Artificial intelligence (AI) is a general term that refers to the use of a machine to imitate intelligent behavior for performing complex tasks with minimal human intervention, such as machine learning; this technology is revolutionizing and reshaping medicine. AI has considerable potential to perfect health-care systems in areas such as diagnostics, risk analysis, health information administration, lifestyle supervision, and virtual health assistance. In terms of immunotherapy, AI has been applied to the prediction of immunotherapy responses based on immune signatures, medical imaging and histological analysis. These features could also be highly useful in the management of cancer immunotherapy given their ever-increasing performance in improving diagnostic accuracy, optimizing treatment planning, predicting outcomes of care and reducing human resource costs. In this review, we present the details of AI and the current progression and state of the art in employing AI for cancer immunotherapy. Furthermore, we discuss the challenges, opportunities and corresponding strategies in applying the technology for widespread clinical deployment. Finally, we summarize the impact of AI on cancer immunotherapy and provide our perspectives about underlying applications of AI in the future.

The Src-homology 2 domain containing phosphatase 2 (SHP2) plays a critical role in crucial signaling pathways and is involved in oncogenesis and in developmental disorders. Its structure includes two SH2 domains (N-SH2 and C-SH2), and a protein tyrosine phosphatase (PTP) domain. Under basal conditions, SHP2 is auto-inhibited, with the N-SH2 domain blocking the PTP active site. Activation involves a rearrangement of the domains that makes the catalytic site accessible, coupled to the association between the SH2 domains and cognate proteins containing phosphotyrosines. Several aspects of this transition are debated and competing mechanistic models have been proposed. A crystallographic structure of SHP2 in an active state has been reported (PDB code 6crf), but several lines of evidence suggests that it is not fully representative of the conformations populated in solution. To clarify the structural rearrangements involved in SHP2 activation, enhanced sampling simulations of the autoinhibited and active states have been performed, for wild type SHP2 and its pathogenic E76K variant. Our results demonstrate that the crystallographic conformation of the active state is unstable in solution, and multiple interdomain arrangements are populated, thus allowing association to bisphosphorylated sequences. Contrary to a recent proposal, activation is coupled to the conformational changes of the N-SH2 binding site, which is significantly more accessible in the active sate, rather than to the structure of the central β-sheet of the domain. In this coupling, a previously undescribed role for the N-SH2 BG loop emerged.

Overexpressed tumor-self antigens represent the largest group of candidate vaccine targets. Those exhibiting a role in oncogenesis may be some of the least studied but perhaps most promising. This review considers this subset of self antigens by highlighting vaccine efforts for some of the better known members and focusing on TPD52, a new promising vaccine target. We shed light on the importance of both preclinical and clinical vaccine studies demonstrating that tolerance and autoimmunity (presumed to preclude this class of antigens from vaccine development) can be overcome and do not present the obstacle that might have been expected. The potential of this class of antigens for broad application is considered, possibly in the context of low tumor burden or adjuvant therapy, as is the need to understand mechanisms of tolerance that are relatively understudied.