Update pub.bib (#139)

Author: yaniguan

source/_data/pub.bib

@@ -12983,4 +12983,98 @@ @Article{Chang_JChemInfModel_2024_v64_p3149
              generalizability on novel compounds and different categories of human
              CYPs, which could greatly facilitate early stage drug design by
              avoiding CYP-reactive compounds.},
-}
+}
+@Article{Luo_JacsAu_2024_v4_p3451,
+    author =   {Weiliang Luo and Gengmo Zhou and Zhengdan Zhu and Yannan Yuan and
+             Guolin Ke and Zhewei Wei and Zhifeng Gao and Hang Zheng},
+    title =    {{Bridging Machine Learning and Thermodynamics for Accurate pK a
+             Prediction}},
+    journal =  {Jacs Au},
+    year =     2024,
+    volume =   4,
+    number =   9,
+    pages =    {3451--3465},
+    doi =      {10.1021/jacsau.4c00271},
+    abstract = {Integrating scientific principles into machine learning models to
+             enhance their predictive performance and generalizability is a central
+             challenge in the development of AI for Science. Herein, we introduce
+             Uni-pK a, a novel framework that successfully incorporates
+             thermodynamic principles into machine learning modeling, achieving
+             high-precision predictions of acid dissociation constants (pK a), a
+             crucial task in the rational design of drugs and catalysts, as well as
+             a modeling challenge in computational physical chemistry for small
+             organic molecules. Uni-pK a utilizes a comprehensive free energy model
+             to represent molecular protonation equilibria accurately. It features
+             a structure enumerator that reconstructs molecular configurations from
+             pK a data, coupled with a neural network that functions as a free
+             energy predictor, ensuring high-throughput, data-driven prediction
+             while preserving thermodynamic consistency. Employing a pretraining-
+             finetuning strategy with both predicted and experimental pK a data,
+             Uni-pK a not only achieves state-of-the-art accuracy in
+             chemoinformatics but also shows comparable precision to quantum
+             mechanics-based methods.},
+}
+@Article{Wang_NatCommun_2024_v15_p1904,
+    author =   {Jingqi Wang and Jiapeng Liu and Hongshuai Wang and Musen Zhou and
+             Guolin Ke and Linfeng Zhang and Jianzhong Wu and Zhifeng Gao and
+             Diannan Lu},
+    title =    {{A comprehensive transformer-based approach for high-accuracy gas
+             adsorption predictions in metal-organic frameworks}},
+    journal =  {Nat. Commun.},
+    year =     2024,
+    volume =   15,
+    number =   1,
+    pages =    1904,
+    doi =      {10.1038/s41467-024-46276-x},
+    abstract = {Gas separation is crucial for industrial production and environmental
+             protection, with metal-organic frameworks (MOFs) offering a promising
+             solution due to their tunable structural properties and chemical
+             compositions. Traditional simulation approaches, such as molecular
+             dynamics, are complex and computationally demanding. Although feature
+             engineering-based machine learning methods perform better, they are
+             susceptible to overfitting because of limited labeled data.
+             Furthermore, these methods are typically designed for single tasks,
+             such as predicting gas adsorption capacity under specific conditions,
+             which restricts the utilization of comprehensive datasets including
+             all adsorption capacities. To address these challenges, we propose
+             Uni-MOF, an innovative framework for large-scale, three-dimensional
+             MOF representation learning, designed for multi-purpose gas
+             prediction. Specifically, Uni-MOF serves as a versatile gas adsorption
+             estimator for MOF materials, employing pure three-dimensional
+             representations learned from over 631,000 collected MOF and COF
+             structures. Our experimental results show that Uni-MOF can
+             automatically extract structural representations and predict
+             adsorption capacities under various operating conditions using a
+             single model. For simulated data, Uni-MOF exhibits remarkably high
+             predictive accuracy across all datasets. Additionally, the values
+             predicted by Uni-MOF correspond with the outcomes of adsorption
+             experiments. Furthermore, Uni-MOF demonstrates considerable potential
+             for broad applicability in predicting a wide array of other
+             properties.},
+}
+@Article{Xiao_arXiv_2024_p2411.10821,
+    author =   {Teng Xiao and Chao Cui and Huaisheng Zhu and Vasant G. Honavar},
+    title =    {{GeomCLIP: Contrastive Geometry-Text Pre-training for Molecules}},
+    journal =  {arXiv},
+    year =     2024,
+    pages =    {2411.10821},
+    doi =      {10.48550/arXiv.2411.10821},
+    abstract = {Pretraining molecular representations is crucial for drug and material
+             discovery. Recent methods focus on learning representations from
+             geometric structures, effectively capturing 3D position information.
+             Yet, they overlook the rich information in biomedical texts, which
+             detail molecules' properties and substructures. With this in mind, we
+             set up a data collection effort for 200K pairs of ground-state
+             geometric structures and biomedical texts, resulting in a PubChem3D
+             dataset. Based on this dataset, we propose the GeomCLIP framework to
+             enhance for multi-modal representation learning from molecular
+             structures and biomedical text. During pre-training, we design two
+             types of tasks, i.e., multimodal representation alignment and unimodal
+             denoising pretraining, to align the 3D geometric encoder with textual
+             information and, at the same time, preserve its original
+             representation power. Experimental results show the effectiveness of
+             GeomCLIP in various tasks such as molecular property prediction, zero-
+             shot text-molecule retrieval, and 3D molecule captioning. Our code and
+             collected dataset are available at
+             {\textbackslash}url{\{}https://github.com/xiaocui3737/GeomCLIP{\}}},
+}