Alper Kucukural, PhD
AI & Data Science Leader · Life Sciences

Cures don't come from one experiment. They come from being able to trust ten thousand of them. That's what I build.

Co-founder & CTO of Via Scientific, Associate Professor at UMass Chan Medical School. Ten-plus years building multi-omics and AI systems used by thousands of scientists across academia and biopharma.

13,500+ Google Scholar citations 26 h-index 35+ peer-reviewed publications

The dossier in ten seconds.

Turning biomedical data into software people actually use.

I lead the technical strategy for Via Foundry, a multi-omics and AI platform commercialized from UMass Chan and used by biotech, pharma, and academic research teams. The work covers modern ML, cloud data engineering, and biomedical science, and all three have to hold up under real use.

I've built or co-authored tools cited tens of thousands of times (I-TASSER, DolphinNext, DEBrowser, GUIDEseq) and published in Nature, Cell, Science, Nature Protocols, and Nature Communications. The goal of everything I ship is the same: to make it obvious whether the data in front of you is telling you something true, and whether the next decision is a good one.

north star

Shorten the distance between a dataset and a medicine.

Strategy, delivery, and scientific credibility.

I've sat on both sides of the table: founder and CTO of a venture-backed platform company, and faculty at UMass Chan with publications in Nature, Cell, and Science.

01 · enterprise AI strategy

The full lifecycle.

I own the path from feasibility and MVP through production scaling, MLOps, and monitoring. Standards and reference architectures that hold up in practice, not just in slide decks.

02 · regulated-environment fluency

Science you can defend.

Ten years building reproducible, version-controlled analytics in biomedical settings where data provenance, validation, and auditability are required, not optional. Familiar with GxP, 21 CFR Part 11, and the EU AI Act.

03 · teams & partnerships

Hiring and mentoring, not just shipping.

Recruited and mentored multidisciplinary teams of data scientists, AI/ML engineers, software engineers, and computational biologists. Day-to-day collaboration with scientists, clinicians, product, legal, and investors.

04 · what actually ships

What matters is the decision downstream.

Metrics, drift monitoring, and the kind of stakeholder communication that tells you when the model is working and when it isn't. I'd rather ship a smaller thing that's honest about its limits than a bigger one that isn't.

10+
years leading data & AI in biomedical
35+
peer-reviewed publications
80+
labs & 240+ scientists supported at UMass Chan
1000s
researchers using tools I've shipped

Ten-plus years across AI, biology, and engineering.

  1. 2023 to Present Current

    Co-founder & Chief Technology Officer

    Via Scientific, Inc. · Cambridge, MA

    Owning technical strategy, architecture, and engineering standards for Via Foundry, a multi-omics & AI analytics platform exclusively licensed from UMass Chan and used by biotech and pharma research teams. Venture-backed, with advisors that include Melissa J. Moore (former CSO of Moderna), Rob Hickey (former EVP Engineering, DataRobot), and Shah Nawaz (former VP Digital Transformation, Regeneron).

    • Defined the AI/ML platform strategy, from data ingestion and feature engineering through model deployment, monitoring, and retraining.
    • Built and led a cross-functional team of AI engineers, software engineers, and computational scientists; shaped hiring bar, delivery cadence, and engineering standards.
    • Evaluated and integrated third-party AI solutions (LLM providers, vector stores, agent frameworks) alongside in-house capabilities.
    • Owned enterprise reliability, reproducibility, and security posture for a platform serving regulated biomedical workflows.
  2. 2020 to Present Academic

    Associate Professor, Program in Molecular Medicine

    UMass Chan Medical School · Worcester, MA

    Faculty appointment in the Program in Molecular Medicine and the Department of Genomics & Computational Biology. Research focused on scalable, reproducible multi-omics analytics, RNA therapeutics, and applied ML for biomedical data.

    • Co-directed the UMass Chan Bioinformatics Core supporting 80+ labs and 240+ scientists across the institution.
    • Published in Nature (2022), Nature Communications (2026), Cell Stem Cell, and others; senior-author on DolphinNext (BMC Genomics 2020).
    • Built and released open-source platforms (DolphinNext, DEBrowser, GUIDEseq, scRNA-Seq browser) that became institutional infrastructure.
    • Invited speaker and panel chair across the field (Mayo Clinic RNA Discoveries and Therapeutics Conference 2025, Center for RNA Biology seminar series at Ohio State, Nextflow Camp, ABRF Genomic Bioinformatics Research Group).
  3. Feb 2015 to 2020

    Assistant Professor & Bioinformatics Core Lead

    UMass Chan Medical School · Worcester, MA

    Promoted into the faculty track to lead the scale-up of the Bioinformatics Core. Designed and built the NGS analytics stack that ultimately became Via Foundry; standardized RNA-Seq, scRNA-Seq, ChIP-Seq, ATAC-Seq, and GATK-based variant-calling pipelines; and delivered enterprise-grade training programs across the institution.

  4. Jun 2013 to Jan 2015

    Bioinformatician III

    UMass Chan Medical School · Bioinformatics Core · Worcester, MA

    Senior engineer on the Bioinformatics Core. Designed and productionized reusable, robust pipelines for NGS, microarray, genomics, proteomics, and chemogenomics data, supporting hundreds of concurrent users on HPC clusters. Installed and maintained Galaxy, GenePattern, and Genome Space for the institution; built custom databases, portals, and visualization apps where off-the-shelf tools fell short; led institution-facing training workshops.

  5. Aug 2009 to Jun 2013

    Bioinformatician

    UMass Chan Medical School · Moore and Zamore Labs · Worcester, MA

    Worked in the Melissa J. Moore and Phillip D. Zamore labs on post-transcriptional gene regulation via RNA mechanisms. Built bioinformatics software and visualizations for SOLEXA and SOLiD NGS platforms, peak-calling and denoising algorithms (the foundation for ASPeak), machine-learning pattern-search methods, custom scientist-facing interfaces, and UCSC Genome Browser mirrors for institutional use.

  6. 2008 to 2009

    Postdoctoral Fellow, Computational Drug Design

    University of Kansas · Yang Zhang Lab · Lawrence, KS

    Co-developed I-TASSER, the unified platform for automated protein structure and function prediction. Co-author on the Nature Protocols 2010 method paper, now cited 7,800+ times, and contributor to subsequent I-TASSER methodology development that remains a reference tool in computational structural biology.

  7. 2004 to 2009

    PhD, Biological Sciences & Bioengineering

    Sabancı University · Istanbul, Turkey

    Dissertation on graph-theoretic discrimination of native protein folds. MS in Systems Analysis and BS in Mathematics Engineering, both from Istanbul Technical University.

  8. 2001 to 2004

    Software Engineer

    KoçSistem · Istanbul, Turkey

    Built one of the first POS-integrated retail loyalty platforms of its era. Java and JSP web tier with an Oracle backend, paired with C development on minimal-OS embedded Linux devices that connected directly to electronic cash registers and printed personalized coupons at the point of sale. Designed and shipped early machine-learning components for customer-behavior segmentation and offer targeting in production retail systems. The architecture became the foundation for nationwide loyalty programs serving millions of members across thousands of retail locations today.

From cash registers in Istanbul to RNA therapeutics in Cambridge.

Before I knew what bioinformatics was, I was 22 in Istanbul, writing C for embedded Linux devices that talked to electronic cash registers and printed personalized coupons at the point of sale. The architecture I helped ship at KoçSistem in 2002 became the foundation for retail loyalty programs that millions of people in Turkey use today. I didn't know it then, but "predict what a customer wants from their last basket" and "predict what a cell will do from its expression profile" turned out to be variants of the same problem.

I caught the bioinformatics bug at Sabancı University, where my PhD was on graph-theoretic discrimination of native protein folds. The math was elegant. The biology was messy. The gap between a model that's elegant and an answer that's correct is the gap I have been working in ever since.

The first real shock came as a postdoc in Yang Zhang's lab at the University of Kansas. We were building I-TASSER, a unified platform for automated protein structure and function prediction that combined template-based modeling with ab initio refinement. The Nature Protocols paper we put out in 2010 has since been cited more than 7,800 times. That taught me what it actually takes for a good method to become a standard: a scientist has to be able to run it on their own data, on their own infrastructure, without a computational biologist next to them.

I came to UMass Chan Medical School in 2009 to work in the labs of Melissa J. Moore and Phillip Zamore, two of the most respected RNA biologists working today. Neither of them needed me to reinvent their field. They needed someone who could turn SOLEXA reads into answers a biologist could trust at the bench. That is where the rest of my career started.

The next decade was tools and pipelines. ASPeak for RIP-seq. GUIDEseq for CRISPR off-target analysis. DEBrowser for differential expression. DolphinNext for distributed pipeline execution. An institutional NGS stack supporting 80+ labs and 240+ scientists at UMass Chan. Most of it open source. All of it built because someone needed it and there was no good alternative within reach.

In 2023 I co-founded Via Scientific to take that stack out of the academic core and into pharma. We licensed Via Foundry from UMass Chan, raised a $5M seed in January 2024 from G20 Ventures and Innospark Ventures, and brought on advisors I had been reading and quoting for years: Melissa J. Moore (former CSO of Moderna), Rob Hickey (former EVP Engineering at DataRobot), Shah Nawaz (former VP Digital Transformation at Regeneron). Via Foundry is the multi-omics and AI analytics core: drag-and-drop pipeline authoring on top of Nextflow, Kubernetes and ShinyProxy orchestrating the interactive apps (RStudio, JupyterLab, CellxGene, IGV, Shiny), MySQL plus MongoDB underneath, React and TypeScript on the front, Node and Express on the back.

Inside the platform, AI Insights is a multi-provider assistant layer (OpenAI, Anthropic Claude, Google Gemini) with page-aware chat, run-report summarization, and log analysis. It is backed by a custom RAG system with a user-facing Knowledge Builder, token-aware chunking, embeddings stored in MySQL, two-phase semantic search for low-latency retrieval, and a multimodal pipeline that extracts and embeds text, images, SVGs, and chart screenshots described by vision models. Via Foundry both exposes and consumes the Model Context Protocol: a Python FastMCP server with around 41 tools lets external clients like Claude Desktop and Cursor drive the platform, while a backend MCP Client Manager and Tool Orchestrator let in-product AI chats discover and call external MCP tools with user confirmation. A "Model Smith" registry brings domain-specific bio-AI models (AbGPT, AbLang2, hosted on Tamarind, Vertex AI, and SageMaker) directly into bioinformatics workflows.

Once Via Foundry was shipping, the next layer became obvious. ArfAI is the conversational interface on top of the same scientific stack. A multi-agent system (planner, executor, analyst, reporter) takes a question in plain English, generates the Python or R, runs it inside sandboxed Docker, and streams plots and intermediate results back over WebSocket in real time. An embedded MLflow stack tracks every experiment, parameter sweep, dataset-drift signal, and prediction log, and the platform ships full reproduction bundles, plan-review gates, and classified failure recovery with auto-fix loops. The point is to make rigorous, reproducible scientific computing as easy as writing a Slack message, without giving up the auditability scientists actually need.

AiDrift is the safety rail underneath all of that. More biotech code over the next five years is going to be written by LLM-powered assistants than was written by humans in the last twenty, and the rails for that have not been built yet. AiDrift watches AI coding sessions in real time, scores each turn against drift heuristics (scope creep, contradiction, churn, sub-agent overlap, build and test outcomes), refuses commits and pushes when the session goes red, blocks writes outside declared paths, and gives you a one-click rollback to a stable checkpoint when the assistant goes off the rails. It ties every git commit back to the session and turn that produced it, with a revert-graph DAG and secret scanning. It ships as a CLI, a Claude Code plugin, a VSCode extension, and a React dashboard. Vibe-coding needs a seatbelt. AiDrift is the one I built.

I am still on the faculty at UMass Chan. I still co-direct the Bioinformatics Core. I still get late-night Slack messages from PhD students. I think you build better engineering when the people who actually use the software can also yell at you in person.

What I am trying to do now is simple to say and hard to do. Shorten the distance between a dataset and a medicine. That is the whole point. Everything else is detail.

Software I've built or co-built.

Open-source bioinformatics that became common infrastructure for NGS and protein analysis, alongside the AI platforms I am shipping now. All of it documented, in active use, and built to hold up at the bench.

Flagship

Via Foundry

Multi-omics and AI analytics platform. Drag-and-drop pipeline builder, versioned reproducibility, cloud-native execution. Licensed from UMass Chan and used by biotech and pharma research teams.

Shipping

ArfAI

AI-native scientific analysis platform. A multi-agent system (planner, executor, analyst, reporter) turns natural-language questions into reproducible Python and R, runs the code inside sandboxed Docker, and streams plots and artifacts back over WebSocket. Embedded MLflow stack for experiment tracking, dataset drift detection, and parameter-sweep optimization that auto-promotes winners.

Live

AiDrift

Drift detector for AI coding sessions. Scores each turn against heuristic drift signals (scope creep, contradiction, churn, sub-agent overlap, build outcomes), gates commits and pushes on red scores, blocks writes outside declared paths, and ships a revert-graph DAG with one-click rollback. CLI, Claude Code plugin, VSCode extension, and React dashboard.

Live

DolphinNext

Distributed data processing platform for high-throughput genomics. GUI-driven Nextflow pipeline authoring with institutional reproducibility and HPC/cloud execution. BMC Genomics, 2020.

Live

DEBrowser

Interactive differential expression analysis and visualization tool for count data. First author; 287+ citations, distributed via Bioconductor. BMC Genomics, 2019.

Foundational

I-TASSER

Unified platform for automated protein structure & function prediction. Co-authored the Nature Protocols (2010) method paper, cited 7,800+ times and still a reference tool in computational structural biology.

Bioconductor

GUIDEseq

Bioconductor package to analyze GUIDE-Seq datasets for CRISPR-Cas nucleases. Standard in CRISPR off-target analysis. BMC Genomics, 2017.

Method

ASPeak

Abundance-sensitive peak detection algorithm for RIP-Seq. First-author method paper in Bioinformatics (2013), standard in RNA-protein interaction studies.

Ten papers that shaped my research.

Full bibliography on Google Scholar: 35+ peer-reviewed publications, 13,500+ citations, h-index 26. Ten representative ones below, covering AI methods, multi-omics platforms, and biology.

a favorite collaboration

One of the more unusual papers I've co-authored: a translational microRNA model of venous thromboembolism in hibernating black bears, with Dr. Mitchell Cahan in the UMass Department of Surgery. The work also led to a patent filed alongside Dr. Basadonna. Hibernating bears don't develop blood clots despite weeks of immobility, and the microRNA signature behind that resistance has real implications for human VTE prevention. Journal of Surgical Research, 2021. Cross-disciplinary collaborations like this one are why I do the work.

Speaking, recognition, and editorial.

Selected invited talks, founder recognition, and editorial service. Full list available on request.

Writing on AI and bioinformatics.

Posts on Medium about reproducibility, pipeline design, scRNA-seq, RNA therapeutics, and the day-to-day of doing science with AI.

Let's talk about AI in life sciences.

Open to senior leadership conversations in data science, AI engineering, and computational biology, in pharma, biotech, and big-tech health and life sciences. Advisory and research collaborations welcome.

Based in Cambridge MA 02139