Machine learning driven dashboard for chronic myeloid leukemia prediction using protein sequences
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.
Bibliographic record
Abstract
The prevalence of Leukaemia, a malignant blood cancer that originates from hematopoietic progenitor cells, is increasing in Southeast Asia, with a worrisome fatality rate of 54%. Predicting outcomes in the early stages is vital for improving the chances of patient recovery. The aim of this research is to enhance early-stage prediction systems in a substantial manner. Using Machine Learning and Data Science, we exploit protein sequential data from commonly altered genes including BCL2, HSP90, PARP, and RB to make predictions for Chronic Myeloid Leukaemia (CML). The methodology we implement is based on the utilisation of reliable methods for extracting features, namely Di-peptide Composition (DPC), Amino Acid Composition (AAC), and Pseudo amino acid composition (Pse-AAC). We also take into consideration the identification and handling of outliers, as well as the validation of feature selection using the Pearson Correlation Coefficient (PCA). Data augmentation guarantees a comprehensive dataset for analysis. By utilising several Machine Learning models such as Support Vector Machine (SVM), XGBoost, Random Forest (RF), K Nearest Neighbour (KNN), Decision Tree (DT), and Logistic Regression (LR), we have achieved accuracy rates ranging from 66% to 94%. These classifiers are thoroughly evaluated utilising performance criteria such as accuracy, sensitivity, specificity, F1-score, and the confusion matrix.The solution we suggest is a user-friendly online application dashboard that can be used for early detection of CML. This tool has significant implications for practitioners and may be used in healthcare institutions and hospitals.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it