Facing small and biased data dilemma in drug discovery with enhanced federated learning approaches

Protein lipidation in the tumor microenvironment: enzymology, signaling pathways, and therapeutics

Protein lipidation is a pivotal post-translational modification that increases protein hydrophobicity and influences their function, localization, and interaction network. Emerging evidence has shown significant roles of lipidation in the tumor microenvironment (TME). However, a comprehensive review of this topic is lacking. In this review, we present an integrated and in-depth literature review of protein lipidation in the context of the TME. Specifically, we focus on three major lipidation modifications: S-prenylation, S-palmitoylation, and N-myristoylation. We emphasize how these modifications affect oncogenic signaling pathways and the complex interplay between tumor cells and the surrounding stromal and immune cells. Furthermore, we explore the therapeutic potential of targeting lipidation mechanisms in cancer treatment and discuss prospects for developing novel anticancer strategies that disrupt lipidation-dependent signaling pathways. By bridging protein lipidation with the dynamics of the TME, our review provides novel insights into the complex relationship between them that drives tumor initiation and progression.

GEFormer: A genotype-environment interaction-based genomic prediction method that integrates the gating multilayer perceptron and linear attention mechanisms

The integration of genotypic and environmental data can enhance genomic prediction accuracy for crop field traits. Existing genomic prediction methods fail to consider environmental factors and the real growth environments of crops, resulting in low genomic prediction accuracy. In this work, we developed GEFormer, a genotype-environment interaction genomic prediction method that integrates gating multilayer perceptron (gMLP) and linear attention mechanisms. First, GEFormer uses gMLP to extract local and global features among SNPs. Then, Omni-dimensional Dynamic Convolution is used to extract the dynamic and comprehensive features of multiple environmental factors within each day, taking into consideration the real growth pattern of crops. A linear attention mechanism is used to capture the temporal features of environmental changes. Finally, GEFormer uses a gating mechanism to effectively fuse the genomic and environmental features. We examined the accuracy of GEFormer for predicting important agronomic traits of maize, rice, and wheat under three experimental scenarios: untested genotypes in tested environments, tested genotypes in untested environments, and untested genotypes in untested environments. The results showed that GEFormer outperforms six cutting-edge statistical learning methods and four machine learning methods, especially with great advantages under the scenario of untested genotypes in untested environments. In addition, we used GEFormer for three real-world breeding applications: phenotype prediction in unknown environments, hybrid phenotype prediction using an inbred population, and cross-population phenotype prediction. The results showed that GEFormer had better prediction performance in actual breeding scenarios and could be used to assist in crop breeding.

Breaking barriers: we need a multidisciplinary approach to tackle cancer drug resistance

Most cancer-related deaths result from drug-resistant disease(1,2). However, cancer drug resistance is not a primary focus in drug development. Effectively mitigating and treating drug-resistant cancer will require advancements in multiple fields, including early detection, drug discovery, and our fundamental understanding of cancer biology. Therefore, successfully tackling drug resistance requires an increasingly multidisciplinary approach. A recent workshop on cancer drug resistance, jointly organised by Cancer Research UK, the Rosetrees Trust, and the UKRI-funded Physics of Life Network, brought together experts in cell biology, physical sciences, computational biology, drug discovery, and clinicians to focus on these key challenges and devise interdisciplinary approaches to address them. In this perspective, we review the outcomes of the workshop and highlight unanswered research questions. We outline the emerging hallmarks of drug resistance and discuss lessons from the COVID-19 pandemic and antimicrobial resistance that could help accelerate information sharing and timely adoption of research discoveries into the clinic. We envisage that initiatives that drive greater interdisciplinarity will yield rich dividends in developing new ways to better detect, monitor, and treat drug resistance, thereby improving treatment outcomes for cancer patients.

kMoL: an open-source machine and federated learning library for drug discovery

Machine learning is quickly becoming integral to drug discovery pipelines, particularly quantitative structure-activity relationship (QSAR) and absorption, distribution, metabolism, and excretion (ADME) tasks. Graph Convolutional Network (GCN) models have proven especially promising due to their inherent ability to model molecular structures using graph-based representations. However, maximizing the potential of such models in practice is challenging, as companies prioritize data privacy and security over collaboration initiatives to improve model performance and robustness. kMoL is an open-source machine learning library with integrated federated learning capabilities developed to address such challenges. Its key features include state-of-the-art model architectures, Bayesian optimization, explainability, and federated learning mechanisms. It demonstrates extensive customization possibilities, advanced security features, straightforward implementation of user-specific models, and high adaptability to custom datasets without additional programming requirements. kMoL is evaluated through locally trained benchmark settings and distributed federated learning experiments using various datasets to assess the features and flexibility of the library, as well as the ability to facilitate fast and practical experimentation. Additionally, results of these experiments provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines. kMoL is available on GitHub at https://github.com/elix-tech/kmol .Scientific contribution The primary scientific contribution of this research project is the introduction and evaluation of kMoL, an open-source machine learning library with integrated federated learning capabilities. By demonstrating advanced customization and security capabilities without additional programming requirements, kMoL represents an accessible yet secure open-source platform for collaborative drug discovery projects. Additionally, the experiment results provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines.

Combined usage of ligand- and structure-based virtual screening in the artificial intelligence era

Drug design has always been pursuing techniques with time- and cost-benefits. Virtual screening, generally classified as ligand-based (LBVS) and structure-based (SBVS) approaches, could identify active compounds in the large chemical library to reduce time and cost. Owing to the intrinsic flaws and complementary nature of both approaches, continued efforts have been made to combine them to mitigate limitations. Meanwhile, the emergence of machine learning (ML) endows them with opportunities to leverage vast amounts of data to improve their defects. However, few discussions on how to merge ML-improved LBVS and SBVS have been conducted. Therefore, this review provides insights into combined usage of ML-improved LBVS and SBVS to enlighten medicinal chemists to utilize these joint strategies to lift the screening efficiency as well as AI professionals to design novel techniques.

Privacy-by-Design with Federated Learning will drive future Rare Disease Research

Up to 6% of the global population is estimated to be affected by one of about 10,000 distinct rare diseases (RDs). RDs are, to this day, often not understood, and thus, patients are heavily underserved. Most RD studies are chronically underfunded, and research faces inherent difficulties in analyzing scarce data. Furthermore, the creation and analysis of representative datasets are often constrained by stringent data protection regulations, such as the EU General Data Protection Regulation. This review examines the potential of federated learning (FL) as a privacy-by-design approach to training machine learning on distributed datasets while ensuring data privacy by maintaining the local patient data and only sharing model parameters, which is particularly beneficial in the context of sensitive data that cannot be collected in a centralized manner. FL enhances model accuracy by leveraging diverse datasets without compromising data privacy. This is particularly relevant in rare diseases, where heterogeneity and small sample sizes impede the development of robust models. FL further has the potential to enable the discovery of novel biomarkers, enhance patient stratification, and facilitate the development of personalized treatment plans. This review illustrates how FL can facilitate large-scale, cross-institutional collaboration, thereby enabling the development of more accurate and generalizable models for improved diagnosis and treatment of rare diseases. However, challenges such as non-independently distributed data and significant computational and bandwidth requirements still need to be addressed. Future research must focus on applying FL technology for rare disease datasets while exploring standardized protocols for cross-border collaborations that can ultimately pave the way for a new era of privacy-preserving and distributed data-driven rare disease research.

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

A Survey on Computational Methods in Drug Discovery for Neurodegenerative Diseases

Currently, the age structure of the world population is changing due to declining birth rates and increasing life expectancy. As a result, physicians worldwide have to treat an increasing number of age-related diseases, of which neurological disorders represent a significant part. In this context, there is an urgent need to discover new therapeutic approaches to counteract the effects of neurodegeneration on human health, and computational science can be of pivotal importance for more effective neurodrug discovery. The knowledge of the molecular structure of the receptors and other biomolecules involved in neurological pathogenesis facilitates the design of new molecules as potential drugs to be used in the fight against diseases of high social relevance such as dementia, Alzheimer's disease (AD) and Parkinson's disease (PD), to cite only a few. However, the absence of comprehensive guidelines regarding the strengths and weaknesses of alternative approaches creates a fragmented and disconnected field, resulting in missed opportunities to enhance performance and achieve successful applications. This review aims to summarize some of the most innovative strategies based on computational methods used for neurodrug development. In particular, recent applications and the state-of-the-art of molecular docking and artificial intelligence for ligand- and target-based approaches in novel drug design were reviewed, highlighting the crucial role of in silico methods in the context of neurodrug discovery for neurodegenerative diseases.

Quantitative risk analysis of treatment plans for patients with tumor by mining historical similar patients from electronic health records using federated learning

The determination of a treatment plan for a target patient with tumor is a difficult problem due to the existence of heterogeneity in patients' responses, incomplete information about tumor states, and asymmetric knowledge between doctors and patients, and so on. In this paper, a method for quantitative risk analysis of treatment plans for patients with tumor is proposed. To reduce the impacts of the heterogeneity in patients' responses on analysis results, the method conducts risk analysis by mining historical similar patients from Electronic Health Records (EHRs) in multiple hospitals using federated learning (FL). For this, the Recursive Feature Elimination based on the Support Vector Machine (SVM) and Deep Learning Important FeaTures (DeepLIFT) are extended into the FL framework to select key features and determine key feature weights for identifying historical similar patients. Then, in the database of each collaborative hospital, the similarities between the target patient and all historical patients are calculated, and the historical similar patients are determined. According to the statistics of tumor states and treatment outcomes of historical similar patients in all collaborative hospitals, the related data (including the probabilities of different tumor states and possible outcomes of different treatment plans) for risk analysis of the alternative treatment plans can be obtained, which can eliminate the asymmetric knowledge between doctors and patients. The related data are valuable for the doctor and patient to make their decisions. Experimental studies have been conducted to verify the feasibility and effectiveness of the proposed method.

Quorum sensing-based interactions among drugs, microbes, and diseases

Many diseases and health conditions are closely related to various microbes, which participate in complex interactions with diverse drugs; nonetheless, the detailed targets of such drugs remain to be elucidated. Many existing studies have reported causal associations among drugs, gut microbes, or diseases, calling for a workflow to reveal their intricate interactions. In this study, we developed a systematic workflow comprising three modules to construct a Quorum Sensing-based Drug-Microbe-Disease (QS-DMD) database ( http://www.qsdmd.lbci.net/ ), which includes diverse interactions for more than 8,000 drugs, 163 microbes, and 42 common diseases. Potential interactions between microbes and more than 8,000 drugs have been systematically studied by targeting microbial QS receptors combined with a docking-based virtual screening technique and in vitro experimental validations. Furthermore, we have constructed a QS-based drug-receptor interaction network, proposed a systematic framework including various drug-receptor-microbe-disease connections, and mapped a paradigmatic circular interaction network based on the QS-DMD, which can provide the underlying QS-based mechanisms for the reported causal associations. The QS-DMD will promote an understanding of personalized medicine and the development of potential therapies for diverse diseases. This work contributes to a paradigm for the construction of a molecule-receptor-microbe-disease interaction network for human health that may form one of the key knowledge maps of precision medicine in the future.

The rise of the machines in chemistry

The use of artificial intelligence and, more specifically, deep learning methods in chemistry is becoming increasingly common. Applications in informatics fields, such as cheminformatics and proteomics, structural biology, and spectroscopy, including NMR, are on the rise. Recent developments in model architectures, such as graph convolutional neural networks and transformers, have been enabled by advancements in computational hardware and software. However, model architectures with more predictive power often require larger amounts of training data, which can be challenging to acquire, but this requirement can be mitigated through techniques like pretraining and fine-tuning. In spite of these successes, challenges remain, such as normalization and scaling of data, availability of experimentally acquired data, and model explainability.

Novel technical and privacy-preserving technology for artificial intelligence in ophthalmology

PURPOSE OF REVIEW

The application of artificial intelligence (AI) in medicine and ophthalmology has experienced exponential breakthroughs in recent years in diagnosis, prognosis, and aiding clinical decision-making. The use of digital data has also heralded the need for privacy-preserving technology to protect patient confidentiality and to guard against threats such as adversarial attacks. Hence, this review aims to outline novel AI-based systems for ophthalmology use, privacy-preserving measures, potential challenges, and future directions of each.

RECENT FINDINGS

Several key AI algorithms used to improve disease detection and outcomes include: Data-driven, imagedriven, natural language processing (NLP)-driven, genomics-driven, and multimodality algorithms. However, deep learning systems are susceptible to adversarial attacks, and use of data for training models is associated with privacy concerns. Several data protection methods address these concerns in the form of blockchain technology, federated learning, and generative adversarial networks.

SUMMARY

AI-applications have vast potential to meet many eyecare needs, consequently reducing burden on scarce healthcare resources. A pertinent challenge would be to maintain data privacy and confidentiality while supporting AI endeavors, where data protection methods would need to rapidly evolve with AI technology needs. Ultimately, for AI to succeed in medicine and ophthalmology, a balance would need to be found between innovation and privacy.