Abstract: A machine learning framework is described for performing generation of candidate molecules for, e.g., drug discovery or other applications. The framework utilizes a pre-trained encoder-decoder model to interface between representations of molecules and embeddings for those molecules in a latent space. A fusion module is located between the encoder and decoder and is used to fuse an embedding for an input molecule with embeddings for one or more exemplary molecules selected from a database that is constructed according to a design criteria. The fused embedding is decoded using the decoder to generate a candidate molecule. The fusion module is trained to reconstruct a nearest neighbor to the input molecule from the database based on the sample of exemplary molecules. An iterative approach may be used during inference to dynamically update the database to include newly generated candidate molecules.

Abstract: A method for processing formulae includes encoding a formula by: training, with a server, a model by using a machine learning algorithm with a data set that includes a plurality of formulae; transforming, with a processor, a first formula into a tree format using the trained model; converting, with the processor, the tree format of the first formula into a plurality of lists; and encoding, with the processor, the plurality of lists into a fixed dimension vector by leveraging a stacked attention module; and generating one or more formula candidates by: obtaining, with the processor, input information; and generating, with the processor, one or more second formula candidates based on input information by using the stacked attention module with a tree beam search algorithm.

Abstract: Provided are an auxiliary alloy casting piece, a high-remanence and high-coercive force NdFeB permanent magnet, and preparation methods thereof. The method for preparing the auxiliary alloy casting piece includes the following steps: providing an auxiliary alloy material including, by mass percentage, 40% to 45% of Pr, 1% to 2% of Co, 0.5% to 1% of Ga, 0.6% to 0.8% of B, 0.1% to 0.2% of V, 0.3% to 0.7% of Ti, and a balance of Fe; smelting the auxiliary alloy material to obtain a smelted material; and subjecting the smelted material to a quick-setting casting to obtain the auxiliary alloy casting piece; where the quick-setting casting includes a refining and a casting in sequence.

Abstract: Provided are an auxiliary alloy casting piece, a high-remanence and high-coercive force NdFeB permanent magnet, and preparation methods thereof. The method for preparing the auxiliary alloy casting piece includes the following steps: providing an auxiliary alloy material including, by mass percentage, 40% to 45% of Pr, 1% to 2% of Co, 0.5% to 1% of Ga, 0.6% to 0.8% of B, 0.1% to 0.2% of V, 0.3% to 0.7% of Ti, and a balance of Fe; smelting the auxiliary alloy material to obtain a smelted material; and subjecting the smelted material to a quick-setting casting to obtain the auxiliary alloy casting piece; where the quick-setting casting includes a refining and a casting in sequence.

Abstract: A machine learning framework is described for performing generation of candidate molecules for, e.g., drug discovery or other applications. The framework utilizes a pre-trained encoder-decoder model to interface between representations of molecules and embeddings for those molecules in a latent space. A fusion module is located between the encoder and decoder and is used to fuse an embedding for an input molecule with embeddings for one or more exemplary molecules selected from a database that is constructed according to a design criteria. The fused embedding is decoded using the decoder to generate a candidate molecule. The fusion module is trained to reconstruct a nearest neighbor to the input molecule from the database based on the sample of exemplary molecules. An iterative approach may be used during inference to dynamically update the database to include newly generated candidate molecules.

Abstract: A method for processing formulae includes encoding a formula by: training, with a server, a model by using a machine learning algorithm with a data set that includes a plurality of formulae; transforming, with a processor, a first formula into a tree format using the trained model; converting, with the processor, the tree format of the first formula into a plurality of lists; and encoding, with the processor, the plurality of lists into a fixed dimension vector by leveraging a stacked attention module; and generating one or more formula candidates by: obtaining, with the processor, input information; and generating, with the processor, one or more second formula candidates based on input information by using the stacked attention module with a tree beam search algorithm.