检索结果-内蒙古大学图书馆

Data-oriented protein kinase drug discovery

EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY 2024年 271卷 116413页

作者： Xerxa, Elena Bajorath, Juergen Rhein Friedrich Wilhelms Univ Lamarr Inst Machine Learning & Artificial Intellig Dept Life Sci Informat & Data Sci B ITLIMES Program Unit Chem Biol & Med Chem Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

The continued growth of data from biological screening and medicinal chemistry provides opportunities for datadriven experimental design and decision making in early-phase drug discovery. Approaches adopted from data science help to integrate internal and public domain data and extract knowledge from historical in-house data. Protein kinase (PK) drug discovery is an exemplary area where large amounts of data are accumulating, providing a valuable knowledge base for discovery projects. Herein, the evolution of PK drug discovery and development of small molecular PK inhibitors (PKIs) is reviewed, highlighting milestone developments in the field and discussing exemplary studies providing a basis for increasing data orientation of PK discovery efforts.

关键词： Drug discovery Protein kinases Inhibitors Modes-of-action Selectivity Multi-target activity Polypharmacology Data science Public domain data

来源：评论

学校读者我要写书评

暂无评论

Comparing Explanations of Molecular machine learning Models Generated with Different Methods for the Calculation of Shapley Values

引用

MOLECULAR INFORMATICS 2025年第3期44卷 e202500067页

作者： Lamens, Alec Bajorath, Juergen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem B IT Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Feature attribution methods from explainable artificial intelligence (XAI) provide explanations of machine learning models by quantifying feature importance for predictions of test instances. While features determining individual predictions have frequently been identified in machine learning applications, the consistency of feature importance-based explanations of machine learning models using different attribution methods has not been thoroughly investigated. We have systematically compared model explanations in molecular machine learning. Therefore, a test system of highly accurate compound activity predictions for different targets using different machine learning methods was generated. For these predictions, explanations were computed using methodological variants of the Shapley value formalism, a popular feature attribution approach in machine learning adapted from game theory. Predictions of each model were assessed using a model-agnostic and model-specific Shapley value-based method. The resulting feature importance distributions were characterized and compared by a global statistical analysis using diverse measures. Unexpectedly, methodological variants for Shapley value calculations yielded distinct feature importance distributions for highly accurate predictions. There was only little agreement between alternative model explanations. Our findings suggest that feature importance-based explanations of machine learning predictions should include an assessment of consistency using alternative methods.

关键词： approximation methods compound activity prediction feature attribution machine learning model explanation Shapley values

来源：评论

学校读者我要写书评

暂无评论

Structural Forecasting for Short-Term Tropical Cyclone Intensity Guidance

引用

WEATHER AND FORECASTING 2023年第6期38卷 985-998页

作者： McNeely, Trey Khokhlov, Pavel Dalmasso, Niccolo Wood, Kimberly M. Lee, Ann B. Carnegie Mellon Univ Dept Stat & Data Sci Pittsburgh PA 15213 USA Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA USA Mississippi State Univ Dept Geosci Mississippi State MS USA Microsoft AI Dev Accelerat Program Cambridge MA USA

Because geostationary satellite (Geo) imagery provides a high temporal resolution window into tropical cyclone (TC) behavior, we investigate the viability of its application to short-term probabilistic forecasts of TC convective structure to subsequently predict TC intensity. Here, we present a prototype model that is trained solely on two inputs: Geo infrared imag-ery leading up to the synoptic time of interest and intensity estimates up to 6 h prior to that time. To estimate future TC struc-ture, we compute cloud-top temperature radial profiles from infrared imagery and then simulate the evolution of an ensemble of those profiles over the subsequent 12 h by applying a deep autoregressive generative model (PixelSNAIL). To forecast TC in-tensities at hours 6 and 12, we input operational intensity estimates up to the current time (0 h) and simulated future radial pro-files up to 112 h into a "nowcasting" convolutional neural network. We limit our inputs to demonstrate the viability of our approach and to enable quantification of value added by the observed and simulated future radial profiles beyond operational intensity estimates alone. Our prototype model achieves a marginally higher error than the National Hurricane Center's official forecasts despite excluding environmental factors, such as vertical wind shear and sea surface temperature. We also demonstrate that it is possible to reasonably predict short-term evolution of TC convective structure via radial profiles from Geo infrared im-agery, resulting in interpretable structural forecasts that may be valuable for TC operational guidance.

关键词： Hurricanes typhoons Satellite observations Probability forecasts models distribution Deep learning Artificial intelligence Short-range prediction

来源：评论

学校读者我要写书评

暂无评论

Anatomy of Potency Predictions Focusing on Structural Analogues with Increasing Potency Differences Including Activity Cliffs

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2023年第22期63卷 7032-7044页

作者： Janela, Tiago Bajorath, Jurgen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem B IT D-53115 Bonn Germany Rheinische Friedrich Wilhelms Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig D-535115 Bonn Germany

Potency predictions are popular in compound design and optimization but are complicated by intrinsic limitations. Moreover, even for nonlinear methods, activity cliffs (ACs, formed by structural analogues with large potency differences) represent challenging test cases for compound potency predictions. We have devised a new test system for potency predictions, including AC compounds, that is based on partitioned matched molecular pairs (MMP) and makes it possible to monitor prediction accuracy at the level of analogue pairs with increasing potency differences. The results of systematic predictions using different machine learning and control methods on MMP-based data sets revealed increasing prediction errors when potency differences between corresponding training and test compounds increased, including large prediction errors for AC compounds. At the global level, these prediction errors were not apparent due to the statistical dominance of analogue pairs with small potency differences. Test compounds from such pairs were accurately predicted and determined the observed global prediction accuracy. Shapley value analysis, an explainable artificial intelligence approach, was applied to identify structural features determining potency predictions using different methods. The analysis revealed that numerical predictions of different regression models were determined by features that were shared by MMP partner compounds or absent in these compounds, with opposing effects. These findings provided another rationale for accurate predictions of similar potency values for structural analogues and failures in predicting the potency of AC compounds.

关键词： Chemical calculations Computer simulations Peptides and proteins Structure activity relationship Testing and assessment

来源：评论

学校读者我要写书评

暂无评论

Assessing Darkness of the Human Kinome from a Medicinal Chemistry Perspective

引用

JOURNAL OF MEDICINAL CHEMISTRY 2024年第19期67卷 17919-17928页

作者： Vossen, Selina Xerxa, Elena Bajorath, Juergen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci B IT D-53115 Bonn Germany Lamarr Inst Machine Learning & Artificial Intellig D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ LIMES Inst Program Unit Chem Biol & Med Chem D-53115 Bonn Germany

In drug discovery, human protein kinases (PKs) represent one of the major target classes due to their central role in cellular signaling, implication in various diseases as a consequence of deregulated signaling, and notable druggability. Individual PKs and their disease biology have been explored to different degrees, giving rise to heterogeneous functional knowledge and disease associations across the human kinome. The U.S. National Institutes of Health previously designated 162 understudied ("dark") human PKs and lipid kinases due to the lack of functional annotations and high-quality molecular probes for functional investigations. Given the large volumes of available PK inhibitors (PKIs) and activity data, we have systematically analyzed the distribution of PKIs and associated data at different confidence levels across the human kinome and distinguished between chemically explored, underexplored, and unexplored PKs. The analysis provides a medicinal chemistry-centric view of PK exploration and further extends prior assessment of the dark kinome.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Systematic generation and analysis of counterfactuals for compound activity predictions using multi-task models

引用

RSC MEDICINAL CHEMISTRY 2024年第5期15卷 1547-1555页

作者： Lamens, Alec Bajorath, Juergen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem LIMES ProgramUnit Chem Biol & Med Chem Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Most machine learning (ML) methods produce predictions that are hard or impossible to understand. The black box nature of predictive models obscures potential learning bias and makes it difficult to recognize and trace problems. Moreover, the inability to rationalize model decisions causes reluctance to accept predictions for experimental design. For ML, limited trust in predictions presents a substantial problem and continues to limit its impact in interdisciplinary research, including early-phase drug discovery. As a desirable remedy, approaches from explainable artificial intelligence (XAI) are increasingly applied to shed light on the ML black box and help to rationalize predictions. Among these is the concept of counterfactuals (CFs), which are best understood as test cases with small modifications yielding opposing prediction outcomes (such as different class labels in object classification). For ML applications in medicinal chemistry, for example, compound activity predictions, CFs are particularly intuitive because these hypothetical molecules enable immediate comparisons with actual test compounds that do not require expert ML knowledge and are accessible to practicing chemists. Such comparisons often reveal structural moieties in compounds that determine their predictions and can be further investigated. Herein, we adapt and extend a recently introduced concept for the systematic generation of molecular CFs to multi-task predictions of different classes of protein kinase inhibitors, analyze CFs in detail, rationalize the origins of CF formation in multi-task modeling, and present exemplary explanations of predictions. For a kinase inhibitor correctly predicted with a multi-task machine learning model (shown on an orange background), counterfactuals with small chemical changes (shown in red) were generated that were predicted to be active against other kinases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Medical Data Analysis Using AutoML Frameworks

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2024年第7期19卷 4515-4522页

作者： Shin, Seunghun Park, Dongyoung Ji, Suhwan Joo, Gihun Im, Hyeonseung Kangwon Natl Univ Interdisciplinary Grad Program Med Bigdata Converg Major AI & Software Chunchon 24341 South Korea Yonsei Univ Theory Computat Lab Seoul 03722 South Korea Kangwon Natl Univ Programming Language & Machine Learning Lab Chunchon 24341 South Korea Kangwon Natl Univ Dept Comp Sci & Engn Chunchon 24341 South Korea

Recently, there has been a growing interest in applying machine learning (ML) and deep learning to medical big data and smart healthcare. However, it can be challenging to possess both domain knowledge of medical data and expertise in ML necessary for conducting research in this area. In this regard, an automated machine learning (AutoML) framework can be a solution, which automates an ML pipeline-building process from data cleansing and preprocessing to model building, optimization, and performance evaluation. Since AutoML can reduce domain dependency in ML and quickly build high-performance models, it has a high potential for use in the medical and healthcare fields. Therefore, in this paper, we aim to validate the effectiveness of various AutoML frameworks using structured and unstructured medical data such as electronic medical records, medical images, and signal data. More specifically, we compare the performance of representative AutoML frameworks and simple handcrafted models in terms of various metrics such as the area under the curve, accuracy, and F1 score. Our experimental results show that AutoML effectively handles structured and unstructured data in general, but it still needs to be further improved to deal with data that is imbalanced or requires special preprocessing, such as signal data.

关键词： AutoML machine learning Medical data Medical imaging Biosignals

来源：评论

学校读者我要写书评

暂无评论

Kinase Drug Discovery: Impact of Open Science and Artificial Intelligence

引用

MOLECULAR PHARMACEUTICS 2024年第10期21卷 4849-4859页

作者： Miljkovic, Filip Bajorath, Juergen AstraZeneca Med Chem Res & Early Dev Cardiovasc Renal & Metab CVRM BioPharmaceut R&D SE-43183 Gothenburg Sweden Rhein Friedrich Wilhelms Univ Lamarr Inst Machine Learning & Artificial Intellig Dept Life Sci Informat & Data Sci LIMES Program Chem Biol & Med ChemB IT D-53115 Bonn Germany

Given their central role in signal transduction, protein kinases (PKs) were first implicated in cancer development, caused by aberrant intracellular signaling events. Since then, PKs have become major targets in different therapeutic areas. The preferred approach to therapeutic intervention of PK-dependent diseases is the use of small molecules to inhibit their catalytic phosphate group transfer activity. PK inhibitors (PKIs) are among the most intensely pursued drug candidates, with currently 80 approved compounds and several hundred in clinical trials. Following the elucidation of the human kinome and development of robust PK expression systems and high-throughput assays, large volumes of PK/PKI data have been produced in industrial and academic environments, more so than for many other pharmaceutical targets. In addition, hundreds of X-ray structures of PKs and their complexes with PKIs have been reported. Substantial amounts of PK/PKI data have been made publicly available in part as a result of open science initiatives. PK drug discovery is further supported through the incorporation of data science approaches, including the development of various specialized databases and online resources. Compound and activity data wealth compared to other targets has also made PKs a focal point for the application of artificial intelligence (AI) in pharmaceutical research. Herein, we discuss the interplay of open and data science in PK drug discovery and review exemplary studies that have substantially contributed to its development, including kinome profiling or the analysis of PKI promiscuity versus selectivity. We also take a close look at how AI approaches are beginning to impact PK drug discovery in light of their increasing data orientation.

关键词： drug discovery protein kinases kinase inhibitors open science data science artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

GENE REGULATORY NETWORK INFERENCE IN THE PRESENCE OF DROPOUTS: A CAUSAL VIEW 12

GENE REGULATORY NETWORK INFERENCE IN THE PRESENCE OF DROPOUT...

引用

12th International Conference on learning Representations, ICLR 2024

作者： Dai, Haoyue Ng, Ignavier Luo, Gongxu Spirtes, Peter Stojanov, Petar Zhang, Kun Department of Philosophy Carnegie Mellon University United States Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Cancer Program Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard United States

Gene regulatory network inference (GRNI) is a challenging problem, particularly owing to the presence of zeros in single-cell RNA sequencing data: some are biological zeros representing no gene expression, while some others are technical zeros arising from the sequencing procedure (aka dropouts), which may bias GRNI by distorting the joint distribution of the measured gene expressions. Existing approaches typically handle dropout error via imputation, which may introduce spurious relations as the true joint distribution is generally unidentifiable. To tackle this issue, we introduce a causal graphical model to characterize the dropout mechanism, namely, Causal Dropout Model. We provide a simple yet effective theoretical result: interestingly, the conditional independence (CI) relations in the data with dropouts, after deleting the samples with zero values (regardless if technical or not) for the conditioned variables, are asymptotically identical to the CI relations in the original data without dropouts. This particular test-wise deletion procedure, in which we perform CI tests on the samples without zeros for the conditioned variables, can be seamlessly integrated with existing structure learning approaches including constraint-based and greedy score-based methods, thus giving rise to a principled framework for GRNI in the presence of dropouts. We further show that the causal dropout model can be validated from data, and many existing statistical models to handle dropouts fit into our model as specific parametric instances. Empirical evaluation on synthetic, curated, and real-world experimental transcriptomic data comprehensively demonstrate the efficacy of our method. © 2024 12th International Conference on learning Representations, ICLR 2024. All rights reserved.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Influence of Data Curation and Confidence Levels on Compound Predictions Using machine learning Models

引用

JOURNAL OF CHEMICAL INFORMATION AND MODELING 2024年第24期64卷 9341-9349页

作者： Xerxa, Elena Vogt, Martin Bajorath, Juergen Rhein Friedrich Wilhelms Univ Dept Life Sci Informat & Data Sci B IT D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ Lamarr Inst Machine Learning & Artificial Intellig D-53115 Bonn Germany Rhein Friedrich Wilhelms Univ Limes Inst Program Unit Chem Biol & Med Chem D-53115 Bonn Germany

While data curation principles and practices are a major topic in data science, they are often not explicitly considered in machine learning (ML) applications in chemistry. We have been interested in evaluating the potential effects of data curation on the performance of molecular ML models. Therefore, a sequential curation scheme was developed for compounds and activity data, and different ML classification models were generated at increasing data confidence levels and evaluated. Sequential data curation was found to systematically increase classification performance in an incremental manner due to cumulative effects of individual data curation criteria. The analysis of chemical space distributions of compound subsets at different data confidence levels revealed that the separation of compounds with different class labels in chemical space generally increased during sequential activity data curation, which was mostly due to subsequent elimination of singletons rather than compounds from analogue series. These findings provided a rationale for increasing the classification performance of ML models as a consequence of increasingly stringent data curation. Taken together, the results reported herein suggest that further attention should be paid to varying data curation and confidence levels when deriving and assessing ML models for chemical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：