Kaushik Sengupta

Emerging roles of lamins and DNA damage repair mechanisms in ovarian cancer

Lamins are type V intermediate filament proteins which are ubiquitously present in all metazoan cells providing a platform for binding of chromatin and related proteins, thereby serving a wide range of nuclear functions including DNA damage repair. Altered expression of lamins in different subtypes of cancer is evident from researches worldwide. But whether cancer is a consequence of this change or this change is a consequence of cancer is a matter of future investigation. However changes in the expression levels of lamins is reported to have direct or indirect association with cancer progression or have regulatory roles in common neoplastic symptoms like higher nuclear deformability, increased genomic instability and reduced susceptibility to DNA damaging agents. It has already been proved that loss of A type lamin positively regulates cathepsin L, eventually leading to degradation of several DNA damage repair proteins, hence impairing DNA damage repair pathways and increasing genomic instability. It is established in ovarian cancer, that the extent of alteration in nuclear morphology can determine the degree of genetic changes and thus can be utilized to detect low to high form of serous carcinoma. In this review, we have focused on ovarian cancer which is largely caused by genomic alterations in the DNA damage response pathways utilizing proteins like RAD51, BRCA1, 53BP1 which are regulated by lamins. We have elucidated the current understanding of lamin expression in ovarian cancer and its implications in the regulation of DNA damage response pathways that ultimately result in telomere deformation and genomic instability.

A deep hybrid learning pipeline for accurate diagnosis of ovarian cancer based on nuclear morphology

Nuclear morphological features are potent determining factors for clinical diagnostic approaches adopted by pathologists to analyze the malignant potential of cancer cells. Considering the structural alteration of the nucleus in cancer cells, various groups have developed machine learning techniques based on variation in nuclear morphometric information like nuclear shape, size, nucleus-cytoplasm ratio and various non-parametric methods like deep learning have also been tested for analyzing immunohistochemistry images of tissue samples for diagnosing various cancers. We aim to correlate the morphometric features of the nucleus along with the distribution of nuclear lamin proteins with classical machine learning to differentiate between normal and ovarian cancer tissues. It has already been elucidated that in ovarian cancer, the extent of alteration in nuclear shape and morphology can modulate genetic changes and thus can be utilized to predict the outcome of low to a high form of serous carcinoma. In this work, we have performed exhaustive imaging of ovarian cancer versus normal tissue and developed a dual pipeline architecture that combines the matrices of morphometric parameters with deep learning techniques of auto feature extraction from pre-processed images. This novel Deep Hybrid Learning model, though derived from classical machine learning algorithms and standard CNN, showed a training and validation AUC score of 0.99 whereas the test AUC score turned out to be 1.00. The improved feature engineering enabled us to differentiate between cancerous and non-cancerous samples successfully from this pilot study.