MFASS: What Three Splice-Variant Rankers Put in the First 100
The baseline, SpliceAI and Pangolin found 61, 64 and 65 disruptions in their top 100 MFASS variants. The differences do not establish a reliable winner.
Writing on machine learning in genomics, proteins, and drug discovery.
What our biology benchmark scores actually counted
A recall reversal and two constant-prediction controls show why benchmark comparisons need populations, selection rules and reference scores.
Read article →
Articles
All articles →
An RNA Sequence Is Not a Molecular State: RNA Foundation Models in 2026
RNA models share an alphabet, not an estimand: choose them by molecular object, output, information inputs, evidence class, and artifact contract.
A DNA Likelihood Is Not a Functional Assay: Genomic Foundation Models in 2026
A genomic model result is credible only when its tokenisation, strand rule, biological target, evaluation split, and artifact terms are explicit.
A Generated Protein Is Not a Result: Protein Design in 2026
Protein generators propose different biological objects. A defensible design starts with the assay, records the complete computational stack, and preserves every experimental denominator.
A Protein Embedding Is Not an Explanation: Protein Language Models in 2026
A practical guide to choosing, extracting, adapting and validating protein language-model representations without mistaking a system score for biological generalisation.
An Antibody Sequence Is Not a Research Plan: Antibody Foundation Models in 2026
A task-first guide to antibody representations, structure prediction, CDR design, humanisation and developability, with the evidence and reproducibility checks that model scores leave out.
Topics
All topics →
Genomics & DNA models
24 postsSequence models, variant-effect prediction, and the work to read non-coding DNA.
Explore topic→
Proteins & structure
5 postsSingle-sequence folding, protein language models, and structure without alignment.
Explore topic→
Drug discovery
3 postsContrastive screening, protein–ligand interaction, and design that survives the wet lab.
Explore topic→
Interpretability & evaluation
2 postsWhat models encode, where they fail, and how evaluation and oversight hold up.
Explore topic→