MétaCan
Menu
Back to cohort
Record W4388928478 · doi:10.1093/bioadv/vbad166

Adversarial training improves model interpretability in single-cell RNA-seq analysis

2023· article· en· W4388928478 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueBioinformatics Advances · 2023
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicSingle-cell and spatial transcriptomics
Canadian institutionsPrincess Margaret Cancer CentreLunenfeld-Tanenbaum Research InstituteUniversity Health NetworkUniversity of TorontoSinai Health SystemUniversity of Waterloo
Fundersnot available
KeywordsInterpretabilityRobustness (evolution)Machine learningComputer scienceArtificial intelligenceClassifier (UML)Data miningBiologyGene

Abstract

fetched live from OpenAlex

Motivation: Predictive computational models must be accurate, robust, and interpretable to be considered reliable in important areas such as biology and medicine. A sufficiently robust model should not have its output affected significantly by a slight change in the input. Also, these models should be able to explain how a decision is made to support user trust in the results. Efforts have been made to improve the robustness and interpretability of predictive computational models independently; however, the interaction of robustness and interpretability is poorly understood. Results: As an example task, we explore the computational prediction of cell type based on single-cell RNA-seq data and show that it can be made more robust by adversarially training a deep learning model. Surprisingly, we find this also leads to improved model interpretability, as measured by identifying genes important for classification using a range of standard interpretability methods. Our results suggest that adversarial training may be generally useful to improve deep learning robustness and interpretability and that it should be evaluated on a range of tasks. Availability and implementation: Our Python implementation of all analysis in this publication can be found at: https://github.com/MehrshadSD/robustness-interpretability. The analysis was conducted using numPy 0.2.5, pandas 2.0.3, scanpy 1.9.3, tensorflow 2.10.0, matplotlib 3.7.1, seaborn 0.12.2, sklearn 1.1.1, shap 0.42.0, lime 0.2.0.1, matplotlib_venn 0.11.9.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.745
Threshold uncertainty score0.791

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.023
GPT teacher head0.250
Teacher spread0.227 · 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