Kemal Inecik

Thrilled to announce the launch of my most significant and promising collaboration to date—a lifelong partnership! 💍 Together, we’ll be co-authoring every chapter ahead, optimizing for shared happiness, resilience, and intellectual curiosity. Looking forward to this interdisciplinary journey. 🥂

13.07.2025 12:55 — 👍 1    🔁 0    💬 0    📌 0

Looking forward to engaging with the community at ICML GenBio in Vancouver and discussing how principled benchmarking can advance single-cell trajectory inference!

30.06.2025 13:44 — 👍 0    🔁 0    💬 0    📌 0

Grateful to all co-authors and collaborators for their contributions and insight throughout this project. Fabian Theis @fabiantheis.bsky.social, Malte Luecken, Muzzlifah Haniffa @mhaniffa.bsky.social, and Antony Rose.

30.06.2025 13:44 — 👍 1    🔁 1    💬 1    📌 0

By providing multiscale, structure-aware benchmarks, scTRAM enables principled model comparison and elevates trajectory representation evaluation from subjective inspection to systematic and reproducible assessment.

30.06.2025 13:44 — 👍 0    🔁 0    💬 1    📌 0

This matters because downstream analyses—from developmental biology to disease progression—depend critically on trajectory integrity, which conventional evaluation protocols often overlook due to their qualitative or ad hoc nature.

30.06.2025 13:44 — 👍 0    🔁 0    💬 1    📌 0

Our comprehensive experiments reveal distinct representational trade-offs and expose localized embedding failures by dissecting trajectory integrity across biologically relevant contexts.

30.06.2025 13:44 — 👍 0    🔁 0    💬 1    📌 0

scTRAM quantitatively evaluates how much single-cell embeddings preserve ground-truth trajectory structures by decomposing fidelity into complementary metrics—topological consistency, manifold continuity, and pseudotime alignment—rather than relying on heuristic visualizations or single surrogates.

30.06.2025 13:44 — 👍 0    🔁 0    💬 1    📌 0

Beyond Visual Inspection: Principled Benchmarking of Single-Cell Trajectory Representations with scTRAM Single-cell representation learning aims to construct low-dimensional embeddings that preserve biologically salient manifold structures. Yet current evaluation protocols remain inadequate for assessin...

Excited to announce that our latest work “Beyond Visual Inspection: Principled Benchmarking of Single-Cell Trajectory Representations with scTRAM” has been accepted to the ICML GenBio workshop, July 13–19 in Vancouver, Canada. 🇨🇦🧬✨ biorxiv.org/content/10.1... #icml2025 @icmlconf.bsky.social

30.06.2025 13:44 — 👍 0    🔁 0    💬 1    📌 0

Couldn’t have asked for a better experience at #RECOMB2025. Thank you for the Best Student Paper / Young Scientist Award 🏆— and for all the inspiring conversations and warm moments. Special thanks to my PI, @fabiantheis.bsky.social for his guidance and support. Feeling excited for what comes next! 🧬

29.04.2025 09:53 — 👍 1    🔁 0    💬 0    📌 0

In Seoul for #RECOMB2025: presented TarDis, exchanged ideas, and found comfort in good conversations and even better kimchi. 🧬👨🏻‍💻🇰🇷🍜

28.04.2025 07:38 — 👍 3    🔁 0    💬 0    📌 0

RECOMB has officially started! 👨🏻‍💻🧬 Super excited for the talks, the people, and all the science ahead. Already fueled up with some incredible Korean food 🇰🇷🍜. Honestly, if the conference is half as good as the food, it’s going to be unforgettable. #recomb @recombconf.bsky.social

26.04.2025 01:58 — 👍 2    🔁 0    💬 0    📌 0