4.6 Article

Explainable AI for Estimating Pathogenicity of Genetic Variants Using Large-Scale Knowledge Graphs

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。
Article Genetics & Heredity

Analysis of missense variants in the human genome reveals widespread gene-specific clustering and improves prediction of pathogenicity

Mathieu Quinodoz et al.

Summary: This study used a machine learning approach to analyze the distribution of missense variants in genes associated with hereditary conditions and cancer. The results showed that pathogenic and benign variants tend to cluster within genes, possibly due to mechanisms shaping pathogenicity at the protein level. Based on these findings, a pathogenicity predictor called MutScore was developed, which outperformed existing tools in identifying pathogenic missense mutations.

AMERICAN JOURNAL OF HUMAN GENETICS (2022)

Review Chemistry, Multidisciplinary

A Systematic Review of Explainable Artificial Intelligence in Terms of Different Application Domains and Tasks

Mir Riyanul Islam et al.

Summary: This paper presents a systematic literature review of recent developments in explainable artificial intelligence (XAI) methods and evaluation metrics for different application domains and tasks. The study finds that XAI methods are mostly used in safety-critical domains, deep learning and ensemble models are popular, visual explanations are preferred, and more attention is needed to generate explanations for general users in sensitive domains.

APPLIED SCIENCES-BASEL (2022)

Article Chemistry, Analytical

Fine-Tuned DenseNet-169 for Breast Cancer Metastasis Prediction Using FastAI and 1-Cycle Policy

Adarsh Vulli et al.

Summary: This study introduces a new method for automated diagnosis and detection of metastases in breast cancer using the Fast AI framework and the 1-cycle policy, and compares it with previous methods. The proposed model has achieved an accuracy of over 97.4% and surpasses other state-of-the-art methods. Additionally, a mobile application has been developed for prompt diagnosis of metastases in early-stage cancer.

SENSORS (2022)

Article Biochemistry & Molecular Biology

Medical Professional Enhancement Using Explainable Artificial Intelligence in Fetal Cardiac Ultrasound Screening

Akira Sakai et al.

Summary: Diagnostic support tools based on AI have shown high performance in medical fields, but lack of explanatory power in AI decisions makes it challenging to establish trust with medical professionals. Visualizing the internal representation of deep neural networks can enhance explanation and boost confidence in AI decisions. Using deep learning-based explainable representation improves the performance of fetal cardiac ultrasound screening, providing evidence of the potential of explainable AI to augment examiner capabilities.

BIOMEDICINES (2022)

Review Cell Biology

Interpreting protein variant effects with computational predictors and deep mutational scanning

Benjamin J. Livesey et al.

Summary: Computational predictors of genetic variant effect have made significant advancements, providing a rapid and scalable method to assess the impacts of new variants. However, the trustworthiness of their results may be uncertain. Benchmarking against large datasets of known variants is common, but overlapping with training data can lead to inflated performance estimates. Deep mutational scans offer an independent solution to this issue.

DISEASE MODELS & MECHANISMS (2022)

Article Computer Science, Artificial Intelligence

Automatic detection of Alzheimer?s disease progression: An efficient information fusion approach with heterogeneous ensemble classifiers

Shaker El-Sappagh et al.

Summary: This study proposes a novel ensemble learning framework for predicting Alzheimer's disease progression. The framework incorporates heterogeneous base learners into an integrated model and utilizes multimodal time-series data. The proposed model achieves outstanding performance in predicting disease progression and can be implemented in low-cost healthcare environments. The balance between accuracy and diversity is found to be critical in selecting ensemble members. The proposed framework holds promise for efficient information fusion ensembles in medical and non-medical problems.

NEUROCOMPUTING (2022)

Article Computer Science, Artificial Intelligence

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Alejandro Barredo Arrieta et al.

INFORMATION FUSION (2020)

Article Multidisciplinary Sciences

Inferring the molecular and phenotypic impact of amino acid variants with MutPred2

Vikas Pejaver et al.

NATURE COMMUNICATIONS (2020)

Review Genetics & Heredity

Artificial intelligence in clinical and genomic diagnostics

Raquel Dias et al.

GENOME MEDICINE (2019)

Article Biochemistry & Molecular Biology

CADD: predicting the deleteriousness of variants throughout the human genome

Philipp Rentzsch et al.

NUCLEIC ACIDS RESEARCH (2019)

Review Oncology

Whole genome sequencing analysis for cancer genomics and precision medicine

Hidewaki Nakagawa et al.

CANCER SCIENCE (2018)

Article Genetics & Heredity

ClinPred: Prediction Tool to Identify Disease-Relevant Nonsynonymous Single-Nucleotide Variants

Najmeh Alirezaie et al.

AMERICAN JOURNAL OF HUMAN GENETICS (2018)

Article Genetics & Heredity

REVEL: An Ensemble Method for Predicting the Pathogenicity of Rare Missense Variants

Nilah M. Ioannidis et al.

AMERICAN JOURNAL OF HUMAN GENETICS (2016)

Article Mathematical & Computational Biology

FALDO: a semantic standard for describing the location of nucleotide and protein feature annotation

Jerven T. Bolleman et al.

JOURNAL OF BIOMEDICAL SEMANTICS (2016)

Article Biochemical Research Methods

PROVEAN web server: a tool to predict the functional effect of amino acid substitutions and indels

Yongwook Choi et al.

BIOINFORMATICS (2015)

Article Biochemical Research Methods

DANN: a deep learning approach for annotating the pathogenicity of genetic variants

Daniel Quang et al.

BIOINFORMATICS (2015)

Article Biochemistry & Molecular Biology

Comparison and integration of deleteriousness prediction methods for nonsynonymous SNVs in whole exome sequencing studies

Chengliang Dong et al.

HUMAN MOLECULAR GENETICS (2015)

Letter Biochemical Research Methods

MutationTaster2: mutation prediction for the deep-sequencing age

Jana Marie Schwarz et al.

NATURE METHODS (2014)

Article Genetics & Heredity

Ranking non-synonymous single nucleotide polymorphisms based on disease concepts

Hashem A. Shihab et al.

HUMAN GENOMICS (2014)

Article Biotechnology & Applied Microbiology

Benchmarking mutation effect prediction algorithms using functionally validated cancer-related missense mutations

Luciano G. Martelotto et al.

GENOME BIOLOGY (2014)

Letter Biochemical Research Methods

A method and server for predicting damaging missense mutations

Ivan A. Adzhubei et al.

NATURE METHODS (2010)

Article Biochemical Research Methods

Identifying a High Fraction of the Human Genome to be under Selective Constraint Using GERP plus

Eugene V. Davydov et al.

PLOS COMPUTATIONAL BIOLOGY (2010)

Article Biochemical Research Methods

Identifying novel constrained elements by exploiting biased substitution patterns

Manuel Garber et al.

BIOINFORMATICS (2009)

Article Biochemistry & Molecular Biology

Identification of deleterious mutations within three human genomes

Sung Chun et al.

GENOME RESEARCH (2009)

Proceedings Paper Computer Science, Information Systems

DBpedia: A nucleus for a web of open data

Soeren Auer et al.

SEMANTIC WEB, PROCEEDINGS (2007)

Article Biochemistry & Molecular Biology

Evolutionarily conserved elements in vertebrate, insect, worm, and yeast genomes

A Siepel et al.

GENOME RESEARCH (2005)

Article Biochemistry & Molecular Biology

Predicting deleterious amino acid substitutions

PC Ng et al.

GENOME RESEARCH (2001)