A Two-Stage Multiple Instance Learning Framework for the Detection of Breast Cancer in Mammograms.

Mammograms are commonly employed in the large scale screening of breast cancer which is primarily characterized by the presence of malignant masses. However, automated image-level detection of malignancy is a challenging task given the small size of the mass regions and difficulty in discriminating between malignant, benign mass and healthy dense fibro-glandular tissue. To address these issues, we explore a two-stage Multiple Instance Learning (MIL) framework.

Identification of the potential regions of Epap-1 that interacts with V3 loop of HIV-1 gp120.

Early pregnancy associated protein-1 (Epap-1), a 90kDa glycoprotein present in first trimester placental tissue, inhibits HIV-1 entry through interaction with HIV-1 gp120 at V3 and C5 regions. In the present study, we have identified the specific 32 mer region of Epap-1 that can interact with V3 loop. This was achieved by docking between Epap-1 molecular model and gp120 and studying the interaction of peptides with gp120 in vitro.