Benchmarking Single-Pose Docking, Consensus Rescoring, and Supervised ML on the LIT-PCBA Library: A Critical Evaluation of DiffDock, AutoDock-GPU, GNINA, and DiffDock-NMDN

• URL: http://arxiv.org/abs/2605.01681v2
• Date: Tue, 05 May 2026 02:26:48 GMT
• Title: Benchmarking Single-Pose Docking, Consensus Rescoring, and Supervised ML on the LIT-PCBA Library: A Critical Evaluation of DiffDock, AutoDock-GPU, GNINA, and DiffDock-NMDN
• Abstract summary: We perform a large-scale evaluation on the LIT-PCBA library (15 targets, 578,295 ligand-target pairs with experimentally confirmed actives and inactives)<n>We compare AutoDock-GPU and DiffDock for pose generation, followed by rescoring with GNINA and NMDN.<n>GNINA rescoring of AutoDock-GPU poses emerged as the strongest single method with a median EF1% of 2.14.<n>We conclude that no single docking method dominates across targets and that rigorously validated, cost-effective combinations with supervised re-ranking currently offer the most practical value for virtual screening.
• Score: 5.044804163732797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Virtual screening performance depends heavily on the chosen docking and scoring methods. Recent AI-based tools such as DiffDock and NMDN have reported strong benchmark results, but their practical utility on realistic, experimentally-derived datasets remains unclear. Here we perform a large-scale evaluation on the LIT-PCBA library (15 targets, 578,295 ligand-target pairs with experimentally confirmed actives and inactives). We compare AutoDock-GPU and DiffDock for pose generation, followed by rescoring with GNINA and NMDN. We further evaluate rank-based consensus strategies and supervised machine learning models trained on docking features. GNINA rescoring of AutoDock-GPU poses (AutoDock-GNINA) emerged as the strongest single method with a median EF1% of 2.14. DiffDock-based approaches underperformed relative to AutoDock-GNINA, particularly on challenging targets such as OPRK1. Carefully designed consensus ranking improved robustness but did not surpass the best single scorer. Supervised ML re-ranking delivered the largest gains, achieving a median EF1% of 4.49 (+110% over AutoDock-GNINA). Our results highlight that even the best classical+ML hybrid workflows provide only modest early enrichment on realistic benchmarks. We conclude that no single docking method dominates across targets and that rigorously validated, cost-effective combinations with supervised re-ranking currently offer the most practical value for virtual screening.

Related papers

• Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation [15.119045051735633]
  We propose an RL fine-tuning framework that uses autonomous vision-language evaluation as a scalable supervision signal for GUI agents.<n>Because autonomous evaluators are imperfect, we model their feedback as a noisy binary reward channel and derive a noise-corrected reward estimator.<n>Experiments show that corrected evaluator rewards outperform both zero-shot baselines and raw evaluator rewards, improving success rates by an average of 12.6 percentage points over zero-shot performance and 5.1 points over raw evaluator fine-tuning.
  arXiv  Detail & Related papers  (2026-06-23T12:46:29Z)
• Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward [69.99652051809737]
  In this work, we propose Verifier-free Intrinsic Gradient-Norm Reward (VIGOR)<n>VIGOR is a simple reward that uses only the policy model itself.<n>It exhibits cross-domain transfer to code benchmarks when trained only on math data.
  arXiv  Detail & Related papers  (2026-05-11T03:15:37Z)
• An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation [50.09718257952108]
  Sequentialsolv has increasingly shifted toward generative recommenders that combine sequential patterns with semantic item information.<n>These methods are often evaluated on a small set of widely used benchmarks, raising a key question: do these benchmarks actually require the advanced modeling capabilities that modern generative recommenders claim to provide?<n>We conduct a benchmark audit with an intentionally simple graph. Starting from only the last one or two items, it retrieves candidates from a few-hop item-transition graph and ranks them by item-feature similarity.
  arXiv  Detail & Related papers  (2026-05-08T02:00:11Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking [5.313085467302315]
  This study introduces an enhanced system, MC-GNNAS-Dock, with three key advances.<n>First, a multi-criteria evaluation integrates binding-pose accuracy (RMSD) with validity checks from PoseBusters, offering a more rigorous assessment.<n>Second, architectural refinements by inclusion of residual connections strengthen predictive robustness.<n>Third, rank-aware loss functions are incorporated to sharpen rank learning.
  arXiv  Detail & Related papers  (2025-09-30T15:08:41Z)
• PoseX: AI Defeats Physics Approaches on Protein-Ligand Cross Docking [74.76447568426276]
  PoseX is an open-source benchmark to evaluate both self-docking and cross-docking.<n>We incorporated 23 docking methods in three methodological categories.<n>We developed a relaxation method for post-processing to minimize conformational energy and refine binding poses.
  arXiv  Detail & Related papers  (2025-05-03T05:35:37Z)
• Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows [0.0]
  We employ a fully automatic workflow using the Surflex-Dock methods to generate a fair baseline for conventional docking approaches.<n>For known binding site condition, Surflex-Dock success rates at 2.0 Angstroms RMSD far exceeded those for DiffDock.<n> DiffDock exhibited a 40 percentage point difference on near-neighbor cases compared with cases with no near-neighbor training.
  arXiv  Detail & Related papers  (2024-12-03T22:47:47Z)
• DSDP: A Blind Docking Strategy Accelerated by GPUs [6.221048348194304]
  We take the advantage of both traditional and machine-learning based methods, and present a method Deep Site and Docking Pose (DSDP) to improve the performance of blind docking. DSDP reaches a 2 top-1 success rate (RMSD 2 AA) on an unbiased and challenging test dataset with 1.2 s wall-clock computational time per system. Its performances on DUD-E dataset and the time-split PDBBind dataset used in EquiBind, TankBind, and DiffDock are also effective.
  arXiv  Detail & Related papers  (2023-03-16T07:00:21Z)
• Efficient Person Search: An Anchor-Free Approach [86.45858994806471]
  Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN. In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs.
  arXiv  Detail & Related papers  (2021-09-01T07:01:33Z)
• Disentangle Your Dense Object Detector [82.22771433419727]
  Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. We propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2021-07-07T00:52:16Z)
• MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation [153.56211546576978]
  In this work, we propose that better soft targets with higher compatibil-ity can be generated by using a label generator. We can employ the meta-learning technique to optimize this label generator. The experiments are conducted on two standard classificationbenchmarks, namely CIFAR-100 and ILSVRC2012.
  arXiv  Detail & Related papers  (2020-08-27T13:04:27Z)
• Fully Convolutional Online Tracking [47.78513247048846]
  We present a fully convolutional online tracking framework, coined as FCOT, for both classification and regression branches. Our key contribution is to introduce an online regression model generator (RMG) for initializing weights of the target filter with online samples. Thanks to the unique design of RMG, our FCOT can not only be more effective in handling target variation along temporal dimension thus generating more precise results.
  arXiv  Detail & Related papers  (2020-04-15T14:21:57Z)

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.