arXiv subjects

Yuming Lu

Publications and source records attributed to Yuming Lu.

3 recordsLinked to original sources

arXiv2026

TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering

AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, a graph-based label-unification pipeline, to reconcile noisy enrichment measurements into consistent cross-round activity labels. Random-split controls show strong interpolation, but future-round ranking and finite-budget candidate selection are much weaker. Controlled analyses suggest that evolutionary coverage is more informative than local data density, positioning TadA-Bench as a reproducible wet-lab replay substrate for future-round discovery toward agentic protein engineering; the data and code are released on Hugging Face and GitHub.

q-bio.QM↗

arXiv2018

Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding

Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to doctors. However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic. To tackle this challenge, we propose to add word-cluster embedding to deep neural network for improving short text classification. Concretely, we first use hierarchical agglomerative clustering to cluster the word vectors in the semantic space. Then we calculate the cluster center vector which represents the implicit topic information of words in the cluster. Finally, we expand word vector with cluster center vector, and implement classifiers using CNN and LSTM respectively. To evaluate the performance of our proposed method, we conduct experiments on public data sets TREC and the medical short sentences data sets which is constructed and released by us. The experimental results demonstrate that our proposed method outperforms state-of-the-art baselines in short sentence classification on both medical domain and general domain.

cs.CL↗

arXiv2017

In situ annealing effects on the iron-based ladder material BaFe_2S_3: A route to improve the crystal quality

We have grown single crystals of the iron-based ladder material BaFe_2S_3, which is superconductive under high pressure, adopting different conditions. By comparing the behaviors of these samples, it is found that the in situ annealing process can affect the crystal structure and the electrical transport, enhance the antiferromagnetic transition temperature, and reduce the extrinsic ferromagnetic component of the system. An in-depth analysis indicates that the crystal quality is improved by the in situ annealing in terms of reducing both the Fe deficiency and the Fe impurity in the samples. The improvement of the sample quality will facilitate the investigations on the intrinsic properties of this material.

cond-mat.supr-con↗