检索结果-内蒙古大学图书馆

Protocol to calculate and compare exact Shapley values for different kernels in support vector machine models using binary features

引用

STAR PROTOCOLS 2024年第4期5卷 103450页

作者： Roth, Jannik P. Bajorath, Juergen Rheinische 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 Lamarr Inst Machine Learning & Artificial Intellig Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

The Shapley value formalism from cooperative game theory was adapted to explain predictions of machine learning models. Here, we present a protocol to calculate and compare exact Shapley values for support vector machine models with commonly used kernels and binary input features. We describe steps for installing software, preparing data, and calculating Shapley values with customizable Python scripts. We then detail procedures for analyzing results via correlation analysis and feature mapping. For complete details on the use and execution of this protocol, please refer to Roth and Bajorath.1

关键词： bioinformatics chemistry computer sciences

来源：评论

学校读者我要写书评

暂无评论

Coarse-Graining Conformational Dynamics with Multidimensional Generalized Langevin Equation: How, When, and Why

引用

JOURNAL OF CHEMICAL THEORY AND COMPUTATION 2024年第18期20卷 7708-7715页

作者： Xie, Pinchen Weinan, E. Princeton Univ Program Appl & Computat Math Princeton NJ 08544 USA Lawrence Berkeley Natl Lab Appl Math & Computat Res Div Berkeley CA 94720 USA AI Sci Inst Beijing 100080 Peoples R China Peking Univ Ctr Machine Learning Res Beijing 100871 Peoples R China Peking Univ Sch Math Sci Beijing 100084 Peoples R China

A data-driven ab initio generalized Langevin equation (AIGLE) approach is developed to learn and simulate high-dimensional, heterogeneous, coarse-grained (CG) conformational dynamics. Constrained by the fluctuation-dissipation theorem, the approach can build CG models in dynamical consistency (DC) with all-atom molecular dynamics. We also propose practical criteria for AIGLE to enforce long-term DC. Case studies of a toy polymer, with 20 CG sites, and the alanine dipeptide, with two dihedral angles, elucidate why one should adopt AIGLE or its Markovian limit for modeling CG conformational dynamics in practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transforming molecular cores, substituents, and combinations into structurally diverse compounds using chemical language models

引用

EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY 2025年 291卷 117615页

作者： Piazza, Lisa Srinivasan, Sanjana Tuccinardi, Tiziano 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 Univ Pisa Dept Pharm Via Bonanno 6 I-56126 Pisa Italy Rhein Friedrich Wilhelms Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Transformer-based chemical language models (CLMs) were derived to generate structurally and topologically diverse embeddings of core structure fragments, substituents, or core/substituent combinations in chemically proper compounds, representing a design task that is difficult to address using conventional structure generation methods. To this end, CLM variants were challenged to learn different fragment-to-compound mappings in the absence of structural rules or any other fragment linking or synthetic information. The resulting alternative models were found to have high syntactic fidelity, but displayed notable differences in their ability to generate valid candidate compounds containing test fragments, with a clear preference for a model variant processing core/substituent combinations. However, the majority of valid candidate compounds generated with all models were distinct from training data and structurally novel. In addition, the CLMs exhibited high chemical diversification capacity and often generated structures with new topologies not encountered during training. Furthermore, all models produced large numbers of close structural analogues of known bioactive compounds covering a large target space, thus indicating the relevance of newly generated candidates for pharmaceutical research. As a part of our study, the new methodology and all data are made publicly available.

关键词： Molecular design Artificial intelligence Chemical language models Fragments Structural embeddings Compound diversification Biological activity

来源：评论

学校读者我要写书评

暂无评论

Automatic Feature Engineering Using Self-Organizing Maps

Automatic Feature Engineering Using Self-Organizing Maps

引用

IEEE Latin American Conference on Computational Intelligence (LA-CCI)

作者： Rodrigues, Ericks da Silva Martins, Denis Mayr Lima de Lima Neto, Fernando Buarque Univ Pernambuco Comp Engn Program Recife PE Brazil Univ Munster ERCIS Machine Learning & Data Engn Munster Germany

ISBN: (纸本)9781728188645

Feature Engineering (FE) consists of generating new, better features to improve the results obtained by machine learning models. Very often, FE is performed in a series of trial-and-error steps conducted manually by data scientists. Moreover, FE requires data-specific and domain knowledge, both rarely easy to acquire. To alleviate these problems, we propose an automatic FE approach based on Self-Organizing Maps (SOM) in which new features are generated via pattern recognition. The use of the SOM algorithm in variable generation tasks can identify data elements that help machine learning models to obtain better results and points out to a broad direction for future researches.

关键词： feature engineering automatic feature engineering self-organizing maps machine learning

来源：评论

学校读者我要写书评

暂无评论

Context-dependent similarity analysis of analogue series for structure-activity relationship transfer based on a concept from natural language processing

引用

JOURNAL OF CHEMINFORMATICS 2025年第1期17卷 1-14页

作者： Yoshimori, Atsushi Bajorath, Jurgen Inst Theoret Med Inc 26-1 Muraoka Higashi 2 chome Fujisawa Kanagawa 2510012 Japan Univ Bonn Dept Life Sci Informat & Data Sci LIMES Program Unit Chem Biol & Med Chem B IT Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany Univ Bonn Lamarr Inst Machine Learning & Artif Intelligence Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Analogue series (AS) are generated during compound optimization in medicinal chemistry and are the major source of structure-activity relationship (SAR) information. Pairs of active AS consisting of compounds with corresponding substituents and comparable potency progression represent SAR transfer events for the same target or across different targets. We report a new computational approach to systematically search for SAR transfer series that combines an AS alignment algorithm with context-depending similarity assessment based on vector embeddings adapted from natural language processing. The methodology comprehensively accounts for substituent similarity, identifies non-classical bioisosteres, captures substituent-property relationships, and generates accurate AS alignments. Context-dependent similarity assessment is conceptually novel in computational medicinal chemistry and should also be of interest for other *** contributionA method is reported to systematically search for and align analogue series with SAR transfer potential. Central to the approach is the assessment of context-dependent similarity for substituents, a new concept in cheminformatics, which is based upon vector embeddings and word pair relationships adapted from natural language processing.

关键词： Active analogue series Potency progression Series alignment SAR transfer Fragment pair relationships Context-dependent similarity

来源：评论

学校读者我要写书评

暂无评论

Self-Organizing Transformations for Automatic Feature Engineering

Self-Organizing Transformations for Automatic Feature Engine...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Rodrigues, Ericks da Silva Lima Martins, Denis Mayr de Lima Neto, Fernando Buarque Univ Pernambuco Comp Engn Program Recife PE Brazil Univ Munster ERCIS Machine Learning & Data Engn Muesnter Germany

ISBN: (纸本)9781728190488

Feature Engineering (FE) consists of generating new, better features to improve machine learning models. Very often, FE is performed in a series of trial-and-error steps conducted manually by data scientists. Moreover, FE requires data-specific and domain knowledge, both rarely easy to acquire. To alleviate these problems, we propose the Self-Organizing Automatic Feature Engineering (SOAFE), a novel approach for Automatic Feature Engineering (AFE). Different from the majority of the existing AFEs, SOAFE employs an unsupervised technique (Self-Organizing Maps) to identify patterns in the data, and apply a form of cooperative training, inspired by Generative Adversarial Networks, to improve the feature construction. Our results on several datasets show that SOAFE can improve classification models when compared with existing AFE approaches.

关键词： feature engineering automatic feature engineering self-organizing maps machine learning

来源：评论

学校读者我要写书评

暂无评论

Generation of dual-target compounds using a transformer chemical language model

引用

CELL REPORTS PHYSICAL SCIENCE 2024年第11期5卷

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

Compounds with defined multi-target activity are candidates for the treatment of multi-factorial diseases. Such compounds are mostly discovered experimentally. Designing compounds with the desired activity against two targets is typically attempted by pharmacophore fusion. In addition, machine learning models can be derived for multi-target prediction of compounds or computational target profiling. Here, we introduce transformer-based chemical language model variants for the generative design of dual-target compounds. Alternative models were pre-trained by learning mappings of single- to dual-target compounds of increasing similarity. Different models were optimized for generating compounds with activity against pairs of functionally unrelated targets using a new cross-fine-tuning approach. Control models confirmed that pre-trained and finetuned models learned the chemical space of dual-target compounds. The final models were found to exactly reproduce known dual-target compounds excluded from model derivation. In addition, many structural analogs of such compounds were generated, further supporting the validity of the methodology.

关键词： dual-target compounds polypharmacology generative design transformer chemical language model cross fine-tuning

来源：评论

学校读者我要写书评

暂无评论

MapView: Exploring Datasets via Unsupervised View Recommendation

MapView: Exploring Datasets via Unsupervised View Recommenda...

引用

IEEE Latin American Conference on Computational Intelligence (LA-CCI)

作者： Aires de Carvalho, Thiego Buenos Lima Martins, Denis Mayr de Lima Neto, Fernando Buarque Univ Pernambuco Comp Engn Program Recife PE Brazil Univ Munster ERCIS Machine Learning & Data Engn Muesnter Germany

ISBN: (纸本)9781728188645

Exploring large datasets in search for valuable insights requires time and sufficient technical knowledge. In order to alleviate this task, we propose and implemented a prototype of a data exploration tool. It is based on Self-Organizing Maps (SOM) and helps non-technical users with limited technical expertise and time. Our proposed approach employs SOM as a clustering mechanism to group and recommend exploratory data views to the user. This recommendation process can also be personalized to meet user's intention in an interactive manner. Experimental results show that the reported prototype is effective in recommending valuable views, hence, being of aid in data exploration tasks.

关键词： view recommendation data exploration self-organizing maps

来源：评论

学校读者我要写书评

暂无评论

machine learning models with distinct Shapley and interpretation for chemical compound predictions

引用

CELL REPORTS PHYSICAL SCIENCE 2024年第8期5卷

作者： Roth, Jannik P. Bajorath, Juergen Univ Bonn Dept Life Sci Informat & Data Sci B IT Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany Univ Bonn Lamarr Inst Machine Learning & Artificial Intellig Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany Univ Bonn Limes Inst Program Unit Chem Biol & Med Chem Friedrich Hirzebruch Allee 5-6 D-53115 Bonn Germany

Explaining black box predictions of machine learning (ML) models is a topical issue in artificial intelligence (AI) research. For the identification of features determining predictions, the Shapley value formalism originally developed in game theory is widely used in different fields. Typically, Shapley values quantifying feature contributions to predictions need to be approximated in machine learning. We introduce a framework for the calculation of exact Shapley values for 4 kernel functions used in support vector machine (SVM) models and analyze consistently accurate compound activity predictions based on exact Shapley values. Dramatic changes in feature contributions are detected depending on the kernel function, leading to mostly distinct explanations of predictions of the same test compounds. Very different feature contributions yield comparable predictions, which complicate numerical and graphical model explanation and decouple feature attribution and human interpretability.

关键词： machine learning explainable artificial intelligence feature attribution exact Shapley values support vector machine model interpretation

来源：评论

学校读者我要写书评

暂无评论

Uncovering and tackling fundamental limitations of compound potency predictions using machine learning models

引用

CELL REPORTS PHYSICAL SCIENCE 2024年第6期5卷

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

Molecular property predictions play a central role in computer-aided drug discovery. Although a variety of physicochemical (e.g., solubility or chemical reactivity) or physiological properties (e.g., metabolic stability or toxicity) can be predicted, biological activity is by far the most frequently investigated compound feature. Activity predictions are carried out in a qualitative (target-based activity, through compound classification) or quantitative (compound potency or studies have evaluated and compared different machine learning methods for activity and potency predictions, recently with a focus on deep learning. Regardless of the methods used, these studies generally rely on conventional benchmark settings. Recent work has shown that potency prediction benchmarks have severe general limitations that have long been unnoticed but prevent a reliable assessment of different methods and their relative performance. In this perspective, we outline general limitations of benchmark settings for compound potency predictions, introduce potential alternatives enabling a more realistic assessment of state-of-the-art predictive models, and discuss future directions for elucidating predictions and further increasing their impact.

关键词： compound potency prediction drug design compound activity classes machine learning performance evaluation data augmentation

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：