Machine learning approach informs biology of cancer drug response

AI-powered precision medicine: utilizing genetic risk factor optimization to revolutionize healthcare

The convergence of artificial intelligence (AI) and biomedical data is transforming precision medicine by enabling the use of genetic risk factors (GRFs) for customized healthcare services based on individual needs. Although GRFs play an essential role in disease susceptibility, progression, and therapeutic outcomes, a gap exists in exploring their contribution to AI-powered precision medicine. This paper addresses this need by investigating the significance and potential of utilizing GRFs with AI in the medical field. We examine their applications, particularly emphasizing their impact on disease prediction, treatment personalization, and overall healthcare improvement. This review explores the application of AI algorithms to optimize the use of GRFs, aiming to advance precision medicine in disease screening, patient stratification, drug discovery, and understanding disease mechanisms. Through a variety of case studies and examples, we demonstrate the potential of incorporating GRFs facilitated by AI into medical practice, resulting in more precise diagnoses, targeted therapies, and improved patient outcomes. This review underscores the potential of GRFs, empowered by AI, to enhance precision medicine by improving diagnostic accuracy, treatment precision, and individualized healthcare solutions.

Deep Learning for the Accurate Prediction of Triggered Drug Delivery

The need to mitigate the adverse effects of chemotherapy has driven the exploration of innovative drug delivery approaches. One emerging trend in cancer treatment is the utilization of Drug Delivery Systems (DDSs), facilitated by nanotechnology. Nanoparticles, ranging from 1 nm to 1000 nm, act as carriers for chemotherapeutic agents, enabling precise drug delivery. The triggered release of these agents is vital for advancing this novel drug delivery system. Our research investigated this multifaceted delivery capability using liposomes and metal organic frameworks as nanocarriers and utilizing all three targeting techniques: passive, active, and triggered. Liposomes are modified using targeting ligands to render them more targeted toward certain cancers. Moieties are conjugated to the surfaces of these nanocarriers to allow for their binding to receptors overexpressed on cancer cells, thus increasing the accumulation of the agent at the tumor site. A novel class of nanocarriers, namely metal organic frameworks, has emerged, showing promise in cancer treatment. Triggering techniques (both intrinsic and extrinsic) can be used to release therapeutic agents from nanoparticles, thus enhancing the efficacy of drug delivery. In this study, we develop a predictive model combining experimental measurements with deep learning techniques. The model accurately predicts drug release from liposomes and MOFs under various conditions, including low- and high-frequency ultrasound (extrinsic triggering), microwave exposure (extrinsic triggering), ultraviolet light exposure (extrinsic triggering), and different pH levels (intrinsic triggering). The deep learning-based predictions significantly outperform linear predictions, proving the utility of advanced computational methods in drug delivery. Our findings demonstrate the potential of these nanocarriers and highlight the efficacy of deep learning models in predicting drug release behavior, paving the way for enhanced cancer treatment strategies.

Next-Generation Cancer Phenomics: A Transformative Approach to Unraveling Lung Cancer Complexity and Advancing Precision Medicine

Lung cancer remains one of the leading causes of cancer-related deaths globally, with its complexity driven by intricate and intertwined genetic, epigenetic, and environmental factors. Despite advances in genomics, transcriptomics, and proteomics, understanding the phenotypic diversity of lung cancer has lagged behind. Next-generation phenomics, which integrates high-throughput phenotypic data with multiomics approaches and digital technologies such as artificial intelligence (AI), offers a transformative strategy for unraveling the complexity of lung cancer. This approach leverages advanced imaging, single-cell technologies, and AI to capture dynamic phenotypic variations at cellular, tissue, and whole organism levels and in ways resolved in temporal and spatial contexts. By mapping the high-throughput and spatially and temporally resolved phenotypic profiles onto molecular alterations, next-generation phenomics provides deeper insights into the tumor microenvironment, cancer heterogeneity, and drug efficacy, safety, and resistance mechanisms. Furthermore, integrating phenotypic data with genomic and proteomic networks allows for the identification of novel biomarkers and therapeutic targets in ways informed by biological structure and function, fostering precision medicine in lung cancer treatment. This expert review examines and places into context the current advances in next-generation phenomics and its potential to redefine lung cancer diagnosis, prognosis, and therapy. It highlights the emerging role of AI and machine learning in analyzing complex phenotypic datasets, enabling personalized therapeutic interventions. Ultimately, next-generation phenomics holds the promise of bridging the gap between molecular alterations and clinical and population health outcomes, providing a holistic understanding of lung cancer biology that could revolutionize its management and improve patient survival rates.

Drug Mechanism: A bioinformatic update

A drug Mechanism of Action (MoA) is a complex biological phenomenon that describes how a bioactive compound produces a pharmacological effect. The complete knowledge of MoA is fundamental to fully understanding the drug activity. Over the years, many experimental methods have been developed and a huge quantity of data has been produced. Nowadays, considering the increasing omics data availability and the improvement of the accessible computational resources, the study of a drug MoA is conducted by integrating experimental and bioinformatics approaches. The development of new in silico solutions for this type of analysis is continuously ongoing; herein, an updating review on such bioinformatic methods is presented. The methodologies cited are based on multi-omics data integration in biochemical networks and Machine Learning (ML). The multiple types of usable input data and the advantages and disadvantages of each method have been analyzed, with a focus on their applications. Three specific research areas (i.e. cancer drug development, antibiotics discovery, and drug repurposing) have been chosen for their importance in the drug discovery fields in which the study of drug MoA, through novel bioinformatics approaches, is particularly productive.

Up to the Herculean Task of Tackling Cancer Therapy Resistance

Cancer therapy resistance still poses the biggest hurdle to cancer treatment [...].

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.

Understanding cancer drug resistance with Sleeping Beauty functional genomic screens: Application to MAPK inhibition in cutaneous melanoma

Combined BRAF and MEK inhibition is an effective treatment for BRAF-mutant cutaneous melanoma. However, most patients progress on this treatment due to drug resistance. Here, we applied the Sleeping Beauty transposon system to understand how melanoma evades MAPK inhibition. We found that the specific drug resistance mechanisms differed across melanomas in our genetic screens of five cutaneous melanoma cell lines. While drivers that reactivated MAPK were highly conserved, many others were cell-line specific. One such driver, VAV1, activated a de-differentiated transcriptional program like that of hyperactive RAC1, RAC1P29S. To target this mechanism, we showed that an inhibitor of SRC, saracatinib, blunts the VAV1-induced transcriptional reprogramming. Overall, we highlighted the importance of accounting for melanoma heterogeneity in treating cutaneous melanoma with MAPK inhibitors. Moreover, we demonstrated the utility of the Sleeping Beauty transposon system in understanding cancer drug resistance.

NeuPD-A Neural Network-Based Approach to Predict Antineoplastic Drug Response

With the beginning of the high-throughput screening, in silico-based drug response analysis has opened lots of research avenues in the field of personalized medicine. For a decade, many different predicting techniques have been recommended for the antineoplastic (anti-cancer) drug response, but still, there is a need for improvements in drug sensitivity prediction. The intent of this research study is to propose a framework, namely NeuPD, to validate the potential anti-cancer drugs against a panel of cancer cell lines in publicly available datasets. The datasets used in this work are Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE). As not all drugs are effective on cancer cell lines, we have worked on 10 essential drugs from the GDSC dataset that have achieved the best modeling results in previous studies. We also extracted 1610 essential oncogene expressions from 983 cell lines from the same dataset. Whereas, from the CCLE dataset, 16,383 gene expressions from 1037 cell lines and 24 drugs have been used in our experiments. For dimensionality reduction, Pearson correlation is applied to best fit the model. We integrate the genomic features of cell lines and drugs' fingerprints to fit the neural network model. For evaluation of the proposed NeuPD framework, we have used repeated K-fold cross-validation with 5 times repeats where K = 10 to demonstrate the performance in terms of root mean square error (RMSE) and coefficient determination (R²). The results obtained on the GDSC dataset that were measured using these cost functions show that our proposed NeuPD framework has outperformed existing approaches with an RMSE of 0.490 and R² of 0.929.

Molecular features and predictive models identify the most lethal subtype and a therapeutic target for osteosarcoma

Background

Osteosarcoma is the most common primary malignant bone tumor. The existing treatment regimens remained essentially unchanged over the past 30 years; hence the prognosis has plateaued at a poor level. Precise and personalized therapy is yet to be exploited.

Methods

One discovery cohort (n=98) and two validation cohorts (n=53 & n=48) were collected from public data sources. We performed a non-negative matrix factorization (NMF) method on the discovery cohort to stratify osteosarcoma. Survival analysis and transcriptomic profiling characterized each subtype. Then, a drug target was screened based on subtypes' features and hazard ratios. We also used specific siRNAs and added a cholesterol pathway inhibitor to osteosarcoma cell lines (U2OS and Saos-2) to verify the target. Moreover, PermFIT and ProMS, two support vector machine (SVM) tools, and the least absolute shrinkage and selection operator (LASSO) method, were employed to establish predictive models.

Results

We herein divided osteosarcoma patients into four subtypes (S-I ~ S-IV). Patients of S- I were found probable to live longer. S-II was characterized by the highest immune infiltration. Cancer cells proliferated most in S-III. Notably, S-IV held the most unfavorable outcome and active cholesterol metabolism. SQLE, a rate-limiting enzyme for cholesterol biosynthesis, was identified as a potential drug target for S-IV patients. This finding was further validated in two external independent osteosarcoma cohorts. The function of SQLE to promote proliferation and migration was confirmed by cell phenotypic assays after the specific gene knockdown or addition of terbinafine, an inhibitor of SQLE. We further employed two machine learning tools based on SVM algorithms to develop a subtype diagnostic model and used the LASSO method to establish a 4-gene model for predicting prognosis. These two models were also verified in a validation cohort.

Conclusion

The molecular classification enhanced our understanding of osteosarcoma; the novel predicting models served as robust prognostic biomarkers; the therapeutic target SQLE opened a new way for treatment. Our results served as valuable hints for future biological studies and clinical trials of osteosarcoma.

SRC-RAC1 signaling drives drug resistance to BRAF inhibition in de-differentiated cutaneous melanomas

Rare gain-of-function mutations in RAC1 drive drug resistance to targeted BRAF inhibition in cutaneous melanoma. Here, we show that wildtype RAC1 is a critical driver of growth and drug resistance, but only in a subset of melanomas with elevated markers of de-differentiation. Similarly, SRC inhibition also selectively sensitized de-differentiated melanomas to BRAF inhibition. One possible mechanism may be the suppression of the de-differentiated state, as SRC and RAC1 maintained markers of de-differentiation in human melanoma cells. The functional differences between melanoma subtypes suggest that the clinical management of cutaneous melanoma can be enhanced by the knowledge of differentiation status. To simplify the task of classification, we developed a binary classification strategy based on a small set of ten genes. Using this gene set, we reliably determined the differentiation status previously defined by hundreds of genes. Overall, our study informs strategies that enhance the precision of BRAFi by discovering unique vulnerabilities of the de-differentiated cutaneous melanoma subtype and creating a practical method to resolve differentiation status.

Machine Learning in Drug Metabolism Study

Metabolic reactions in the body transform the administered drug into metabolites. These metabolites exhibit diverse biological activities. Drug metabolism is the major underlying cause of drug overdose-related toxicity, adversative drug effects and the drug's reduced efficacy. Though metabolic reactions deactivate a drug, drug metabolites are often considered pivotal agents for off-target effects or toxicity. On the other side, in combination drug therapy, one drug may influence another drug's metabolism and clearance and is thus considered one of the primary causes of drug-drug interactions. Today with the advancement of machine learning, the metabolic fate of a drug candidate can be comprehensively studied throughout the drug development procedure. Naïve Bayes, Logistic Regression, k-Nearest Neighbours, Decision Trees, different Boosting and Ensemble methods, Support Vector Machines and Artificial Neural Network boosted Deep Learning are some machine learning algorithms which are being extensively used in such studies. Such tools are covering several attributes of drug metabolism, with an emphasis on the prediction of drug-drug interactions, drug-target-interactions, clinical drug responses, metabolite predictions, sites of metabolism, etc. These reports are crucial for evaluating metabolic stability and predicting prospective drug-drug interactions, and can help pharmaceutical companies accelerate the drug development process in a less resourcedemanding manner than what in vitro studies offer. It could also help medical practitioners to use combinatorial drug therapy in a more resourceful manner. Also, with the help of the enormous growth of deep learning, traditional fields of computational drug development like molecular interaction fields, molecular docking, quantitative structure-toactivity relationship (QSAR) studies and quantum mechanical simulations are producing results which were unimaginable couple of years back. This review provides a glimpse of a few contextually relevant machine learning algorithms and then focuses on their outcomes in different studies.