Filters








13 Hits in 12.8 sec

Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development [article]

Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W. Coley, Cao Xiao, Jimeng Sun, Marinka Zitnik
2021 arXiv   pre-print
However, advancement in this field requires formulation of meaningful learning tasks and careful curation of datasets.  ...  To date, TDC includes 66 AI-ready datasets spread across 22 learning tasks and spanning the discovery and development of safe and effective medicines.  ...  /mims-harvard/TDC https://app.circleci.com/pipelines/github/mims-harvard/TDC ); ( ) state-of-the-art (SOTA) ML models use graph neural network based models on molecular D graphs, including neural fingerprint  ... 
arXiv:2102.09548v2 fatcat:i5f5vrbaxnehhmhqiuwkkx2s6y

QSAR without borders

Eugene N. Muratov, Jürgen Bajorath, Robert P. Sheridan, Igor V. Tetko, Dmitry Filimonov, Vladimir Poroikov, Tudor I. Oprea, Igor I. Baskin, Alexandre Varnek, Adrian Roitberg, Olexandr Isayev, Stefano Curtalolo (+7 others)
2020 Chemical Society Reviews  
Word cloud summary of diverse topics associated with QSAR modeling that are discussed in this review.  ...  Visualization and analysis of reaction space Both graph-based and vector-based approaches have been used to visualize the chemical space of reactions.  ...  Neural network potentials A ML approach applicable to chemical systems containing large numbers of atoms, originally proposed by Behler and Parrinello (BP method) in 2007, used high-dimensional neural  ... 
doi:10.1039/d0cs00098a pmid:32356548 fatcat:l456rjoqbzgehkqa63uvqrv2gy

Crowdsourced identification of multi-target kinase inhibitors for RET- and TAU- based disease: The Multi-Targeting Drug DREAM Challenge

Zhaoping Xiong, Minji Jeon, Robert J. Allaway, Jaewoo Kang, Donghyeon Park, Jinhyuk Lee, Hwisang Jeon, Miyoung Ko, Hualiang Jiang, Mingyue Zheng, Aik Choon Tan, Xindi Guo (+11 others)
2021 PLoS Computational Biology  
Here, we report the results of this DREAM Challenge and the development of two neural network-based machine learning approaches that were applied to the challenge of rational polypharmacology.  ...  A continuing challenge in modern medicine is the identification of safer and more efficacious drugs.  ...  Participating teams used a broad array of different datasets and computational approaches to develop these methods.  ... 
doi:10.1371/journal.pcbi.1009302 pmid:34520464 pmcid:PMC8483411 fatcat:eyskatil6bd5hm22qse6n4flm4

A novel framework integrating AI model and enzymological experiments promotes identification of SARS-CoV-2 3CL protease inhibitors and activity-based probe

Fan Hu, Lei Wang, Yishen Hu, Dongqi Wang, Weijie Wang, Jianbing Jiang, Nan Li, Peng Yin
2021 Briefings in Bioinformatics  
From a bioactive chemical library, we have conducted two rounds of experiments and identified six novel inhibitors with a hit rate of 29.41%, and four of them showed an IC50 value <3 μM.  ...  Moreover, we explored the interpretability of the central model in AIMEE, mapping the deep learning extracted features to the domain knowledge of chemical properties.  ...  Acknowledgements We would like to thank Diana Czuchry for her helpful feedback on a draft of the paper.  ... 
doi:10.1093/bib/bbab301 pmid:34368837 pmcid:PMC8385923 fatcat:vuahaflnjzftbc3hchcyhqakti

CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models [article]

Vijil Chenthamarakshan, Payel Das, Samuel C. Hoffman, Hendrik Strobelt, Inkit Padhi, Kar Wai Lim, Benjamin Hoover, Matteo Manica, Jannis Born, Teodoro Laino, Aleksandra Mojsilovic
2020 arXiv   pre-print
embeddings learned unsupervised from a large corpus.  ...  CogMol combines adaptive pre-training of a molecular SMILES Variational Autoencoder (VAE) and an efficient multi-attribute controlled sampling scheme that uses guidance from attribute predictors trained  ...  The DeepAffinity models use a separate held-out set with four different protein classes to test the generalizability of their predictor.  ... 
arXiv:2004.01215v2 fatcat:4braxgraqnd3vm7fm664ig7oem

Computational Methods in Drug Discovery

G. Sliwoski, S. Kothiwale, J. Meiler, E. W. Lowe
2013 Pharmacological Reviews  
Authorship Contributions Wrote or contributed to the writing of the manuscript: Sliwoski, Kothiwale, Meiler, Lowe.  ...  Although many chemical libraries are constructed in a combinatorial manner, it was reported that the chemical space covered by combinatorially synthesized libraries is different from the chemical space  ...  Benchmarking Techniques of Computer-Aided Drug Design Effective benchmarks are essential for assessment of performance and accuracy of CADD algorithms.  ... 
doi:10.1124/pr.112.007336 pmid:24381236 pmcid:PMC3880464 fatcat:4dzrdkspkjecnombnchznma2ny

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors.  ...  The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic  ...  This new class of extremely low-power and lowlatency artificial intelligence systems could, In a world where power-hungry deep learning techniques are becoming a commodity, and at the same time, environmental  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

ACNP 58th Annual Meeting: Panels, Mini-Panels and Study Groups

2019 Neuropsychopharmacology  
The kinetics of dynorphin signal activation, duration and spread were characterized in striatum using a combination of photorelease, sensor imaging and electrophysiology.  ...  Bulk fluorescence imaging of Dyn-8 photorelease using KOR-light sensors revealed large, graded fluorescence changes that lasted for several minutes (ΔFmax = 23%, tau-off = 185 sec).  ...  Studies using resting-state functional magnetic resonance imaging (rsfMRI) have described large-scale brain network differences from controls in a variety of DSM diagnoses but have not examined symptom  ... 
doi:10.1038/s41386-019-0544-z pmid:31801977 pmcid:PMC6957922 fatcat:hjyvf7fcpbf2fhxit6rlhsvg2y

The discovery of small molecule inhibitors for TOX1 and ERG oncotargets with the development and use of progressive docking PD2.0 approach

Vibudh Agrawal
2019
We also used the PD2.0 method to dock up to 1.3 billion compounds from the ZINC15 database and demonstrated that this deep-learning-based approach resulted in 65X speed acceleration and 130X Full Predicted  ...  available chemical databases which already exceed billions of entries.  ...  We tested different sample sizes and compared the stability, generalizability, and accuracy of the two methods.  ... 
doi:10.14288/1.0384604 fatcat:fcx6ok72hzez3mn2gw3y623jvu

In-silico models for the characterization of compounds interfering with clinical relevant ABC-multidrug-transporters

Michael Alexander Demel
2013 unpublished
An additional focus is also the in-silico characterization of MDR-selective ("collateral sensitive") molecules by means of Network-like Similarity Graphs (NSGs).  ...  From a methodological viewpoint the thesis concentrates on the assessment of different feature selection methods, descriptor development (extension of the SIBAR approach), and evaluation of distance-to-model  ...  Acknowledgement This work was supported by grants from the Austrian Promotion Agency (B1-812074) and from the Austrian Science Fund (L344-N17).  ... 
doi:10.25365/thesis.30426 fatcat:pkwghfepojf75ag3qerzsd3emm

45th Annual SER Meeting Minneapolis, Minnesota June 27-30, 2012

2012 American Journal of Epidemiology  
Biomass use was associated with up to a 1.7 times (95% confidence intervals: 1.6 -1.8) increase in household PM2.5 around morning, lunch and evening periods compared to use of clean fuels.  ...  We used generalized additive models to characterize the diurnal variability in the effect of cooking fuel on indoor PM2.5 concentrations.  ...  This removes the confounding of race and SES often present in large national datasets.  ... 
doi:10.1093/aje/kws258 pmid:22684495 fatcat:oqvpk3zbtfbenmssr5uy2bwymm

Improved In Silico Methods for Target Deconvolution in Phenotypic Screens

Lewis Mervin, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository, Andreas Bender, Ola Engkvist
2018
We therefore also focused on an in-depth analysis of orthologue bioactivity data and its relevance and applicability towards expanding compound and target bioactivity space for predictive studies.  ...  One limitation of previous methods has been the ability to assess the applicability domain of the models, that is, when the assumptions made by a model are fulfilled and which input chemicals are reliably  ...  Deep neural networks (DNNs) have also been recently applied for the area of target prediction [68] [69] [70] [71] .  ... 
doi:10.17863/cam.30369 fatcat:oq2zzirnwzex5d5clqdzchcq2i

Romano_columbia_0054D_15271.pdf [article]

2019
VenomKB is structured according to a fully-featured ontology of venoms, and provides data aggregated from many popular web resources.  ...  Romano Venoms are complex mixtures of biological macromolecules and other compounds that are used for predatory and defensive purposes by hundreds of thousands of known species worldwide.  ...  features of the dataset a large number of times.  ... 
doi:10.7916/d8-spcd-yh22 fatcat:qj4yn44c6nd7jj3fegklasfrua