Machine learning enabled classification of lung cancer cell lines co-cultured with fibroblasts with lightweight convolutional neural network for initial diagnosis.

BACKGROUND: Identification of lung cancer subtypes is critical for successful treatment in patients, especially those in advanced stages. Many advanced and personal treatments require knowledge of specific mutations, as well as up- and down-regulations of genes, for effective targeting of the cancer cells. While many studies focus on individual cell structures and delve deeper into gene sequencing, the present study proposes a machine learning method for lung cancer classification based on low-magnification cancer outgrowth patterns in a 2D co-culture environment. METHODS: Using a magnetic well plate holder, circular pattern lung cancer cell clusters were generated among fibroblasts, and daily images were captured to monitor cancer outgrowth over a 9-day period. These outgrowth images were then augmented and used to train a convolutional neural network (CNN) model based on the lightweight TinyVGG architecture. The model was trained with pairs of classes representing three subtypes of NSCLC: A549 (adenocarcinoma), H520 (squamous cell carcinoma), and H460 (large cell carcinoma). The objective was to assess whether this lightweight machine learning model could accurately classify the three lung cancer cell lines at different stages of cancer outgrowth. Additionally, cancer outgrowth images of two patient-derived lung cancer cells, one with the KRAS oncogene and the other with the EGFR oncogene, were captured and classified using the CNN model. This demonstration aimed to investigate the translational potential of machine learning-enabled lung cancer classification. RESULTS: The lightweight CNN model achieved over 93% classification accuracy at 1 day of outgrowth among A549, H460, and H520, and reached 100% classification accuracy at 7 days of outgrowth. Additionally, the model achieved 100% classification accuracy at 4 days for patient-derived lung cancer cells. Although these cells are classified as Adenocarcinoma, their outgrowth patterns vary depending on their oncogene expressions (KRAS or EGFR). CONCLUSIONS: These results demonstrate that the lightweight CNN architecture, operating locally on a laptop without network or cloud connectivity, can effectively create a machine learning-enabled model capable of accurately classifying lung cancer cell subtypes, including those derived from patients, based upon their outgrowth patterns in the presence of surrounding fibroblasts. This advancement underscores the potential of machine learning to enhance early lung cancer subtyping, offering promising avenues for improving treatment outcomes in advanced stage-patients.

Screening and brief intervention for unhealthy substance use in patients with chronic medical conditions: a systematic review.

AIMS AND OBJECTIVES: This systematic review describes studies evaluating screening tools and brief interventions for addressing unhealthy substance use in primary care patients with hypertension, diabetes or depression. BACKGROUND: Primary care is the main entry point to the health care system for most patients with comorbid unhealthy substance use and chronic medical conditions. Although of great public health importance, systematic reviews of screening tools and brief interventions for unhealthy substance use in this population that are also feasible for use in primary care have not been conducted. DESIGN: Systematic review. METHODS: We systematically review the research literature on evidence-based tools for screening for unhealthy substance use in primary care patients with depression, diabetes and hypertension, and utilising brief interventions with this population. RESULTS: Despite recommendations to screen for and intervene with unhealthy substance use in primary care patients with chronic medical conditions, the review found little indication of routine use of these practices. Limited evidence suggested the Alcohol Use Disorders Identification Test and Alcohol Use Disorders Identification Test-C screeners had adequate psychometric characteristics in patients with the selected chronic medical conditions. Screening scores indicating more severe alcohol use were associated with health-risk behaviours and poorer health outcomes, adding to the potential usefulness of screening for unhealthy alcohol use in this population. CONCLUSIONS: Studies support brief interventions' effectiveness with patients treated for hypertension or depression who hazardously use alcohol or cannabis, for both substance use and chronic medical condition outcomes. RELEVANCE TO CLINICAL PRACTICE: Although small, the international evidence base suggests that screening with the Alcohol Use Disorders Identification Test or Alcohol Use Disorders Identification Test-C and brief interventions for primary care patients with chronic medical conditions, delivered by nurses or other providers, are effective for identifying unhealthy substance use and associated with healthy behaviours and improved outcomes. Lacking are studies screening for illicit drug use, and using single-item screening tools, which could be especially helpful for frontline primary care providers including nurses.

Social processes explaining the benefits of Al-Anon participation.

This study examined social processes of support, goal direction, provision of role models, and involvement in rewarding activities to explain benefits of participating in Al-Anon, a 12-step mutual-help program for people concerned about another person's substance use. Newcomers to Al-Anon were studied at baseline and 6 months later, at which time they were identified as having either sustained attendance or dropped out. Among both newcomers and established Al-Anon members ("old-timers"), we also used number of Al-Anon meetings attended during follow-up to indicate extent of participation. Social processes significantly mediated newcomers' sustained attendance status versus dropped out and outcomes of Al-Anon in the areas of life context (e.g., better quality of life, better able to handle problems due to the drinker), improved positive symptoms (e.g., higher self-esteem, more hopeful), and decreased negative symptoms (e.g., less abuse, less depressed). Social processes also significantly mediated newcomers' number of meetings attended and outcomes. However, among old-timers, Al-Anon attendance was not associated with outcomes, so the potential mediating role of social processes could not be examined, but social processes were associated with outcomes. Findings add to the growing body of work identifying mechanisms by which 12-step groups are effective, by showing that bonding, goal direction, and access to peers in recovery and rewarding pursuits help to explain associations between sustained Al-Anon participation among newcomers and improvements on key concerns of Al-Anon attendees. Al-Anon is free of charge and widely available, making it a potentially cost-effective public health resource for help alleviating negative consequences of concern about another's addiction.

Self-made phage libraries with heterologous inserts in the Mtd of Bordetella bronchiseptica.

Phage display libraries are widely used as tools for identifying, dissecting and optimizing ligands. Development of a simple method to access greater library diversities could expedite and expand the technique. This paper reports progress toward harnessing the naturally occurring diversity generating retroelement used by Bordetella bronchiseptica bacteriophage to alter its tail-fiber protein. Mutagenesis and testing identified four sites amenable to the insertion of <19-residue heterologous peptides within the variable region. Such sites allow auto-generation of peptide libraries surrounded by a scaffold with additional variations. The resultant self-made phage libraries were used successfully for selections targeting anti-FLAG antibody, immobilized metal affinity chromatography microtiter plates and HIV-1 gp41. The reported experiments demonstrate the utility of the major tropism determinant protein of B.bronchiseptica as a natural scaffold for diverse, phage-constructed libraries with heterologous self-made phage libraries.

Human genome sequencing using unchained base reads on self-assembling DNA nanoarrays.

Genome sequencing of large numbers of individuals promises to advance the understanding, treatment, and prevention of human diseases, among other applications. We describe a genome sequencing platform that achieves efficient imaging and low reagent consumption with combinatorial probe anchor ligation chemistry to independently assay each base from patterned nanoarrays of self-assembling DNA nanoballs. We sequenced three human genomes with this platform, generating an average of 45- to 87-fold coverage per genome and identifying 3.2 to 4.5 million sequence variants per genome. Validation of one genome data set demonstrates a sequence accuracy of about 1 false variant per 100 kilobases. The high accuracy, affordable cost of $4400 for sequencing consumables, and scalability of this platform enable complete human genome sequencing for the detection of rare variants in large-scale genetic studies.