Yue Qian

De novo protein design has advanced rapidly, yet designing binders to polar, solvent-exposed epitopes and small, flexible ligands remains challenging. Such hydrated surfaces and flexible molecules, including carbohydrates, provide few of the hydrophobic contacts favoured by current methods and have largely resisted de novo binders. To address this challenge, here we introduce latent generative search for binder design, a novel framework that uses reward-guided search at inference time to steer the Proteína-Complexa generative model. The model codesigns sequence and structure — generating them together in a continuous latent space — and thereby removes the inverse-folding step on which current methods rely. In a screen of more than one million designs by multiplexed phage display, latent generative search produced more validated binders than every other method tested, its codesigned sequences surpassing post hoc redesign. It delivered high-affinity binders across therapeutic receptors, a viral attachment protein and intracellular signalling targets. Our approach also accessed previously untapped biology, generating the first de novo proteins that bind a free carbohydrate, including one that discriminates between blood-group antigens — a polar, flexible target class beyond the reach of current design methods.

Motivation: Accurate prediction of B-cell epitopes is essential for antibody design and vaccine development, yet remains fundamentally challenging. A major but often overlooked limitation of existing predictors is their implicit assumption that epitope identity can be decomposed into independent residue-level signals. In contrast, antibody recognition is governed by spatially contiguous surface patches whose functional identity emerges from coherent three-dimensional geometry rather than isolated residues. Results: Here, we reformulate structure-based B-cell epitope prediction as a surface-patch learning problem and introduce PatchEpi, a patch-aware geometric deep learning framework for antigen-intrinsic epitope modeling. It employs a patch-aware attention encoder and boundary-contrastive objectives to align the learning patch signal with the biological reality of antibody binding. PatchEpi integrates patch embeddings, fine-tuned ESM2 representations, and an equivariant message-passing network to model the 3D topology of antigen surfaces. To enable rigorous evaluation, we created a homology leakage-controlled split by reclustering the ANABAG dataset. Across multiple benchmarks, PatchEpi consistently outperforms residue-centric and graph-based state-of-the-art methods. Structural analyses further show that the model learns coherent surface patches that closely match experimentally resolved antibody footprints. These results demonstrate that accurate epitope prediction benefits primarily from reformulating the task around surface-patch learning. Patch-aware learning provides a principled and biologically grounded pathway toward more reliable structure-based epitope detection. Availability and implementation: The code and related resources are available at GitHub (https://github.com/wsicheng739/PatchEpi) and Zenodo (https://doi.org/10.5281/zenodo.20366444).

Cyclic peptides are promising therapeutic agents, but their clinical translation is often limited by poor membrane permeability arising from complex, solvent-dependent conformational ensembles. Here, we present a modeling framework inspired by molecular chameleon, integrating sequence and structural information by explicitly representing solvent-dependent ensembles in aqueous and nonpolar environments. The model achieves strong predictive performance (MAE = 0.29, R = 0.85, R2 = 0.70 on CycPeptMPDB) under random split and retains robust performance under scaffold split evaluation (MAE = 0.34, Pearson R = 0.68). Beyond molecule-level prediction, analysis of one-residue analog-pair in testing set shows that the model captures experimentally meaningful ΔPAMPA trends, supporting its utility for cyclic peptide lead optimization. Model interpretation highlights polarity shielding captured by ΔPSA3D as a key mechanistically interpretable feature associated with permeability. These results demonstrate that permeability emerges from ensemble reorganization rather than a single conformational transition, establishing a generalizable framework for cyclic peptide design and ADMET prediction.

Cyclic peptide represents an attractive drug modality with its advantages in targeting proteins that were traditionally considered “undruggable”. Molecular dynamics (MD) simulation remains a powerful tool for understanding peptide conformations and their interactions with the corresponding receptors in complex form. However, the preparation of macrocyclic peptide parameter files consisting of nonproteinogenic amino acids can be time-consuming and error prone. Here, we introduce an automatic workflow for the preparation of topology and force field parameter files for cyclic peptide systems. Partial charges and force field parameters of nonproteinogenic amino acids are automatically processed in a widely adopted rigorous way. Peptides spanning from mono- to tetra-cyclization were tested in bound and unbound states, which yielded valid parameter files and similar simulation results to those generated by different MD engines. Overall, the tool chain streamlines macrocyclic peptide MD setup while maintaining rigor and transferability across diverse cyclization patterns and simulation engines.

Transmembrane B cell lymphoma 2-associated X protein inhibitor motif-containing (TMBIM) 6, also known as Bax Inhibitor-1 (BI-1), has been heavily researched for its cytoprotective functions. TMBIM6 functional diversity includes modulating cell survival, stress, metabolism, cytoskeletal dynamics, organelle function, regulating cytosolic acidification, calcium, and reactive oxygen species (ROS). Clinical research shows TMBIM6 plays a key role in many of the world’s top diseases/injuries (i.e., Alzheimer’s, Parkinson’s, diabetes, obesity, brain injury, liver disease, heart disease, aging, etc.), including cancer, where TMBIM6 expression impacts patient survival, chemoresistance, cancer progression, and metastasis. We show TMBIM6 is activated by, and undergoes, different conformational changes that dictate its function following a significant change in the cell’s IntraCellular Environment (ICE). TMBIM6 agonism, following ICE change, can help the cell overcome multiple stresses including toxin exposure, viral infection, wound healing, and excitotoxicity. However, in cancer cells TMBIM6 agonism results in rapid paraptotic induction irrespective of the cancer type, sub-type, genotype or phenotype. Furthermore, the level of TMBIM6 expression in cancer did not dictate the level of paraptotic induction; however, it did dictate the rate at which paraptosis occurred. TMBIM6 agonism did not induce paraptosis in cancer via canonical routes involving p38 MAPK, JNK, ERK, UPR, autophagy, proteasomes, or Caspase-9. Instead, TMBIM6 agonism in cancer upregulates cytosolic Ca2+ and ROS, activates lysosome biogenesis, and induces paraptosis via ERAD II mechanisms. In xenograft models, we show TMBIM6 agonism induces rapid cancer cell death with no toxicity, even at high doses of TMBIM6 agonist (>450 mg/kg). In summary, this study shows TMBIM6’s functional diversity is only activated by severe ICE change in diseased/injured cells, highlighting its transformative potential as a therapeutic target across various diseases and injuries, including cancer.

The growing field of computational chemistry and artificial intelligence is drawing unprecedented attention in drug discovery. However, the underrepresentation of female scientists persists in the field. While the gender disparity is acknowledged in academic settings, the issue is less addressed and intensifies in the pharmaceutical and biotech industry both at the entry-level and leadership positions. At Viva Biotech, we challenge this norm: over 60% of the full-time employees in our computational chemistry group are women, a testament of our commitment to the pursuit of gender equality. We share our vision of the evolving role of computational chemistry in drug discovery and where women stand and rise in the field. In this article, we discuss how we engage female empowerment with tactical approaches and from personal experiences. The intention is to offer actionable guidance for female computational chemists at early career stages to bring visibility to their impacts, and ascent to senior positions.

The relative free energy perturbation (RFEP) calculation is one of the most theoretically sound computational chemistry approaches for the binding affinity prediction. However, its application is often hindered by the complexity of the calculation choices and the requirement of expertise in the field. Improper lambda scheme of RFEP may result in deviations from an accurate description of the perturbation process and is prone to erroneous affinity predictions. To address such challenges, an automated adaptive lambda method is proposed where the adaptive lambda schemes are obtained through a split‐and‐merge algorithm based on the pilot runs. The newly established workflow along with a series of improvements to the perturbation settings increases the consistency of the RFEP calculation results. Comparing the pilot and adaptive lambda schemes, the latter demonstrated improvements in convergence and reproducibility and lowered the mean unsigned error and the root‐mean‐square error. Overall, the adaptive lambda method is a reliable and robust choice to predict small molecule relative binding free energy and can be capitalized to benefit routine RFEP calculations for drug discovery projects.

Calculation of the absolute free energy of binding (ΔG_bind) for a complex in solution is challenging owing to the need for adequate configurational sampling and an accurate energetic description, typically with a force field (FF). In this study, Monte Carlo (MC) simulations with improved side-chain and backbone sampling are used to assess ΔG_bind for the complex of a druglike inhibitor (MIF180) with the protein macrophage migration inhibitory factor (MIF) using free energy perturbation (FEP) calculations. For comparison, molecular dynamics (MD) simulations were employed as an alternative sampling method for the same system. With the OPLS-AA/M FF and CM5 atomic charges for the inhibitor, the ΔG_bind results from the MC/FEP and MD/FEP simulations, −8.80 ± 0.74 and −8.46 ± 0.85 kcal/mol, agree well with each other and with the experimental value of −8.98 ± 0.28 kcal/mol. The convergence of the results and analysis of the trajectories indicate that sufficient sampling was achieved for both approaches. Repeating the MD/FEP calculations using current versions of the CHARMM and AMBER FFs led to a 6 kcal/mol range of computed ΔG_bind. These results show that calculation of accurate ΔG_bind for large ligands is both feasible and numerically equivalent, within error limits, using either methodology.