Bioinformatics analysis service

Machine learning analysis services: leakage-aware models with DOME- and TRIPOD+AI-aligned reporting

Machine learning (ML) analysis learns predictive patterns from high-dimensional omics, imaging, and clinical data to build biomarker signatures and outcome models. Pepkio delivers version-pinned workflows, nested cross-validation with holdout or external validation when available, interpretability reports, full code ownership, and a Methods draft for academic, biotech, and pharma teams. Custom inputs, outcomes, model types, and non-standard analyses are scoped at kickoff.

Key facts

Key facts about machine learning analysis
FactValue
Data types supportedRNA-seq, proteomics, metabolomics, and methylation feature matrices; clinical covariates; single-cell embeddings; multi-omics matrices merged by sample ID; vendor-normalized outputs (e.g., Olink NPX, DESeq2 vst)
Reference builds or standards usedDOME reporting checklist [4]; TRIPOD+AI for clinical prediction models when scoped [5]; patient-level nested cross-validation; independent holdout or external cohort validation when available; GENCODE v44 / Ensembl 110 gene IDs and UniProt Swiss-Prot accessions for feature harmonization
Primary tools (with versions)scikit-learn 1.6.1; XGBoost 2.1.3; scikit-survival 0.24.1; glmnet 4.1-8 (R); SHAP 0.46.0; Boruta 11.0.0; PyTorch 2.5.1 + scGPT 0.2.4 for transformer fine-tuning when scoped
Typical turnaround range3-5 weeks (single cohort, one outcome, ≤500 features, internal validation); 5-8 weeks (survival models, multi-cohort external validation, or scGPT fine-tuning). Confirmed at kickoff
Deliverable formatsFeature matrices; split manifests; model_performance_summary.csv; SHAP plots; nested-CV results; serialized models; PDF/SVG figures; DOME summary table; commented R/Python scripts; Methods draft
Regulatory/reproducibility standards followedDOME checklist in every deliverable; TRIPOD+AI checklist when clinical prediction reporting is scoped; version-pinned conda or renv environments; logged random seeds; documented leakage audit per Bernett et al. [3]; private Git or Zenodo archival on request
Custom / bespoke analysisNon-standard outcomes, custom feature engineering, domain-specific models, multi-omics fusion beyond standard signatures, client-specified validation schemes, or foundation-model adaptation (e.g., scGPT fine-tuning for perturbation or cell-state tasks) scoped at kickoff
Key terms:

Machine learning (ML) learns patterns from data without hand-coded rules. Supervised learning trains on labeled outcomes (e.g., responder vs non-responder). Cross-validation repeatedly splits data to estimate generalization. Data leakage shares information between training and test sets, inflating performance [3]. AUROC (area under the receiver operating characteristic curve) measures classifier discrimination. C-index (concordance index) measures survival-model discrimination. A foundation model is pretrained on large datasets and fine-tuned for downstream tasks. A transformer is an attention-based neural architecture used in models such as scGPT [1].

What is machine learning?

Machine learning learns predictive or clustering patterns from high-dimensional biological data, often when features (genes, proteins, variants) outnumber samples. Supervised algorithms adjust parameters from labeled outcomes; unsupervised methods find structure without labels. Typical questions include which features or combinations predict an outcome, treatment response, or patient subgroup. scGPT was pretrained on more than 33 million cells and fine-tuned for annotation, integration, and perturbation prediction [1]. A 2023 systematic review screened 682 PubMed articles (2017-2023) and critically reviewed 30 cancer biomarker ML studies; the review noted reporting heterogeneity and data-leakage risks [2].

What machine learning analysis can answer

Published examples of questions machine learning can address:

Which gene signature predicts hepatocellular carcinoma overall survival?

Feng et al. [11] combined scRNA-seq and bulk RNA-seq to derive an 11-gene NK-cell-related signature from 77 ML algorithms, validated across TCGA, GEO, and ICGC cohorts with concordance-index benchmarking.

Which transcriptomic features classify breast cancer for diagnosis and prognosis?

Mirza et al. [12] applied seven ML methods to 701 samples from 11 GEO datasets, identifying a nine-gene diagnostic signature and an eight-gene prognostic signature validated by qRT-PCR.

Which T cell states precede anti-PD-1 response in NSCLC?

Liu et al. [13] profiled 47 biopsies from 36 patients before and after PD-1 therapy, linking precursor exhausted T cell expansion to response. Those states are candidate features for immunotherapy stratification models.

How do genetic or chemical perturbations shift cell-state programs?

Cui et al. [1] showed that scGPT, a generative pretrained transformer on single-cell data, predicts perturbation responses after fine-tuning, which allows transfer learning when labeled perturbation data are limited.

Services included in this category

This category includes biomarker discovery and predictive modeling. Each spoke page lists inputs, validation design, tools, and deliverables.

Machine learning services offered by Pepkio
ServiceDescriptionPrimary tools
Biomarker discoveryFeature selection and compact signature construction from omics or clinical matrices with stability analysis and cross-validationglmnet 4.1-8, Boruta 11.0.0, XGBoost 2.1.3, SHAP 0.46.0
Predictive modelingSupervised classifiers and survival models with nested CV, calibration assessment, and TRIPOD+AI-aligned reporting when scopedscikit-learn 1.6.1, scikit-survival 0.24.1, XGBoost 2.1.3

What Pepkio delivers

Each project includes validated model outputs, interpretability artifacts, version-pinned code, and a Methods draft.

Performance tables and figures

  • model_performance_summary.csv (AUROC, AUPRC, C-index, calibration metrics); ROC, precision-recall, calibration, and SHAP plots (PDF/SVG); Kaplan-Meier plots when survival models are scoped

Feature and model artifacts

  • Ranked feature lists; selected_features.csv; serialized models with documented thresholds

Reporting and code

  • DOME summary table; TRIPOD+AI checklist when clinical prediction reporting is scoped; commented R/Python scripts with conda or renv locks; README; Methods draft. You retain full ownership

Support

  • Milestone check-ins; reviewer clarification and minor revisions within agreed scope (typically ≤20% of deliverables)

Non-standard outcomes, multi-omics fusion, or foundation-model fine-tuning are scoped at kickoff.

How the analysis works — step by step

  1. 1. Scope outcome, cohort, and validation plan

    Confirm the prediction target, inclusion criteria, endpoint type (binary, multiclass, survival), and whether an independent external cohort is available [4, 5].

    Tools and outputs

    Output: signed scope with primary and secondary metrics

  2. 2. Validate inputs and harmonize metadata

    Match sample IDs; audit missingness, duplicate patients, and batch structure.

    Tools and outputs

    Output: sample_manifest.csv and feature_qc_summary.csv

  3. 3. Preprocess and normalize features

    Apply transforms and scaling; use batch correction only when batch is not confounded with the outcome [6].

    Tools and outputs

    Tools used: scikit-learn ColumnTransformer; ComBat or limma when scoped

    Output: analysis-ready feature matrix

  4. 4. Audit for data leakage

    Apply the seven guiding questions from Bernett et al. [3] before splitting.

    Tools and outputs

    Output: leakage_audit.md

  5. 5. Partition data with nested cross-validation

    Use patient-level nested cross-validation to separate tuning from performance estimation [4].

    Tools and outputs

    Tools used: scikit-learn CV splitters; scikit-survival for censored outcomes

    Output: fold assignment table

  6. 6. Select features and train candidate models

    Compare regularized linear models, tree ensembles, and survival forests with simpler baselines [7]. Fine-tune scGPT when single-cell transfer learning is scoped [1].

    Tools and outputs

    Output: candidate model list

  7. 7. Evaluate performance and calibration

    Report discrimination and calibration on held-out or external data; avoid claiming clinical utility without independent validation [6].

    Tools and outputs

    Output: model_performance_summary.csv

  8. 8. Interpret features and biological context

    Annotate selected features with pathways and cell types; document where interpretability limits causal claims [1].

    Tools and outputs

    Output: enrichment tables and interpretation memo

  9. 9. Package deliverables and draft Methods

    Assemble figures, models, DOME table, scripts, environment locks, README, and Methods draft.

    Tools and outputs

    Output: final deliverable bundle

Tools and standards we use

Versions are pinned at kickoff and cited in the Methods draft. Representative tools across biomarker and prediction projects:

Machine learning tools and standards
ToolVersionRolePrimary citation
scikit-learn1.6.1Classification, regression, nested CV, metrics[8] — https://jmlr.org/papers/v12/pedregosa11a.html
XGBoost2.1.3Gradient-boosted classifiers and regressorshttps://doi.org/10.1145/2939672.2939785
scikit-survival0.24.1Random survival forests, gradient boosting survival, C-index[9] — https://www.jmlr.org/papers/v21/20-729.html
glmnet4.1-8LASSO and elastic-net feature selection (R)https://doi.org/10.18637/jss.v033.i01
SHAP0.46.0Post hoc feature attribution and interpretability[10]
Boruta11.0.0All-relevant feature selection against shadow featureshttps://doi.org/10.18637/jss.v036.i11
scGPT0.2.4Transformer foundation model for single-cell fine-tuninghttps://doi.org/10.1038/s41592-024-02201-0
PyTorch2.5.1Deep learning backend for foundation-model adaptationhttps://doi.org/10.48550/arXiv.1912.01703
clusterProfiler4.20.0GO/KEGG enrichment of selected feature listshttps://doi.org/10.1089/omi.2011.0118

Validation reporting follows DOME [4] and TRIPOD+AI when clinical prediction reporting is scoped [5]. Feature annotation uses GENCODE v44 (human) unless a project requires a custom reference. Studies with p >> n typically require regularization and nested cross-validation rather than single train/test splits [6].

Common challenges — and how we handle them

Common issues include data leakage, overfitting, incomplete reporting, unstable feature selection, and models that are hard to interpret. Pepkio documents validation design and interpretability in the deliverables.

Data leakage inflates reported performance

Illicit information sharing between training and test sets is common in high-dimensional biological data and can make models fail in real application [3]. Pepkio completes a leakage audit before splitting and uses patient-level partitions throughout.

p >> n overfitting with small cohorts

When features outnumber samples, complex models memorize noise [6]. Pepkio applies regularization and nested cross-validation, and reports simpler baselines alongside complex models so reviewers can assess incremental value.

Incomplete ML reporting

A 2023 systematic review of 30 cancer biomarker ML studies listed data leakage and inconsistent evaluation among common limitations [2]. Pepkio includes a DOME summary table in every deliverable and a TRIPOD+AI checklist when clinical prediction reporting is scoped.

Unstable feature selection across resamples

Features selected in one split may not replicate in another, which weakens biomarker claims. Pepkio reports selection frequency across cross-validation folds and prioritizes stable signatures over single-split lists.

Black-box models without interpretability

Deep models can discriminate well but obscure biological mechanism [1]. Pepkio delivers SHAP plots and coefficient tables and documents where interpretability does not support causal inference.

Common questions

What data do I need to provide for a machine learning analysis project?

Provide a sample-level feature matrix, a metadata table with the outcome and covariates, and a data dictionary. For survival endpoints, include event indicators and follow-up times. DOME recommends reporting sample-size rationale [4]. Custom formats are accepted when scoped in advance.

How long does machine learning analysis take at Pepkio?

Standard projects typically complete in 3-5 weeks. Survival models, external validation, or scGPT fine-tuning may take 5-8 weeks. Exact timelines are confirmed at kickoff.

What do Pepkio machine learning deliverables look like?

You receive performance tables, figures, SHAP plots, feature lists, serialized models, a DOME summary table, scripts, a README, and a Methods draft. Optional GitHub or Zenodo archival is available on request.

Can you handle my specific omics platform or feature matrix?

When scoped at kickoff, Pepkio accepts matrices from RNA-seq, proteomics, metabolomics, methylation, and clinical-laboratory tables, including vendor-normalized outputs with documented upstream processing.

What if my sample size is small or data quality is poor?

Small cohorts need regularized models and nested cross-validation. Pepkio avoids claiming external validity without a holdout cohort [6]. QC flags high missingness or batch confounding before modeling.

Do you provide the code, and do I own it?

You retain full ownership. Pepkio delivers commented R or Python scripts with conda or renv lock files and a README.

Can I be involved during the machine learning analysis?

Checkpoint reviews occur after QC, after the leakage audit, and before delivery. A PhD-level bioinformatician is your primary contact.

What happens if a reviewer requests changes after delivery?

Methods clarification and minor revisions within agreed scope (typically ≤20% of deliverables) are included. Substantial new analyses are scoped as separate milestones.

Do you use deep learning or transformer models like scGPT?

When scoped, Pepkio fine-tunes scGPT, a transformer pretrained on more than 33 million cells, for single-cell perturbation and integration tasks [1]. Regularized linear models and tree ensembles remain the default for small tabular cohorts [7].

Can Pepkio run custom or non-standard machine learning analyses?

Bespoke workflows, including custom outcomes, multi-omics fusion, domain-specific loss functions, client-specified validation schemes, or non-standard deliverables, are scoped at kickoff after a feasibility review.

Related services

  • Transcriptomics — Generate expression feature matrices and differential-expression contrasts as ML inputs.
  • Proteomics — Protein abundance features and orthogonal validation of transcript-level predictors.
  • Genomics — Variant, CNV, and structural features for germline or somatic prediction models.
  • Statistical analysis — Experimental design, power estimation, and covariate planning before committing to ML.
  • Bioinformatics consulting — Feasibility assessment, cohort-size guidance, and validation planning before model development.
References
  1. Chen V, Yang M, Cui W, et al. Applying interpretable machine learning in computational biology—pitfalls, recommendations and opportunities for new developments. Nature Methods. 2024;21(8):1454–1461. https://doi.org/10.1038/s41592-024-02359-7 (PMID: 39122941)
  2. Al-Tashi Q, Saad MB, Muneer A, et al. Machine learning models for the identification of prognostic and predictive cancer biomarkers: a systematic review. International Journal of Molecular Sciences. 2023;24(9):7781. https://doi.org/10.3390/ijms24097781 (PMID: 37175487)
  3. Bernett J, Blumenthal DB, Grimm DG, et al. Guiding questions to avoid data leakage in biological machine learning applications. Nature Methods. 2024;21(8):1444–1453. https://doi.org/10.1038/s41592-024-02362-y (PMID: 39122953)
  4. Walsh I, Fishman D, Garcia-Gasulla D, et al. DOME: recommendations for supervised machine learning validation in biology. Nature Methods. 2021;18(10):1122–1127. https://doi.org/10.1038/s41592-021-01205-4 (PMID: 34316068)
  5. Collins GS, Moons KGM, Dhiman P, et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. https://doi.org/10.1136/bmj-2023-078378 (PMID: 38626948)
  6. Whalen S, Schreiber J, Noble WS, Pollard KS. Navigating the pitfalls of applying machine learning in genomics. Nature Reviews Genetics. 2022;23(3):169–181. https://doi.org/10.1038/s41576-021-00434-9 (PMID: 34837041)
  7. Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nature Reviews Molecular Cell Biology. 2022;23(1):40–55. https://doi.org/10.1038/s41580-021-00407-0 (PMID: 34518686)
  8. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in Python. Journal of Machine Learning Research. 2011;12:2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html
  9. Pölsterl S. scikit-survival: a library for time-to-event analysis built on top of scikit-learn. Journal of Machine Learning Research. 2020;21(212):1–6. https://www.jmlr.org/papers/v21/20-729.html
  10. Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30:4765–4774.
  11. Feng Q, Huang Z, Song L, Wang L, Lu H, Wu L. Combining bulk and single-cell RNA-sequencing data to develop an NK cell-related prognostic signature for hepatocellular carcinoma based on an integrated machine learning framework. European Journal of Medical Research. 2023;28(1):300. https://doi.org/10.1186/s40001-023-01300-6 (PMID: 37649103)
  12. Mirza Z, Ansari MS, Iqbal MS, et al. Identification of novel diagnostic and prognostic gene signature biomarkers for breast cancer using artificial intelligence and machine learning assisted transcriptomics analysis. Cancers. 2023;15(12):3237. https://doi.org/10.3390/cancers15123237 (PMID: 37370847)
  13. Liu B, Hu X, Feng K, et al. Temporal single-cell tracing reveals clonal revival and expansion of precursor exhausted T cells during anti-PD-1 therapy in lung cancer. Nature Cancer. 2022;3(1):108–121. https://doi.org/10.1038/s43018-021-00292-8 (PMID: 35121991)

Individual services

Deep-dive pages for specific machine learning methods and workflows.

Let's Talk About Your Science

Tell us:

  • • Your biological question
  • • Data type and size
  • • Timeline constraints

We'll tell you:

  • • What's feasible
  • • How long it will take
  • • Exactly what it will cost
Discuss Your Project

Contact us to start with a free consultation. Need everyday bench calculators? Try our free lab tools.