Full archive
Bioinformatics & AI
Week of 22 September 2026
9 articles
Geno'X Veille — genox-veille.fr
Key takeaways this week
- ►Pangenome — F1 score 0.86 versus 0 to 0.57 for variants of at least 20 bp on a cardiomyopathy panel.
- ►dicast — 20% more candidate pathogenic deletions than consensus approaches, from short-read data.
- ►Electronic health records — more than a year of median lead time over the first diagnostic code, across 3 million records.
- ►STXBP1 — a gene-calibrated predictor, tested against functional assays and publicly deployed.
- ►Cas9-targeted nanopore — 27 repeat expansion genes analysed on R10 flow cells.
9 articles of 9
Sort
Structural variants
PubMed★ Top pick
Pangenomes aid accurate detection of large insertions and deletions from targeted sequencing: the case of cardiomyopathies.
Cardiomyopathies — large variant detection on gene panels
9
Structural variantsSV callerBenchmark
Genome Med 2026· AugRead
Structural variants
PubMeddicast: a machine learning method for accurate structural variant detection from short-read sequencing data.
Structural variant detection from short-read sequencing
8
Structural variantsSV callerNew tool
Genome Biol 2026· SepRead
Clinical pipeline
medRxivEarly identification of rare disease using deep phenotyping of electronic health records
Rare disease — early identification from electronic health records
7
Clinical pipelineClinical pipeline
medRxiv 2026· SepRead
STXBP1
PubMedGene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1.
STXBP1-related developmental and epileptic encephalopathies
6
Pathogenicity predictionPathogenicity predictionNew tool
J Clin Invest 2026· SepRead
Long-read
PubMedParallel Analysis of Repeat Expansions: An Updated Clinical Nanopore Cas9-Targeted Sequencing Workflow for Nanopore R10 Flow Cells.
Repeat expansions — hereditary ataxias and neuromuscular disorders
6
Long-readLong-read sequencingClinical pipeline
J Mol Diagn 2026· SepRead
Language model / AI
PubMedGenolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction.
Protein function interpretation
5
Language model / AILLM appliedNew tool
Genome Biol 2026· SepRead
GLP1R
PubMedThe GPCRVP score reliably predicts the impact of GLP1R human variants on receptor function.
Type 2 diabetes and obesity — GLP-1 receptor variants
5
Pathogenicity predictionPathogenicity predictionNew tool
Diabetologia 2026· SepRead
KMT2B
PubMedNanopore long-read sequencing facilitates accurate diagnosis of KMT2B-related dystonia.
KMT2B-related dystonia
5
Long-readLong-read sequencingClinical pipeline
Clin Epigenetics 2026· SepRead
Disease-associated variants in phase-separating proteins
PubMedDisPhaseDB 2.0: Improved interpretation of disease-associated variants in liquid-liquid phase separation proteins with agent-accessible querying.
Disease-associated variants in phase-separating proteins
5
New toolLLM applied
Protein Sci 2026· SepRead
References and sources
- Cardiomyopathies — large variant detection on gene panels. Genome Med 2026. PMID 42723105. Score 9/10. https://pubmed.ncbi.nlm.nih.gov/42723105/
- Structural variant detection from short-read sequencing. Genome Biol 2026. PMID 42754892. Score 8/10. https://pubmed.ncbi.nlm.nih.gov/42754892/
- Rare disease — early identification from electronic health records. medRxiv 2026. doi:10.64898/2026.09.11.26362811. Score 7/10. https://www.medrxiv.org/content/10.64898/2026.09.11.26362811v1
- STXBP1 — STXBP1-related developmental and epileptic encephalopathies. J Clin Invest 2026. PMID 42752354. Score 6/10. https://pubmed.ncbi.nlm.nih.gov/42752354/
- Repeat expansions — hereditary ataxias and neuromuscular disorders. J Mol Diagn 2026. PMID 42744283. Score 6/10. https://pubmed.ncbi.nlm.nih.gov/42744283/
- Protein function interpretation. Genome Biol 2026. PMID 42750043. Score 5/10. https://pubmed.ncbi.nlm.nih.gov/42750043/
- GLP1R — Type 2 diabetes and obesity — GLP-1 receptor variants. Diabetologia 2026. PMID 42752967. Score 5/10. https://pubmed.ncbi.nlm.nih.gov/42752967/
- KMT2B — KMT2B-related dystonia. Clin Epigenetics 2026. PMID 42754922. Score 5/10. https://pubmed.ncbi.nlm.nih.gov/42754922/
- Disease-associated variants in phase-separating proteins. Protein Sci 2026. PMID 42742059. Score 5/10. https://pubmed.ncbi.nlm.nih.gov/42742059/