☆ 4.6 Article

Deep learning-based automatic action extraction from structured chemical synthesis procedures

PEERJ COMPUTER SCIENCE (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Review Computer Science, Artificial Intelligence

Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges

Bernd Bischl et al.

Summary: Machine learning algorithms often require carefully chosen hyperparameters, which greatly affect performance. To avoid manual trial-and-error, automatic hyperparameter optimization methods, such as resampling error estimation, can be used. This paper provides an overview of important optimization methods, offering practical recommendations for conducting hyperparameter optimization.

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY (2023)

添加到收藏夹

Article Biochemistry & Molecular Biology

PubChem 2023 update

Sunghwan Kim et al.

Summary: PubChem, a popular chemical information resource, has undergone several changes and improvements. It has added data from over 120 sources and introduced new functionalities, including the integration of Google Patents data, creation of Cell Line and Taxonomy data collections, and updates to the bioassay data model.

NUCLEIC ACIDS RESEARCH (2023)

添加到收藏夹

Article Chemistry, Medicinal

Machine Learning of Reaction Properties via Learned Representations of the Condensed Graph of Reaction

Esther Heid et al.

Summary: This study combined the condensed graph of reaction (CGR) with a graph convolutional neural network (GCNN) to develop a versatile, robust, and compact deep learning model for chemical reactions. The model outperforms current state-of-the-art models in accuracy, applicability, and predictive capabilities for diverse target properties. A large curated dataset of atom-mapped reactions with their target properties is provided as benchmark data for future work.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Retrosynthetic reaction pathway prediction through neural machine translation of atomic environments

Umit Ucak et al.

Summary: The study presents a new approach for retrosynthetic prediction using fragments and the Transformer architecture. By learning the changes in atom environments, the method predicts reactant candidates for chemical reactions, achieving high accuracy in reaction route prediction and discovery.

NATURE COMMUNICATIONS (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Digitization and validation of a chemical synthesis literature database in the ChemPU

Simon Rohrbacht et al.

Summary: Despite potential, the automation of synthetic chemistry has only made slow progress in recent decades. In this study, we introduce an automated chemical reaction database with 100 representative molecules. Through robotic experimentation, over 50 reactions from the database were performed, achieving yields and purities comparable to those achieved by experts.

SCIENCE (2022)

添加到收藏夹

Article Chemistry, Medicinal

Large-Scale Distributed Training of Transformers for Chemical Fingerprinting

Hisham Abdel-Aty et al.

Summary: Transformer models have been applied in chemistry for various tasks, but require large amounts of data and compute resources. This work demonstrates the successful training of a distributed Transformer model in the field of chemistry, achieving state-of-the-art results in virtual screening for molecular fingerprints.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2022)

添加到收藏夹

Review Chemistry, Multidisciplinary

From Word Embeddings to Pre-Trained Language Models: A State-of-the-Art Walkthrough

Mourad Mars

Summary: This paper provides a comprehensive review of prior embedding models as well as current breakthroughs in pre-trained language models. The various models are analyzed and contrasted, and the major issues and future directions are discussed.

APPLIED SCIENCES-BASEL (2022)

添加到收藏夹

Article Physics, Multidisciplinary

An Insider Data Leakage Detection Using One-Hot Encoding, Synthetic Minority Oversampling and Machine Learning Techniques

Taher Al-Shehari et al.

Summary: Insider threats, carried out by authorized employees within an organization, pose a significant cybersecurity challenge by potentially causing more damage than external attacks. This paper proposes a machine learning-based model to detect data leakage attacks executed by malicious insiders before leaving an organization, addressing bias in detection results and data imbalance with feature scaling, one-hot encoding, and synthetic minority oversampling techniques. Experimental results demonstrate the model's superior performance in detecting insider data leakage events.

ENTROPY (2021)

添加到收藏夹

Review Chemistry, Multidisciplinary

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems

John A. Keith et al.

Summary: The article discusses the potential impact of machine learning models on chemical sciences and emphasizes the importance of collaboration between expertise in computer science and physical sciences. It provides concise tutorials of computational chemistry and machine learning methods, and demonstrates how they can be used together to provide insightful predictions.

CHEMICAL REVIEWS (2021)

添加到收藏夹

Article Chemistry, Medicinal

ChemDataExtractor 2.0: Autopopulated Ontologies for Materials Science

Juraj Mavracic et al.

Summary: The article introduces a framework for automated populating ontologies, enabling direct extraction of a larger group of properties linked by a semantic network. Exploiting data-rich sources, a new model concept is presented for data extraction of chemical and physical properties. With automatically generated parsers for data extraction and forward-looking interdependency resolution, the power of the approach is illustrated through automatic extraction of a crystallographic hierarchy.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Chatbot Interaction with Artificial Intelligence: human data augmentation with T5 and language transformer ensemble for text classification

Jordan J. Bird et al.

Summary: This study introduces a new Chatbot Interaction with Artificial Intelligence (CI-AI) framework, which uses artificial paraphrasing to augment human-sourced data and improve the accuracy of text classification models. By comparing various transformer models, it is found that augmenting training data with the T5 model significantly enhances model performance, with the RoBERTa model achieving the best results when trained on T5 augmented data.

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Morphology Matters: A Multilingual Language Modeling Analysis

Hyunji Hayley Park et al.

Summary: Previous studies have conflicting views on whether inflectional morphology makes language modeling more difficult. This research attempts to resolve the disagreement by compiling a larger corpus and considering additional typological features. The study finds that certain morphological measures are significantly associated with higher surprisal, and linguistically motivated subword segmentation strategies can improve performance and mitigate the impact of a language's morphology on language modeling.

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (2021)

添加到收藏夹

Article Chemistry, Multidisciplinary

Chemputation and the Standardization of Chemical Informatics

Alexander J. S. Hammer et al.

Summary: The explosion in the use of machine learning for automated chemical reaction optimization is gaining momentum, yet the lack of a standard architecture connecting chemical transformations to software and hardware poses barriers. The development of digital chemistry or chemputation, using a universal code-enabled control of chemical reactions, aims to eliminate these barriers and allow users to focus on chemistry research while inserting algorithms as needed. This universal approach can unify all chemistry automation strategies, facilitate reproducibility and interoperability, and enable chemistry to follow computation, ensuring consistent results with low error rates across different capable hardware.

JACS AU (2021)

添加到收藏夹

Review Psychology, Multidisciplinary

Closed- and Open-Vocabulary Approaches to Text Analysis: A Review, Quantitative Comparison, and Recommendations

Johannes C. Eichstaedt et al.

Summary: This article compares five predominant closed- and open-vocabulary methods for analyzing written text, finding that closed-vocabulary methods efficiently summarize concepts and help understand how people think, while open-vocabulary approaches better elucidate specific thoughts and patterns.

PSYCHOLOGICAL METHODS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Prediction of chemical reaction yields using deep learning

Philippe Schwaller et al.

Summary: Artificial intelligence is playing a crucial role in organic chemistry, particularly in areas such as reaction prediction and synthesis planning. Despite the potential of accurately predicting reaction yields, it has received less attention compared to other aspects. Predicting reaction yields can guide chemists in selecting high-yielding reactions and reducing the number of experimental attempts.

MACHINE LEARNING-SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

A deep learning based method for extracting semantic information from patent documents

Liang Chen et al.

SCIENTOMETRICS (2020)

添加到收藏夹

Article Multidisciplinary Sciences

Automated extraction of chemical synthesis actions from experimental procedures

Alain C. Vaucher et al.

NATURE COMMUNICATIONS (2020)

添加到收藏夹

Review Cell Biology

Named Entity Recognition and Relation Detection for Biomedical Information Extraction

Nadeesha Perera et al.

FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY (2020)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Character level and word level embedding with bidirectional LSTM - Dynamic recurrent neural network for biomedical named entity recognition from literature

Sudhakaran Gajendran et al.

JOURNAL OF BIOMEDICAL INFORMATICS (2020)

添加到收藏夹

Proceedings Paper Automation & Control Systems

On the vanishing and exploding gradient problem in Gated Recurrent Units

Alexander Rehmer et al.

IFAC PAPERSONLINE (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

A Review of Activation Function for Artificial Neural Network

Andrinandrasana David Rasamoelina et al.

2020 IEEE 18TH WORLD SYMPOSIUM ON APPLIED MACHINE INTELLIGENCE AND INFORMATICS (SAMI 2020) (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Are GRU Cells More Specific and LSTM Cells More Sensitive in Motive Classification of Text?

Nicole Gruber et al.

FRONTIERS IN ARTIFICIAL INTELLIGENCE (2020)

添加到收藏夹

Article Mathematical & Computational Biology

Automatic identification of relevant chemical compounds from patents

Saber A. Akhondi et al.

DATABASE-THE JOURNAL OF BIOLOGICAL DATABASES AND CURATION (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction

Philippe Schwaller et al.

ACS CENTRAL SCIENCE (2019)

添加到收藏夹

Article Chemistry, Multidisciplinary

A Text Abstraction Summary Model Based on BERT Word Embedding and Reinforcement Learning

Qicai Wang et al.

APPLIED SCIENCES-BASEL (2019)

添加到收藏夹

Article Computer Science, Information Systems

Transformer-Based Neural Network for Answer Selection in Question Answering

Taihua Shao et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Predicting reaction performance in C-N cross-coupling using machine learning

Derek T. Ahneman et al.

SCIENCE (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Found in Translation: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models

Philippe Schwaller et al.

CHEMICAL SCIENCE (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Rafael Gomez-Bombarelli et al.

ACS CENTRAL SCIENCE (2018)

添加到收藏夹

Article Multidisciplinary Sciences

Planning chemical syntheses with deep neural networks and symbolic AI

Marwin H. S. Segler et al.

NATURE (2018)

添加到收藏夹

Article Chemistry, Multidisciplinary

Prediction of Organic Reaction Outcomes Using Machine Learning

Connor W. Coley et al.

ACS CENTRAL SCIENCE (2017)

添加到收藏夹

Review Chemistry, Multidisciplinary

Computer-Assisted Synthetic Planning: The End of the Beginning

Sara Szymkuc et al.

ANGEWANDTE CHEMIE-INTERNATIONAL EDITION (2016)

添加到收藏夹

Article Physics, Multidisciplinary

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

Matthias Rupp et al.

PHYSICAL REVIEW LETTERS (2012)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Enhancing Bag-of-Words Models with Semantics-Preserving Metric Learning

Lei Wu et al.

IEEE MULTIMEDIA (2011)

添加到收藏夹

Article Chemistry, Medicinal

Chemical Name to Structure: OPSIN, an Open Source Solution

Daniel M. Lowe et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2011)

添加到收藏夹

Software Review Chemistry, Medicinal

Reaxys

Jonathan Goodman

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2009)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.