Anyone can run the analysis.
Can you trust the answers?
Gene Cutler, PhD — over twenty-five years of computational biology in drug discovery. Experience matters.
From data to decisions
Generating biological data has never been cheaper, nor has analyzing it. Any scientist can now run a differential expression analysis. It takes experience to distinguish between real findings and artifacts; to know whether an analysis was too sensitive or not sensitive enough. But the most important part of all is knowing whether you asked the right questions in the first place.
That judgment comes from having made those calls over many years in many situations with countless datasets — from target ID through clinical trial strategy, across a range of therapeutic areas. I bring experience in machine learning, large-scale data analysis, and drug development experience to the same problem, so your team can move forward with confidence.
With Ridgeline Computational Biology, you'll work directly with an experienced computational biologist throughout the engagement in a method that works for you.
Many ways to work together
Pick the one that fits your needs — or get in touch and we'll figure it out.
Analysis Review
For teams about to make a call on a result nobody outside the group has checked.
A fresh, independent look at an analysis before it goes into a board deck, a partnering data room, an IND, or a manuscript. I re-examine the data and the reasoning, not just the code.
- Independent re-analysis of the primary result
- Assessment of study design, power, and confounders
- Written findings: what passes the test and what doesn't
- A working session with your team and continuing email conversations
Two to three weeks, fixed scope. Engagements typically start at $10,000.
What's included →Computational & AI Strategy Review
For companies deciding what computational capability to build or buy.
A four-to-six-week review of where computational biology and AI can improve your programs and where the investment is unlikely to pay off. Recommendations you can take to a board, with the reasoning behind them.
- Review of current data assets, workflows, and analytical gaps
- Build / buy / partner recommendations, with vendor evaluation
- Realistic assessment of where AI methods or conventional ML actually fit your needs
- Hiring plan and infrastructure advice if building in-house
Four to six weeks. From $20,000, depending on scope.
What's included →Fractional Head of Computational Biology
For companies that need computational leadership but not a full-time hire — or need coverage during a search.
Roughly one day a week, working as part of your research team. The senior judgment of a Head of Comp Bio without the headcount, available in three- or six-month blocks.
- In the (virtual) room when experiments are designed, not just after the data comes back
- Review of internal and vendor-generated analyses
- CRO and software vendor selection and oversight
- Hiring: role scoping, technical interviews, onboarding
- Attendance at research and data review meetings
One day per week, in three- or six-month blocks, working remotely. Day rate quoted on scope. Interim coverage during an active search available on the same terms.
What's included →Project Analysis
For teams with a dataset needing analysis.
Hands-on analysis, for one-off projects or for the beginning of something bigger. RNA-seq and other omics, high-throughput screening data, biomarker data, and custom analyses that don't fit a standard pipeline.
Hourly pricing or per-project. Scope based on discussion.
What's included →- Bulk and single-cell RNA-seq: differential expression, deconvolution, signature development
- HTS and screening data analysis
- Custom method development where off-the-shelf tools don't fit
- Figures and written interpretation ready for internal review or publication
- Pipeline code documented and delivered
Selected clients
Work spanning discovery-stage biotechs, clinical-stage companies, venture funds, and academic translational groups.
The difference experience makes
When the founders' pipelines disagreed
An early-stage biotech was building their discovery platform around a novel biological target class, using two analysis pipelines developed by their scientific co-founders. I ran both pipelines and benchmarked them against a third published method — and found near-complete disagreement across all three. Rather than recommending incremental fixes, I recommended a different analytical approach: train a neural network to enumerate all possible candidates, then validate those predictions against sequencing data, rather than attempting to extract candidates directly from sequencing reads. This new approach reoriented the discovery platform.
Self-service tools for a bench science team
A biotech running antibody discovery campaigns needed to track clone diversity and enrichment across panning rounds — but the scientists closest to the data couldn't write code. I built a sequencing analysis pipeline and delivered it as two self-service cloud-hosted web applications. Bench scientists could then interrogate their own campaign data without waiting on a computational specialist. The team went from batch analysis requests to real-time exploration during active campaigns.
Predicting drug response before the experiment
An oncology drug discovery company needed to understand which molecular features predicted compound response across cancer types. I integrated their internal screening data with multiple public cancer cell-line databases and trained machine-learning models to surface predictors of drug response — delivered as a reusable internal tool the team could apply to new compounds. The work gave the company a way to prioritize which tumor types to pursue before committing to expensive in vivo studies.
A patient population no one had looked for
For a clinical-stage immuno-oncology company, I used public databases and careful patient metadata parsing to identify a previously-unsuspected subpopulation likely to be particularly sensitive to their drug. Rather than stopping at the computational finding, I initiated validation through a CRO to independently confirm protein expression in tumor biopsies — and in the right immunologic context. The clinical plan was rewritten to add enrollment arms for this population. Phase 1 data subsequently confirmed that these patients are, in fact, particularly responsive to the treatment.
“I've worked with Gene on several projects, where he delivered ingenious solutions to challenging problems each time, and with seeming ease. One of Gene's greatest assets is that he is a rare combination of an experienced biologist and a seasoned bioinformaticist. This makes him a thought partner in every project, and enables him to deliver value beyond mere data processing.”CSO, Antibody-technology biotech
“Gene's work helped us uncover an MOA for our drug that we hadn't expected. He delivered not only program-changing results, but also suggestions for next steps. This allowed us to make fully-informed go/no-go decisions and significantly changed the course of our program.”SVP, Immuno-oncology biopharma
Experience
CAREER HISTORY
25+ years in drug discovery across Amgen, FLX Bio, RAPT Therapeutics, and Ridgeline Computational Biology — from target identification to clinical biomarker strategy.
Read full history →EDUCATION
PhD in Molecular and Cell Biology, UC Berkeley. BA in Biology, Cornell University.
View credentials →PUBLICATIONS & PATENTS
Peer-reviewed research and patents spanning oncology, immuno-oncology, genomics, and computational biology.
View complete list →Not sure which of these fits?
Most engagements start with an email and a short call about the data you have and the decisions you're facing. My first goal is to help good science get done, so I am happy to discuss what makes the most sense for you.
Get in touch