Computational Biologist
Computational biologist with a PhD in bioinformatics and six years of experience across immuno-oncology, tumour biology, autoimmune disease and computational drug discovery. I integrate multi-omics, machine learning, deep learning and agentic AI systems to identify biomarkers, prioritise and validate therapeutic targets, and stratify patients.
Science has been a journey into the unknown, with a humbling lesson waiting at every turn. I can’t wait to be reminded again just how little I truly know, and how much is left to discover
Based in Lund, Sweden · Open to opportunities from September 2026
01 / Now
BioInvent International AB · Lund, Sweden
Contract period Aug 2025 – Aug 2026
Company focus Antibody therapeutics for oncology and autoimmunity
Role Multi-omics lead · Immunotherapy · Biomarker discovery · Patient stratification · Mode of action
I carry out the computational work behind the BI-1206 anti-FcγRIIB and BI-1808 anti-TNFR2 programmes, putting clinical, mouse and in-vitro evidence together to work out how the antibodies act and where resistance comes from. Alongside that I run target discovery and validation for autoimmune disease, and train and deploy AI models. Day to day the work means scRNA-seq, CITE-seq, spatial transcriptomics, proteomics and clinical metadata, run through AWS and HPC pipelines the rest of the team can rerun.
02 / Selected tools
Eight public repositories, covering target discovery and safety, method reliability, drug response and protein modelling. Most of them started as something I needed for my own work and could not find.
| 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
Explainable target discovery and prioritisation
Separates therapeutic targets, biomarkers, resistance mechanisms and poor direct targets in anti-PD-1-resistant melanoma, then ranks them by antibody/IO, biomarker or small-molecule intent.
3 intent rankings 331 discovery universe 26Q1 real DepMap layer
02 v0.5.0 · Research preview
Hidden safety risk in surface targets
Audits how much of a target’s apparent tumour selectivity disappears when healthy tissue is inflamed rather than resting, using paired public single-cell cohorts.
52 automated tests 85.4% non-I/O coverage
03 v0.8.0 · Research preview
Is the target physically reachable?
Combines simplified reaction–diffusion modelling with an explicit evidence graph to ask whether target-positive tumour cells are reachable by an antibody, and returns NOT_COMPUTED when the biology it needs has not been measured.
117 automated tests 20,000 uncertainty draws
04 v0.5.0 · Research preview
Does the conclusion survive the segmentation?
Tests whether a spatial-transcriptomics claim still holds when transcript-to-cell assignment changes across Xenium, ProSeg and Baysor, labelling each claim robust, segmentation-sensitive or not reportable.
62 automated tests 90.3% line coverage
05 v0.5.0a1 · Pre-release
Do foundation models actually add value?
A leakage-aware temporal-holdout benchmark testing whether Geneformer and scGPT representations improve target prioritisation over cheaper baselines. The completed v0.4 result was negative, and is reported as such.
79,542 holdout rows NOT SUPPORTED primary conclusion
06 v1.1.0.dev0 · Evidence review
Evidence-led prioritisation of drug-response experiments
Compares XGBoost with linear and lineage baselines on the same held-out cell lines. In a retrospective trametinib ranking, the top ten contain seven sensitive models, versus 2.53 expected at random.
5 drugs compared 3 matched model families 41 passing tests
07 v1.0.0 · Research analysis
Topology-aware protein deep learning
Screens human and mouse membrane-protein domains for transcription-factor-like sequence features using DeepTFactor, then interprets selected predictions with Captum Integrated Gradients.
2 mammalian species 3 × 3 classes × boundaries
08 v0.9.1 · CLI preview
Auditable AI-agent workflow for scientific software
A Python and SQLite orchestrator that ties review evidence to the exact code changes. Changed code invalidates earlier reviews; durable state supports restart recovery, and a person retains release authority.
418 Linux tests passed 3.11–3.13 Python CI
03 / Experience
Six years across industry and academia, in cortical development, precision oncology and now antibody programmes. Every time, the work has been getting from messy molecular data to something a team can act on.
Translational multi-omics on the anti-TNFR2 and anti-FcγRIIB antibody programmes, covering mode of action and biomarker strategy.
Patient-derived gene signatures, preclinical model mapping with TCGA and Celligner, and CosMx and Visium HD spatial transcriptomics across tumour cohorts.
Cross-species single-cell and epigenomic analysis of cortical development, plus paediatric brain-tumour genomics.
Hi-C, chromatin accessibility and sequence-to-signal deep learning with ChromBPNet.
04 / What I bring
Immuno-oncology, inflammation and tumour biology: mechanism of action, target validation, biomarkers and patient stratification.
scRNA-seq, CITE-seq, spatial transcriptomics, bulk RNA-seq, epigenomics, proteomics and functional genomics.
XGBoost, survival analysis, variational autoencoders, foundation models and sequence-to-signal deep learning, always with the uncertainty and the provenance attached.
Python, R, Bash, Nextflow, Snakemake, Docker, AWS and HPC, with versioned inputs, automated tests and reporting a stakeholder can read.
05 / Contact
I am looking for roles that merge computational biology, translational research and AI for biology.