Public research software
Research software you can check
The tools answer different biological questions, but I build them the same way. Each one says what it does, uses data you can download and run yourself, shows how sure it is, and stops where the evidence stops.
The eight tools
Grouped by the question they answer. Each one helps with a decision that comes up early, before you spend time or money on a candidate.
| Field | Tool | The problem | What it is for | What it adds | Key skills applied |
|---|---|---|---|---|---|
| Target discovery & safety | TargetIntel-IO | A gene linked to disease is not automatically a good drug target, yet most tools collapse that judgement into a single score. | Sorting candidate genes into genuine targets, biomarkers, resistance mechanisms and poor candidates. | Three separate rankings, one per therapeutic strategy, plus the evidence for and against each call. | |
| Activation Liability | A target can look safely tumour-specific in healthy resting tissue and stop looking that way once the tissue is inflamed. | Spotting targets whose apparent safety margin shrinks under immune activation. | A direct resting-versus-activated comparison in public data, with abstention when the evidence is too thin. | ||
| reach-gap | A target can be highly expressed and still sit too far from a working blood vessel for an antibody to reach it. | Asking whether target-positive tumour cells are physically accessible to an antibody. |
Mechanistic diffusion modelling paired with an evidence graph that returns NOT_COMPUTED rather than guessing.
|
||
| Method reliability | segmentation-fragility | In spatial data, a small change in where a cell boundary is drawn can move a marker between cell types and flip the conclusion. | Testing whether a spatial-transcriptomics claim survives a change in transcript-to-cell assignment. | Each claim is labelled robust, segmentation-sensitive or not reportable, instead of trusting one segmentation as final. | |
| FM Value Audit | A foundation-model embedding can look biologically structured and still add nothing to a real decision. | Testing whether single-cell foundation models beat cheaper baselines at target prioritisation. | A leakage-aware temporal holdout designed to report a negative result when that is what the data shows. | ||
| Drug response prediction | DrugMatch-Confidence | Cancer models respond very differently to the same drug, and predictions rarely say how much to trust them. | Prioritising preclinical cancer models for drug-response experiments. | Matched baseline comparisons show when complexity helps; uncertainty checks expose when categorical decisions lack support. | |
| Protein deep learning | MTF Prediction | Whether a membrane protein carries transcription-factor-like features can change depending on where you draw its boundary. | Screening human and mouse membrane-protein domains for those features under different boundary definitions. | The same screen repeated across three boundary conditions, so a result that holds under only one is visible as such. | |
| Research engineering | Dev Autopilot | AI coding agents can move fast through a repository and leave no reliable trail of what changed or why. | Running AI agents on real code with hard limits on what they may touch. | Separate implementation and review roles, evidence tied to the exact code changes, restart recovery and human release authority. |
01 v0.6.0 · Research preview
TargetIntel-IO
Therapeutic-intent-aware target triage
A deterministic platform for interpreting candidate genes in anti-PD-1-resistant melanoma. It avoids one universal score by separating antibody/IO, resistance-biomarker and small-molecule strategies.
- Stable role classification and three intent-specific rankings
- Typed, source-linked evidence with mandatory human-review boundaries
- Real DepMap Public 26Q1 dependency layer that never silently changes the baseline
- Graph-native evidence with a deterministic, GraphRAG-compatible research-preview export
02 v0.5.0 · Research preview
Activation Liability
Detecting hidden safety risk in surface targets
A target can look tumour-selective against resting healthy tissue and lose that selectivity once normal cells are inflamed or immune-activated. alia audits how much of that apparent selectivity survives biologically matched activation.
- Paired resting and activated public single-cell cohorts
- Donor-level robustness, negative controls and explicit abstention
- Frozen manifests and checksums for every executed cohort
03 v0.8.0 · Research preview
reach-gap
Is the target physically reachable?
A tumour target can be strongly expressed and still sit too far from a perfused vessel for an antibody to engage it. reach-gap combines simplified reaction–diffusion modelling with an explicit evidence graph.
- Separates same-tissue measurement from external validation and literature priors
- Relative target ranking across six defensible vessel definitions
-
Returns
NOT_COMPUTEDinstead of inventing an absolute answer
04 v0.5.0 · Research preview
segmentation-fragility
Does the conclusion survive the segmentation?
In spatial transcriptomics a small boundary change can move a marker between cell types and flip a biological claim. This tool makes the claim, not the segmented object, the unit of analysis.
- Compares claims across Xenium, ProSeg and Baysor with fixed biological anchors
- Labels each claim robust, segmentation-sensitive or not reportable
- Abstains when claim-specific anchor coverage is insufficient
05 v0.5.0a1 · Pre-release
FM Value Audit
Do foundation models actually add value?
A leakage-aware benchmark testing whether representations from Geneformer and scGPT improve a real target-prioritisation decision over cheaper, easier-to-explain baselines.
- Prespecified decision metric evaluated on unseen future outcomes
- Explicit leakage control across feature selection and tuning
- Designed to report a negative result when that is what the data shows
06 v1.1.0.dev0 · Evidence review
DrugMatch-Confidence
Matched evaluation for preclinical drug-response ranking
Five drugs evaluated with XGBoost, ElasticNet and lineage-only baselines on identical held-out cell lines. The review adds independent calibration, explicit abstention and an experimental-budget analysis.
- Fold-local feature selection and response cutoffs; separate calibration data
- Matched five-fold evaluation shows no demonstrated XGBoost advantage over ElasticNet
- Five review figures, interval-feasibility audit and a proposed MAPK experiment
07 v1.0.0 · Research analysis
MTF Prediction
Topology-aware deep learning for membrane proteins
A reproducible research archive screening human and mouse membrane-protein domains for transcription-factor-like sequence features under alternative transmembrane-boundary definitions.
- Human and mouse UniProtKB membrane-protein domains
- DeepTFactor inference across no-, half- and full-TMD conditions
- Residue-level interpretation with Captum Integrated Gradients
08 v0.9.1 · CLI preview
Dev Autopilot
Persistent, auditable development orchestration
Coordinates implementation, adversarial audit and independent review while SQLite preserves progress across restarts. The 0.9.1 CLI preview adds bounded code retrieval, durable budget controls and an optional Docker execution adapter.
- Immutable project charter with a dependency-checked milestone DAG
- Mechanical scope, test, context and Git-metadata gates, with bounded autocorrection instead of a terminal stop
- Review conclusions bound to an exact diff; any later change invalidates them
- Produces a verified review bundle for human approval before commit, push or release
Collaboration
Interested in the science or the implementation?
Every repository is public. If you want to talk about the biology or the code behind it, get in touch.