MétaCan
Menu
Back to cohort

Prediction of Protein-Protein Interactions through Deep Learning Based on Sequence Feature Extraction and Interaction Network

2022· article· en· W4309242540 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

Venue2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) · 2022
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicMachine Learning in Bioinformatics
Canadian institutionsArtificial Intelligence in Medicine (Canada)
FundersMinistry of EducationMinistry of Science and Technology
KeywordsComputer scienceArtificial intelligenceArtificial neural networkMachine learningDeep learningProcess (computing)Feature extractionCross-validationField (mathematics)Protein function predictionSet (abstract data type)Sequence (biology)Test setPattern recognition (psychology)Data miningProtein functionMathematics

Abstract

fetched live from OpenAlex

Protein-protein interaction (PPI) is an important molecular process in the cell, which is vital to the function of the cell in the biochemical process. This study focuses on human protein. It uses protein information and the relationship of protein interaction network structure to predict PPI. Deep neural network model is implemented to realize PPI prediction. Through five-fold cross-validation, a high performance in the prediction accuracy is produced. The accuracy rate on the test set is 92.45%. To further evaluate the performance of this method, we compared it with other machine learning algorithms. The experimental results show that the method based on neural network is significantly better than the others on the same dataset. It also shows a superior performance compared to previous predictors in this field on PPI prediction.

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)0.001
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: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.930
Threshold uncertainty score0.825

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
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 head0.037
GPT teacher head0.280
Teacher spread0.243 · 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