Abstract: One or more techniques for optimizing cancer classification based on covariate characteristics is disclosed. In a first approach, an analytics system may determine separate cutoff thresholds for positively detecting disease signal for different labels for a covariate characteristic. The system may subdivide training samples based on their labels for the covariate characteristic, to separately determine the cutoff thresholds. In other approaches, the system may train disparate classifiers for each population. The system separates the training samples based on their labels for the covariate characteristic, and separately trains classifiers to generate a signal vector representing an amount of disease signal detected in a sample. The classifiers may be trained on different feature sets as determined based on mutual information gain, genomic region coverage, and healthy activation fraction.

Abstract: Disclosed are methods and systems to facilitate automatic distribution of communications. In particular, a server may maintain data that indicates at least one registered subject-matter interest respectively for each of a plurality of users. Further, the server may receive a communication from a source user. The source user may be served by a particular base station. In response to receiving the communication, the server may identify one or more target users based on each target user (i) having at least one registered subject-matter interest that matches at least one subject-matter interest of the source user and (ii) being served either by the same particular base station that serves the source user or by a base station adjacent to the particular base station that serves the source user. The server may forward the communication to each identified target user.