Filters








9 Hits in 2.7 sec

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction [article]

Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas
<span title="2018-03-18">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we develop an approach of using rule-based knowledge for training ChemNet, a transferable and generalizable deep neural network for chemical property prediction that learns in a weak-supervised  ...  Our results indicate a pre-trained ChemNet that incorporates chemistry domain knowledge, enables the development of generalizable neural networks for more accurate prediction of novel chemical properties  ...  Nathan Baker for helpful discussions. is work is supported by the following PNNL LDRD programs: Pauling Postdoctoral Fellowship and Deep Learning for Scienti c Discovery Agile Investment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.02734v2">arXiv:1712.02734v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/itrjobfzkzexnlw5nqwxjqmzk4">fatcat:itrjobfzkzexnlw5nqwxjqmzk4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191020021044/https://arxiv.org/pdf/1712.02734v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cd/5f/cd5f2b71d97a8fc3cc2720e6f3ab5a16e47cba44.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.02734v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective [article]

Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
<span title="2019-06-25">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.  ...  Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction.  ...  Deep Neural Networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.11081v1">arXiv:1906.11081v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5xtcjvez6bd2rg4tkgun33aqte">fatcat:5xtcjvez6bd2rg4tkgun33aqte</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915020915/https://arxiv.org/pdf/1906.11081v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5d/8b/5d8b271c412f4be0c689bdfde93916efa0951deb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.11081v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective

Chengqiang Lu, Qi Liu, Chao Wang, Zhenya Huang, Peize Lin, Lixin He
<span title="2019-07-17">2019</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.  ...  Furthermore, the detailed results also prove that MGCN is generalizable and transferable for the prediction.  ...  Deep Neural Networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33011052">doi:10.1609/aaai.v33i01.33011052</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zseoxqmawnbflf33i3duogi6qm">fatcat:zseoxqmawnbflf33i3duogi6qm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305181149/https://aaai.org/ojs/index.php/AAAI/article/download/3896/3774" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/25/13/25138f362fcf32d796cacb851f08aaa2ab2fc81b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v33i01.33011052"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design – Toward a Unified Approach: State-of-the-Art and Future Directions [article]

Abdulelah S. Alshehri, Rafiqul Gani, Fengqi You
<span title="2020-07-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The main focus of the survey is given to deep generative modeling of molecules under various deep learning architectures and different molecular representations.  ...  The review article also presents a detailed discussion of the current perspectives and challenges of knowledge-based and data-driven CAMD and identifies key areas for future research directions.  ...  For example, a potential alternative to complex property prediction models is the use of input-convex neural networks, which would allow for the optimization over molecules [212] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.08968v2">arXiv:2005.08968v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p2mfdbkqsjekxa6qwoz5xpfzuu">fatcat:p2mfdbkqsjekxa6qwoz5xpfzuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710052221/https://arxiv.org/ftp/arxiv/papers/2005/2005.08968.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.08968v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Reinforcement Learning with Real-time Docking of 3D Structures to Cover Chemical Space: Mining for Potent SARS-CoV-2 Main Protease Inhibitors [article]

Jie Li, Oufan Zhang, Fiona L. Kearns, Mojtaba Haghighatlari, Conor Parks, Xingyi Guan, Itai Leven, Rommie E. Amaro, Teresa Head-Gordon
<span title="2021-10-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel framework that generates new inhibitor molecules for target proteins by combining deep reinforcement learning (RL) with real-time molecular docking on 3-dimensional structures.  ...  Ultimately 54 molecules are proposed as potent Mpro inhibitors (7 of which have better synthetic accessibility), covering a much broader range than crowd-sourced projects like the COVID moonshot, and our  ...  Chem-Net is a deep network trained on canonized SMILES strings of molecules as input and encodes each molecule into a 512-dimensional latent vector to predict their chemical and biological Prediction of  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.01806v1">arXiv:2110.01806v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ck46g2youvb4ljeykybgojok2i">fatcat:ck46g2youvb4ljeykybgojok2i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007032550/https://arxiv.org/pdf/2110.01806v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/64/a3/64a3ef25687e38dc10cf4d72bb0c263df6139a92.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.01806v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning [article]

Yibo Li, Jianxing Hu, Yanxing Wang, Jielong Zhou, Liangren Zhang and Zhenming Liu
<span title="2019-09-05">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We proposed a scaffold-based molecular generative model for scaffold-based drug discovery, which performs molecule generation based on a wide spectrum of scaffold definitions, including BM-scaffolds, cyclic  ...  Designing molecules retaining particular scaffolds as the core structures of the molecules is one of the efficient ways to obtain potential drug candidates with desirable properties.  ...  A neural network for completing atom and bond type for cyclic skeletons; b. A scaffold-based molecule generative model; c. A filter based on side-chain properties Figure 3 : 3 Figure 3: a-d.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.07209v4">arXiv:1908.07209v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vbp2yoo5pjhufi3i5t4sym23k4">fatcat:vbp2yoo5pjhufi3i5t4sym23k4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200916065509/https://arxiv.org/pdf/1908.07209v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/49/1949989738a66d6f132d398cf632b5bae33fb86f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.07209v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Semantic Preserving Generative Adversarial Models [article]

Shahar Harel, Meir Maor, Amir Ronen
<span title="2019-10-07">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrate the usefulness of our approach by applying it to several unrelated domains: generating good locations for cellular antennae, molecule generation preserving key chemical properties, and generating  ...  They require less data than ordinary GANs, provide natural stopping conditions, uncover important properties of the data, and enhance transfer learning.  ...  For example f (x) > α or f (x)/g(x) < 0. In order to prevent over-fitting the component chooses a small subset of the features with strong combined predictive power.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02804v1">arXiv:1910.02804v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7jmw3kr2b5a3hn3kwgcn423hj4">fatcat:7jmw3kr2b5a3hn3kwgcn423hj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831055702/https://arxiv.org/pdf/1910.02804v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/eb/e4/ebe4fd47f8840cb437b1b4ad229876e9d5e277e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02804v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

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
<span title="2021-08-28">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
TDC also provides an ecosystem of tools and community resources, including 33 data functions and types of meaningful data splits, 23 strategies for systematic model evaluation, 17 molecule generation oracles  ...  Therapeutics machine learning is an emerging field with incredible opportunities for innovatiaon and impact.  ...  TDC.QM : QM is a dataset of geometric, energetic, electronic, and thermodynamic properties for k stable small organic molecules made up of CHONF.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09548v2">arXiv:2102.09548v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i5f5vrbaxnehhmhqiuwkkx2s6y">fatcat:i5f5vrbaxnehhmhqiuwkkx2s6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210901155114/https://arxiv.org/pdf/2102.09548v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/54/ca/54ca116f1e9a45768a3a2c47a4608ff34adefa0c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09548v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Xin Yang, Yifei Wang, Ryan Byrne, Gisbert Schneider, Shengyong Yang
<span title="2019-09-25">2019</span>
Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs.  ...  ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects.  ...  In this section, we focus on some of the most recent developments in predicting the log S value of small molecules with deep neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3929/ethz-b-000367388">doi:10.3929/ethz-b-000367388</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5lno7hywmva6pg3nlufgln23se">fatcat:5lno7hywmva6pg3nlufgln23se</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309081718/https://www.research-collection.ethz.ch/bitstream/handle/20.500.11850/367388/acs.chemrev.8b00728.pdf;jsessionid=EE182A9EC53574BDE412EC280366C700?sequence=3" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d2/13/d213059d096ae0705086ce654999a77abe9c13ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3929/ethz-b-000367388"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>