Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction

• URL: http://arxiv.org/abs/2601.03704v1
• Date: Wed, 07 Jan 2026 08:43:08 GMT
• Title: Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction
• Authors: Wajid Arshad Abbasi, Syed Ali Abbas, Maryum Bibi, Saiqa Andleeb, Muhammad Naveed Akhtar,
• Abstract summary: Trade-off between predictive accuracy and data availability makes it difficult to predict protein--protein binding affinity accurately.<n>We suggest a regression framework based on knowledge distillation that uses protein structural data during training and only needs sequence data during inference.
• Score: 0.22369578015657954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The trade-off between predictive accuracy and data availability makes it difficult to predict protein--protein binding affinity accurately. The lack of experimentally resolved protein structures limits the performance of structure-based machine learning models, which generally outperform sequence-based methods. In order to overcome this constraint, we suggest a regression framework based on knowledge distillation that uses protein structural data during training and only needs sequence data during inference. The suggested method uses binding affinity labels and intermediate feature representations to jointly supervise the training of a sequence-based student network under the guidance of a structure-informed teacher network. Leave-One-Complex-Out (LOCO) cross-validation was used to assess the framework on a non-redundant protein--protein binding affinity benchmark dataset. A maximum Pearson correlation coefficient (P_r) of 0.375 and an RMSE of 2.712 kcal/mol were obtained by sequence-only baseline models, whereas a P_r of 0.512 and an RMSE of 2.445 kcal/mol were obtained by structure-based models. With a P_r of 0.481 and an RMSE of 2.488 kcal/mol, the distillation-based student model greatly enhanced sequence-only performance. Improved agreement and decreased bias were further confirmed by thorough error analyses. With the potential to close the performance gap between sequence-based and structure-based models as larger datasets become available, these findings show that knowledge distillation is an efficient method for transferring structural knowledge to sequence-based predictors. The source code for running inference with the proposed distillation-based binding affinity predictor can be accessed at https://github.com/wajidarshad/ProteinAffinityKD.

Related papers

• Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice [109.9635246405237]
  We show that the experiment conclusions about data quality can flip with even minor adjustments to training hyper parameters.<n>We introduce a simple patch to the evaluation protocol: using reduced learning rates for proxy model training.<n> Empirically, we validate this approach across 23 data recipes covering four critical dimensions of data curation.
  arXiv  Detail & Related papers  (2025-12-30T23:02:44Z)
• On fine-tuning Boltz-2 for protein-protein affinity prediction [1.7607577951969595]
  We adapt Boltz-2, a structure-based protein-ligand affinity predictor, for protein-protein affinity regression.<n>Despite high structural accuracy, Boltz-2-PPI underperforms relative to sequence-based alternatives in both small- and larger-scale data regimes.<n>Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction.
  arXiv  Detail & Related papers  (2025-12-06T23:07:10Z)
• S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening [72.89086338778098]
  We propose a two-stage framework for protein-ligand contrastive representation learning.<n>In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone.<n>In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module.<n>This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement.
  arXiv  Detail & Related papers  (2025-11-10T11:57:47Z)
• Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity [0.0]
  FIRM-DTI is a lightweight framework that conditions molecular embeddings on protein embeddings through a feature-wise linear modulation layer.<n>An RBF regression head operating on embedding distances yields smooth, interpretable affinity predictions.<n>Our results underscore the value of conditioning and metric learning for robust drug-target affinity prediction.
  arXiv  Detail & Related papers  (2025-09-25T02:55:24Z)
• PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs [88.98041407783502]
  PRING is the first benchmark that evaluates protein-protein interaction prediction from a graph-level perspective.<n> PRING curates a high-quality, multi-species PPI network dataset comprising 21,484 proteins and 186,818 interactions.
  arXiv  Detail & Related papers  (2025-07-07T15:21:05Z)
• FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction [3.8366697175402225]
  FlowDock is the first deep geometric generative model that learns to map unbound (apo) structures to their bound (holo) counterparts.<n>FlowDock provides predicted structural confidence scores and binding affinity values with each of its generated protein-ligand complex structures.
  arXiv  Detail & Related papers  (2024-12-14T20:54:37Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• From Static to Dynamic Structures: Improving Binding Affinity Prediction with Graph-Based Deep Learning [40.83037811977803]
  Dynaformer is a graph-based deep learning model developed to predict protein-ligand binding affinities. It exhibits state-of-the-art scoring and ranking power on the CASF-2016 benchmark dataset. In a virtual screening on heat shock protein 90 (HSP90), 20 candidates are identified and their binding affinities are experimentally validated.
  arXiv  Detail & Related papers  (2022-08-19T14:55:12Z)
• EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models [53.17320541056843]
  We propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network. Our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
  arXiv  Detail & Related papers  (2021-05-11T03:40:29Z)
• Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction [3.499870393443268]
  Deep learning approaches can predict drug-protein interactions without trial-and-error by humans. We propose two methods to construct a deep learning framework that exhibits superior performance with a small labeled dataset.
  arXiv  Detail & Related papers  (2020-12-15T10:24:34Z)
• Transfer Learning for Protein Structure Classification at Low Resolution [124.5573289131546]
  We show that it is possible to make accurate ($geq$80%) predictions of protein class and architecture from structures determined at low ($leq$3A) resolution. We provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function.
  arXiv  Detail & Related papers  (2020-08-11T15:01:32Z)

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.