Journal of Chemical Information and Modeling

Biased signaling occurs when a ligand preferentially activates a specific signaling pathway at a certain receptor within a particular cellular environment. As pharmaceuticals, functionally selective (biased) compounds can engage beneficial signaling pathways while avoiding those linked to adverse effects, resulting in safer and targeted therapeutics. However, existing experimental methods for characterizing ligand bias are often time-consuming and costly, and they hardly elucidate the structural basis of biased signaling. Here, we present microswitch-guided sampling (MGS), a computational method that uses conformational changes in molecular switches to assess ligand bias in G protein-coupled receptor systems. Using initial 2 s all-atom molecular dynamics simulations of the {beta}1-adrenergic receptor ({beta}1AR), the chemokine receptor CXCR3, and the -opioid receptor (OR) in complex with either G protein or {beta}-arrestin and known biased ligands, we identified microswitches whose conformational changes were linked to activation of a specific signaling pathway. We then sampled simulation trajectories for representative complex conformations selected at these microswitch-change time points and used them as starting points for 500 ns ligand-swapped simulations, in which we exchanged biased ligands between complexes. We observed clear differences in conformational changes between complexes bound to pathway-activating and non-activating ligands in at least two of three replicas across all examined systems, demonstrating that MGS can distinguish G protein-biased from {beta}-arrestin-biased ligands. These findings show that MGS is an effective tool for assessing signaling pathway bias in GPCR systems and suggest that this methodology can be applied to other GPCR targets to act as a fast, ns-scale computational assay to detect functional selectivity with molecular dynamics.

Drug resistance often emerges through mutations that reshape protein conformational ensembles, allowing inhibitor potency to be altered without directly disrupting protein-ligand contacts. Consequently, the molecular mechanisms underlying these effects remain difficult to identify, hindering the design of inhibitors with durable potency against rapidly evolving drug targets. To address this challenge, we developed ROBUST, a physics-informed machine learning framework that integrates experimental measurements, molecular dynamics simulations, and interpretable statistical modeling to identify energetic determinants of inhibitor potency. Using HIV-1 protease as a stringent model system for drug resistance, we determined 157 new inhibition constants and integrated them with prior measurements to establish a comprehensive experimental dataset of 364 protease-inhibitor pairs. Analysis of the corresponding molecular dynamics simulations revealed a compact network of energetic interactions that quantitatively explains how resistance mutations and inhibitor modifications jointly reshape molecular recognition and inhibitor potency across the multidimensional resistance landscape. Models constructed from these energetic signatures predicted binding free energies with high accuracy (RMSE < 1 kcal mol-1) and successfully generalized to unseen darunavir analogs. Importantly, ROBUST accurately prioritized unseen analogs based on their potency across the variant set, demonstrating its utility for identifying compounds with improved resistance profiles. Together, these results uncover the energetic principles through which resistance mutations and inhibitor modifications alter potency and establish ROBUST as a mechanistically interpretable framework for translating these insights into resistance-aware inhibitor optimization against rapidly evolving drug targets.

Proteolysis-targeting chimeras (PROTACs) are large, flexible molecules that frequently extend beyond conventional drug-like chemical space, including Lipinski's rule-of-five boundaries. Their membrane permeability has often been linked to molecular chameleonicity and the ability to adopt compact conformations with reduced polar surface exposure; however, the underlying conformational determinants remain unclear. Here, we investigated 20 PROTACs spanning distinct passive-permeability classes using enhanced-sampling molecular dynamics (ES-MD). All permeability classes accessed compact states with low radius of gyration (Rg) and polar surface area (PSA), indicating that compact-state accessibility alone does not distinguish permeable from non-permeable PROTACs. We therefore introduce maximum ring size (MRS), defined as the size of the largest intramolecular hydrogen-bonded ring, as a metric for identifying compact conformations stabilized by long-range intramolecular hydrogen bonding. Like the other descriptors examined, MRS neither separates nor ranks the permeability classes, but helps locate folded states in the large ensemble. Representative compact conformations from selected highly permeable, moderately permeable, and non-permeable compounds were subsequently examined by all-atom unbiased MD in water and chloroform. The highly permeable PROTAC held a closed-flat ensemble in both environments, but in two structurally distinct arrangements, whereas the other two redistributed across heterogeneous ensembles. Passive diffusion therefore appears to depend on the population, stability, and environment-dependent persistence of permeable-like states rather than on compactness alone.

Predicting ligand efficacy is a critical challenge in drug discovery, as a target's functional response is often determined by the way a ligand shifts conformational equilibria between different functional states, a process that is particularly intricate in ion channels. We classify ligands based on the difference of their binding free energies on putative active and inactive conformations, calculated via free energy perturbation (FEP) for 78 protein-ligand pairs across six ion channels from four structural superfamilies: GluA2, GABAAR {rho}1, 3{beta}4 nAChR, 5-HT3AR, TRPML1, and KCNQ2. This approach accurately distinguishes agonists from antagonists across all these ion-channel families with large or subtle structural differences, including at membrane-facing sites, and enables quantitative prediction of maximum response and partial agonism. Importantly, we find that local binding-pocket conformations encode the bound ligand's efficacy even when global channel states are ambiguous. Our results demonstrate that state-specific binding thermodynamics provides a robust framework for leveraging ion channel structures of diverse conformational states to elucidate mechanisms of action and to advance ion-channel drug discovery beyond simple affinity measurements, enabling the identification of new chemical matter with desired functional attributes.

Allosteric and cryptic binding sites provide unique opportunities in drug discovery for achieving selectivity, reducing toxicity and unlocking challenging therapeutical targets. Yet, cryptic pockets are particularly elusive in that they are difficult to capture with experimental methodologies, and therefore often remain undetected. Computational approaches for flexible cryptic site detection traditionally involve extensive unbiased molecular dynamics simulations, or more efficient but computationally still highly demanding biased MD alternatives that make use of enhanced sampling along low-frequency motions of the protein structure. Here we utilize a new variant of the recently introduced and orders of magnitude faster, MD-free COVIB algorithm to identify cryptic pockets efficiently in two challenging targets, the KRAS oncoprotein and the N-terminal domain of the STAT5B transcription factor. Using experimental and AI-modelled structures, respectively, we identify numerous cryptic sites, some of which have not yet been reported. The sites are prioritized and validated with our pharmacophore optimized photoaffinity-tagged fragment library via MS-based peptide mapping and NMR spectroscopy. Besides identifying new, targetable regions on the surface of these important oncotargets, we have established a protocol combining COVIB-based cryptic pocket detection and photoaffinity-based experimental peptide mapping as a robust approach for exploring unique and tractable cryptic pockets.

Within the ADMET continuum, metabolism and excretion (ME) form a critical bridge between drug exposure established by absorption and distribution and downstream efficacy and toxicity. However, no existing framework for drug ME prediction has simultaneously achieved broad coverage of endpoints and robust data recency and completeness. Here, we developed MetExPred, a multi-view prediction framework that comprises 17 classification endpoints and two regression endpoints, covering the overall drug ME process. The framework combines sequence-based and graph-based molecular representations, while optionally incorporating ESM-2 protein representations when experimentally annotated targets are available. A protein-aware masking strategy enables the same architecture to operate in both molecular-only and target-enhanced settings, and multi-view attention adaptively integrates the available representations. Across the classification tasks, MetExPred achieved mean AUROC, AUPRC and F1 scores of 0.844, 0.734 and 0.697, respectively. For clearance and half-life prediction, the model achieved RMSE values of 0.686 and 0.668. MetExPred showed the strongest average performance among the evaluated baselines, while ablation studies confirmed the complementary contributions of molecular sequence, graph and protein information. These results provide a unified and flexible modeling framework for systematic ME prediction of drug compounds, enabling early-stage virtual screening and pharmacokinetic assessment during lead optimization.

Hit-to-lead optimization is a multi-objective molecular-design problem in which binding-related scores must be considered together with drug-likeness and synthetic accessibility. We developed a closed-loop language-model medicinal-chemistry agent that combines target and starting-hit context, PubMed retrieval, molecular-property tools, docking, and feedback from previously scored analogues. In a matched computational benchmark comprising six kinase targets, six methods, a 40-candidate budget, and six independent campaigns per method, the agent achieved the highest mean aggregate score under a pre-specified composite objective on four targets. Re-analysis of the same candidate sets with drug-likeness-gated docking and docking-drug-likeness hypervolume produced different target-level winners, showing that evaluation rules can change the comparative interpretation of an optimization campaign. Candidate distributions and component ablations indicated that the agent's advantage was associated primarily with retention of scored-candidate feedback and higher-QED regions rather than with docking alone. An EGFR case study illustrates a scaffold-preserving in-silico optimization trajectory from erlotinib. The study is a computational benchmark and evaluation framework; the prioritized molecules are hypotheses for subsequent experimental testing, not experimentally validated leads.

Peptides containing noncanonical amino acids (ncAAs) are becoming increasingly important in drug discovery, but their molecular dynamics (MD) simulation remains limited by labor-intensive residue parameterization and topology preparation. Here, we present TopFor (Topology and Residue Force-Field Parameter Preparation), an open-source, peptide-oriented workflow that automates the generation of ncAA residue templates and force-field parameter files for MD simulations with AMBER using established charge-derivation methods. TopFor supports single-residue, whole-peptide, and batch parameterization workflows. The workflow was validated using the MDM2-p53 complex by comparing native AMBER residue definitions with residues processed by TopFor using three charge-derivation methods, each evaluated in three independent 100 ns MD simulations. TopFor-generated residue definitions showed structural and conformational behavior comparable to the native AMBER representation. Applicability to more complex peptide architectures was demonstrated using the head-to-tail cyclic peptide cyclosporin A and the cyclic depsipeptide cyclohexylgriselimycin. At library scale, 1,138 of 1,214 cyclohexylgriselimycin derivatives (93.7%) successfully completed TopFor parameterization and the subsequent initial AMBER-based computational workflow across two derivatization campaigns. TopFor was further integrated into a structure-based peptide discovery workflow based on the DnaN-griselimycin complex. Six GM-derived peptides were computationally prioritized and experimentally evaluated, of which four produced SPR responses against Mycobacterium smegmatis (M. smegmatis) DnaN and three showed concentration-dependent responses. TopFor reduces the manual effort required to prepare ncAA-containing peptides for MD simulations and enables their integration into both library-scale computational screening and structure-based peptide discovery workflows. Keywords: noncanonical amino acids; peptide parameterization; molecular dynamics; AMBER; AmberTools; peptide design; high-throughput virtual screening

Antibiotic resistance driven by {beta}-lactamases has become a major threat to public health. Here, we propose a computational protocol for rapid estimation of {beta}-lactamase activity towards carbapenem antibiotics from sequence alone. Starting from AI-predicted acylenzyme complexes, only approximate transition state ensembles are sampled to compute catalytic electric fields, which strongly correlate with experimental activation barriers (R2 = 0.8). Compared with full quantum mechanics/molecular mechanics (QM/MM) reaction simulations, the protocol substantially reduces the amount of configurational sampling and thus computational cost. Our protocol enables efficient identification of carbapenem breakdown efficiency, further highlighting the important role of electric fields in enzyme catalysis.

Accurate modelling of biomolecular interactions is fundamental to drug discovery, yet current artificial intelligence (AI) workflows remain fragmented across structure prediction, affinity estimation, molecular design, and experimental decision-making. We introduce AnewDDE, an agentic Drug Discovery Engine that connects these capabilities into a closed-loop system for biomolecular interaction modelling and design. We demonstrate several components of this system: AnewFold delivers superior performance on challenging targets, including antibody-antigen complexes and molecular glues, providing more reliable structural hypotheses together with pocket identification and conformational analysis; AnewDesign achieves a 10.7% success rate in identifying binders with single-digit-nanomolar affinities measured by surface plasmon resonance (SPR) in a representative nanobody discovery campaign, substantially reducing the experimental search burden; AnewAffinity combines accuracy approaching that of free-energy perturbation (FEP) methods with the speed required for high-throughput screening and prioritizes promising transformations; and AnewMind, a large language model (LLM) at the hundred-billion-parameter scale that underwent in-house full-parameter post-training, provides scientific reasoning and absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction for pharmaceutical research and development (R&D). To systematically evaluate AnewMind, we introduce PharmBench, an internal benchmark designed by pharmaceutical R&D experts to evaluate long-horizon decision-making in drug discovery. Evaluations on ADMET tasks and PharmBench show that AnewMind performs competitively with leading frontier models. Together, these capabilities establish AnewDDE as an integrated engine for addressing challenging therapeutic targets and translating molecular insights into experimentally validated candidates at scale.

Ultra-large-scale virtual screening (ULVS) increasingly relies on make-on-demand chemical spaces, but efficient access to these spaces remains challenging because their scale far exceeds what can be exhaustively enumerated and docked. Here, we present REAL-SWIT, a generative ULVS framework that learns Enamine REAL Space as a synthesizable molecular distribution and couples this generator with a target-specific scoring model to enable docking-guided exploration of REAL Space at the level of complete molecule. The generative model learned transferable features of the REAL Space distribution: approximately 96% of generated molecules were found in REAL Space, and a subset of generated molecules absent from the training release appeared in later expanded releases. In computational benchmarks, REAL-SWIT identified more molecules with favorable docking scores than representative fragment-based search strategies, including cooperative building-block combinations that fragment-level prioritization tended to miss. Experimental validation for ROCK1 yielded six biochemical inhibitors among 23 synthesized compounds, including RX-3 with an IC50 of 0.17 M. These results establish generative access to make-on-demand chemical space as a practical strategy for ULVS.

Ligand transport through proteins underlies many aspects of molecular function, but its detailed mechanisms remain largely inaccessible to direct observation. Molecular dynamics simulations could close this gap, but are computationally too demanding for practical purposes, including filtering stages of enzyme design pipelines. Simplified docking-based approaches might be informative, but sometimes the oversimplifications required for high throughput applications might lead to unreliable predictions. Here we present RosettaLigand PathFinder (RLPF), a fast and practical tool explicitly built to ensure conformational continuity of the ligand trajectory, protein and ligand flexibility, and robustness of every run. Built using a flexible RosettaScripts XML interface, it enables fine-grained control over all simulation parameters and adaptability for a wide range of use cases. Applied to several representative systems, RLPF reproduced established transport features and mutation effects, highlighting its ability to produce biologically relevant insights and serve as a filter in enzyme design campaigns. Wide customizability and well-defined scope of RLPF make it a useful addition to the family of tools to study the dynamics of interactions between small molecules and proteins.

Transition state (TS) generation is typically evaluated by geometric similarity, yet low root-mean-square deviation (RMSD) does not establish first-order saddle-point character or reaction-path connectivity. Here we introduce Kairos-GFM, a deterministic equivariant flow-matching model that combines a two-dimensional reaction graph with the Kabsch-aligned mean of three-dimensional reactant and product geometries. Using 881 Transition1x reactions whose reference TSs passed strict saddle-point and bidirectional intrinsic reaction coordinate validation, Kairos-GFM generates one candidate in 0.0118 s with a median RMSD of 0.14 [A]. A hierarchical physical-validation framework--spanning reaction-center geometry, raw single-point energy, DFT saddle-point optimization, harmonic frequency analysis, and IRC endpoint matching reveals that low RMSD and saddle-point convergence do not guarantee the intended reaction channel. Kairos-GFM recovers the target channel in 75.94% of reactions, outperforming diffusion-based baselines but remaining below transport-based methods. These results position Kairos-GFM as a rapid initial-geometry generator for quantum-chemical refinement and provide a transferable validation standard that distinguishes geometric similarity from physical fidelity.

Cyclic peptides can engage extended protein interfaces, but sequence changes that improve developability often disrupt the selected target-bound geometry. Existing property-guided design methods lack a principled way to preserve this geometry during local multiproperty optimization. Here we present RF-PepTune, which separates structural eligibility from property prioritization. Before any property score is queried, RF-PepTune evaluates single substitutions and all position-distinct pairs induced by admitted substitutions to build a parent-specific, pair-complete admission graph. Pareto Monte Carlo tree search then optimizes predicted permeability, solubility, non-fouling, and low-haemolysis scores exclusively within this graph, and selected sequences undergo full structural re-evaluation. In a matched three-arm comparison of 334 parents across MDM2, GABARAP, and MCL1, joint property-structure success rose from 10.2% without admission to 51.5% with single-substitution admission and 77.5% with pair-complete admission; pair-complete gating improved success by 26.0 percentage points over single-substitution gating (95% CI, 20.7-31.4). Property-positive but structure-failing endpoints fell from 88.3% to 9.3%. In a separate target-balanced set, all 90 prioritized outputs improved all four model-native scores while satisfying prespecified structural criteria. This work establishes pairwise structural gating as a general strategy for constrained multi-objective molecular optimization.

Predicting ligand activity across G protein-coupled receptors (GPCRs) requires models that capture both molecular structure and receptor-specific information while remaining robust to chemical and target-domain shifts. We developed a multimodal graph neural network that combines explicit ligand molecular graphs with frozen protein language model representations of GPCR sequences and jointly predicts quantitative pActivity and binary activity. The model was trained on 271,739 curated ligand-GPCR pairs spanning 183,694 ligands and 216 human GPCRs and evaluated using random, Bemis-Murcko scaffold, and strict cold-ligand partitions. With ESM-2 650M receptor embeddings, the selected model achieved mean absolute errors of 0.513 {+/-} 0.006, 0.540 {+/-} 0.006, and 0.641 {+/-} 0.005 pActivity units under random, cold-ligand, and scaffold evaluation, respectively, substantially outperforming a protein-aware fixed-feature multilayer perceptron and consistently improving quantitative prediction over a matched GINE reference. Removing receptor embeddings markedly degraded both regression and classification, whereas differences among ESM-2 35M, ESM-2 650M, and ProtT5 were comparatively small. Independent evaluation on 6,319 ChEMBL 37/BindingDB pairs revealed a substantial external domain shift, with mean absolute error increasing to approximately 0.94-0.95 despite chemically stringent internal validation. Nevertheless, receptor-specific information remained highly informative in a DRD2-DRD3 selectivity analysis: the cold-ligand ensemble achieved R^2 = 0.853, Spearman {rho} = 0.916, and ROC-AUC = 0.966 for strong DRD3 selectivity, whereas the receptor-independent ablation approached chance-level discrimination. These results establish protein-language-model-conditioned molecular graph learning as a scalable strategy for GPCR bioactivity prediction while identifying chemotype novelty, external-domain transfer, and richer ligand-receptor interaction representations as key remaining challenges.

Autonomous drug discovery via generative molecular design is critically bottlenecked by the production of chemically intractable structures. Multi-trillion-scale make-on-demand libraries guarantee synthetic feasibility, but conventional virtual screening cannot efficiently navigate these vast spaces or address multi-parameter optimization. We introduce Hyper Screening X, a generative AI framework integrating structure-based design with automated synthesis hardware. By encoding deterministic reaction logic in a generative flow network, the framework evaluates only 10 million candidates to navigate an 11-trillion-compound space, jointly optimizing physicochemical properties while ensuring compatibility with automated synthesis. Prospective validation against an SLC1A5 variant with a cryptic interface yielded a 96% synthesis success rate and a 50% functional hit rate, identifying two first-in-class lead compounds. This synthesis-aware strategy advances autonomous, closed-loop drug discovery.

Protein function is determined not only by the static structure of molecules, but also by coordinated conformational fluctuations that occur across various spatial and temporal scales. Molecular dynamics simulations, elastic network models, principal component analysis, and related approaches offer useful descriptions of protein motion. However, representing heterogeneous trajectories in a compact, informative manner that is applicable to proteins with different sequences, structures, and historical evolution is not trivial. Here we present the Topology Invariant Dynamic Graph Network (TIDGN), a deep representation learning approach that encodes protein conformational dynamics into a shared latent representation, termed the protein motion signature (Zp). TIDGN encodes each trajectory as a time-dependent residue-level graph and builds structural connectivity, dynamic cross-correlation, low-dimensional motion features, sequence context, and temporal aggregation into the design. Instead of learning a protein-specific collective variable, the approach learns a representation that retains functionally informative patterns of coordinated motion applicable to different proteins. We evaluate the framework using 1,250 molecular-dynamics trajectories representing 1,120 distinct proteins that range in size from 50-600 residues, 142 CATH/SCOP families, 88 structural folds, and six broad functional classes. The set of trajectories spans durations of 100 ns to 10 (mu)s, sampled at 100 ps intervals, representing approximately 12.5 million conformational frames in total. In the context of a sequence-disjoint evaluation using a 30% sequence-identity threshold, the approach achieves a mean AUROC of 0.8838 (margin of error:) 0.0107 compared to 0.8174 for a dynamic graph neural-network baseline, 0.7257 for a dynamic descriptor, 0.7227 for a PCA descriptor, 0.6592 for a sequence baseline, and 0.6587 for a static-structure baseline. As the biological distance between training and evaluation proteins increases, transfer performance decreases, with AUROC values of 0.92 for random splitting, 0.85 for sequence-disjoint evaluation, 0.78 for family-disjoint evaluation, and 0.71 for fold-disjoint evaluation. Component ablations suggest that graph structure, dynamic cross-correlation, low-dimensional motion features, sequence information, and the combination of these factors contribute to predictive performance. Residue-level attribution, when applied to adenylate kinase, highlights regions that are associated with known conformational rearrangements that involve the LID and NMP domains, offering a biologically interpretable hypothesis about the dynamic information that is encoded by the model. Taken together, these results suggest that it is possible to learn transferable representations of protein dynamics that retain functionally informative patterns of coordinated motion beyond considerations of sequence identity and static structure. Moreover, although the learned representation is transferable, it is not universally invariant to the biological distance between training and evaluation proteins. The resulting approach offers a computational basis for connecting molecular motion, functional prediction, and mechanistically informative representation learning.

Peptide offers a powerful modality for targeting protein-protein interfaces, yet their computational design remains challenging because sequence identity, backbone geometry and side-chain packing must be optimized simultaneously within a three-dimensional pocket constrained environment. Here we present PeTFlow, a pocket-conditioned all-atom peptide co-design framework that rationalizes this constrained design problem through discrete side-chain state tokenization. In PeTFlow, each residue is represented as a chemically compatible state token, enabling unified modeling of peptide sequence, conformation and all-atom interface geometry. PeTFlow achieved superior generation quality on peptide-design benchmarks and can further be applied to therapeutically relevant peptide drug design.

Accurate molecular property prediction requires effective molecular representations that can describe a molecule from multiple complementary perspectives. Existing deep learning approaches typically use SMILES strings, two-dimensional molecular graphs, or three-dimensional conformations as inputs. These representations capture different aspects of molecular information: SMILES encodes a sequential description, molecular graphs describe atom-bond connectivity, and 3D conformations provide spatial information from atomic coordinates. However, these modalities are often learned separately or merged with low effective fusion operations, which may not sufficiently capture interactions among sequential, topological, and geometric features. In this work, we propose Tri-Modality Cross-Attention (TMCA), a multimodal framework that integrates 1D SMILES, 2D molecular graphs, and 3D molecular conformations for molecular property prediction. TMCA uses pretrained encoders for the 1D and 3D branches, with a SMILES-based Transformer for the 1D branch and a recent conformation-aware pretrained model for the 3D branch. At the same time, a trainable 2D graph encoder is designed to support modality fusion. All the parameters from the pretrained models are frozen to make overall training more efficient. We evaluate TMCA on four datasets (i.e., BBBP, BACE, ClinTox, and HIV) from the MoleculeNet database for classification tasks and compare its performance with state-of-the-art competing approaches. Experimental results show that TMCA achieves the best overall performance, demonstrating the value of multi-modality integration for drug property prediction and the effectiveness of our cross-attention-based fusion strategy. The source code of TMCA is available at: https://github.com/Ay-Zhao/TMCA

Membrane permeability remains a major challenge in cyclic-peptide drug discovery, where optimization often depends on estimating changes relative to measured reference compounds. Existing predictors mainly model absolute permeability, while heterogeneity across literature sources complicates pooled training and comparative evaluation. We present CycDelta, a multimodal residue-graph model trained directly on within-source permeability differences. CycDelta combines directed message passing with pretrained Uni-Mol monomer embeddings, physicochemical descriptors and assay information in a shared encoder for reference and query peptides. To evaluate this comparative formulation under controlled conditions, we establish CycDeltaBench, comprising in-distribution, scaffold-based out-of-distribution, external and zero-shot unseen-assay tests. On the out-of-distribution task, CycDelta achieved Pearson 0.69 versus 0.46 for the strongest baseline. It also led all evaluated methods on two external data sets and achieved zero-shot Spearman 0.70 versus 0.32 for the strongest baseline on an unseen assay. Residue-level attribution relates predictions to monomer contributions, while gradient-guided screening supports prioritization of permeability-enhancing analogue hypotheses. These results position CycDelta as a transferable and interpretable framework for comparative permeability prediction and cyclic-peptide optimization.