This abstract reviews recent methods for predicting protein-ligand binding affinity.
problem Predicting protein-ligand binding affinity for various applications in life sciences.
method Traditional and deep learning models for binding affinity prediction.
result Improved predictive performance of AI-driven models.
DeepDTA predicts drug-target binding affinities using deep learning.
problem Predicting the continuum of binding strength values between drugs and targets.
method Uses deep learning, specifically CNNs, to model 1D representations of drug and target sequences.
result Deep learning model outperforms state-of-the-art methods in predicting DT binding affinities.
WideDTA predicts drug-target binding affinity using text-based information.
problem Predicting drug-target binding affinity is a major challenge in drug discovery.
method WideDTA uses chemical and biological textual sequence information, including protein sequence, ligand SMILES, protein domains and motifs, and maximum common substructure words.
result WideDTA outperformed DeepDTA on the KIBA dataset, indicating the word-based sequence representation is a promising alternative.
PANDA predicts protein binding affinity changes from sequences, outperforming existing methods.
problem Accurately predicting changes in protein binding affinity due to mutations.
method Sequence-based machine learning approach using protein sequence information.
result PANDA achieves higher Pearson correlation coefficients than existing methods.
Deep learning predicts protein-ligand binding affinity with high accuracy.
problem Predicting protein-ligand binding affinity for drug discovery.
method 3D convolutional neural network trained on CASF and Astex Diverse Set benchmarks.
result Deep learning model outperformed classical scoring functions.
ChemBoost predicts protein-ligand binding affinity using SMILES syntax.
problem Predicting high affinity drug-target interactions from sequence similarity alone.
method ChemBoost uses SMILES syntax to represent ligands as documents and proteins as sequences or ligand-centric features. It learns chemical word embeddings and predicts affinities using eXtreme Gradient Boosting.
result ChemBoost outperforms state-of-the-art systems in predicting protein-ligand affinities.
We propose a specialized string kernel for small bio-molecules, peptides and pseudo-sequences of binding interfaces. The kernel incorporates physico-chemical properties of amino acids and elegantly generalize eight kernels, such as the Oligo, the Weighted Degree, the Blended Spectrum, and the Radial Basis Function. We …
Active learning speeds up antibody affinity prediction.
problem Challenging to identify mutations enhancing antibody affinity.
method Iterative proposal of promising sequences for simulation.
result Accelerates search for improved binders.
Co-Diffusion predicts drug-target affinity by learning latent manifolds and diffusion, improving generalization.
problem Cold-start regimes in drug-target affinity prediction due to label scarcity and domain shifts.
method Two-stage framework: latent manifold alignment and latent diffusion regularization.
result Significantly outperforms state-of-the-art baselines, especially in zero-shot generalization.
Empirical scoring functions based on either molecular force fields or cheminformatics descriptors are widely used, in conjunction with molecular docking, during the early stages of drug discovery to predict potency and binding affinity of a drug-like molecule to a given target. These models require expert-level knowled…
A new method predicts compounds for orphan proteins.
problem Predicting binding affinities for orphan proteins.
method Corresponding projections for transfer learning.
result The method outperforms state-of-the-art in orphan screening.
This paper presents regression models obtained from a process of blind prediction of peptide binding affinity from provided descriptors for several distinct datasets as part of the 2006 Comparative Evaluation of Prediction Algorithms (COEPRA) contest. This paper finds that kernel partial least squares, a nonlinear part…
Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding an…
Two ML frameworks predict antibody properties using structural data.
problem Predicting antibody properties using sequence and structural data.
method ANTIPASTI and INFUSSE models using graph representations and neural networks.
result ANTIPASTI predicts binding affinity; INFUSSE predicts residue flexibility.
NucleusDiff models atomic nuclei interactions to prevent separation violations in drug design.
problem Maintaining minimum pairwise distance between atoms to avoid separation violations in drug design.
method Enforces distance constraint between atomic nuclei and manifolds in a diffusion model.
result Reduces separation violations by up to 100.00% and enhances binding affinity by up to 22.16%.
GEFA predicts drug-target affinity using graph neural networks.
problem Accurate prediction of drug-target interactions for rapid drug repurposing.
method GEFA (Graph Early Fusion Affinity) is a novel graph-in-graph neural network with attention mechanism.
result GEFA effectively models drug-target interactions, demonstrating the effectiveness of pre-trained protein embedding and nested graph representation.
GCPNet improves molecular graph learning for protein structure and binding.
problem Learning from 3D molecular graphs for protein structure and binding.
method SE(3)-equivariant graph neural network for 3D molecular graphs.
result GCPNet achieves state-of-the-art performance in multiple molecular tasks.
NeuralMD accelerates protein-ligand binding simulations 1Kx faster.
problem Accurate and efficient simulation of protein-ligand binding dynamics.
method Physics-informed multi-grained group symmetric framework with BindingNet and augmented neural differential equation solver.
result Achieves over 1Kx speedup and up to 15x reduction in reconstruction error compared to standard methods.
CogMol designs novel drug-like molecules for SARS-CoV-2 targets.
problem Designing efficient drugs for novel viral proteins.
method End-to-end framework combining VAE, controlled sampling, and predictors.
result Highly selective and affinity molecules for SARS-CoV-2 targets.
Visualizes 3D CNNs for protein-ligand scoring.
problem Interpreting complex neural network decisions for protein-ligand scoring.
method Three visualization methods for 3D CNNs, including filters and weights.
result Visualizations aid in tuning and designing neural networks.
PADME predicts drug-target interaction strengths using deep learning.
problem Challenges in drug-target interaction prediction, especially for cold-target problems.
method PADME uses deep neural networks to predict real-valued interaction strengths between compounds and proteins, handling cold-target problems.
result PADME consistently outperforms baseline methods on multiple datasets, including the ToxCast dataset.
New method models aptamer libraries as Boltzmann-weighted graph ensembles for better affinity predictions.
problem Anomalous candidates in SELEX datasets obscure true aptamer-ligand affinity.
method Boltzmann graph ensemble embeddings for thermodynamically parameterized exponential-family random graphs.
result Proposed embedding enables robust community detection and subgraph-level explanations for aptamer ligand affinity.
Proposes a meta-loss function for regression and classification using privileged information.
problem Improving prediction performance in machine learning problems using privileged information.
method A simple yet effective custom loss function for regression and classification.
result The proposed model outperforms state-of-the-art predictors in protein binding affinity prediction.
iDeepA predicts RNA-protein binding sites from RNA sequences using a CNN with attention.
problem Predicting RNA-protein binding sites from raw RNA sequences efficiently.
method Attention based convolutional neural network (iDeepA) encoding RNA sequences into one-hot encoding, followed by a CNN with an attention mechanism.
result iDeepA achieves comparable performance to state-of-the-art methods on CLIP-seq data.
Deep learning model predicts protein-ligand binding modes from docking data.
problem Improving protein-ligand binding mode prediction accuracy.
method Dual-graph architecture with separate sub-networks for ligand topology and protein-ligand interactions.
result Deep learning model outperforms docking programs in binding mode prediction.
Flexible Kernels for Protein Property Prediction
problem Predicting protein properties from sparse experimental data
method Sequence kernels using evolutionary substitution matrices and local linearity
result Data-efficient models of protein property landscapes
Prototype Matching Network (PMN) improves genomic TFBS prediction.
problem Predicting Transcription Factor Binding Sites (TFBSs) with hundreds of TFs as labels.
method Prototype Matching Network (PMN) that learns motif-like features and TF-TF interactions.
result PMN significantly outperforms baselines on a large TFBS dataset.
Framework designs antiviral drugs using deep learning and RL.
problem Designing effective antiviral drugs for SARS-CoV-2.
method Deep learning framework with conditional molecular generator and RL.
result Framework generates more antiviral ligands than a VAE baseline.
Paper presents a new model to predict peptide:MHC-II interactions.
problem Predicting peptide interactions with MHC-II for vaccine design and immune response understanding.
method Developed a trans-allelic prediction model using sequence and structural data.
result Model predicts interactions for all three human MHC-II loci and performs comparably to state-of-the-art methods.
SILVR generates new molecules fitting protein binding sites.
problem Generating novel small molecule compounds for drug design.
method Selective Iterative Latent Variable Refinement (SILVR) for diffusion-based molecule generation.
result SILVR can generate new molecules similar in shape to original fragments without protein knowledge.
New method for manifold topological learning avoids remeshing issues.
problem Persistent homology on manifolds is numerically inconsistent.
method Persistent de Rham-Hodge Laplacians in Eulerian representation.
result Avoids numerical inconsistency over multiscale manifolds.
DeepRAM evaluates and selects the best deep learning architecture for DNA/RNA binding specificity prediction.
problem Selecting the best deep learning architecture for predicting DNA/RNA binding specificity.
method Systematic exploration of various deep learning architectures using deepRAM, an end-to-end deep learning tool.
result A k-mer embedding convolutional layer and recurrent layer architecture outperforms other methods.
AntBO optimizes antibody design using Bayesian optimization for efficient and effective CDRH3 sequence generation.
problem Designing optimal antigen-specific CDRH3 regions in antibody design due to combinatorial sequence space.
method Combinatorial Bayesian optimization framework with trust region for developability.
result AntBO designs CDRH3 regions with diverse biophysical properties and outperforms existing methods.
A new method uses IVA to fuse diverse molecular features for better machine learning predictions.
problem Challenges in selecting features for accurate molecular property prediction.
method Independent Vector Analysis (IVA) for fusing multiple molecular feature vectors into a single, compact set.
result Improved prediction performance of regression models for molecular properties.
InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.
problem Modeling noncovalent protein-ligand interactions with graph neural networks.
method InteractionNet uses a GNN architecture with separated covalent and noncovalent convolution layers and layer-wise relevance propagation for explainability.
result InteractionNet successfully predicts noncovalent protein-ligand interactions with chemical relevance.
AFP-CKSAAP predicts antifreeze proteins using k-spaced amino acid pairs with deep neural networks.
problem Predicting antifreeze proteins due to their diverse sequence characteristics.
method Deep neural network with skipped connections and ReLU non-linearity to learn protein sequence descriptors.
result AFP-CKSAAP achieves excellent prediction scores and high Youden's index (0.82) on independent dataset.
Novel parallel GNN predicts protein-ligand interactions with high accuracy.
problem Accurate prediction of protein-ligand interactions for drug design.
method Parallel Graph Neural Networks (GNN) integrating 3D structural data.
result GNN achieves high accuracy in predicting binary interactions and activity.
In cheminformatics, compound-target binding profiles has been a main source of data for research. For data repositories that only provide positive profiles, a popular assumption is that unreported profiles are all negative. In this paper, we caution audience not to take this assumption for granted, and present empirica…
Study on binding numbers of tight contact structures on lens spaces L(n,1).
problem Determining the minimum number of binding components for tight contact structures on lens spaces.
method Using the d3-invariant, restrictions on planar monodromy factorizations, and the Durst-Kegel algorithm. result The binding number of universally tight contact structures on L(n,1) is equal to n. Optimizes ligand binding poses using CNNs and atomic grids.
problem Improving the accuracy of docking predictions for drug discovery.
method Differentiable atomic grid representation, CNN for scoring and optimization.
result Iteratively-trained CNNs outperform single CNNs in optimizing poses.
Motivation: Prediction of ligands for proteins of known 3D structure is important to understand structure-function relationship, predict molecular function, or design new drugs. Results: We explore a new approach for ligand prediction in which binding pockets are represented by atom clouds. Each target pocket is compar…
We attempt to set a mathematical foundation of immunology and amino acid chains. To measure the similarities of these chains, a kernel on strings is defined using only the sequence of the chains and a good amino acid substitution matrix (e.g. BLOSUM62). The kernel is used in learning machines to predict binding affinit…
The paper proposes a method to reliably select design algorithms for machine learning-guided design tasks.
problem Choosing the right design algorithm for machine learning-guided design tasks.
method Combining designs' predicted property values with held-out labeled data to reliably forecast characteristics of the label distributions produced by different design algorithms.
result The method is guaranteed to return design algorithms that yield successful label distributions.
The study shows examples of contact 3-manifold binding sums that fail to preserve certain properties.
problem Examples of contact 3-manifold binding sums that fail to preserve properties like tightness or symplectic fillability.
method Examples and proofs of vanishing Heegaard Floer contact invariant for Stein fillable manifolds.
result Binding sums of contact 3-manifolds do not preserve properties such as tightness or symplectic fillability.
Protein Thoughts interprets protein interactions with clear reasoning, improving prediction accuracy.
problem Lack of mechanistic justification in protein-protein interaction predictions.
method Interpretable search problem reformulation, hypothesis-guided entropy-regularized Tree-of-Thoughts search, embedding-space flow matching.
result Improves mean best-binder rank from 47.7 to 11.2 on SHS148k benchmark.
New method shows links can be braided open book bindings.
problem Understanding fibered links and their bindings.
method Mutual arc presentations and braided open books.
result Every fibered link is the binding of a braided open book.
Study optimal policies under budget and coverage constraints.
problem Optimal policy learning with budget and coverage constraints.
method Combination of knapsack structure, affine threshold rule, linear programming relaxation, Greedy-Lagrangian (GLC), and rank-and-cut (RC) algorithms.
result GLC closely approximates the optimal solution and achieves near-optimal performance in finite samples; RC is approximately optimal under certain conditions.
Stochastic gradient descent improves Gaussian process regression.
problem Efficiently solving large linear systems in Gaussian process regression.
method Developed a stochastic dual descent algorithm using insights from optimisation and kernel communities.
result Stochastic gradient descent is highly effective when done right.