Hash Collisions in Molecular Fingerprints: Effects on Property Prediction and Bayesian Optimization

• URL: http://arxiv.org/abs/2511.17078v1
• Date: Fri, 21 Nov 2025 09:31:42 GMT
• Title: Hash Collisions in Molecular Fingerprints: Effects on Property Prediction and Bayesian Optimization
• Abstract summary: Molecular fingerprinting methods use hash functions to create fixed-length vector representations of molecules.<n>Hash collisions cause distinct substructures to be represented with the same feature, leading to overestimates in molecular similarity calculations.<n>We find that using exact fingerprints yields a small yet consistent improvement in predictive accuracy on five molecular property prediction benchmarks.
• Score: 4.157678834755669
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Molecular fingerprinting methods use hash functions to create fixed-length vector representations of molecules. However, hash collisions cause distinct substructures to be represented with the same feature, leading to overestimates in molecular similarity calculations. We investigate whether using exact fingerprints improves accuracy compared to standard compressed fingerprints in molecular property prediction and Bayesian optimization where the underlying predictive model is a Gaussian process. We find that using exact fingerprints yields a small yet consistent improvement in predictive accuracy on five molecular property prediction benchmarks from the DOCKSTRING dataset. However, these gains did not translate to significant improvements in Bayesian optimization performance.

Related papers

• Hyper-Dimensional Fingerprints as Molecular Representations [2.5082404486343424]
  Hyperdimensional fingerprints replace learned transformations of message-passing neural networks with operations on high-dimensional vectors.<n> HDF outperforms conventional fingerprints in the majority of tasks while exhibiting greater consistency across datasets and models.<n>We show how HDF-based surrogate models achieve substantially improved sample efficiency in regimes where Morgan fingerprints perform comparably to random search.
  arXiv  Detail & Related papers  (2026-04-30T12:53:58Z)
• Molecular Fingerprints Are Strong Models for Peptide Function Prediction [0.0]
  Long-range molecular interactions are often assumed to require modeling complex graph neural networks and pretrained transformers.<n>We investigate if simple, domain-specific molecular fingerprints can capture peptide function without these assumptions.<n>Our results challenge the presumed necessity of long-range interaction modeling and highlight molecular fingerprints as efficient, interpretable, and computationally lightweight alternatives for peptide prediction.
  arXiv  Detail & Related papers  (2025-01-29T10:05:27Z)
• ADMET property prediction through combinations of molecular fingerprints [0.0]
  Random forests or support vector machines paired with extended-connectivity fingerprints consistently outperformed recently developed methods. A detailed investigation into regression algorithms and molecular fingerprints revealed gradient-boosted decision trees. We successfully validated our model across 22 Therapeutics Data Commons ADMET benchmarks.
  arXiv  Detail & Related papers  (2023-09-29T22:39:18Z)
• ProxyFAUG: Proximity-based Fingerprint Augmentation [81.15016852963676]
  ProxyFAUG is a rule-based, proximity-based method of fingerprint augmentation. The best performing positioning method on this dataset is improved by 40% in terms of median error and 6% in terms of mean error, with the use of the augmented dataset.
  arXiv  Detail & Related papers  (2021-02-04T15:59:30Z)
• Bayesian Graph Neural Networks for Molecular Property Prediction [15.160090982544867]
  This study benchmarks a set of Bayesian methods applied to a directed MPNN, using the QM9 regression dataset. We find that capturing uncertainty in both readout and message passing parameters yields enhanced predictive accuracy, calibration, and performance on a downstream molecular search task.
  arXiv  Detail & Related papers  (2020-11-25T22:32:54Z)
• CIMON: Towards High-quality Hash Codes [63.37321228830102]
  We propose a new method named textbfComprehensive stextbfImilarity textbfMining and ctextbfOnsistency leartextbfNing (CIMON) First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes.
  arXiv  Detail & Related papers  (2020-10-15T14:47:14Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)
• Generative Semantic Hashing Enhanced via Boltzmann Machines [61.688380278649056]
  Existing generative-hashing methods mostly assume a factorized form for the posterior distribution. We propose to employ the distribution of Boltzmann machine as the retrievalal posterior. We show that by effectively modeling correlations among different bits within a hash code, our model can achieve significant performance gains.
  arXiv  Detail & Related papers  (2020-06-16T01:23:39Z)
• Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and Self-Control Gradient Estimator [62.26981903551382]
  Variational auto-encoders (VAEs) with binary latent variables provide state-of-the-art performance in terms of precision for document retrieval. We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing. This new semantic hashing framework achieves superior performance compared to the state-of-the-arts.
  arXiv  Detail & Related papers  (2020-05-21T06:11:33Z)

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.