Author

Ana-Maria Istrate

Chan Zuckerberg Initiative (United States)ORCID 0000-0002-7953-5168Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 2 Systems Biology· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 3 Approach:deep learning· 3 Research Focus:gene regulatory network inference· 2 Assay:scRNA-seq· 2 Approach:transformer / foundation model· 2 Research Focus:cell type annotation· 1 Research Focus:drug response / drug discovery· 1 Organism:human· 1

Frequent Co-Authors

Donghui LiiD· 3 shared Theofanis KaraletsosiD· 3 shared Alexander J. TarashanskyiD· 1 shared B.E. NelsoniD· 1 shared Fabrizio CastrotorresiD· 1 shared Fausto MilletarìiD· 1 shared Giovanni PallaiD· 1 shared Gita MahmoudabadiiD· 1 shared

Activity by Year

2024-2026 · peak 1/yr

Co-Author Collaboration Network

10 top collaborators · 30 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

3 shared papersBioinformatics

Donghui LiORCID

Mutual co-authors in cluster

Author profile →

3 papers

Recent·Most cited

A Cross-Species Generative Cell Atlas Across 1.5 Billion Years of Evolution: The TranscriptFormer Single-cell Model

James D. Pearce, Sara E. Simmonds, Gita Mahmoudabadi, Lakshmi Krishnan, Giovanni Palla, Ana-Maria Istrate, Alexander J. Tarashansky, B.E. Nelson, Omar Valenzuela, Donghui Li, Stephen R. Quake, Theofanis Karaletsos

The paper introduces TranscriptFormer, a generative model trained on 112 million cells across 12 species, demonstrating cross-species cell type classification and disease state prediction.

Science · May 7, 2026Peer-reviewedSystems Biology

rbio1-training scientific reasoning LLMs with biological world models as soft verifiers

Ana-Maria Istrate, Fausto Milletarì, Fabrizio Castrotorres, Jakub M. Tomczak, Michaela Torkar, Donghui Li, Theofanis Karaletsos

This paper introduces rbio1, a biology reasoning model trained using soft verification via biological world models, achieving state-of-the-art performance on perturbation prediction.

bioRxiv · Aug 18, 2025 · PreprintBioinformatics

scGenePT: Is language all you need for modeling single-cell perturbations?

Ana-Maria Istrate, Donghui Li, Theofanis Karaletsos

The paper shows that combining language-based gene representations with experimental data improves perturbation prediction in single-cell data.

bioRxiv · Oct 23, 2024 · PreprintBioinformatics