AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Non-identifiability and the Blessings of Misspecification in Models of Molecular Fitness

Eli N Weinstein, Alan Nawzad Amin, Jonathan Frazer, Debora Susan Marks

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein fitness and variant effect prediction · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
relax parametric AR model toward nonparametric BEAR (higher h) (ablation)Autoregressive fitness model · Fitness estimation (Spearman) vs density estimationfitness estimation vs likelihoodMixed
use misspecified parametric fitness models instead of true data densitySWI, EVE, Wavenet · Functional assays (37)Spearman correlation vs assay: 35/37 (95%) SWI, 35/37 (95%) EVE, 36/37 (97%) Wavenet beat data densityImproved
use misspecified parametric models instead of true data densitySWI, EVE · Pathogenicity prediction (97 genes)AUROC: 31/97 (32%) SWI, 46/97 (47%) EVE beat data densityMixed
nonparametric BEAR instead of Wavenet for density estimationDensity estimation · Functional assays (37)held-out predictive performance: better on 27/37 assays (73%)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy