Abstract: Embodiments disclosed herein generally relate to using an attention-based machine learning model to generate an output that includes at least one of an interaction prediction for a target interaction, an interaction affinity prediction, or an immunogenicity prediction relating to a target interaction for a corresponding peptide-immunoprotein complex (IPC) combination. A target interaction may be between a peptide and an immunogenicity complex (IPC) such as, for example, a major histocompatibility complex (MHC), a T cell receptor (TCR), or both. A pharmaceutical composition may be identified, manufactured, and/or used that includes one or more peptides for which one or more target interactions are predicted to be more likely. Methods of treatment may be defined and/or used that include administration of such a pharmaceutical composition.

Abstract: In one embodiment, a signal processor for linearizing a non-linear circuit through pre-distortion of an input signal is provided that includes: a first coupler for extracting a version of the input signal, wherein a remaining portion of the input signal not extracted by the first coupler is provided to a first node; a mixer for multiplying the extracted version of the input signal with a pre-distortion signal to produce an additive signal, the pre-distortion signal having a relatively small or zero constant component such that the additive signal includes either no linear version of the input signal or a linear version of the input signal that has a lower power than the remaining portion of the input signal; and a second coupler to add the additive signal to the remaining portion of the input signal at the first node to form a pre-distorted input signal, whereby if the non-linear circuit processes the pre-distorted input signal to form an output signal, the output signal is a substantially linear function of