Author

Carlos Albors

University of California, Berkeley

Listed by name: these papers carry no ORCID for this author, so different people with the same name may be mixed together.

Biology Disciplines

Click to filter author papers

Bioinformatics· 2 Genetics· 1 Genomics· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Organism:human· 4 Approach:deep learning· 3 Research Focus:variant effect prediction· 3 Research Focus:fine-mapping· 2 Approach:statistical model· 2 Assay:whole-genome sequencing· 2 Research Focus:benchmarking· 1 Research Focus:GWAS / association mapping· 1

Frequent Co-Authors

Chengzhong YeiD· 3 shared Yun S. SongiD· 3 shared Gonzalo BenegasiD· 2 shared Akihide Masumoto· 1 shared Akiko NagaiiD· 1 shared Alan J. AwiD· 1 shared Antoine KoehliD· 1 shared Brian ClarkeiD· 1 shared

Activity by Year

2021-2025 · peak 2/yr

Co-Author Collaboration Network

10 top collaborators · 17 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

Chengzhong YeORCID

Mutual co-authors in cluster

Author profile →

4 papers

Recent·Most cited

Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models

Chengzhong Ye, Gonzalo Benegas, Carlos Albors, Jianan Canal Li, Sebastian Prillo, Peter D. Fields, Brian Clarke, Yun S. Song

This paper introduces GPN-Star, a phylogeny-informed genomic language model that improves variant effect prediction across species and evolutionary timescales.

bioRxiv · Sep 21, 2025 · PreprintBioinformatics

GPN-MSA: an alignment-based DNA language model for genome-wide variant effect prediction

Gonzalo Benegas, Carlos Albors, Alan J. Aw, Chengzhong Ye, Yun S. Song

GPN-MSA is a DNA language model that predicts variant effects across the human genome using whole-genome alignments, achieving strong performance on deleteriousness prediction for coding and non-coding variants.

Nature Biotechnology · Jan 2, 2025Peer-reviewedBioinformatics

Cross-protein transfer learning substantially improves disease variant prediction

Milind Jagota, Chengzhong Ye, Carlos Albors, Ruchir Rastogi, Antoine Koehl, Nilah M. Ioannidis, Yun S. Song

This paper introduces a cross-protein transfer learning framework that improves disease variant prediction using deep mutational scanning data from few proteins, achieving better specificity than existing models.

Genome biology · Aug 7, 2023Peer-reviewedGenetics

Leveraging supervised learning for functionally-informed fine-mapping of cis-eQTLs identifies an additional 20,913 putative causal eQTLs

Qingbo S. Wang, David R. Kelley, Jacob C. Ulirsch, Masahiro Kanai, Shuvom Sadhuka, Ran Cui, Carlos Albors, Nathan Cheng, Yukinori Okada, The Biobank Japan Project, Koichi Matsuda, Yuji Yamanashi, Yoichi Furukawa, Takayuki Morisaki, Yoshinori Murakami, , Hilary K. Finucane

The paper uses supervised learning to fine-map cis-eQTLs, identifying 20,913 additional putative causal eQTLs and 310 candidate genes.

Nature Communications · Jun 7, 2021Peer-reviewedGenomics