Filters








762 Hits in 7.8 sec

The influence of hashed fingerprints density on the machine learning methods performance

Sabina Smusz, Rafał Kurczab, Andrzej J Bojarski
2013 Journal of Cheminformatics  
The aim of our study was to examine the impact of such fingerprint density on the performance of machine learning methods.  ...  Both length and density (the percentage of 1's) can be modified during hashed fingerprint generation, which (as it was already proved) influence the similarity searching process [3] .  ...  Acknowledgements The study was supported by a grant PRELUDIUM 2011/03/N/NZ2/02478 financed by the National Science Centre.  ... 
doi:10.1186/1758-2946-5-s1-p25 pmcid:PMC3606238 fatcat:yopjg5jmfrbvtbko35ck3mbkxy

Ensemble Machine Learning and Applicability Domain Estimation for Fluorescence Properties and its Application to Structural Design

Yuki Sugawara, Masaaki Kotera, Kenichi Tanaka, Kimito Funatsu
2019 Journal of Computer Aided Chemistry  
The performance of the AD models was shown better than the OCSVM-based model.  ...  Fluorescent substances are used in a wide range of applications, and the method that effectively design molecules having desirable absorption and emission wavelength is required.  ...  We compared the predictive performance with other machine learning methods and also with quantum computation.  ... 
doi:10.2751/jcac.20.7 fatcat:xwtvpd64xzfq3ouop5ts72eroa

LigEGFR: Spatial graph embedding and molecular descriptors assisted bioactivity prediction of ligand molecules for epidermal growth factor receptor on a cell line-based dataset [article]

Puri Virakarin, Natthakan Saengnil, Bundit Boonyarit, Jiramet Kinchagawat, Rattasat Laotaew, Treephop Saeteng, Thanasan Nilsu, Naravut Suvannang, Thanyada Rungrotmongkol, Sarana Nutanong
2020 bioRxiv   pre-print
Our model was notable for higher performance in hit compound classification, compared to molecular docking and machine learning approaches.  ...  One of the leading mechanisms underlying the development of lung cancer in nonsmokers is an amplification of the epidermal growth factor receptor (EGFR) gene.  ...  These results were obtained by comparing baseline machine 389 learning algorithms and molecular docking methods. 390 Nowadays, research is focused on machine learning development for pIC 50 with the human  ... 
doi:10.1101/2020.12.24.423424 fatcat:4fq47wu64fdhhhkhpuvquul45i

Reaction Classification and Yield Prediction using the Differential Reaction Fingerprint DRFP

Daniel Probst, Philippe Schwaller, Jean-Louis Reymond
2022 Digital Discovery  
The recent application of deep learning-based learned fingerprints to reaction classification and...  ...  Predicting the nature and outcome of reactions using computational methods is a crucial tool to accelerate chemical research.  ...  Acknowledgements This work was supported financially by the Swiss National Science Foundation, NCCR TransCure.  ... 
doi:10.1039/d1dd00006c pmid:35515081 pmcid:PMC8996827 fatcat:5mtvpkg6erdgznll464pitm4by

Towards Automated Classification of Firmware Images and Identification of Embedded Devices [chapter]

Andrei Costin, Apostolis Zarras, Aurélien Francillon
2017 IFIP Advances in Information and Communication Technology  
[19] introduced the area of remote physical device fingerprinting. Desmond et al.  ...  Shah [29] presented early techniques to fingerprint and identify web applications at the HTTP level. Similar, the BlindElephant [1] attempts to discover the version of a web application.  ...  The accuracy of the fuzzy hashing can be influenced by the file size and various other factors.  ... 
doi:10.1007/978-3-319-58469-0_16 fatcat:5cptmxpbmvgo5mycdcmp3c22ge

Learned Feature Generation for Molecules [chapter]

Patrick Winter, Christian Borgelt, Michael R. Berthold
2018 Lecture Notes in Computer Science  
The most common methods use a static algorithm that has been created based on domain knowledge to perform this generation of features.  ...  We propose an approach where this conversion is learned by a convolutional neural network finding features that are useful for the task at hand based on the available data.  ...  This work was partially funded by the Konstanz Research School Chemical Biology and KNIME AG.  ... 
doi:10.1007/978-3-030-01768-2_31 fatcat:4sklkmnvdnealm4bf3haz5pay4

A Text Book Of Research Papers On Fingerprint Recognition & Hash Code Techniques

K. Dr. Krishna Prasad
2018 Zenodo  
This book contains research articles related to Fingerprint image enhancement, recognition and Hash code generation methods.  ...  This Book has written with an intention to get all papers together under one roof, which will benefit all the researchers of related areas.  ...  Segmentation algorithm generally falls under two categories of machine learning techniques as supervised learning and unsupervised learning.  ... 
doi:10.5281/zenodo.1409464 fatcat:243353fegrfxji7jvxzmqg5sge

Implicit-descriptor ligand-based virtual screening by means of collaborative filtering

Raghuram Srinivas, Pavel V Klimovich, Eric C Larson
2018 Journal of Cheminformatics  
Current ligand-based machine learning methods in virtual screening rely heavily on molecular fingerprinting for preprocessing, i.e., explicit description of ligands' structural and physicochemical properties  ...  Our implicit descriptor method does not require any fingerprint similarity search, which makes the method free of the bias arising from the empirical nature of the fingerprint models.  ...  Acknowledgements RS thanks the support of DataScience@SMU. PVK acknowledges the support from the SMU Office of Research and Graduate Studies.  ... 
doi:10.1186/s13321-018-0310-y pmid:30467684 pmcid:PMC6755561 fatcat:zt2n6qiiezfenbchld4rw32gf4

A STUDY ON MULTIPLE METHODS OF FINGERPRINT HASH CODE GENERATION BASED ON MD5 ALGORITHM USING MODIFIED FILTERING TECHNIQUES AND MINUTIAE DETAILS

Krishna Prasad K
2021 Zenodo  
A STUDY ON MULTIPLE METHODS OF FINGERPRINT HASH CODE GENERATION BASED ON MD5 ALGORITHM USING MODIFIED FILTERING TECHNIQUES AND MINUTIAE DETAILS - Thesis  ...  The concept of machine learning and neural network are efficiently used in order to learn or train the various features of the enrolled fingerprint.  ...  METHODS USED FOR FINGERPRINT HASH CODE GENERATION BASED ON MD5 ALGORITHM For the purpose of finding performance and efficiency of the hash function based fingerprint matching, we have used four methods  ... 
doi:10.5281/zenodo.5140714 fatcat:steqwl6bcrg3volizjwqk2weuu

MULTI-MODAL RETRIEVAL IN NEWS FEED APP USING GCDL TECHNIQUE

2017 International Journal of Recent Trends in Engineering and Research  
Existing methods proposed to use Canonical Correlation Analysis (CCA), manifolds learning, dual-wing harmoniums, deep autoencoder, and deep Boltzmann machine to approach the task.  ...  Experimental results show that the proposed method achieves significantly better performance than state-of-the-art approaches.  ...  Previous works studied the problem from different aspects such as fingerprint extraction methods with or without linguistic knowledge, hash codes learning methods, different granularities, and so on.  ... 
doi:10.23883/ijrter.2017.3365.aeikk fatcat:6dmfmfsmtbaejale6t63ts7may

Android Malware Clustering using Community Detection on Android Packages Similarity Network [article]

ElMouatez Billah Karbab, Mourad Debbabi, Abdelouahid Derhab, Djedjiga Mouheb
2020 arXiv   pre-print
Furthermore, we propose a novel fingerprinting technique, namely community fingerprint, based on a one-class machine learning model for each malicious community.  ...  performance of the framework.  ...  Instead of employing a hash or fuzzy hash-based signature of the app, the One-Class Support Vector Machine learning model (OC-SVM) [9] is used to compute the community fingerprint of the Android malware  ... 
arXiv:2005.06075v1 fatcat:43wg2wbvejg35ix6yz6tskmie4

Deep Learning Insights into Lanthanides Complexation Chemistry

Artem A. Mitrofanov, Petr I. Matveev, Kristina V. Yakubova, Alexandru Korotcov, Boris Sattarov, Valery Tkachenko, Stepan N. Kalmykov
2021 Molecules  
It was shown that the main influence on the constants had a mutual location of the binding centers.  ...  Here we present an example of deep learning usage not only to build a model but also to determine key structural fragments of ligands influencing metal complexation.  ...  Acknowledgments: The authors would like to express gratitude to A. Mitrofanova for illustrations, and A. Varnek and Yu. Ustynuyk for discussion on the topic of QSPR and metal complexation.  ... 
doi:10.3390/molecules26113237 pmid:34072262 fatcat:e7nmiw4gvre2je2uzw76nceu5e

DeepFrag: A Deep Convolutional Neural Network for Fragment-based Lead Optimization [article]

Harrison Green, David R Koes, Jacob D Durrant
2021 bioRxiv   pre-print
Machine learning has been increasingly applied to the field of computer-aided drug discovery in recent years, leading to notable advances in binding-affinity prediction, virtual screening, and QSAR.  ...  In an independent benchmark of known ligands with missing (deleted) fragments, our DeepFrag model selected the known (correct) fragment from a set over 6,500 about 58% of the time.  ...  The voxelation method controls the shape of atomic densities 2 and the atom-influence radius controls the size of atomic densities (Tables 2 and S1).  ... 
doi:10.1101/2021.01.07.425790 fatcat:zqipo5zybbcqdhs2h3nq3kdovm

Editorial

2019 Intelligent Data Analysis  
Editorial Dear Colleague: Welcome to volume 23(5) of Intelligent Data Analysis (IDA) Journal.  ...  The authors analyze one of the means to increase the performances of machine learning algorithms which is exploiting data locality.  ...  reuse in some selected machine learning algorithms.  ... 
doi:10.3233/ida-190005 fatcat:x3vz7qnegvgwbeulzzqgup7nvy

MoleculeNet: A Benchmark for Molecular Machine Learning [article]

Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, Vijay Pande
2018 arXiv   pre-print
Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties.  ...  to gauge the quality of proposed methods.  ...  We investigated how the performance of machine learning methods on FreeSolv changes with the volume of training data.  ... 
arXiv:1703.00564v3 fatcat:pmhnvly7qfhrxkel5a6tctowv4
« Previous Showing results 1 — 15 out of 762 results