MLASM: Machine learning based prediction of anticancer small molecules.

Cancer, being the second leading cause of death globally. So, the development of effective anticancer treatments is crucial in the field of medicine. Anticancer peptides (ACPs) have shown promising therapeutic potential in cancer treatment compared to traditional methods. However, the process of identifying ACPs through experimental means is often time-intensive and expensive. To overcome this issue, we employed a machine learning-based approach for the first time to develop an anticancer model using small molecules. Anticancer small molecules (ACSMs) are compounds that have been developed to target and inhibit cancer cells. In this study, we used 10,000 compounds to develop the machine learning models using five algorithms such as, Random Forest (RF), Light gradient boosting machine (LightGBM), K-nearest neighbors (KNN), Decision tree (DT) and Extreme Gradient Boosting (XGB). The developed models were evaluated using the test set and top three models were identified (RF, LightGBM and XGB). Furthermore, to validate the predictive performance of our models, we have performed external validation using an FDA approved anticancer compounds/drugs. Following this analysis, we found that our LightGBM model correctly predicted 9 compounds as active. However, RF and XGB exhibited some limitations by predicting 8 and 7 compounds as active out of 10, respectively. These results demonstrate that, when compared to RF and XGB, the LightGBM model showcase robust prediction capabilities, achieving a superior accuracy of 79% with an AUC of 0.88. These findings provide promising insights into the potential of our approach for predicting anticancer small molecules, highlighting the role of machine learning in advancing cancer treatment research.

ANN multi-layer perceptron for prediction of blood-brain barrier permeable compounds for central nervous system therapeutics.

Endothelial cells produce a semipermeable barrier known as the blood-brain barrier (BBB) to keep undesired chemicals out of the central nervous system (CNS). However, this barrier also restricts the exploration of potential new medications due to insufficient exposure. To address this challenge, machine learning (ML) algorithms can be useful to predict the BBB permeability of chemical compounds. Support vector machines, continuous neural networks, and deep learning approaches have been used to identify compounds that can penetrate the BBB. However, predicting BBB permeability based solely on chemical structure can be difficult. In the current research, we developed an ML model using a large dataset to predict BBB permeability, which could be used for early-stage drug screening of potential CNS medications. Our artificial neural network ANN algorithm exhibited an accuracy of 0.94, specificity of 0.83, sensitivity of 0.97, AUC of 0.96, and MCC of 0.83. These metrics suggest that our model has a high accuracy rate in predicting BBB permeability and therefore has the potential to advance drug discovery efforts in the CNS. This study's outcomes demonstrate the potential for ML models to predict BBB permeability accurately, aiding in the identification of new CNS therapeutic options.Communicated by Ramaswamy H. Sarma.

Inducing Cytotoxicity in Colon Cancer Cells and Suppressing Cancer Stem Cells by Dolasetron and Ketoprofen through Inhibition of RNA Binding Protein PUM1.

Clinical trials of new drugs often face a high failure rate of approximately 45 percent due to safety and toxicity concerns. Repurposing drugs with well-established safety profiles becomes crucial in addressing this challenge. Colon cancer ranks as the third most prevalent cancer and the second leading cause of cancer related mortality worldwide. This study focuses on the RNA-binding protein pumilio1 (PUM1), a member of the PUF family involved in post-transcriptional gene expression regulation. By utilizing molecular docking techniques and FDA-approved drugs, potential inhibitors against PUM1 were identified. Notably, dolasetron and ketoprofen demonstrated promising results, exhibiting strong binding affinity, hydrophobic interactions, and favorable chemical reactivity according to Conceptual-DFT calculations. Both compounds effectively reduced cell viability, with IC50 values of 150 µM and 175 µM, respectively and shows long term inhibitory effects as seen by reduced in number of colonies. Moreover, they exhibited inhibitory effects on colon cancer stem cells, as indicated by reduced colonospheroid size and numbers. Apoptosis is induced by these compounds and has triggered activation of executioner caspase 3/7 in HCT116 cells which is evident through a caspase 3/7 assay and AO/EB staining, while the non-toxic effect of these compounds was evident from viability against non-cancerous cell line and hemolysis assay. Additionally, the treatment group showed a significant decrease in PUM1 and cancer stem cell markers expression compared to the control group. In conclusion, this study highlights the potential of targeting PUM1 as a novel approach to colon cancer treatment. Dolasetron and ketoprofen demonstrate promise as effective anti-cancer and anti-cancer stem cell drugs, inducing apoptosis in colon cancer cells through inhibition of PUM1.

Randomized Trial of Mindfulness-Based Stress Reduction in Cardiac Patients Eligible for Cardiac Rehabilitation.

Currently, exercise-based cardiac rehabilitation (CR) is the only recommended secondary prevention strategy for cardiac patients that attempts to tackle stress and psychosocial wellbeing, but it is under-utilized and lacks a comprehensive curriculum for this purpose; hence there is a critical gap to address psychosocial needs of cardiac patients after an event. Mindfulness-based stress reduction (MBSR) has shown benefits in the general population but its role in cardiac patients is not clear. We conducted a pilot randomized controlled trial (RCT) of MBSR in CR-eligible cardiac patients during their initial year of recovery. Patients were allocated 2:1 (intervention:control) to an 8-week MBSR group intervention or usual care. Standard measures of depression, anxiety, perceived stress, health related quality of life (HRQOL), blood pressure, biomarkers (lipids, HbA1c, CRP) and 24-hour Holter monitoring were obtained at baseline, 3- and 9-months post-randomization. Sub-group analyses were performed for participants with at least mild depression (PHQ-9 ≥ 5). 47 patients [mean age 58.6 years; 38% female; 77% white] were enrolled in 2 cohorts. 87% of MBSR patients completed the intervention; study retention was >95% at each follow-up visit. At 3 months, compared to controls, MBSR patients showed improvements in depression [p = 0.01] and anxiety [p = 0.04] with a similar trend in HRQOL [p = 0.06]. The MBSR group showed greater improvement or less worsening of most CV risk factors, with an attenuation of treatment effects at 9 months. Participants with at PHQ-9 scores ≥5 at baseline showed greater improvement in psychosocial and CV outcomes, that persisted at 9 months. MBSR is a safe and well received secondary prevention strategy. This pilot RCT provides preliminary evidence of MBSR's potential to improve short term psychosocial well-being in cardiac patients during their first year of recovery.

FDG-PET/CT for Assessing the Response to Neoadjuvant Chemotherapy in Bladder Cancer Patients.

PURPOSE: To determine the accuracy of 18F-fluorodeoxyglucose with positron emission tomography and computed tomography (FDG-PET/CT) scans in assessing the response to neoadjuvant chemotherapy (NAC) in patients with bladder cancer scheduled to undergo radical cystectomy (RC). PATIENTS AND METHODS: All patients treated at our center for muscle-invasive bladder cancer (MIBC) were counseled and offered NAC before RC. FDG-PET/CT scans were performed before the initiation of chemotherapy and after completion of the regimen. Patients with disease with complete response to NAC were those who had (pT0) or residual carcinoma-in-situ (pTis) on final pathology. Those who were downstaged from MIBC to non-MIBC were considered to have a chemosensitive tumor. We used percentage reduction in standardized maximum uptake value (SUVmax) from PET/CT scans as our measure to correlate with the final pathology after cystectomy. RESULTS: Thirty-seven patients with MIBC who underwent NAC followed by RC were included in the final analysis. FDG-PET/CT had 75% sensitivity (89.66% specificity) in identifying those with complete pathologic response with a 100% change in SUVmax, and 83% sensitivity (94% specificity) for the detection of chemosensitive tumors. CONCLUSION: FDG-PET/CT can help determine the response of primary tumor to NAC in patients with MIBC and thus can more accurately predict the prognosis of the patients, or potentially the appropriate time for cystectomy.

Comparative Evaluation of Bladder-specific Health-related Quality of Life Instruments for Bladder Cancer.

OBJECTIVE: To compare 2 bladder cancer-specific health-related quality of life instruments (HRQOL) in the same patient population. Previous HRQOL studies in cystectomy patients have yielded conflicting results. Using a cross-sectional study design, we examined the only 2 validated bladder cancer-specific (HRQOL) measures. METHODS: Of the 256 patients who had undergone radical cystectomy from 2009 to 2014, 131 met both inclusion and exclusion criteria. The Functional Assessment Cancer Therapy-Vanderbilt Cystectomy Index (FACT-VCI) and Bladder Cancer Index (BCI) were mailed to these patients. Overall HRQOL and individual domain scores were compared between the 2 instruments with a Spearman correlation coefficient. HRQOL scores were compared by urinary diversion type as well using a non-parametric Wilcoxon rank sum test. RESULTS: Our study had a response rate of 49% from 31 ileal conduit (IC) and 33 orthotopic neobladder patients. Overall, there was a moderate correlation between the FACT-VCI and BCI surveys (r = 0.57, P <.001). Responses on the BCI domains were strongly correlated with responses on the bladder cancer-specific domain of the FACT-VCI (r = 0.74, P <.001). The BCI scores for urinary function were significantly better in the IC group (P = .002). No significant difference was found between IC and orthotopic neobladder using the FACT-VCI. CONCLUSION: The FACT-VCI and BCI instruments correlate well within the same patient cohort but capture different aspects of HRQOL. By focusing exclusively on bladder cancer treatment concerns, the BCI appears to be a better tool for assessing and counseling patients on expected treatment-specific changes after diversion type.