←
Altuna Akalin1,329 posts
Altuna Akalin avatar

Altuna Akalin

@AltunaAkalin

Head of bioinformatics @MDC_berlin/@BIMSB_MDC 🛠 loves genomics, R, data science, machine learning, visualization & 🎣. also @arcas_ai

◷ Joined November 2014▧ 206 Photos and videos
Altuna Akalin avatar
Altuna Akalin@AltunaAkalin·Jun 8

Can an ECG reveal whether a heart looks older than expected? We explored ECG-derived biological age as a marker of cardiovascular disease burden. The idea is simple: train a model to learn “normal ECG aging” from healthy subjects, then ask whether disease shifts the ECG

Post attachment
Genetic Engineering & Biotechnology News avatar
⟳ Altuna Akalin retweeted
Genetic Engineering & Biotechnology News@GENbio·17 Sep 2025

Deep Learning Integrates Multi-Omics for Precision Oncology Decision Making Flexynesis uses #deeplearning to evaluate multi-omics data as well as specially processed texts and images, including CT or MRI scans @AltunaAkalin #multiomics #precisiononcology hubs.li/Q03JyMFq0

Azer Koçulu avatar
⟳ Altuna Akalin retweeted
Azer Koçulu@azerkoculu·16 Jul 2025

introducing mitte 1.0. AI creative suite, built for precision. photorealistic scenes. perfect product placement. video and sound. check us out on @ProductHunt today.

0:43
Ahmet Sarıgün avatar
⟳ Altuna Akalin retweeted
Ahmet Sarıgün@a_sarig_·26 Jun 2025

We benchmarked PocketVina across four widely used datasets (PDBbind, PoseBusters, Astex, DockGen), and introduce TargetDock-AI — a large-scale benchmark of >500K protein–ligand pairs with activity labels from PubChem. (5/n)

Post attachment
Ahmet Sarıgün avatar
⟳ Altuna Akalin retweeted
Ahmet Sarıgün@a_sarig_·26 Jun 2025

I'm excited to share our new preprint: PocketVina — a fast, scalable, and accurate multi-pocket molecular docking method. Docking remains essential in early-stage drug discovery, but recent deep learning–based approaches still face limitations in generating... Thread - (1/n)

0:46
Ahmet Sarıgün avatar
⟳ Altuna Akalin retweeted
Ahmet Sarıgün@a_sarig_·26 Jun 2025

All results, code (MIT License), and data are open and available: 📄 Paper: arxiv.org/abs/2506.20043 📦 Data: zenodo.org/records/15733460 💻 Code: github.com/BIMSBbioinfo/Pock… Huge thanks to co-authors @AltunaAkalin, Bora Uyar, and @vedranfranke!

Altuna Akalin avatar
⟳ Altuna Akalin retweeted
Altuna Akalin@AltunaAkalin·14 May 2025

Happy to announce the first public release of rolv app. Rolv is your AI-powered research assistant for life sciences! It provides a new way to accelerate data analysis, literature reviews, and hypothesis generation. ✨ Core Features: AI-Assisted Data Analysis: Ask data analysis questions, rolv desktop is integrated with your data Local Data Analysis: Your data stays secure on your device—no cloud dependency for analysis. PubMed integration: Get PubMed backed answers to your queries. Dataset Search Integration: Find the relevant datasets you need for your analysis. Create AI-Assisted Analysis Workflows: Data analysis is not linear; build complex workflows using the graph interface and natural language. Ask A Human Feature: AI gets you far, but sometimes you need human expertise. When you're stuck, connect with data analysis experts through our platform. 📥 How to get access Request access to the platform here rolv.io/access Download the Rolv desktop app and start analyzing. See releases and docs here: github.com/rolv-io/rolvapp/r…

Post attachment
Altuna Akalin avatar
Altuna Akalin@AltunaAkalin·9 May 2025

🚑✨ Our new research in @SpringerNature journal npj Digital Medicine shows that large language models—including a RAG-enhanced one—accurately triaged, referred and even suggested diagnoses for 2,000 real emergency-department cases. 🩺 Clinicians mostly agree with what the models spit out—what mattered was whether its advice would guide safe care, not whether every word matched the textbook. 🤖 AI isn’t replacing clinicians; it’s fast becoming the teammate we’ve been waiting for. #HealthcareAI

Post attachment
Kyle Fedorchak avatar
⟳ Altuna Akalin retweeted
Kyle Fedorchak@kfedorchak·2 Mar 2025

Just finished module 1 on AI-assisted data analysis and was amazed by @rolv_io. Made it incredibly easy to visualize gene expression heatmaps and apply ML to methylation data. Thanks @AltunaAkalin and team!

I'm happy to announce our next computational genomics course for 2025. The deadline for application is January 30th 2025. We will cover: - AI-assisted data analysis - Spatial omics analysis - Multi-omics data analysis. More info is here: bioinformatics.mdc-berlin.de…

Post attachment