Better Protein Function Prediction by Modeling Survivorship Bias

• URL: http://arxiv.org/abs/2605.06879v1
• Date: Thu, 07 May 2026 19:26:38 GMT
• Title: Better Protein Function Prediction by Modeling Survivorship Bias
• Abstract summary: Evo-PU is a learning framework that uses a scientific understanding of nucleotide mutation to model survivorship bias for single-organism sequence data.<n>On three prediction tasks using single-organism uniform-coverage surveillance data, Evo-PU outperforms standard PU learning, one-class classification, and protein language models.
• Score: 4.101866024329502
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Protein sequence data from nature exhibits survivorship bias: we only observe data from those organisms that survive and reproduce, while non-functional protein mutations are eliminated by natural selection. Thus, predicting whether a protein sequence is functional often requires learning from positive examples alone. While positive-unlabeled (PU) learning frameworks offer a generic solution to this problem, existing PU methods ignore the evolutionary processes that shape sequence observability and cause survivorship bias. Consider a sequence that is one mutation away from a commonly-observed protein variant in a well-surveilled organism. If the sequence were functional, it would likely be observed. If it is not observed, this suggests non-functionality. In contrast, sequences that are unlikely to arise through mutation may be missing simply because they never arose. Thus, these two kinds of missing sequences should be treated differently when training models. In this work, we propose Evo-PU, a PU learning framework that uses a scientific understanding of nucleotide mutation to model survivorship bias for well-surveilled single-organism sequence data. On three prediction tasks using single-organism uniform-coverage surveillance data -- predicting results from held-out influenza and respiratory syncytial virus (RSV) mutagenesis studies, and predicting future SARS-CoV-2 variants -- Evo-PU outperforms standard PU learning, one-class classification (OCC), and protein language models (PLMs). On prediction tasks from multi-organism ProteinGym datasets with more heterogeneous surveillance coverage, we identify opportunities to generalize our approach.

Related papers

• Seek and You Shall Fold [0.0]
  Most predictors of experimental observables are non-differentiable, making them incompatible with gradient-based conditional sampling.<n>This is especially limiting in nuclear magnetic resonance, where rich data such as chemical shifts are hard to directly integrate into generative modeling.<n>We introduce a framework for non-differentiable guidance of protein generative models, coupling a continuous diffusion-based generator with any black-box objective via a tailored genetic algorithm.
  arXiv  Detail & Related papers  (2025-11-17T11:07:49Z)
• Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges [51.83259180910313]
  A major bottleneck in gene function analysis is the unpaired nature of single-cell data.<n>We approximate Schrdinger Bridge (SB) to tackle unpaired single-cell perturbation data.<n>Our model effectively captures heterogeneous single-cell responses and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-17T08:27:13Z)
• Boosting In-Silicon Directed Evolution with Fine-Tuned Protein Language Model and Tree Search [67.15159962819979]
  We propose AlphaDE, a novel framework to optimize protein sequences by harnessing the innovative paradigms of large language models.<n>First, AlphaDE fine-tunes pretrained protein language models using masked language modeling on protein sequences to activate the evolutionary plausibility for the interested protein class.<n>Second, AlphaDE introduces test-time inference based on Monte Carlo tree search, which effectively evolves proteins with evolutionary guidance from fine-tuned protein language model.
  arXiv  Detail & Related papers  (2025-11-13T03:00:52Z)
• A Diffusion Model to Shrink Proteins While Maintaining Their Function [35.556730321134275]
  We propose SCISOR, a novel discrete diffusion model that deletes letters from sequences to generate protein samples that resemble those found in nature.<n> SCISOR trains a de-noiser to reverse a forward noising process that adds random insertions to natural sequences.<n>In evaluation, SCISOR achieves state-of-the-art predictions of the functional effects of deletions on ProteinGym.
  arXiv  Detail & Related papers  (2025-11-10T18:46:24Z)
• Evaluating DNA function understanding in genomic language models using evolutionarily implausible sequences [0.25489046505746704]
  We introduce a benchmark called Nullsettes, which assesses how well models can predict in silico loss-of-function (LOF) mutations.<n>We find that most fail to consistently detect strong LOF mutations.<n>All models show a sharp drop in predictive accuracy as the likelihood assigned to the original (nonmutant) sequence decreases.
  arXiv  Detail & Related papers  (2025-06-12T01:28:04Z)
• JanusDDG: A Thermodynamics-Compliant Model for Sequence-Based Protein Stability via Two-Fronts Multi-Head Attention [0.0]
  understanding how residue variations affect protein stability is crucial for designing functional proteins.<n>Recent advances in protein language models (PLMs) have revolutionized computational protein analysis.<n>We introduce JanusDDG, a deep learning framework that leverages PLM-derived embeddings and a bidirectional cross-attention transformer architecture.
  arXiv  Detail & Related papers  (2025-04-04T09:02:32Z)
• G2PDiffusion: Cross-Species Genotype-to-Phenotype Prediction via Evolutionary Diffusion [108.94237816552024]
  We propose the first genotype-to-phenotype diffusion model (G2PDiffusion) that generates morphological images from DNA.<n>The model contains three novel components: 1) a MSA retrieval engine that identifies conserved and co-evolutionary patterns; 2) an environment-aware MSA conditional encoder that effectively models complex genotype-environment interactions; and 3) an adaptive phenomic alignment module to improve genotype-phenotype consistency.
  arXiv  Detail & Related papers  (2025-02-07T06:16:31Z)
• Detecting and Identifying Selection Structure in Sequential Data [53.24493902162797]
  We argue that the selective inclusion of data points based on latent objectives is common in practical situations, such as music sequences. We show that selection structure is identifiable without any parametric assumptions or interventional experiments. We also propose a provably correct algorithm to detect and identify selection structures as well as other types of dependencies.
  arXiv  Detail & Related papers  (2024-06-29T20:56:34Z)
• Learning to Predict Mutation Effects of Protein-Protein Interactions by Microenvironment-aware Hierarchical Prompt Learning [78.38442423223832]
  We develop a novel codebook pre-training task, namely masked microenvironment modeling. We demonstrate superior performance and training efficiency over state-of-the-art pre-training-based methods in mutation effect prediction.
  arXiv  Detail & Related papers  (2024-05-16T03:53:21Z)
• Efficiently Predicting Protein Stability Changes Upon Single-point Mutation with Large Language Models [51.57843608615827]
  The ability to precisely predict protein thermostability is pivotal for various subfields and applications in biochemistry. We introduce an ESM-assisted efficient approach that integrates protein sequence and structural features to predict the thermostability changes in protein upon single-point mutations.
  arXiv  Detail & Related papers  (2023-12-07T03:25:49Z)
• Unsupervised language models for disease variant prediction [3.6942566104432886]
  We find that a single protein LM trained on broad sequence datasets can score pathogenicity for any gene variant zero-shot. We show that it achieves scoring performance comparable to the state of the art when evaluated on clinically labeled variants of disease-related genes.
  arXiv  Detail & Related papers  (2022-12-07T22:28:13Z)
• InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detection [3.5213888068272197]
  anomaly detection (AD) is a well-established field in Machine Learning (ML) We propose to tackle this challenge through anomaly detection (AD) We conduct a large number of experiments on four publicly available datasets.
  arXiv  Detail & Related papers  (2022-10-25T02:08:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.