparison of the enantioselective predictive classification models built from each descriptors of chiral iodoarenes.  ...  This study is one case showing how to overcome the sparsity of experimental data in organic reactions, especially asymmetric catalysis.  ...  Acknowledgment The acknowledgment will be added after the blind peer review.  ... 
arXiv:2103.14065v1 fatcat:fmqrwy7eq5ehxk77s4ghypwwwm

Interpretable Machine Learning for Materials Design [article]

James Dean, Matthias Scheffler, Thomas A. R. Purcell, Sergey V. Barabash, Rahul Bhowmik, Timur Bazhirov
2021 arXiv   pre-print
When training models to predict material properties, researchers often face a difficult choice between a model's interpretability or its performance.  ...  Fueled by the widespread adoption of Machine Learning (ML) and the high-throughput screening of materials, the data-centric approach to materials design has asserted itself as a robust and powerful tool  ...  The authors also wish to acknowledge fruitful discussions with Rhys Goodall (University of Cambridge) regarding the Roost framework.  ... 
arXiv:2112.00239v1 fatcat:43d55y7p7fhwvbry3ewduxzmei

Incorporating Machine Learning into Established Bioinformatics Frameworks

Noam Auslander, Ayal B. Gussow, Eugene V. Koonin
2021 International Journal of Molecular Sciences  
By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems.  ...  The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijms22062903 pmid:33809353 pmcid:PMC8000113 fatcat:ssfoobbtcjhidbaffbkakqbwfe

Ligand Binding Prediction using Protein Structure Graphs and Residual Graph Attention Networks [article]

Mohit Pandey, Mariia Radaeva, Hazem Mslati, Olivia Garland, Michael Fernandez, Martin Ester, Artem Cherkasov
2022 bioRxiv   pre-print
As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers.  ...  AbstractMotivationComputational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening.  ...  classification on SARS-CoV Mpro inhibitor and to overcome the problem of class imbalance between actives and inactives, we oversampled the actives and randomly subsampled inactives to construct a class-balanced  ... 
doi:10.1101/2022.04.27.489750 fatcat:2d5dhwxzlrc6totpqv76tprwuu

Computational Prediction of Metabolism: Sites, Products, SAR, P450 Enzyme Dynamics, and Mechanisms

Johannes Kirchmair, Mark J. Williamson, Jonathan D. Tyzack, Lu Tan, Peter J. Bond, Andreas Bender, Robert C. Glen
2012 Journal of Chemical Information and Modeling  
and modeling approaches is accelerating the development of effective tools for prediction of in vivo metabolism, which is reflected by the diverse and comprehensive data sources and methods for metabolism  ...  This review attempts to survey the range and scope of computational methods applied to metabolism prediction and also to compare and contrast their applicability and performance.  ...  Furthermore, different parameters can vary from model to model, such as the composition of the training set, the validation method, the choice of descriptors, and last but not least, the mathematical modeling  ... 
doi:10.1021/ci200542m pmid:22339582 pmcid:PMC3317594 fatcat:z3rgdgqxrrgupcyvshb6kqurbe

Radiomic and radiogenomic modeling for radiotherapy: strategies, pitfalls, and challenges

James T. T. Coates, Giacomo Pirovano, Issam El Naqa
2021 Journal of Medical Imaging  
Strategies to overcome common pitfalls that are unique to data-intensive radiomics are also discussed.  ...  We review classical analytical and data-driven approaches for outcomes prediction that serve as antecedents to both radiomic and radiogenomic strategies.  ...  Alternatively, methods in AI are becoming increasingly popular to explore the complex, hidden relationships between outcomes and biological variables. 82 In contrast to brute-force estimating of correlations  ... 
doi:10.1117/1.jmi.8.3.031902 pmid:33768134 pmcid:PMC7985651 fatcat:y4djrrysrbbifcm5dz6gbjsumu

Integrative Radiogenomics Approach for Risk Assessment of Post-Operative Metastasis in Pathological T1 Renal Cell Carcinoma: A Pilot Retrospective Cohort Study

Hye Won Lee, Hwan-Ho Cho, Je-Gun Joung, Hwang Gyun Jeon, Byong Chang Jeong, Seong Soo Jeon, Hyun Moo Lee, Do-Hyun Nam, Woong-Yang Park, Chan Kyo Kim, Seong Il Seo, Hyunjin Park
2020 Cancers  
Therefore, this study aimed to create a radiomics model using imaging features from multiphase computed tomography (CT) to more accurately predict the postoperative metastasis of pT1 RCC and further investigate  ...  postcontrast CT (Under80HURatio), were detected to predict the postsurgical metastasis of patients with pathological stage T1 RCC, and the clinical outcomes of patients could be successfully stratified  ...  Acknowledgments: The biospecimens for this study were provided by the Samsung Medical Center BioBank. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cancers12040866 pmid:32252440 pmcid:PMC7226068 fatcat:qhh5aoyj65bnnij3cdw44kw42u

PhANNs, a fast and accurate tool and web server to classify phage structural proteins

Vito Adrian Cantu, Peter Salamon, Victor Seguritan, Jackson Redfield, David Salamon, Robert A. Edwards, Anca M. Segall, Mihaela Pertea
2020 PLoS Computational Biology  
no homologous proteins between sets yet maintains the maximum sequence diversity for training.  ...  Structural protein-encoding genes constitute a large fraction of the average phage genome and are among the most divergent and difficult-to-identify genes using homology-based methods.  ...  Acknowledgments AMS would like to acknowledge Drs. Sherwood Casjens (University of Utah) and Ian Molineux (University of Texas Austin) for helpful conversations on phage biology.  ... 
doi:10.1371/journal.pcbi.1007845 pmid:33137102 fatcat:dcwilwidkbbcbgm3lhquoaheaq

Comparison of Chemometric Problems in Food Analysis Using Non-Linear Methods

Werickson Fortunato de Carvalho Rocha, Charles Bezerra do Prado, Niksa Blonder
2020 Molecules  
Food analysis is a challenging analytical problem, often addressed using sophisticated laboratory methods that produce large data sets.  ...  The principles of algorithms are described, and examples are presented for solving the problems of exploratory analysis, classification, and prediction.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/molecules25133025 pmid:32630676 pmcid:PMC7411792 fatcat:pkourlj2v5anfl7zsgu2wa3nuy
« Previous Showing results 1 — 15 out of 39 results