KUALA: a machine learning-driven framework for kinase inhibitors repositioning

Simone, Giada De; Sardina, Davide Stefano; Gulotta, Maria Rita; Perricone, Ugo

doi:10.1038/s41598-022-22324-8

Cited by 6 publications

(3 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integration of data on kinase-ligand interaction from different source is a challenging task, due to the wide range of experiment types and definitions of activities, which could lead to significant systematic errors in results 54 , 55 . To address this challenge, previous studies have employed classification models, rather than regression models, or trained each data source separately 16 , 18 , 56 , 57 . On the contrary, our study used both IC50 and Ki values as targets for bioactivity, which are commonly used in the literature as measures of inhibitor potency and can provide a more comprehensive coverage of the dataset.…”

Section: Discussionmentioning

confidence: 99%

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Park¹,

Hong²,

Lee³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson’s correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

show abstract

Section: Discussionmentioning

confidence: 99%

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Park¹,

Hong²,

Lee³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…91 In cancer research, a novel approach called KUALA (Kinase drUgs mAchine Learning framework) utilized AI to automatically identify kinase active ligands for effective drug repositioning within the protein kinase family. 92 AI is not limited to ligand identification, but it can help identify molecular targets. For example, PandaOmics, an AI platform, was used to identify 11 novel therapeutic targets for ALS from CNS and iPSC-derived motor neuron data.…”

Section: Computer-aided Drug Design and Artificial Intelligencementioning

confidence: 99%

Antineoplastics for treating Alzheimer's disease and dementia: Evidence from preclinical and observational studies

Das,

Miller,

Alladi

et al. 2024

Medicinal Research Reviews

View full text Add to dashboard Cite

As the world population ages, there will be an increasing need for effective therapies for aging‐associated neurodegenerative disorders, which remain untreatable. Dementia due to Alzheimer's disease (AD) is one of the leading neurological diseases in the aging population. Current therapeutic approaches to treat this disorder are solely symptomatic, making the need for new molecular entities acting on the causes of the disease extremely urgent. One of the potential solutions is to use compounds that are already in the market. The structures have known pharmacokinetics, pharmacodynamics, toxicity profiles, and patient data available in several countries. Several drugs have been used successfully to treat diseases different from their original purposes, such as autoimmunity and peripheral inflammation. Herein, we divulge the repurposing of drugs in the area of neurodegenerative diseases, focusing on the therapeutic potential of antineoplastics to treat dementia due to AD and dementia. We briefly touch upon the shared pathological mechanism between AD and cancer and drug repurposing strategies, with a focus on artificial intelligence. Next, we bring out the current status of research on the development of drugs, provide supporting evidence from retrospective, clinical, and preclinical studies on antineoplastic use, and bring in new areas, such as repurposing drugs for the prion‐like spreading of pathologies in treating AD.

show abstract

“…Beyond traditional molecular docking approaches, machine learning methods have emerged as promising tools in this context, offering time- and cost-effective means to navigate the kinase chemical space. In fact, several new models for compound-kinase binding prediction are introduced every month [CCAS + 15, CRA + 21, DQJ + 22, DSSGP22]. They differ in the learning algorithm used, such as simple k-nearest neighbor regression [BHS + 21], decision trees [TAA + 22], kernel learning [MM12, NPC16, CRP + 17, CPS + 18] and deep learning methods [BHS + 21, O18, KZEK23, LLP23, SSB + 23], as well as compound and protein descriptors, including compound SMILES and graphs [DTME20], protein amino acid sequences [BHS + 21, KZEK23] and, lately, more complex 3D structure-based features [KZK + 23, PHL + 23, LKN + 23, LTZ + 23] and embeddings from pretrained large language models [SSB + 23].…”

Section: Introductionmentioning

confidence: 99%

Leveraging multiple data types for improved compound-kinase bioactivity prediction

Theisen,

Wang,

Ravikumar

et al. 2024

Preprint

View full text Add to dashboard Cite

Machine learning methods offer time- and cost-effective means for identifying novel chemical matter as well as guiding experimental efforts to map enormous compound-kinase interaction spaces. However, considerable challenges for compound-kinase interaction modeling arise from the heterogeneity of available bioactivity readouts, including single-dose compound profiling results, such as percentage inhibition, and multi-dose-response results, such as IC50. Standard activity prediction approaches utilize only dose-response data in the model training, disregarding a substantial portion of available information contained in single-dose measurements. Here, we propose a novel machine learning methodology for compound-kinase activity prediction that leverages both single-dose and dose-response data. Our two-stage model first learns a mapping between single-dose and dose-response bioactivity readouts, and then generates proxy dose-response activity labels for compounds that have only been tested in single-dose assays. The predictions from the first-stage model are then integrated with experimentally measured dose-response activities to model compound-kinase binding based on chemical structures and kinase features. We demonstrate that our two-stage approach yields accurate activity predictions and significantly improves model performance compared to training solely on dose-response labels, particularly in the most practical and challenging scenarios of predicting activities for new compounds and new compound scaffolds. This superior performance is consistent across five evaluated machine learning methods, including traditional models such as random forest and kernel learning, as well as deep learning-based approaches. Using the best performing model, we carried out extensive experimental profiling on a total of 347 selected compound-kinase pairs, achieving a high hit rate of 40% and a negative predictive value of 78%. We show that these rates can be improved further by incorporating model uncertainty estimates into the compound selection process. By integrating multiple activity data types, we demonstrate that our approach holds promise for facilitating the development of training activity datasets in a more efficient and cost-effective way.

show abstract

KUALA: a machine learning-driven framework for kinase inhibitors repositioning

Cited by 6 publications

References 73 publications

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors

Antineoplastics for treating Alzheimer's disease and dementia: Evidence from preclinical and observational studies

Leveraging multiple data types for improved compound-kinase bioactivity prediction

Contact Info

Product

Resources

About