MétaCan
Menu
Back to cohort
Record W4388731451 · doi:10.1002/widm.1523

The use of gene expression datasets in feature selection research: 20 years of inherent bias?

2023· article· en· W4388731451 on OpenAlexafffund
Bruno Iochins Grisci, Bruno César Feltes, Joice de Faria Poloni, Pedro Henrique Narloch, Márcio Dorn

Bibliographic record

VenueWiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · 2023
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicGene expression and cancer classification
Canadian institutionsDalhousie University
FundersGlobal Affairs CanadaFundação de Amparo à Pesquisa do Estado do Rio Grande do SulConselho Nacional de Desenvolvimento Científico e TecnológicoCoordenação de Aperfeiçoamento de Pessoal de Nível Superior
KeywordsFeature selectionPreprocessorComputer scienceSelection (genetic algorithm)Feature (linguistics)Machine learningData miningDNA microarrayData pre-processingArtificial intelligenceBiological dataData scienceBioinformaticsGeneGene expressionBiologyGenetics

Abstract

fetched live from OpenAlex

Abstract Feature selection algorithms are frequently employed in preprocessing machine learning pipelines applied to biological data to identify relevant features. The use of feature selection in gene expression studies began at the end of the 1990s with the analysis of human cancer microarray datasets. Since then, gene expression technology has been perfected, the Human Genome Project has been completed, new microarray platforms have been created and discontinued, and RNA‐seq has gradually replaced microarrays. However, most feature selection methods in the last two decades were designed, evaluated, and validated on the same datasets from the microarray technology's infancy. In this review of over 1200 publications regarding feature selection and gene expression, published between 2010 and 2020, we found that 57% of the publications used at least one outdated dataset, 23% used only outdated data, and 32% did not cite data sources. Other issues include referencing databases that are no longer available, the slow adoption of RNA‐seq datasets, and bias toward human cancer data, even for methods designed for a broader scope. In the most popular datasets, some being 23 years old, mislabeled samples, experimental biases, distribution shifts, and the absence of classification challenges are common. These problems are more predominant in publications with computer science backgrounds compared to publications from biology and can lead to inaccurate and misleading biological results. This article is categorized under: Algorithmic Development > Biological Data Mining Technologies > Machine Learning

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.088
metaresearch head score (Gemma)0.158
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.912
Threshold uncertainty score0.465

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0880.158
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0050.010
Science and technology studies0.0010.003
Scholarly communication0.0060.005
Open science0.0020.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.284
GPT teacher head0.427
Teacher spread0.144 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

Study designObservational
DomainMethods
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2023
Admission routes2
Has abstractyes

Explore more

Same venueWiley Interdisciplinary Reviews Data Mining and Knowledge DiscoverySame topicGene expression and cancer classificationFrench-language works237,207