Avatar

Links

Download CV (PDF)

About

Industrial PhD student in Bioinformatics & Data Science, working at the intersection of long-read RNA sequencing, protein functions, and deep learning. Particularly interested in AI agents and the responsible use of AI in bioinformatics.

Based in Valencia, Spain. Open to local positions and remote work worldwide.

Education

Industrial PhD in Bioinformatics

BioBam Bioinformatics S.L. & University of Valencia · 2023 – present (expected defense Q4 2026 – Q1 2027)
Fellow of the Marie Skłodowska-Curie Actions (MSCA) Doctoral Network LongTREC, pursuing doctoral studies at the University of Valencia. Supervised by Stefan Götz (CEO of BioBam), co-supervised by Ana Conesa (Genomics of Gene Expression lab, I2SysBio).
  • Developed a LangGraph-based LLM agent for bioinformatic analysis within OmicsBox, helping users discuss their data, identify suitable analyses, configure and launch workflows, and interpret results. Implemented tool calling, retrieval-augmented generation (RAG), and web search.
  • Independently conceived of, designed, and developed a novel deep learning method for protein function prediction, PLM2GO (manuscript in preparation). This involved data engineering of public protein and Gene Ontology annotation data, use of protein language models, model training and evaluation, and orchestration in AWS infrastructure (including S3 and EC2 spot instances).
  • Developed a Nextflow pipeline for benchmarking transcript reconstruction tools on long-read RNA-seq data sets with multiple biological replicates.
  • Development, maintenance, and user support of the OmicsBox long-read transcriptomics submodule, making complex long-read RNA-seq analysis accessible to biologists.

MSc in Data Science and Engineering

University of Applied Sciences Upper Austria · 2021 – 2023
Thesis: Named Entity Recognition on German traffic-related texts. Contributed to building a hybrid NER pipeline combining a custom rule engine with fine-tuned transformer language models and a disambiguation step, benchmarked against GPT-3.

BSc in Medical and Bioinformatics

University of Applied Sciences Upper Austria · 2018 – 2021
Thesis: Dimension Reduction on Time Series Data. Applied PCA, t-SNE, UMAP, and an autoencoder (TensorFlow/Keras) to anomaly detection in clinical time-series data.

Matura Diploma (Higher Technical College for Informatics)

HTBLA Grieskirchen, Austria · 2012 – 2017
Thesis: Towards Predicting the Popularity of Music Artists. Presented at the 10th International Workshop on Machine Learning and Music at Universitat Pompeu Fabra, Barcelona.

Experience

Industrial PhD Student

BioBam Bioinformatics S.L. · 2023 – 2026
Developing methods for protein function prediction, and responsible for development, maintenance, and support of the OmicsBox long-read transcriptomics submodule.

Junior Data Scientist

RISC Software GmbH · 2021 – 2023
Contributed to development of a hybrid named-entity recognition pipeline (rule-based engine + fine-tuned BERT/DistilBERT/ELECTRA transformer models, with a T5-based question-answering disambiguation step) to automate German-language traffic-incident reporting from speech-to-text data, as part of a multi-partner research project; benchmarked against GPT-3.

Data Science Intern

RISC Software GmbH · 2019 – 2021
Applied dimension reduction techniques (PCA, t-SNE, UMAP) and deep convolutional autoencoders to real-world clinical time-series data for visualization and anomaly detection.

Publications

Jetzinger, F., et al. “To join or not to join: handling biological replicates in long-read RNA sequencing data.” bioRxiv (2025). Accepted for publication in Nature Communications.
First author. Performed pre-processing, transcript reconstruction and benchmarking analysis across PacBio, ONT, and Illumina sequencing platforms to compare strategies to combine data from multiple biological replicates in long-read RNA-seq data.
Liu, T., et al. “TUSCO: benchmarking transcriptome reconstruction with endogenous single-isoform controls.” Nature Communications (2026).
Contributed to pre-processing of long-read RNA-seq data and transcript reconstruction.

Skills

Programming: Python, R, Bash, Java, C#, C++, MATLAB
Data Science: Deep Learning (PyTorch), Natural Language Processing, LLM Agents (LangGraph, Tool Calling, RAG), Quantitative Statistics, SQL / Relational Databases, Visualization, Big Data
Bioinformatics: Analysis of short- and long-read RNA-seq data, Protein Function Prediction, Fusion Transcript Analysis, Allele-Specific Expression Analysis
Tools & Infrastructure: Linux / WSL, Nextflow, HPC (SLURM), Cloud Computing (AWS basics), Docker / Singularity, CI/CD, Git / GitHub, FAIR Principles
Soft Skills: Teamwork, Leadership, Science Communication, Customer Support, Public Presentations
Languages:
  • German: Native
  • English: Full Professional Proficiency (Near-Native)
  • Spanish: Conversational (B2; planning C1 certification)

Activities

Scientific Presentations

To join or not to join: handling biological replicates in long-read RNA-Seq data
Talk. VALT2026. 29.06.–01.07.2026. Valencia, Spain.
To join or not to join: handling biological replicates in long-read RNA-Seq data
Talk. 3rd General Assembly of the Conexión BCB. 21.–22.04.2026. Madrid, Spain.
Call & Join vs. Join & Call: identifying isoforms across biological replicates
Poster. JBI2025. 22.–24.10.2025. Madrid, Spain.
Call & Join vs. Join & Call: identifying isoforms across biological replicates
Poster. ISMB/ECCB2025. 20.–24.07.2025. Liverpool, United Kingdom.
Call & Join vs. Join & Call: identifying isoforms across biological replicates
Poster. LRUA2024. 21.–23.10.2024. Uppsala, Sweden.
IsoAnnot: a new pipeline for functional annotation at isoform resolution
Poster. ECCB2024. 16.–20.09.2024. Turku, Finland.
IsoAnnot: a new pipeline for functional annotation at isoform resolution
Poster. SciLifeLab Science Talks 2024. 12.09.2024. Stockholm, Sweden.
Call & Join vs. Join & Call: identifying isoforms across biological replicates
Virtual poster. ONT London Calling 2024. 21.–24.05.2024.

Training

Research Secondment: IBMCP, Valencia
May 2026. Secondment in the lab of Aureliano Bombarely at IBMCP (Instituto de Biología Molecular y Celular de Plantas), Valencia, working on functional annotation of plant proteomes.
LongTREC Final Meeting: Wrap-Up & Closing
Closing meeting following VALT2026: ERC-style grant-proposal practice, career-planning discussions, talks on technology transfer, venture capital, and corporate values in the bioindustry, a round-table on AI for grant and paper writing, and the network’s final deliverables and closing. 2–3 July 2026. Valencia, Spain.
LongTREC Summer School in Long-Read Transcriptomics
4-day summer school where LongTREC doctoral candidates delivered training in lrRNA-seq methods to participants from across Europe. I taught sessions on long-read RNA-seq transcript reconstruction concepts, working with large replicated data sets, functional annotation with IsoAnnot Lite, and visualization with tappAS. ~July 2025. Earlham Institute, Norwich, UK.
Tutorial IP3: Genomic Variant Interpretation & Prioritisation for Clinical Research
Workshop at ISMB/ECCB 2025. July 19, 2025.
Consultant: Hexaploid Sweet Potato lrRNA-seq Analysis
April 2025 – February 2026. Consultant on a project analyzing hexaploid sweet potato long-read RNA-seq data, exploring transcript reconstruction, allele-specific expression, and fusion transcript analysis.
LongTREC Mid-Term Meeting
Network meeting with training on software development good practices, containerization, and CI/CD at BSC, and career, exploitation, and communication sessions at CRG. I taught a short course on developing bioinformatic pipelines with Nextflow, together with Fabio and Nadja. 24 February – 4 March 2025. Barcelona, Spain (BSC & CRG).
Research Secondment: SciLifeLab, Stockholm
2 months (August–October 2024) in the group of Kristoffer Sahlin at SciLifeLab, Stockholm, Sweden, working on de novo transcript reconstruction for non-model organisms without a reference genome.
LongTREC Fellow's Retreat
Retreat combining doctoral-candidate project presentations, Thesis Advisory Board meetings, science talks and statistics workshops, and multi-day management training covering feedback, assertiveness, stress management, conflict resolution, and negotiation. 24–30 October 2024. Stockholm, Sweden.
Workshop: lrRNA-seq Analysis (LRUA2024)
Contributed to teaching a workshop on long-read RNA-seq analysis. LRUA2024. October 2024. Uppsala, Sweden.
Workshops: FAIR Principles for Research Software & Data Management
Two workshops on applying FAIR principles to research software development and research data management. ECCB2024. September 2024. Turku, Finland.
Workshop: Bioinformatics Workflow Development in ONT EPI2ME
Workshop on bioinformatics workflow development within the Oxford Nanopore EPI2ME infrastructure, using Nextflow and nf-core. Oxford Nanopore Technologies London Calling 2024. May 2024.
LongTREC "Focus on Research" and Mid-Term Meeting
Network meeting combining LongTREC’s 1-year research check-in with an interim mid-term review, including workshops on paper writing, grant writing, and lrRNA-seq data pre-processing across multiple tools. I taught a workshop on long-read bioinformatics data pre-processing with OmicsBox. 9–15 March 2024. CNRS, Valbonne & Nice, France.
Spanish Language Classes (A1–B2)
October 2023 – May 2025. Centre d’Idiomes de la Universitat de València.
Intercept-MDS Single Cell Data Analysis Course
3-day series of lectures and hands-on workshops covering single-cell data pre-processing, clustering, cell type annotation, and trajectory analysis. 2023. Valencia, Spain.
LongTREC Welcome Retreat
Retreat where doctoral candidates were introduced to the network’s structure and work packages, presented their PhD projects to host labs and their Thesis Advisory Board, and took part in workshops on long-read RNA-seq library preparation protocols, research ethics, EU research values, NGS/omics applications in the bioindustry, and intellectual property strategy, plus multi-day professional-skills training in project management, time management, and communication. 27 November – 1 December 2023. Valencia, Spain.

Dissemination and Outreach

Long-read transcriptomic analysis of hexaploid sweet potato in OmicsBox
Webinar. 18.11.2025. 2 live webinar sessions and YouTube.
Numerous blog posts about bioinformatic analyses of long-read RNA-seq data
Published throughout 2024–2025. BioBam homepage.
How on earth did I get here?
Talk. ISCB-RSG Spain, Node Valencia. 11.03.2025. Valencia, Spain.
Presentation to visiting students, winners of the Spanish Biology Olympics
Talk (with Tianyuan Liu). 2024 and 2025. Valencia, Spain.
Quantification and Functional Analysis of Long Reads
Webinar. 03.07.2024. 2 live webinar sessions and YouTube.
Long-Read Isoform Identification and Quantification using IsoQuant
Video. 08.05.2024. YouTube.