[
  {
    "id": "dna-foundation-models-2025",
    "title": "Benchmarking DNA foundation models for genomic and genetic tasks",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC12663285.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12663285/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Nature Communications; PMC ID: PMC12663285.",
    "doi": "10.1038/s41467-025-65823-8"
  },
  {
    "id": "enbed-2024",
    "title": "Understanding the natural language of DNA using encoder–decoder foundation models with byte-level precision",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11341122/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Bioinformatics Advances; PMC ID: PMC11341122.",
    "doi": "10.1093/bioadv/vbae117"
  },
  {
    "id": "quadruplex-llm-benchmark-2025",
    "title": "Benchmarking DNA large language models on quadruplexes",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11953744/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Computational and Structural Biotechnology Journal; PMC ID: PMC11953744.",
    "doi": "10.1016/j.csbj.2025.03.007"
  },
  {
    "id": "dnalongbench-2025",
    "title": "DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks",
    "year": 2025,
    "publication_status": "preprint",
    "version": "PMC11741265.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11741265/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC11741265.",
    "doi": "10.1101/2025.01.06.631595"
  },
  {
    "id": "mrnabench-2025",
    "title": "mRNABench: A curated benchmark for mature mRNA property and function prediction",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint archived 2025-07-08",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12265608/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC12265608.",
    "doi": "10.1101/2025.07.05.662870"
  },
  {
    "id": "bpfold-2025",
    "title": "Deep generalizable prediction of RNA secondary structure via base pair motif energy",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12216785/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Nature Communications; PMC ID: PMC12216785.",
    "doi": "10.1038/s41467-025-60048-1"
  },
  {
    "id": "tu-fold-2025",
    "title": "RNA secondary structure prediction by conducting multi-class classifications",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12008525/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Computational and Structural Biotechnology Journal; PMC ID: PMC12008525.",
    "doi": "10.1016/j.csbj.2025.04.001"
  },
  {
    "id": "debfold-2024",
    "title": "DEBFold: Computational Identification of RNA Secondary Structures for Sequences across Structural Families Using Deep Learning",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "PMC11094721.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11094721/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Journal of Chemical Information and Modeling; PMC ID: PMC11094721.",
    "doi": "10.1021/acs.jcim.4c00458"
  },
  {
    "id": "proteingym-2023",
    "title": "ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction",
    "year": 2023,
    "publication_status": "preprint",
    "version": "PMC10723403.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10723403/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC10723403.",
    "doi": "10.1101/2023.12.07.570727"
  },
  {
    "id": "fujisan-2024",
    "title": "Enhanced prediction of protein functional identity through the integration of sequence and structural features",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "PMC11609699.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11609699/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Computational and Structural Biotechnology Journal; PMC ID: PMC11609699.",
    "doi": "10.1016/j.csbj.2024.11.028"
  },
  {
    "id": "prime-2026",
    "title": "PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13425921/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: BMC Genomics; PMC ID: PMC13425921.",
    "doi": "10.1186/s12864-026-12976-5"
  },
  {
    "id": "pst-2025",
    "title": "Endowing protein language models with structural knowledge",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC12603367.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12603367/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Bioinformatics; PMC ID: PMC12603367.",
    "doi": "10.1093/bioinformatics/btaf582"
  },
  {
    "id": "single-cell-peft-2024",
    "title": "Parameter-Efficient Fine-Tuning Enhances Adaptation of Single Cell Large Language Model for Cell Type Identification",
    "year": 2024,
    "publication_status": "preprint",
    "version": "preprint archived 2024-01-30",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10862733/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC10862733.",
    "doi": "10.1101/2024.01.27.577455"
  },
  {
    "id": "cell2sentence-2024",
    "title": "Cell2Sentence: Teaching Large Language Models the Language of Biology",
    "year": 2024,
    "publication_status": "preprint",
    "version": "preprint archived 2024-10-29",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11565894/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC11565894.",
    "doi": "10.1101/2023.09.11.557287"
  },
  {
    "id": "scelmo-2025",
    "title": "scELMo: Embeddings from Language Models are Good Learners for Single-cell Data Analysis",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint archived 2025-08-23",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12393277/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC12393277.",
    "doi": "10.1101/2023.12.07.569910"
  },
  {
    "id": "scregnet-2025",
    "title": "Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning",
    "year": 2025,
    "publication_status": "preprint",
    "version": "PMC11838224.2",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11838224/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC11838224.",
    "doi": "10.1101/2024.12.16.628715"
  },
  {
    "id": "prokbert-2024",
    "title": "ProkBERT family: genomic language models for microbiome applications",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "PMC10810988.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10810988/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Frontiers in Microbiology; PMC ID: PMC10810988.",
    "doi": "10.3389/fmicb.2023.1331233"
  },
  {
    "id": "cyaprombert-2022",
    "title": "TSSNote-CyaPromBERT: Development of an integrated platform for highly accurate promoter prediction and visualization of Synechococcus sp. and Synechocystis sp. through a state-of-the-art natural language processing model BERT",
    "year": 2022,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9745317/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Frontiers in Genetics; PMC ID: PMC9745317.",
    "doi": "10.3389/fgene.2022.1067562"
  },
  {
    "id": "lambda-prophage-2026",
    "title": "LAMBDA: A Prophage Detection Benchmark for Genomic Language Models",
    "year": 2026,
    "publication_status": "preprint",
    "version": "PMC13041943.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13041943/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC13041943.",
    "doi": "10.64898/2026.03.26.714501"
  },
  {
    "id": "nabas-plus-2025",
    "title": "Advancing metagenomic classification with NABAS+: a novel alignment-based approach",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC12231603.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12231603/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: NAR Genomics and Bioinformatics; PMC ID: PMC12231603.",
    "doi": "10.1093/nargab/lqaf092"
  },
  {
    "id": "lipp-2026",
    "title": "The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "PMC13292216.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13292216/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Journal of Chemical Information and Modeling; PMC ID: PMC13292216.",
    "doi": "10.1021/acs.jcim.6c01457"
  },
  {
    "id": "nmdn-2025",
    "title": "Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11815853/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Journal of Chemical Information and Modeling; PMC ID: PMC11815853.",
    "doi": "10.1021/acs.jcim.4c01014"
  },
  {
    "id": "boltz-stereochemistry-2025",
    "title": "Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12658688/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: ACS Omega; PMC ID: PMC12658688.",
    "doi": "10.1021/acsomega.5c07675"
  },
  {
    "id": "mpro-pose-affinity-2025",
    "title": "A Comparative Study of Deep Learning and Classical Modeling Approaches for Protein–Ligand Binding Pose and Affinity Prediction in Coronavirus Main Proteases",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12801289/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:25:00Z",
    "notes": "Primary full text via Europe PMC XML; venue: Journal of Chemical Information and Modeling; PMC ID: PMC12801289.",
    "doi": "10.1021/acs.jcim.5c02481"
  },
  {
    "id": "dart-eval-regulatory-2024",
    "title": "DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "NeurIPS 2024 Datasets and Benchmarks Track proceedings",
    "source_url": "https://proceedings.neurips.cc/paper_files/paper/2024/file/71998bfc3217ffe1cca1ee084dfadadd-Paper-Datasets_and_Benchmarks_Track.pdf",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "notes": "Proceedings Table 3, DNABERT-2 Zero-Shot Accuracy 0.876 checked directly; the PMC/arXiv manuscript carries the same printed row.",
    "doi": "10.52202/079017-1981"
  },
  {
    "id": "fusion-breakpoint-foundation-models-2026",
    "title": "Benchmarking genomic foundation models for binary classification of gene fusion breakpoints from DNA sequences",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13182013/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1186/s13040-026-00553-1",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: BioData Mining."
  },
  {
    "id": "polya-glm-2025",
    "title": "PolyA-GLM: A comprehensive framework for De novo polyadenylation site prediction using genome language models",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12799945/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1016/j.csbj.2025.12.011",
    "notes": "Numeric result checked against Table 1 in primary full-text XML; journal/source: Computational and Structural Biotechnology Journal."
  },
  {
    "id": "phylogpn-2025",
    "title": "A Phylogenetic Approach to Genomic Language Modeling",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint version in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11908359/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "notes": "Numeric result checked against Table 1. in primary full-text XML; journal/source: ArXiv."
  },
  {
    "id": "dnabert2-enhancer-2025",
    "title": "Utilizing a deep learning model based on BERT for identifying enhancers and their strength",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11981215/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1371/journal.pone.0320085",
    "notes": "Numeric result checked against Table 4 in primary full-text XML; journal/source: PLOS One."
  },
  {
    "id": "barcodebert-2026",
    "title": "BarcodeBERT: transformers for biodiversity analyses",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13008329/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioadv/vbag054",
    "notes": "Numeric result checked against Table 1 in primary full-text XML; journal/source: Bioinformatics Advances."
  },
  {
    "id": "genomic-tokenizer-selection-2025",
    "title": "The impact of tokenizer selection in genomic language models",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12453675/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioinformatics/btaf456",
    "notes": "Final Bioinformatics journal article Table 2, Caduceus (char) Regulatory MCC 0.778 checked directly; same study also has a bioRxiv manuscript."
  },
  {
    "id": "eden-genomic-classification-2026",
    "title": "EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12879454/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1186/s12859-026-06367-6",
    "notes": "DNABERT-2 comparator 70.52 is printed in Table 5. The article does not clearly document whether this comparator was independently rerun or consolidated from prior GUE results, so evaluation origin is conservatively marked paper_compilation."
  },
  {
    "id": "cobra-rna-binding-2026",
    "title": "CoBRA: compound binding site prediction using RNA language model",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12790621/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bib/bbaf713",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Briefings in Bioinformatics."
  },
  {
    "id": "ernie-rna-2025",
    "title": "ERNIE-RNA: an RNA language model with structure-enhanced representations",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12627772/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s41467-025-64972-0",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Nature Communications."
  },
  {
    "id": "codonbert-vaccines-2024",
    "title": "CodonBERT large language model for mRNA vaccines",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11368176/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1101/gr.278870.123",
    "notes": "Numeric result checked against Table 2. in primary full-text XML; journal/source: Genome Research."
  },
  {
    "id": "mrna-lm-2025",
    "title": "mRNA-LM: full-length integrated SLM for mRNA analysis",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11962594/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/nar/gkaf044",
    "notes": "Numeric result checked against Table 1. in primary full-text XML; journal/source: Nucleic Acids Research."
  },
  {
    "id": "rnaret-2026",
    "title": "Retentive Network promotes efficient RNA language modeling of long sequences",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13111708/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s42003-026-09757-x",
    "notes": "Numeric result checked against Table 1 in primary full-text XML; journal/source: Communications Biology."
  },
  {
    "id": "rlsite-rna-binding-2025",
    "title": "RNA language model and graph attention network for RNA and small molecule binding sites prediction",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12417085/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioinformatics/btaf447",
    "notes": "Numeric result checked against Table 1. in primary full-text XML; journal/source: Bioinformatics."
  },
  {
    "id": "birna-bert-2025",
    "title": "BiRNA-BERT allows efficient RNA language modeling with adaptive tokenization",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12635123/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s42003-025-08982-0",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Communications Biology."
  },
  {
    "id": "mrnabert-2025",
    "title": "mRNABERT: advancing mRNA sequence design with a universal language model and comprehensive dataset",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12644827/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s41467-025-65340-8",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Nature Communications."
  },
  {
    "id": "2ome-lm-2025",
    "title": "2OMe-LM: predicting 2′-O-methylation sites in human RNA using a pre-trained RNA language model",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12342186/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioinformatics/btaf417",
    "notes": "Numeric result checked against Table 1. in primary full-text XML; journal/source: Bioinformatics."
  },
  {
    "id": "cathe2-2025",
    "title": "CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12631783/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/biomethods/bpaf080",
    "notes": "Numeric result checked against Table 3. in primary full-text XML; journal/source: Biology Methods & Protocols."
  },
  {
    "id": "clathrin-plm-2025",
    "title": "Advancing the accuracy of clathrin protein prediction through multi-source protein language models",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12238356/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s41598-025-08510-4",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Scientific Reports."
  },
  {
    "id": "gsmformer-ppi-2026",
    "title": "Multimodal graph, surface, and language-based model for protein protein interaction prediction",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12873117/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1038/s41598-025-34758-x",
    "notes": "Numeric result checked against Table 6 in primary full-text XML; journal/source: Scientific Reports."
  },
  {
    "id": "antibody-deamidation-plm-2024",
    "title": "The Accurate Prediction of Antibody Deamidations by Combining High-Throughput Automated Peptide Mapping and Protein Language Model-Based Deep Learning",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11417914/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.3390/antib13030074",
    "notes": "Numeric result checked against Table 1 in primary full-text XML; journal/source: Antibodies."
  },
  {
    "id": "spin-protein-function-2026",
    "title": "Scaling the profile of life by function with SPIN",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12970593/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioadv/vbag064",
    "notes": "Numeric result checked against Table 1 in primary full-text XML; journal/source: Bioinformatics Advances."
  },
  {
    "id": "mulan-2025",
    "title": "MULAN: multimodal protein language model for sequence and structure encoding",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12452268/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bioadv/vbaf117",
    "notes": "Numeric result checked against Table 2. in primary full-text XML; journal/source: Bioinformatics Advances."
  },
  {
    "id": "megsite-2025",
    "title": "MegSite: an accurate nucleic acid-binding residue prediction method based on multimodal protein language model",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "journal full text in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12496013/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1093/bib/bbaf524",
    "notes": "Numeric result checked against Table 2 in primary full-text XML; journal/source: Briefings in Bioinformatics."
  },
  {
    "id": "esm2-ofs-fitness-2025",
    "title": "Pseudo-perplexity in One Fell Swoop for Protein Fitness Estimation",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PRX Life 2025 journal article",
    "source_url": "https://journals.aps.org/prxlife/pdf/10.1103/zhx7-hcmm",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1103/zhx7-hcmm",
    "notes": "Final journal Table I, ESM2: OFS PP Aggregate Mean 0.403 checked directly; manuscript PMC11257618 printed the same value. Other models in the table are imported ProteinGym baselines; this row is the authors’ own evaluation."
  },
  {
    "id": "structure-informed-plm-2025",
    "title": "Structure-Informed Protein Language Models are Robust Predictors for Variant Effects",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "Human Genetics 2025 journal article (online 2024)",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12068927/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:33:26Z",
    "doi": "10.1007/s00439-024-02695-w",
    "notes": "Final Human Genetics Table 4, AA+SS+RSA+CM AUROC .803 checked directly; Research Square preprint Table 3 prints the same value."
  },
  {
    "id": "kidney-cell-segmentation-2025",
    "title": "Evaluating cell AI foundation models in kidney pathology with human-in-the-loop enrichment",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12644679.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12644679/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Communications Medicine; PMC ID: PMC12644679.",
    "doi": "10.1038/s43856-025-01205-x"
  },
  {
    "id": "mouse-geneformer-2025",
    "title": "Mouse-Geneformer: A deep learning model for mouse single-cell transcriptome and its cross-species utility",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11964219/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: PLOS Genetics; PMC ID: PMC11964219.",
    "doi": "10.1371/journal.pgen.1011420"
  },
  {
    "id": "scatac-llmda-2026",
    "title": "Cell type annotation for scATAC-seq via DNA large language model and graph domain adaptation",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13132462/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: PLOS Computational Biology; PMC ID: PMC13132462.",
    "doi": "10.1371/journal.pcbi.1014226"
  },
  {
    "id": "anndictionary-2025",
    "title": "Benchmarking cell type and gene set annotation by large language models with AnnDictionary",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12569162.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12569162/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Nature Communications; PMC ID: PMC12569162.",
    "doi": "10.1038/s41467-025-64511-x"
  },
  {
    "id": "llm-cell-identification-2025",
    "title": "Evaluation of cell type annotation reliability using a large language model-based identifier",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12462508/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Communications Biology; PMC ID: PMC12462508.",
    "doi": "10.1038/s42003-025-08745-x"
  },
  {
    "id": "genept-2024",
    "title": "GenePT: A Simple But Effective Foundation Model for Genes and Cells Built From ChatGPT",
    "year": 2024,
    "publication_status": "preprint",
    "version": "PMC archival version PMC10614824.2",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10614824/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: bioRxiv; PMC ID: PMC10614824.",
    "doi": "10.1101/2023.10.16.562533"
  },
  {
    "id": "single-cell-aging-probes-2026",
    "title": "Inflammation-linked aging signals in frozen single-cell foundation models: donor-aware detection and robustness testing",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC13407579.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13407579/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Biogerontology; PMC ID: PMC13407579.",
    "doi": "10.1007/s10522-026-10471-8"
  },
  {
    "id": "scalr-2025",
    "title": "scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12121358/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Briefings in Bioinformatics; PMC ID: PMC12121358.",
    "doi": "10.1093/bib/bbaf243"
  },
  {
    "id": "scxdr-2026",
    "title": "scXDR: drug response prediction across single-cell datasets via heterogeneous network transfer learning",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12859067.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12859067/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Communications Biology; PMC ID: PMC12859067.",
    "doi": "10.1038/s42003-025-09418-5"
  },
  {
    "id": "cammiq-2022",
    "title": "Strain level microbial detection and quantification with applications to single cell metagenomics",
    "year": 2022,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9616933/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Nature Communications; PMC ID: PMC9616933.",
    "doi": "10.1038/s41467-022-33869-7"
  },
  {
    "id": "lazypipe-2020",
    "title": "Novel NGS pipeline for virus discovery from a wide spectrum of hosts and sample types",
    "year": 2020,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7772471/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Virus Evolution; PMC ID: PMC7772471.",
    "doi": "10.1093/ve/veaa091"
  },
  {
    "id": "ncd-metagenomics-2026",
    "title": "Normalized compression distance for DNA classification",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12884959/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: PeerJ; PMC ID: PMC12884959.",
    "doi": "10.7717/peerj.20677"
  },
  {
    "id": "viral-contig-simulation-2021",
    "title": "Simulation study and comparative evaluation of viral contiguous sequence identification tools",
    "year": 2021,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8207588/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: BMC Bioinformatics; PMC ID: PMC8207588.",
    "doi": "10.1186/s12859-021-04242-0"
  },
  {
    "id": "genomeocean-2025",
    "title": "GenomeOcean: An Efficient Genome Foundation Model Trained on Large-Scale Metagenomic Assemblies",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint archived 2025-02-05",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11838515/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: bioRxiv; PMC ID: PMC11838515.",
    "doi": "10.1101/2025.01.30.635558"
  },
  {
    "id": "kmetashot-2025",
    "title": "kMetaShot: a fast and reliable taxonomy classifier for metagenome-assembled genomes",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC11695915.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11695915/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Briefings in Bioinformatics; PMC ID: PMC11695915.",
    "doi": "10.1093/bib/bbae680"
  },
  {
    "id": "lemur-magnet-2024",
    "title": "Lightweight taxonomic profiling of long-read metagenomic datasets with Lemur and Magnet",
    "year": 2024,
    "publication_status": "preprint",
    "version": "PMC archival version PMC11185576.2",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11185576/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: bioRxiv; PMC ID: PMC11185576.",
    "doi": "10.1101/2024.06.01.596961"
  },
  {
    "id": "ipromp-2025",
    "title": "iPro-MP: a BERT-based model to predict multiple prokaryotic promoters",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12516880/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Genome Biology; PMC ID: PMC12516880.",
    "doi": "10.1186/s13059-025-03819-9"
  },
  {
    "id": "icctax-2025",
    "title": "ICCTax: a hierarchical taxonomic classifier for metagenomic sequences on a large language model",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12619997/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Bioinformatics Advances; PMC ID: PMC12619997.",
    "doi": "10.1093/bioadv/vbaf257"
  },
  {
    "id": "antibody-flexibility-2025",
    "title": "Enhancing antibody-antigen interaction prediction with atomic flexibility",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12530544/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: PLOS Computational Biology; PMC ID: PMC12530544.",
    "doi": "10.1371/journal.pcbi.1013576"
  },
  {
    "id": "boltz1-2025",
    "title": "Boltz-1 Democratizing Biomolecular Interaction Modeling",
    "year": 2025,
    "publication_status": "preprint",
    "version": "PMC archival version PMC11601547.4",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11601547/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: bioRxiv; PMC ID: PMC11601547.",
    "doi": "10.1101/2024.11.19.624167"
  },
  {
    "id": "ibex-2025",
    "title": "Conformation-aware structure prediction of antigen-recognizing immune proteins",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12710905.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12710905/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: mAbs; PMC ID: PMC12710905.",
    "doi": "10.1080/19420862.2025.2602217"
  },
  {
    "id": "deelig-2021",
    "title": "DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity",
    "year": 2021,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC8274096.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8274096/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Bioinformatics and Biology Insights; PMC ID: PMC8274096.",
    "doi": "10.1177/11779322211030364"
  },
  {
    "id": "molas-2026",
    "title": "Molecular embedding-based algorithm selection in protein-ligand docking",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC13104262.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13104262/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: Journal of Cheminformatics; PMC ID: PMC13104262.",
    "doi": "10.1186/s13321-026-01168-8"
  },
  {
    "id": "ensemble-idp-docking-2025",
    "title": "Ensemble docking for intrinsically disordered proteins",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint archived 2025-01-26",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11785235/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: bioRxiv; PMC ID: PMC11785235.",
    "doi": "10.1101/2025.01.23.634614"
  },
  {
    "id": "akscore-2020",
    "title": "AK-Score: Accurate Protein-Ligand Binding Affinity Prediction Using an Ensemble of 3D-Convolutional Neural Networks",
    "year": 2020,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7697539/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: International Journal of Molecular Sciences; PMC ID: PMC7697539.",
    "doi": "10.3390/ijms21228424"
  },
  {
    "id": "fingerprint-scoring-2022",
    "title": "Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints",
    "year": 2022,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC9178954.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9178954/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:29:32Z",
    "notes": "Primary full text verified using Europe PMC XML; venue: ACS Omega; PMC ID: PMC9178954.",
    "doi": "10.1021/acsomega.2c02822"
  },
  {
    "id": "arsenal-regulatory-dna-2026",
    "title": "Short-Context Regulatory DNA Language Models with Motif-Discovery Regularization",
    "year": 2026,
    "publication_status": "preprint",
    "version": "preprint version in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12889687/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: bioRxiv; PMC ID: PMC12889687. Preprint; result is a supervised downstream model rather than a general-purpose DNA foundation model.",
    "doi": "10.64898/2026.02.05.703637"
  },
  {
    "id": "plantcad2-2025",
    "title": "PlantCAD2: A Long-Context DNA Language Model for Cross-Species Functional Annotation in Angiosperms",
    "year": 2025,
    "publication_status": "preprint",
    "version": "preprint version in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12425018/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: bioRxiv; PMC ID: PMC12425018. Preprint; Table 1 pairs PlantCAD2 with an unnamed best benchmark; only PlantCAD2 value recorded.",
    "doi": "10.1101/2025.08.27.672609"
  },
  {
    "id": "hi-enhancer-2025",
    "title": "Hi-Enhancer: a two-stage framework for prediction and localization of enhancers based on Blending-KAN and Stacking-Auto models",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12758598/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Bioinformatics; PMC ID: PMC12758598. Task-specific enhancer predictor; not a DNA foundation model. Comparison values from older papers excluded.",
    "doi": "10.1093/bioinformatics/btaf441"
  },
  {
    "id": "enhancer-position-encoding-2024",
    "title": "A deep learning model for DNA enhancer prediction based on nucleotide position aware feature encoding",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11167433/",
    "primary_domain": "dna-genomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: iScience; PMC ID: PMC11167433. Task-specific CNN baseline, included as a DNA benchmark protocol reference.",
    "doi": "10.1016/j.isci.2024.110030"
  },
  {
    "id": "adar-gpt-editing-2026",
    "title": "ADAR-GPT: A continually fine-tuned language model for predicting A-to-I RNA editing sites",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12798952/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Proceedings of the National Academy of Sciences of the United States of America; PMC ID: PMC12798952. RNA editing site benchmark on a restricted liver validation set.",
    "doi": "10.1073/pnas.2529073123"
  },
  {
    "id": "r3design-2025",
    "title": "R3Design: deep tertiary structure-based RNA sequence design and beyond",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC11685104.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11685104/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Briefings in Bioinformatics; PMC ID: PMC11685104. Architecture and task differ from RNA language-model encoding benchmarks.",
    "doi": "10.1093/bib/bbae682"
  },
  {
    "id": "cupid-rna-interactions-2026",
    "title": "Computational understanding of non-coding RNA pairwise interactions",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12957212.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12957212/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Frontiers in Artificial Intelligence; PMC ID: PMC12957212. RNA-RNA pairwise interaction predictor; not a foundation model.",
    "doi": "10.3389/frai.2026.1749205"
  },
  {
    "id": "mrna-protein-diversity-2026",
    "title": "Generalizable deep-learning-based mRNA-protein interaction prediction strongly depends on protein diversity",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13235059/",
    "primary_domain": "rna-transcriptomes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Journal of Cheminformatics; PMC ID: PMC13235059. ProteinBERT encodes the protein side of an mRNA-protein task; score is not an RNA foundation-model result.",
    "doi": "10.1186/s13321-026-01197-3"
  },
  {
    "id": "viral-immune-mimicry-2025",
    "title": "Protein Language Models Expose Viral Immune Mimicry",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12474240/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Viruses; PMC ID: PMC12474240. Downstream classifier uses ESM2 representations; table does not report a pure zero-shot language-model score.",
    "doi": "10.3390/v17091199"
  },
  {
    "id": "protein-binding-sites-2023",
    "title": "Learning the protein language of proteome-wide protein-protein binding sites via explainable ensemble deep learning",
    "year": 2023,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9849350/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Communications Biology; PMC ID: PMC9849350. Downstream binding-site classifier; not a native ProtT5 prediction head.",
    "doi": "10.1038/s42003-023-04462-5"
  },
  {
    "id": "clape-smb-2024",
    "title": "Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11542454/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Journal of Cheminformatics; PMC ID: PMC11542454. ESM-2 feature extractor embedded in CLAPE-SMB; score belongs to combined downstream system.",
    "doi": "10.1186/s13321-024-00920-2"
  },
  {
    "id": "vaxign-esm-2024",
    "title": "Enhancing Vaxign-DL for Vaccine Candidate Prediction with added ESM-Generated Features",
    "year": 2024,
    "publication_status": "preprint",
    "version": "preprint version in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11398487/",
    "primary_domain": "proteins-complexes",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: bioRxiv; PMC ID: PMC11398487. Preprint; combined classifier uses ESM features rather than ESM-only predictions.",
    "doi": "10.1101/2024.09.04.611295"
  },
  {
    "id": "single-cell-residual-geometry-2026",
    "title": "Residual-stream geometry of single-cell foundation models carries incremental gene-regulatory signal across tissues",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13418759/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: BMC Bioinformatics; PMC ID: PMC13418759. Score reflects scGPT plus paper geometry features, not raw scGPT.",
    "doi": "10.1186/s12859-026-06538-5"
  },
  {
    "id": "gremln-2026",
    "title": "GREmLN: A Cellular Graph Structure Aware Transcriptomics Foundation Model",
    "year": 2026,
    "publication_status": "preprint",
    "version": "preprint version in PMC",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13060794/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: bioRxiv; PMC ID: PMC13060794. Preprint; table labels metric F1; paper does not specify macro in this row.",
    "doi": "10.1101/2025.07.03.663009"
  },
  {
    "id": "cell-dino-2025",
    "title": "Cell-DINO: Self-supervised image-based embeddings for cell fluorescent microscopy",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12826486/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: PLOS Computational Biology; PMC ID: PMC12826486. PL column is F1-score reported on a 0–100 scale; Cell-DINO is a vision encoder plus downstream classifier.",
    "doi": "10.1371/journal.pcbi.1013828"
  },
  {
    "id": "insilico-perturbation-auprc-2025",
    "title": "AUPRC: a metric for evaluating the performance of in-silico perturbation methods in identifying differentially expressed genes",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC12400816.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12400816/",
    "primary_domain": "cells-tissues",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Briefings in Bioinformatics; PMC ID: PMC12400816. Paper benchmarks metrics and scGen perturbation method; no foundation-model result in this row.",
    "doi": "10.1093/bib/bbaf426"
  },
  {
    "id": "metagenomic-pathogens-2025",
    "title": "Enhancing pathogen identification through AI-assisted metagenomic sequencing",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12493982/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Frontiers in Microbiology; PMC ID: PMC12493982. Primary article has mixed biomedical-text and metagenomics assessments; selected MetaHIT pathogen-detection table only.",
    "doi": "10.3389/fmicb.2025.1634194"
  },
  {
    "id": "detire-viral-metagenomes-2023",
    "title": "DETIRE: a hybrid deep learning model for identifying viral sequences from metagenomes",
    "year": 2023,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC10313334.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC10313334/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Frontiers in Microbiology; PMC ID: PMC10313334. Task-specific viral classifier, included as a microbial metagenomics benchmark.",
    "doi": "10.3389/fmicb.2023.1169791"
  },
  {
    "id": "pc-mer-2024",
    "title": "PC-mer: An Ultra-fast memory-efficient tool for metagenomics profiling and classification",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11293629/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: PLOS ONE; PMC ID: PMC11293629. Feature-extraction classifier; not a biological foundation model.",
    "doi": "10.1371/journal.pone.0307279"
  },
  {
    "id": "mdl4microbiome-2022",
    "title": "Multimodal deep learning applied to classify healthy and disease states of human microbiome",
    "year": 2022,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC8763943.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8763943/",
    "primary_domain": "microbes-communities",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Scientific Reports; PMC ID: PMC8763943. Study predates most microbial foundation models; useful task baseline only.",
    "doi": "10.1038/s41598-022-04773-3"
  },
  {
    "id": "ligand-affinity-meta-model-2024",
    "title": "Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling",
    "year": 2024,
    "publication_status": "peer_reviewed",
    "version": "PMC archival version PMC11632770.1",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11632770/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Journal of Chemical Information and Modeling; PMC ID: PMC11632770. Mixed prediction units across Table 4 comparators; only meta-model PCC recorded.",
    "doi": "10.1021/acs.jcim.4c01116"
  },
  {
    "id": "deepinteraware-2025",
    "title": "DeepInterAware: Deep Interaction Interface‐Aware Network for Improving Antigen‐Antibody Interaction Prediction from Sequence Data",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11967782/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Advanced Science; PMC ID: PMC11967782. Neutralization prediction, not generic binding affinity; uncertainty printed in source table.",
    "doi": "10.1002/advs.202412533"
  },
  {
    "id": "transbind-2026",
    "title": "Integrating protein and DNA embeddings for improving genome-wide transcription factor binding site prediction",
    "year": 2026,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13145115/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: NAR Genomics and Bioinformatics; PMC ID: PMC13145115. Protein-DNA model; comparator scores in table not copied into this batch.",
    "doi": "10.1093/nargab/lqag047"
  },
  {
    "id": "esm2-amp-2025",
    "title": "ESM2_AMP: an interpretable framework for protein–protein interactions prediction and biological mechanism discovery",
    "year": 2025,
    "publication_status": "peer_reviewed",
    "version": "version of record",
    "source_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12392411/",
    "primary_domain": "molecular-interactions",
    "retrieved_utc": "2026-09-15T23:37:05Z",
    "notes": "Primary full text verified via Europe PMC fullTextXML; venue: Briefings in Bioinformatics; PMC ID: PMC12392411. Paper has multiple model variants; selected named ESM2_AMPS variant only.",
    "doi": "10.1093/bib/bbaf434"
  }
]