Abstract: A polypeptide capable of inhibiting Tau aggregation includes an amino acid sequence sharing between 20% and 99% sequence similarity with a structured core region of a pathological Tau filament, where the polypeptide is capable of binding to an end of a Tau fibril and reducing Tau aggregation or Tau seeding activity. The polypeptide may include an amino acid sequence derived from a microtubule-associated protein such as MAP2 or MAP4. Methods for inhibiting Tau aggregation in a biological sample include contacting the biological sample containing Tau with the polypeptide, where the polypeptide binds to an end of a Tau fibril and reduces Tau aggregation relative to a control sample.

Abstract: Methods for serial amplification of Tau filaments and Tau assemblies include contacting monomeric Tau protein with Tau seed material under conditions permissive for seed-dependent fibril or assembly growth to produce amplified Tau filaments or assemblies, processing at least a portion of the amplified material to generate Tau seed material for further amplification, and repeating the contacting and processing steps to produce serially amplified Tau filaments or assemblies, where the monomeric Tau includes one or more Tau isoforms, variants, fragments, or modified forms. In some embodiments, Tau seed material is obtained from a biological sample associated with a Tauopathy. The methods further include characterizing amplified Tau filaments or assemblies or using the serial amplification process to identify compounds that modulate Tau assembly propagation by comparing propagation characteristics in the presence and absence of a test compound.

Abstract: Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.

Abstract: Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.

Abstract: Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.

Abstract: Approaches for cross-lingual regularization for multilingual generalization include a method for training a natural language processing (NLP) deep learning module. The method includes accessing a first dataset having a first training data entry, the first training data entry including one or more natural language input text strings in a first language; translating at least one of the one or more natural language input text strings of the first training data entry from the first language to a second language; creating a second training data entry by starting with the first training data entry and substituting the at least one of the natural language input text strings in the first language with the translation of the at least one of the natural language input text strings in the second language; adding the second training data entry to a second dataset; and training the deep learning module using the second dataset.