RESUMEN
Protein loop modeling is a challenging yet highly nontrivial task in protein structure prediction. Despite recent progress, existing methods including knowledge-based, ab initio, hybrid, and deep learning (DL) methods fall substantially short of either atomic accuracy or computational efficiency. To overcome these limitations, we present KarmaLoop, a novel paradigm that distinguishes itself as the first DL method centered on full-atom (encompassing both backbone and side-chain heavy atoms) protein loop modeling. Our results demonstrate that KarmaLoop considerably outperforms conventional and DL-based methods of loop modeling in terms of both accuracy and efficiency, with the average RMSDs of 1.77 and 1.95 Å for the CASP13+14 and CASP15 benchmark datasets, respectively, and manifests at least 2 orders of magnitude speedup in general compared with other methods. Consequently, our comprehensive evaluations indicate that KarmaLoop provides a state-of-the-art DL solution for protein loop modeling, with the potential to hasten the advancement of protein engineering, antibody-antigen recognition, and drug design.
RESUMEN
The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.
Asunto(s)
Complejo Antígeno-Anticuerpo , Aprendizaje Profundo , Complejo Antígeno-Anticuerpo/química , Antígenos/química , Antígenos/genética , Antígenos/metabolismo , Antígenos/inmunología , Afinidad de Anticuerpos , Secuencia de Aminoácidos , Biología Computacional/métodos , Humanos , Mutación , Anticuerpos/química , Anticuerpos/inmunología , Anticuerpos/genética , Anticuerpos/metabolismoRESUMEN
In the past few years, a number of machine learning (ML)-based molecular generative models have been proposed for generating molecules with desirable properties, but they all require a large amount of label data of pharmacological and physicochemical properties. However, experimental determination of these labels, especially bioactivity labels, is very expensive. In this study, we analyze the dependence of various multi-property molecule generation models on biological activity label data and propose Frag-G/M, a fragment-based multi-constraint molecular generation framework based on conditional transformer, recurrent neural networks (RNNs), and reinforcement learning (RL). The experimental results illustrate that, using the same number of labels, Frag-G/M can generate more desired molecules than the baselines (several times more than the baselines). Moreover, compared with the known active compounds, the molecules generated by Frag-G/M exhibit higher scaffold diversity than those generated by the baselines, thus making it more promising to be used in real-world drug discovery scenarios.
Asunto(s)
Descubrimiento de Drogas , Redes Neurales de la Computación , Descubrimiento de Drogas/métodos , Aprendizaje Automático , Modelos MolecularesRESUMEN
Protein loops play a critical role in the dynamics of proteins and are essential for numerous biological functions, and various computational approaches to loop modeling have been proposed over the past decades. However, a comprehensive understanding of the strengths and weaknesses of each method is lacking. In this work, we constructed two high-quality datasets (i.e. the General dataset and the CASP dataset) and systematically evaluated the accuracy and efficiency of 13 commonly used loop modeling approaches from the perspective of loop lengths, protein classes and residue types. The results indicate that the knowledge-based method FREAD generally outperforms the other tested programs in most cases, but encountered challenges when predicting loops longer than 15 and 30 residues on the CASP and General datasets, respectively. The ab initio method Rosetta NGK demonstrated exceptional modeling accuracy for short loops with four to eight residues and achieved the highest success rate on the CASP dataset. The well-known AlphaFold2 and RoseTTAFold require more resources for better performance, but they exhibit promise for predicting loops longer than 16 and 30 residues in the CASP and General datasets. These observations can provide valuable insights for selecting suitable methods for specific loop modeling tasks and contribute to future advancements in the field.
Asunto(s)
Proteínas , Conformación Proteica , Proteínas/químicaRESUMEN
Clarifying the process of formation of diversity hotspots and the biogeographic connection between regions is critical in understanding the impact of environmental changes on organismal evolution. Polygonatum (Asparagaceae) is distributed across the Northern Hemisphere. It displays an uneven distribution, with more than 50% of its species occurring in the Himalaya-Hengduan Mountains (HHM). Here, we generated a time-calibrated phylogeny of Polygonatum, based on whole-plastome data, to reconstruct the genus' biogeographical history and morphological/chromosomal evolution. Our phylogenetic analyses strongly support the monophyly of Polygonatum and its division into three sections (i.e., Verticillata, Sibirica, and Polygonatum). Polygonatum originated from the HHM region during the early-Miocene (c. 20.10 Ma), and began to radiate since the mid-Miocene, driven by the uplift of the Qinghai-Tibet Plateau (QTP), increasingly colder/arid climates following the mid-Miocene Climatic Optimum (MMCO), and intensification of the East Asian winter monsoon. Dispersal from the HHM region to other regions was facilitated by the intensification of East Asian summer monsoon in response to global climatic warming during the MMCO. Decreasing dysploidy accompanied by karyotype change and polyploidization in Polygonatum appears to be associated with its diversification and colonization of new ecological niches. Our results highlight the importance of regional tectonic activities and past climatic changes from the Neogene onwards to the spatial-temporal diversification and distribution patterns of plant lineages with a wide distribution in the Northern Hemisphere. They also contribute to the knowledge of the uneven species richness between East Asia and other regions.