Article
Multidisciplinary Sciences
Alexander Kroll, Sahasra Ranjan, Martin K. M. Engqvist, Martin J. Lercher
Summary: For most proteins annotated as enzymes, it is unknown which primary and/or secondary reactions they catalyze. Machine learning predictions could provide an efficient alternative, but are hampered by a lack of information regarding enzyme non-substrates, as available training data comprises mainly positive examples. Here, we present ESP, a general machine-learning model for the prediction of enzyme-substrate pairs with an accuracy of over 91% on independent and diverse test data.
NATURE COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Alexandre Magalhaes Serra, Jacinto Estima, Alberto Rodrigues da Silva
Summary: The research introduces Maestro, a platform that allows users to create specialized search contexts to automatically search, gather, and classify data from various web sources. Maestro can process and filter the obtained data, classify it using machine learning models, and send the results to external services. The usability and extensibility of Maestro were evaluated through user assessments, with positive feedback on its ease of use and versatility.
INFORMATION PROCESSING & MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Yasuyuki Tanaka, Pascale Minet, Malisa Vucinic, Xavier Vilajosana, Thomas Watteyne
Summary: This article proposes a full-featured 6TiSCH scheduling function called YSF that takes into account the dynamics of a network and aims to minimize latency and maximize reliability. It is evaluated through simulation and compared to the current scheduling function MSF.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Chemistry, Medicinal
Rociio Mercado, Steven M. Kearnes, Connor W. Coley
Summary: The past decade has witnessed impressive developments in predictive chemistry and reaction informatics driven by machine learning applications in computer-aided synthesis planning. However, in order to further advance the role of AI in this field, significant improvements in reporting and curating reaction data are needed. Currently, publicly available data is mostly unstructured and biased towards high-yielding reactions, limiting the types of models that can be trained successfully. This Perspective analyzes successful initiatives in data curation and sharing in chemistry and molecular biology, highlighting the Open Reaction Database and proposing actions to make reaction data more FAIR.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Chemistry, Multidisciplinary
Antanas Vaitkus, Andrius Merkys, Thomas Sander, Miguel Quiros, Paul A. Thiessen, Evan E. Bolton, Saulius Grazulis
Summary: Knowledge of the 3-dimensional structure, orientation, and interaction of chemical compounds is crucial in many fields. This publication presents an automatic pipeline to derive chemical attributes from crystallographic models and applies it to build a catalog in an open-access crystallographic database.
JOURNAL OF CHEMINFORMATICS
(2023)
Article
Chemistry, Applied
Zhuoting Liu, Yunfang Ping, Lumei Zhang, Jingran Zhang, Ann Van Schepdael, Xu Wang
Summary: In this study, a ligand fishing method was developed to screen potential IDO1 inhibitors from coffee extracts using immobilized IDO1 enzyme on amino-modified magnetic nanoparticles and UHPLC-Q-TOF-MS/MS analysis. The optimized parameters included enzyme concentration, immobilization time, glutaraldehyde pH, and the amount of magnetic nanoparticles. The results showed that the immobilized IDO1 could be reused and remained stable during storage. Several IDO1 ligands were captured, with ferulic acid and chlorogenic acid exhibiting better inhibitory activity. This method provides an effective platform for identifying and screening IDO1 inhibitors from natural products.
Article
Immunology
Mohammed Toufiq, Susie Shih Yin Huang, Sabri Boughorbel, Mohamed Alfaki, Darawan Rinchai, Luis R. Saraiva, Damien Chaussabel, Mathieu Garand
Summary: This study presents a unique collection of human blood transcriptomic datasets, SysInflam HuDB, aimed at identifying specific human blood gene signatures in response to infection and delineating major genetic drivers associated with inflammation onset and progression under various conditions.
JOURNAL OF IMMUNOLOGY
(2021)
Article
Biochemical Research Methods
Eszter Csibra, Guy-Bart Stan
Summary: With the increasing demand for automation of biological assays, the range of measurement types implemented by multiwell plate readers has expanded. However, most plate readers export data in formats without metadata, which requires specific parser functions for analysis. To address this issue, we have developed an interactive web application called Parsley, which allows users to parse plate reader data easily without the need for software installation or coding.
Review
Biotechnology & Applied Microbiology
Harpreet Kaur, Rajesh Kumar, Anjali Lathwal, Gajendra P. S. Raghava
Summary: This review provides a comprehensive summary of various omics data related to cancer and the computational resources and tools available to assist researchers and clinicians in effectively managing cancer and improving patient outcomes.
BRIEFINGS IN FUNCTIONAL GENOMICS
(2021)
Article
Environmental Sciences
Giacomo Butte, Yady Tatiana Solano-Correa, Maria Valasia Peppa, Diana Marcela Ruiz-Ordonez, Rachael Maysels, Nasser Tuqan, Xanthe Polaine, Carolina Montoya-Pachongo, Claire Walsh, Thomas Curtis
Summary: Water security has gained increasing attention at the international level, and evaluating water security requires diverse data with barriers in designing data gathering strategies. The proposed framework aims to fill existing gaps and guide practitioners towards an optimal data gathering strategy.
Article
Computer Science, Hardware & Architecture
Marcio Jose Sembay, Douglas Dyllon Jeronimo de Macedo, Moises Lima Dutra
Summary: This paper proposes a generic method for collecting provenance data based on W3C's Provenance Data Model. The method uses a scientific workflow to capture, store, and analyze anemia-index provenance data, and can be applied in various domains.
MOBILE NETWORKS & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Zhenhuang Cai, Guo-Sen Xie, Xingguo Huang, Dan Huang, Yazhou Yao, Zhenmin Tang
Summary: This paper proposes a simple yet effective method named MS-DeJOR for training robust models in the presence of web noise in deep neural networks. Unlike existing methods, MS-DeJOR decouples sample selection from the training procedure, uses a negative entropy term to prevent false positives from being overemphasized, and leverages accumulated predictions to refurbish noisy labels and re-weight training images for improved performance.
PATTERN RECOGNITION
(2023)
Article
Management
Joanna Berlinska, Bartlomiej Przybylski
Summary: This paper analyzes the scheduling problem of gathering multitype data in a star network, proving its NP-hardness and proposing various solutions including integer linear programming, dynamic programming algorithm, and a polynomial 2-approximation algorithm. These methods are tested in computational experiments to evaluate their performance.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Computer Science, Information Systems
Maryam Gillani, Hafiz Adnan Niaz, Ata Ullah, Muhammad Umar Farooq, Saad Rehman
Summary: Vehicular Ad-Hoc Networks (VANETs) is an active research area with diverse applications. This paper proposes a real-time traffic-aware data gathering protocol that utilizes dynamic segmentation switching to handle communication limitations and reduce network and data communication overhead.
Article
Computer Science, Theory & Methods
Mario Jose Divan, Maria Laura Sanchez-Reynoso, Silvio Miguel Gonnet
Summary: The Internet-of-Things devices have improved the Spatiotemporal resolution in Real-time Data Gathering Systems. However, the heterogeneity of sensors has increased the complexity. This work presents a strategy for defining and communicating measurement projects using a conceptual hierarchy derived from a measurement ontology. It also introduces a data interchange format called BriefPD.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)