A decision support system based on artificial intelligence and systems biology for the simulation of pancreatic cancer patient status.

Oncology treatments require continuous individual adjustment based on the measurement of multiple clinical parameters. Prediction tools exploiting the patterns present in the clinical data could be used to assist decision making and ease the burden associated to the interpretation of all these parameters. The goal of this study was to predict the evolution of patients with pancreatic cancer at their next visit using information routinely recorded in health records, providing a decision-support system for clinicians. We selected hematological variables as the visit's clinical outcomes, under the assumption that they can be predictive of the evolution of the patient. Multivariate models based on regression trees were generated to predict next-visit values for each of the clinical outcomes selected, based on the longitudinal clinical data as well as on molecular data sets streaming from in silico simulations of individual patient status at each visit. The models predict, with a mean prediction score (balanced accuracy) of 0.79, the evolution trends of eosinophils, leukocytes, monocytes, and platelets. Time span between visits and neutropenia were among the most common factors contributing to the predicted evolution. The inclusion of molecular variables from the systems-biology in silico simulations provided a molecular background for the observed variations in the selected outcome variables, mostly in relation to the regulation of hematopoiesis. In spite of its limitations, this study serves as a proof of concept for the application of next-visit prediction tools in real-world settings, even when available data sets are small.

Female Sex, Age, and Unfavorable Response to Tumor Necrosis Factor Inhibitors in Patients With Axial Spondyloarthritis: Results of Statistical and Artificial Intelligence-Based Data Analyses of a National Multicenter Prospective Registry.

OBJECTIVE: Real-world studies are needed to identify factors associated with response to biologic therapies in patients with axial spondyloarthritis (SpA). The objective was to assess sex differences in response to tumor necrosis factor inhibitors (TNFi) and to explore possible risk factors associated with TNFi efficacy. METHODS: A total of 969 patients with axial SpA (315 females, 654 males) enrolled in the BIOBADASER registry (2000-2019) who initiated a TNFi (first, second, or further lines) were studied. Statistical and artificial intelligence (AI)-based data analyses were used to explore the association of sex differences and other factors to TNFi response, using the Bath Ankylosing Spondylitis Disease Activity Index (BASDAI), to calculate the BASDAI50, with an improvement of at least 50% of the BASDAI score, and using the Ankylosing Spondylitis Disease Activity Score, calculated using the C-reactive protein level (ASDAS-CRP). RESULTS: Females had a lower probability of reaching a BASDAI50 response with a first line TNFi treatment at the second year of follow-up (P = 0.018) and a lesser reduction of the ASDAS-CRP at this time point. The logistic regression model showed lower BASDAI50 responses to TNFi in females (P = 0.05). Other factors, such as older age (P = 0.004), were associated with unfavorable responses. The AI data analyses reinforced the idea that age at the beginning of the treatment was the main factor associated with an unfavorable response. The combination of age with other clinical characteristics (female sex or cardiovascular risk factors and events) potentially contributed to an unfavorable response to TNFi. CONCLUSION: In this national multicenter registry, female sex was associated with less response to a first-line TNFi by the second year of follow-up. A higher age at the start of the TNFi was the main factor associated with an unfavorable response to TNFi.

The LEGACy study: a European and Latin American consortium to identify risk factors and molecular phenotypes in gastric cancer to improve prevention strategies and personalized clinical decision making globally.

BACKGROUND: Gastric Cancer (GC) is the fourth most deadly cancer worldwide. Enhanced understanding of its key epidemiological and molecular drivers is urgently needed to lower the incidence and improve outcomes. Furthermore, tumor biology in European (EU) and Latin American (LATAM) countries is understudied. The LEGACy study is a Horizon 2020 funded multi-institutional research approach to 1) detail the epidemiological features including risk factors of GC in current time and 2) develop cost-effective methods to identify and integrate biological biomarkers needed to guide diagnostic and therapeutic approaches with the aim of filling the knowledge gap on GC in these areas. METHODS: This observational study has three parts that are conducted in parallel during 2019-2023 across recruiting centers from four EU and four LATAM countries: Part 1) A case-control study (800 cases and 800 controls) using questionnaires on candidate risk factors for GC, which will be correlated with clinical, demographic and epidemiological parameters. Part 2) A case-control tissue sampling study (400 cases and 400 controls) using proteome, genome, microbiome and immune analyses to characterize advanced (stage III and IV) GC. Patients in this part of the study will be followed over time to observe clinical outcomes. The first half of samples will be used as training cohort to identify the most relevant risk factors and biomarkers, which will be selected to propose cost-effective diagnostic and predictive methods that will be validated with the second half of samples. Part 3) An educational study, as part of our prevention strategy (subjects recruited from the general public) to test and disseminate knowledge on GC risk factors and symptoms by a questionnaire and informative video. Patients could be recruited for more than one of the three LEGACy studies. DISCUSSION: The LEGACy study aims to generate novel, in-depth knowledge on the tumor biological characteristics through integrating epidemiological, multi-omics and clinical data from GC patients at an EU-LATAM partnership. During the study, cost-effective panels with potential use in clinical decision making will be developed and validated. TRIAL REGISTRATION: ClinicalTrials.gov Identifiers: Part 1: NCT03957031 . Part 2: NCT04015466 . Part 3: NCT04019808 .

Exploring the synergistic effects of cabozantinib and a programmed cell death protein 1 inhibitor in metastatic renal cell carcinoma with machine learning.

Clinical evidence supports the combination of cabozantinib with an immune checkpoint inhibitor for the treatment of metastatic clear cell renal cell carcinoma (mccRCC) and suggests a synergistic antitumour activity of this combination. Nevertheless, the biological basis of this synergy is not fully characterized. We studied the mechanisms underpinning the potential synergism of cabozantinib combined with a PD1 inhibitor in mccRCC and delved into cabozantinib monotherapy properties supporting its role to partner these combinations. To model physiological drug action, we used a machine learning-based technology known as Therapeutic Performance Mapping Systems, applying two approaches: Artificial Neural Networks and Sampling Methods. We found that the combined therapy was predicted to exert a wide therapeutic action in the tumour and the microenvironment. Cabozantinib may enhance the effects of PD1 inhibitors on immunosurveillance by modulating the innate and adaptive immune system, through the inhibition of VEGF-VEGFR and Gas6-AXL/TYRO3/MER (TAM) axes, while the PD1 inhibitors may boost the antiangiogenic and pro-apoptotic effects of cabozantinib by modulating angiogenesis and T-cell cytotoxicity. Cabozantinib alone was predicted to restore cellular adhesion and hamper tumour proliferation and invasion. These data provide a biological rationale and further support for cabozantinib plus PD1 inhibitor combination and may guide future nonclinical and clinical research.

Proteomics based drug repositioning applied to improve in vitro fertilization implantation: an artificial intelligence model.

Embryo implantation is one of the most inefficient steps in assisted reproduction, so the identifying drugs with a potential clinical application to improve it has a strong interest. This work applies artificial intelligence and systems biology-based mathematical modeling strategies to unveil potential treatments by computationally analyzing and integrating available molecular and clinical data from patients. The mathematical models of embryo implantation computationally generated here simulate the molecular networks underneath this biological process. Once generated, these models were analyzed in order to identify potential repositioned drugs (drugs already used for other indications) able to improve embryo implantation by modulating the molecular pathways involved. Interestingly, the repositioning analysis has identified drugs considering two endpoints: (1) drugs able to modulate the activity of proteins whose role in embryo implantation is already bibliographically acknowledged, and (2) drugs that modulate key proteins in embryo implantation previously predicted through a mechanistic analysis of the mathematical models. This second approach increases the scope open for examination and potential novelty of the repositioning strategy. As a result, a list of 23 drug candidates to improve embryo implantation after IVF was identified by the mathematical models. This list includes many of the compounds already tested for this purpose, which reinforces the predictive capacity of our approach, together with novel repositioned candidates (e.g., Infliximab, Polaprezinc, and Amrinone). In conclusion, the present study exploits existing molecular and clinical information to offer new hypotheses regarding molecular mechanisms in embryo implantation and therapeutic candidates to improve it. This information will be very useful to guide future research.Abbreviations: IVF: in vitro fertilization; EI: Embryo implantation; TPMS: Therapeutic Performance Mapping System; MM: mathematical models; ANN: Artificial Neuronal Networks; TNFα: tumour necrosis factor factor-alpha; HSPs: heat shock proteins; VEGF: vascular endothelial growth factor; PPARA: peroxisome proliferator activated receptor-α PXR: pregnane X receptor; TTR: transthyretin; BED: Biological Effectors Database; MLP: multilayer perceptron.

Head to head evaluation of second generation ALK inhibitors brigatinib and alectinib as first-line treatment for ALK+ NSCLC using an in silico systems biology-based approach.

Around 3-7% of patients with non-small cell lung cancer (NSCLC), which represent 85% of diagnosed lung cancers, have a rearrangement in the ALK gene that produces an abnormal activity of the ALK protein cell signaling pathway. The developed ALK tyrosine kinase inhibitors (TKIs), such as crizotinib, ceritinib, alectinib, brigatinib and lorlatinb present good performance treating ALK+ NSCLC, although all patients invariably develop resistance due to ALK secondary mutations or bypass mechanisms. In the present study, we compare the potential differences between brigatinib and alectinib's mechanisms of action as first-line treatment for ALK+ NSCLC in a systems biology-based in silico setting. Therapeutic performance mapping system (TPMS) technology was used to characterize the mechanisms of action of brigatinib and alectinib and the impact of potential resistances and drug interferences with concomitant treatments. The analyses indicate that brigatinib and alectinib affect cell growth, apoptosis and immune evasion through ALK inhibition. However, brigatinib seems to achieve a more diverse downstream effect due to a broader cancer-related kinase target spectrum. Brigatinib also shows a robust effect over invasiveness and central nervous system metastasis-related mechanisms, whereas alectinib seems to have a greater impact on the immune evasion mechanism. Based on this in silico head to head study, we conclude that brigatinib shows a predicted efficacy similar to alectinib and could be a good candidate in a first-line setting against ALK+ NSCLC. Future investigation involving clinical studies will be needed to confirm these findings. These in silico systems biology-based models could be applied for exploring other unanswered questions.

Systems biology drug screening identifies statins as enhancers of current therapies in chronic lymphocytic leukemia.

Chronic lymphocytic leukemia (CLL) is a B lymphoid malignancy highly dependent on the microenvironment. Despite new targeted therapies such as ibrutinib and venetoclax, disease progression and relapse remain an issue. CLL cell interactions with the supportive tissue microenvironment play a critical role in disease pathogenesis. We used a platform for drug discovery based on systems biology and artificial intelligence, to identify drugs targeting key proteins described to have a role in the microenvironment. The selected compounds were screened in CLL cell lines in the presence of stromal cells to mimic the microenvironment and validated the best candidates in primary CLL cells. Our results showed that the commercial drug simvastatin was the most effective and selective out of the tested compounds. Simvastatin decreased CLL cell survival and proliferation as well as cell adhesion. Importantly, this drug enhanced the antitumor effect of venetoclax and ibrutinib. We proposed that systems biology approaches combined with pharmacological screening could help to find new drugs for CLL treatment and to predict new combinations with current therapies. Our results highlight the possibility of repurposing widely used drugs such as statins to target the microenvironment and to improve the efficacy of ibrutinib or venetoclax in CLL cells.

In-silico simulated prototype-patients using TPMS technology to study a potential adverse effect of sacubitril and valsartan.

Unveiling the mechanism of action of a drug is key to understand the benefits and adverse reactions of a medication in an organism. However, in complex diseases such as heart diseases there is not a unique mechanism of action but a wide range of different responses depending on the patient. Exploring this collection of mechanisms is one of the clues for a future personalized medicine. The Therapeutic Performance Mapping System (TPMS) is a Systems Biology approach that generates multiple models of the mechanism of action of a drug. Each molecular mechanism generated could be associated to particular individuals, here defined as prototype-patients, hence the generation of models using TPMS technology may be used for detecting adverse effects to specific patients. TPMS operates by (1) modelling the responses in humans with an accurate description of a protein network and (2) applying a Multilayer Perceptron-like and sampling strategy to find all plausible solutions. In the present study, TPMS is applied to explore the diversity of mechanisms of action of the drug combination sacubitril/valsartan. We use TPMS to generate a wide range of models explaining the relationship between sacubitril/valsartan and heart failure (the indication), as well as evaluating their association with macular degeneration (a potential adverse effect). Among the models generated, we identify a set of mechanisms of action associated to a better response in terms of heart failure treatment, which could also be associated to macular degeneration development. Finally, a set of 30 potential biomarkers are proposed to identify mechanisms (or prototype-patients) more prone of suffering macular degeneration when presenting good heart failure response. All prototype-patients models generated are completely theoretical and therefore they do not necessarily involve clinical effects in real patients. Data and accession to software are available at http://sbi.upf.edu/data/tpms/.

Novel Neuroprotective Multicomponent Therapy for Amyotrophic Lateral Sclerosis Designed by Networked Systems.

Amyotrophic Lateral Sclerosis is a fatal, progressive neurodegenerative disease characterized by loss of motor neuron function for which there is no effective treatment. One of the main difficulties in developing new therapies lies on the multiple events that contribute to motor neuron death in amyotrophic lateral sclerosis. Several pathological mechanisms have been identified as underlying events of the disease process, including excitotoxicity, mitochondrial dysfunction, oxidative stress, altered axonal transport, proteasome dysfunction, synaptic deficits, glial cell contribution, and disrupted clearance of misfolded proteins. Our approach in this study was based on a holistic vision of these mechanisms and the use of computational tools to identify polypharmacology for targeting multiple etiopathogenic pathways. By using a repositioning analysis based on systems biology approach (TPMS technology), we identified and validated the neuroprotective potential of two new drug combinations: Aliretinoin and Pranlukast, and Aliretinoin and Mefloquine. In addition, we estimated their molecular mechanisms of action in silico and validated some of these results in a well-established in vitro model of amyotrophic lateral sclerosis based on cultured spinal cord slices. The results verified that Aliretinoin and Pranlukast, and Aliretinoin and Mefloquine promote neuroprotection of motor neurons and reduce microgliosis.

Methods for diagnosing perceived age on the basis of an ensemble of phenotypic features.

BACKGROUND: Perceived age has been defined as the age that a person is visually estimated to be on the basis of physical appearance. In a society where a youthful appearance are an object of desire for consumers, and a source of commercial profit for cosmetic companies, this concept has a prominent role. In addition, perceived age is also an indicator of overall health status in elderly people, since old-looking people tend to show higher rates of morbidity and mortality. However, there is a lack of objective methods for quantifying perceived age. METHODS: In order to satisfy the need of objective approaches for estimating perceived age, a novel algorithm was created. The novel algorithm uses supervised mathematical learning techniques and error retropropagation for the creation of an artificial neural network able to learn biophysical and clinically assessed parameters of subjects. The algorithm provides a consistent estimation of an individual's perceived age, taking into account a defined set of facial skin phenotypic traits, such as wrinkles and roughness, number of wrinkles, depth of wrinkles, and pigmentation. A nonintervention, epidemiological cross-sectional study of cases and controls was conducted in 120 female volunteers for the diagnosis of perceived age using this novel algorithm. Data collection was performed by clinical assessment of an expert panel and biophysical assessment using the ANTERA 3D(®) device. RESULTS AND DISCUSSION: Employing phenotype data as variables and expert assignments as objective data, the algorithm was found to correctly classify the samples with an accuracy of 92.04%. Therefore, we have developed a method for determining the perceived age of a subject in a standardized, consistent manner. Further application of this algorithm is thus a promising approach for the testing and validation of cosmetic treatments and aesthetic surgery, and it also could be used as a screening method for general health status in the population.