Biology subjects

St. John, J.

Publications and source records attributed to St. John, J..

3 recordsLinked to original sources

bioRxiv2025

Genome modeling and design across all domains of life with Evo 2

All of life encodes information with DNA. While tools for sequencing, synthesis, and editing of genomic code have transformed biological research, intelligently composing new biological systems would also require a deep understanding of the immense complexity encoded by genomes. We introduce Evo 2, a biological foundation model trained on 9.3 trillion DNA base pairs from a highly curated genomic atlas spanning all domains of life. We train Evo 2 with 7B and 40B parameters to have an unprecedented 1 million token context window with single-nucleotide resolution. Evo 2 learns from DNA sequence alone to accurately predict the functional impacts of genetic variation--from noncoding pathogenic mutations to clinically significant BRCA1 variants--without task-specific finetuning. Applying mechanistic interpretability analyses, we reveal that Evo 2 autonomously learns a breadth of biological features, including exon-intron boundaries, transcription factor binding sites, protein structural elements, and prophage genomic regions. Beyond its predictive capabilities, Evo 2 generates mitochondrial, prokaryotic, and eukaryotic sequences at genome scale with greater naturalness and coherence than previous methods. Guiding Evo 2 via inference-time search enables controllable generation of epigenomic structure, for which we demonstrate the first inference-time scaling results in biology. We make Evo 2 fully open, including model parameters, training code, inference code, and the OpenGenome2 dataset, to accelerate the exploration and design of biological complexity.

genomics↗

bioRxiv2018

Machine learning enables detection of early-stage colorectal cancer by whole-genome sequencing of plasma cell-free DNA

BackgroundBlood-based methods using cell-free DNA (cfDNA) are under development as an alternative to existing screening tests. However, early-stage detection of cancer using tumor-derived cfDNA has proven challenging because of the small proportion of cfDNA derived from tumor tissue in early-stage disease. A machine learning approach to discover signatures in cfDNA, potentially reflective of both tumor and non-tumor contributions, may represent a promising direction for the early detection of cancer.\n\nMethodsWhole-genome sequencing was performed on cfDNA extracted from plasma samples (N=546 colorectal cancer and 271 non-cancer controls). Reads aligning to protein-coding gene bodies were extracted, and read counts were normalized. cfDNA tumor fraction was estimated using IchorCNA. Machine learning models were trained using k-fold cross-validation and confounder-based cross-validation to assess generalization performance.\n\nResultsIn a colorectal cancer cohort heavily weighted towards early-stage cancer (80% stage I/II), we achieved a mean AUC of 0.92 (95% CI 0.91-0.93) with a mean sensitivity of 85% (95% CI 83-86%) at 85% specificity. Sensitivity generally increased with tumor stage and increasing tumor fraction. Stratification by age, sequencing batch, and institution demonstrated the impact of these confounders and provided a more accurate assessment of generalization performance.\n\nConclusionsA machine learning approach using cfDNA achieved high sensitivity and specificity in a large, predominantly early-stage, colorectal cancer cohort. The possibility of systematic technical and institution-specific biases warrants similar confounder analyses in other studies. Prospective validation of this machine learning method and evaluation of a multi-analyte approach are underway.

cancer biology↗

bioRxiv2017

Evolution and clinical impact of genetic epistasis within EGFR-mutant lung cancers

Introductory paragraph Introductory paragraph Main text Methods Author Contributions Author Information References The current understanding of tumorigenesis is largely centered on a monogenic driver oncogene model. This paradigm is incompatible with the prevailing clinical experience in most solid malignancies: monotherapy with a drug directed against an individual oncogenic driver typically results in incomplete clinical responses and eventual tumor progression1-7. By profiling the somatic genetic alterations present in over 2,000 cases of lung cancer, the leading cause of cancer mortality worldwide8,9, we show that combinations of functional genetic alterations, i.e. genetic collectives dominate the landscape of ...

cancer biology↗