[Optimization of prediction model for personalized water pills based on semantic analysis of traditional Chinese medicine materials].

This study aims to optimize the prediction model of personalized water pills that has been established by our research group. Dioscoreae Rhizoma, Leonuri Herba, Codonopsis Radix, Armeniacae Semen Amarum, and calcined Oyster were selected as model medicines of powdery, fibrous, sugary, oily, and brittle materials, respectively. The model prescriptions were obtained by uniform mixing design. With hydroxypropyl methylcellulose E5(HPMC-E5) aqueous solution as the adhesive, personalized water pills were prepared by extrusion and spheronizaition. The evaluation indexes in the pill preparation process and the multi-model statistical analysis were employed to optimize and evaluate the prediction model of personalized water pills. The prediction equation of the adhesive concentration was obtained as follows: Y_1=-4.172+3.63X_A+15.057X_B+1.838X_C-0.997X_D(adhesive concentration of 10% when Y_1<0, and 20% when Y_1>0). The overall accuracy of the prediction model for adhesive concentration was 96.0%. The prediction equation of adhesive dosage was Y_2=6.051+94.944X_A~(1.5)+161.977X_B+70.078X_C~2+12.016X_D~(0.3)+27.493X_E~(0.3)-2.168X_F~(-1)(R~2=0.954, P<0.001). Furthermore, the semantic prediction model for material classification of traditional Chinese medicines was used to classify the materials contained in the prescription, and thus the prediction model of personalized water pills was evaluated. The results showed that the prescriptions for model evaluation can be prepared with one-time molding, and the forming quality was better than that established by the research group earlier. This study has achieved the optimization of the prediction model of personalized water pills.

[Intelligent material classification of traditional Chinese medicine based on semantic analysis].

A method for material classification of traditional Chinese medicines based on the physical properties of powder has been established by our research group. This method involves pre-treatment of traditional Chinese medicine decoction pieces, powder preparation, and determination of physical properties, being cumbersome. In this study, the word segmentation logic of semantic analysis was adopted to establish the thesaurus and local standardized semantic word segmentation database with the macroscopic and microscopic characteristics of 36 model traditional Chinese medicines as the basic data. The physical properties of these medicines have been determined and the classification of these medicines is clear in the cluster analysis. A total of 55 keywords for powdery, fibrous, sugary, oily, and brittle materials were screened by association rules and the set inclusion and exclusion criteria, and the weights of the keywords were calculated. Furthermore, the algorithms of the keyword matching scores and the computation rules of the single or multiple material classification were established for building the intelligent model of semantic analysis for the material classification. The semantic classification results of the other 35 TCMs except Pseudostellariae Radix(multi-material medicine) agreed with the clustering results based on the physical properties of the powder, with an agreement rate of 97.22%. In model validation, the prediction results of semantic classification of traditional Chinese medicines were consistent with the clustering results based on the physical properties of powder, with an agreement rate of 83.33%. The results showed that the method of material classification based on semantic analysis was feasible, which laid a foundation for the development of intelligent decision-making technology for personalized traditional Chinese medicine preparations.

Advanced Data Processing of Pancreatic Cancer Data Integrating Ontologies and Machine Learning Techniques to Create Holistic Health Records.

The modern healthcare landscape is overwhelmed by data derived from heterogeneous IoT data sources and Electronic Health Record (EHR) systems. Based on the advancements in data science and Machine Learning (ML), an improved ability to integrate and process the so-called primary and secondary data fosters the provision of real-time and personalized decisions. In that direction, an innovative mechanism for processing and integrating health-related data is introduced in this article. It describes the details of the mechanism and its internal subcomponents and workflows, together with the results from its utilization, validation, and evaluation in a real-world scenario. It also highlights the potential derived from the integration of primary and secondary data into Holistic Health Records (HHRs) and from the utilization of advanced ML-based and Semantic Web techniques to improve the quality, reliability, and interoperability of the examined data. The viability of this approach is evaluated through heterogeneous healthcare datasets pertaining to personalized risk identification and monitoring related to pancreatic cancer. The key outcomes and innovations of this mechanism are the introduction of the HHRs, which facilitate the capturing of all health determinants in a harmonized way, and a holistic data ingestion mechanism for advanced data processing and analysis.

Processing of auditory novelty in human cortex during a semantic categorization task.

Auditory semantic novelty - a new meaningful sound in the context of a predictable acoustical environment - can probe neural circuits involved in language processing. Aberrant novelty detection is a feature of many neuropsychiatric disorders. This large-scale human intracranial electrophysiology study examined the spatial distribution of gamma and alpha power and auditory evoked potentials (AEP) associated with responses to unexpected words during performance of semantic categorization tasks. Participants were neurosurgical patients undergoing monitoring for medically intractable epilepsy. Each task included repeatedly presented monosyllabic words from different talkers ("common") and ten words presented only once ("novel"). Targets were words belonging to a specific semantic category. Novelty effects were defined as differences between neural responses to novel and common words. Novelty increased task difficulty and was associated with augmented gamma, suppressed alpha power, and AEP differences broadly distributed across the cortex. Gamma novelty effect had the highest prevalence in planum temporale, posterior superior temporal gyrus (STG) and pars triangularis of the inferior frontal gyrus; alpha in anterolateral Heschl's gyrus (HG), anterior STG and middle anterior cingulate cortex; AEP in posteromedial HG, lower bank of the superior temporal sulcus, and planum polare. Gamma novelty effect had a higher prevalence in dorsal than ventral auditory-related areas. Novelty effects were more pronounced in the left hemisphere. Better novel target detection was associated with reduced gamma novelty effect within auditory cortex and enhanced gamma effect within prefrontal and sensorimotor cortex. Alpha and AEP novelty effects were generally more prevalent in better performing participants. Multiple areas, including auditory cortex on the superior temporal plane, featured AEP novelty effect within the time frame of P3a and N400 scalp-recorded novelty-related potentials. This work provides a detailed account of auditory novelty in a paradigm that directly examined brain regions associated with semantic processing. Future studies may aid in the development of objective measures to assess the integrity of semantic novelty processing in clinical populations.

A study on pharmaceutical text relationship extraction based on heterogeneous graph neural networks.

Effective information extraction of pharmaceutical texts is of great significance for clinical research. The ancient Chinese medicine text has streamlined sentences and complex semantic relationships, and the textual relationships may exist between heterogeneous entities. The current mainstream relationship extraction model does not take into account the associations between entities and relationships when extracting, resulting in insufficient semantic information to form an effective structured representation. In this paper, we propose a heterogeneous graph neural network relationship extraction model adapted to traditional Chinese medicine (TCM) text. First, the given sentence and predefined relationships are embedded by bidirectional encoder representation from transformers (BERT fine-tuned) word embedding as model input. Second, a heterogeneous graph network is constructed to associate words, phrases, and relationship nodes to obtain the hidden layer representation. Then, in the decoding stage, two-stage subject-object entity identification method is adopted, and the identifier adopts a binary classifier to locate the start and end positions of the TCM entities, identifying all the subject-object entities in the sentence, and finally forming the TCM entity relationship group. Through the experiments on the TCM relationship extraction dataset, the results show that the precision value of the heterogeneous graph neural network embedded with BERT is 86.99% and the F1 value reaches 87.40%, which is improved by 8.83% and 10.21% compared with the relationship extraction models CNN, Bert-CNN, and Graph LSTM.

Comparing two unitisation manipulations: effects on familiarity, recollection-based recognition, and semantic interference.

The recognition of associative memory can be significantly influenced by the use of an encoding strategy known as unitisation, which has been implemented through various manipulations. However, [Shao, H., Opitz, B., Yang, J., & Weng, X. (2016). Recollection reduces unitised familiarity effect. Memory (Hove, England), 24(4), 535-547. https://doi.org/10.1080/09658211.2015.1021258] found intriguing distinctions between two common manipulations, the compound task and the imagery task, leading to a dispute. We propose that differences in levels of processing in the imagery task may account for these discrepancies. This study tested our hypothesis using two approaches. The first two experiments utilised the R/K paradigm to investigate the effects of these methods on familiarity-based and recollection-based recognition. The results demonstrated that familiarity was increased in the compound task, while recollection was increased in the imagery task. In the subsequent two experiments, an interference paradigm was employed to examine differences in semantic processing within the two tasks. The results showed that the compound task did not impact participants' inclination towards lures, while the imagery task led to a bias towards semantic lures over episodic lures, suggesting that the two encodings in the imagery task involve different levels of semantic processing. These results support our hypothesis and underscore the importance of carefully choosing comparisons that account for other variables in the study of unitisation.

The neural oscillations in delta- and theta-bands contribute to divided attention in audiovisual integration.

One of key mechanisms implicated in multisensory processing is neural oscillations in distinct frequency band. Many studies explored the modulation of attention by recording the electroencephalography signals when subjects attended one modality, and ignored the other modality input. However, when attention is directed toward one modality, it may be not always possible to shut out completely inputs from a different modality. Since many situations require division of attention between audition and vision, it is imperative to investigate the neural mechanisms underlying processing of concurrent auditory and visual sensory streams. In the present study, we designed a task of audiovisual semantic discrimination, in which the subjects were asked to share attention to both auditory and visual stimuli. We explored the contribution of neural oscillations in lower-frequency to the modulation of divided attention on audiovisual integration. Our results implied that theta-band activity contributes to the early modulation of divided attention, and delta-band activity contributes to the late modulation of divided attention to audiovisual integration. Moreover, the fronto-central delta- and theta-bands activity is likely a marker of divided attention in audiovisual integration, and the neural oscillation on delta- and theta-bands is conducive to allocating attention resources to dual-tasking involving task-coordinating abilities.

That means something to me: How linguistic and emotional experience affect the acquisition, representation, and processing of novel abstract concepts.

We used a novel linguistic training paradigm to investigate the experience-dependent acquisition, representation, and processing of novel emotional and neutral abstract concepts. Participants engaged in mental imagery (n = 32) or lexico-semantic rephrasing (n = 34) of linguistic material during five training sessions and successfully learned the novel abstract concepts. Feature production after training showed that specifically emotion features enriched the emotional concepts' representations. Unexpectedly, for participants engaging in vivid mental imagery during training a higher semantic richness of the acquired emotional concepts slowed down lexical decisions. Rephrasing, in turn, promoted a better learning and processing performance than imagery, probably due to stronger established lexical associations. Our results confirm the importance of emotional and linguistic experience and additional deep lexico-semantic processing for the acquisition, representation, and processing of abstract concepts. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

The shared and unique neural correlates of personal semantic, general semantic, and episodic memory.

One of the most common distinctions in long-term memory is that between semantic (i.e., general world knowledge) and episodic (i.e., recollection of contextually specific events from one's past). However, emerging cognitive neuroscience data suggest a surprisingly large overlap between the neural correlates of semantic and episodic memory. Moreover, personal semantic memories (i.e., knowledge about the self and one's life) have been studied little and do not easily fit into the standard semantic-episodic dichotomy. Here, we used fMRI to record brain activity while 48 participants verified statements concerning general facts, autobiographical facts, repeated events, and unique events. In multivariate analysis, all four types of memory involved activity within a common network bilaterally (e.g., frontal pole, paracingulate gyrus, medial frontal cortex, middle/superior temporal gyrus, precuneus, posterior cingulate, angular gyrus) and some areas of the medial temporal lobe. Yet the four memory types differentially engaged this network, increasing in activity from general to autobiographical facts, from autobiographical facts to repeated events, and from repeated to unique events. Our data are compatible with a component process model, in which declarative memory types rely on different weightings of the same elementary processes, such as perceptual imagery, spatial features, and self-reflection.

Leading and following: Noise differently affects semantic and acoustic processing during naturalistic speech comprehension.

Despite the distortion of speech signals caused by unavoidable noise in daily life, our ability to comprehend speech in noisy environments is relatively stable. However, the neural mechanisms underlying reliable speech-in-noise comprehension remain to be elucidated. The present study investigated the neural tracking of acoustic and semantic speech information during noisy naturalistic speech comprehension. Participants listened to narrative audio recordings mixed with spectrally matched stationary noise at three signal-to-ratio (SNR) levels (no noise, 3 dB, -3 dB), and 60-channel electroencephalography (EEG) signals were recorded. A temporal response function (TRF) method was employed to derive event-related-like responses to the continuous speech stream at both the acoustic and the semantic levels. Whereas the amplitude envelope of the naturalistic speech was taken as the acoustic feature, word entropy and word surprisal were extracted via the natural language processing method as two semantic features. Theta-band frontocentral TRF responses to the acoustic feature were observed at around 400 ms following speech fluctuation onset over all three SNR levels, and the response latencies were more delayed with increasing noise. Delta-band frontal TRF responses to the semantic feature of word entropy were observed at around 200 to 600 ms leading to speech fluctuation onset over all three SNR levels. The response latencies became more leading with increasing noise and decreasing speech comprehension and intelligibility. While the following responses to speech acoustics were consistent with previous studies, our study revealed the robustness of leading responses to speech semantics, which suggests a possible predictive mechanism at the semantic level for maintaining reliable speech comprehension in noisy environments.

Treatment-Induced Recovery Patterns Between Nouns and Verbs in Mandarin-English Bilingual Adults With Aphasia.

PURPOSE: This study aimed to investigate treatment effects of naming therapy targeting nouns and verbs in Mandarin-English bilingual adults with aphasia (BWA). METHOD: Twelve Mandarin-English bilingual adults with chronic aphasia completed a 40-hr semantic-based naming treatment for either nouns or verbs. Eight of these participants completed both noun and verb treatment, and the other four completed either noun or verb treatment. Participants were trained in either Mandarin or English for both treatment cycles. Weekly naming probes were measured to capture the direct treatment gain and within- and cross-language generalizations. Performance on the standardized language assessments was analyzed to examine further generalizations beyond the word level and to standardized naming tasks. RESULTS: Responses in the weekly naming probes showed significant treatment gains in both noun and verb treatment, but the effect was greater in verb treatment. Generalization to semantically related items was captured in noun treatment only. Cross-language generalization was identified in both noun and verb treatment with a larger effect in verb treatment. Additionally, widespread generalizations beyond the word level and to standardized naming tasks were found following both noun and verb treatment, but the effect was larger following noun treatment in discourse and verb naming tasks. CONCLUSIONS: Findings from this study suggested robust treatment effects of semantic-based naming treatment targeting nouns and verbs in Mandarin-English BWA. However, patterns of treatment gains and generalizations differed between these word categories. This study provides strong evidence of bilingual aphasia rehabilitation in Mandarin-English BWA. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.23818299.

Evaluation Mechanism of Political Discourse: A Holistic Approach.

Taking the economic issue of Trump's First State of the Union Address (SUA) as original data, the present study examined the evaluation features of political speeches by adopting a holistic approach, which includes both macro and micro dimensions. At the macro level, a series of semantic patterns were identified, with Goal-Achievement and General-Example Patterns being the most prevalent. They predetermine the evaluative tone, giving the surrounding statements evaluative meanings, exhibiting the radiating nature of evaluative meaning; at the micro level, a variety of resources have been identified, both explicit and implicit, lexical and syntactical, attitudinal and gradational, which collaborate to reinforce the subjective evaluation, revealing the holistic characteristic in the realization of evaluative meaning. Throughout the analysis, three evaluative mechanisms have been proposed, which are the coupling of meaning, semantic prosody, and tense switching. They collaborate and promote the subjective evaluation to be established and reinforced in a cumulative, gradient or hybrid pattern. In a narrow sense, the present study has partially revealed Trump's political discourse feature. Broadly speaking, it contributes to the theoretical development of the appraisal framework by refining existing evaluation systems through a holistic research paradigm, which in turn facilitates accurate interpretation of various types of discourse.

More is not necessarily better: How different aspects of sensorimotor experience affect recognition memory for words.

Semantic richness theory predicts that words with richer, more distinctive semantic representations should facilitate performance in a word recognition memory task. We investigated the contribution of multiple aspects of sensorimotor experience-those relating to the body, communication, food, and objects-to word recognition memory, by analyzing megastudy data in a series of hierarchical linear regressions. We found that different forms of sensorimotor experience produced different effects on memory. While stronger grounding in object- and food-related experience facilitated word memory performance as expected for semantic richness, experience relating to communication did not. Critically, sensorimotor experience relating to the body impaired rather than facilitated recognition memory by inflating false alarms, which was not consistent with the idea that semantically richer representations are more memorable. Additionally, we found that pure imageability (i.e., consciously generating mental imagery, distinct from sensorimotor experience) contributes to semantic richness effects on word memory but with much smaller effect sizes than previously reported, once sensorimotor grounding was taken into account. These results suggest that word recognition memory is often but not consistently facilitated by rich semantic representations and that it is essential to separately consider distinct forms of sensorimotor experience rather than assuming more information is always better. The findings have implications for the use of semantic variables in memory research. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Virtual screening of antimicrobial plant extracts by machine-learning classification of chemical compounds in semantic space.

Plant extract is a mixture of diverse phytochemicals, and considered as an important resource for drug discovery. However, large-scale exploration of the bioactive extracts has been hindered by various obstacles until now. In this research, we have introduced and evaluated a new computational screening strategy that classifies bioactive compounds and plants in semantic space generated by word embedding algorithm. The classifier showed good performance in binary (presence/absence of bioactivity) classification for both compounds and plant genera. Furthermore, the strategy led to the discovery of antimicrobial activity of essential oils from Lindera triloba and Cinnamomum sieboldii against Staphylococcus aureus. The results of this study indicate that machine-learning classification in semantic space can be a highly efficient approach for exploring bioactive plant extracts.

SMRGAT: A traditional Chinese herb recommendation model based on a multi-graph residual attention network and semantic knowledge fusion.

ETHNOPHARMACOLOGICAL RELEVANCE: Traditional Chinese Medicine (TCM) prescriptions are a product of the Chinese medical theory's distinct thinking and clinical experience. TCM practitioners treat diseases by enhancing the efficacy of TCM prescriptions and reducing their poisonous effects. Some TCM herb recommendation methods have been provided for curing the given symptoms to generate a group of herbs according to the TCM principles. However, they ignored the symptoms' semantic characteristics and herbs' different effects on symptoms. AIM OF THE STUDY: We aim to recommend TCM herbs by considering symptoms' semantic information and the strength of different herbs in curing symptoms. MATERIALS AND METHODS: We propose a herb recommendation model named Multi-Graph Residual Attention Network and Semantic Knowledge Fusion (SMRGAT) to address these problems. Concretely, it uses a multi-head attention mechanism to focus on herbs' different effects on symptoms. Meanwhile, it augments entities' features with a residual network structure while incorporating symptoms' semantic information and external knowledge of herbs. We will verify the effect of SMRGAT on the existing public datasets and the datasets that we have collected and cleaned. RESULTS: Compared with the current best TCM herb recommendation model, on the public dataset, SMRGAT were increased by 15.11%, 20.60%, and 18.25% in Precision@5, Recall@5, and F1 - score@5, respectively; on ours, respectively increased by 9.72%, 9.03%, 9.24%. CONCLUSIONS: Our experimental results on two datasets indicate that SMRGAT is capable of recommending herbs with greater precision and outperforms several comparison methods. It can provide a basis for assisting TCM clinical prescriptions.

Hypnotic suggestions cognitively penetrate tactile perception through top-down modulation of semantic contents.

Perception is subject to ongoing alterations by learning and top-down influences. Although abundant studies have shown modulation of perception by attention, motivation, content and context, there is an unresolved controversy whether these examples provide true evidence that perception is penetrable by cognition. Here we show that tactile perception assessed as spatial discrimination can be instantaneously and systematically altered merely by the semantic content during hypnotic suggestions. To study neurophysiological correlates, we recorded EEG and SEPs. We found that the suggestion "your index finger becomes bigger" led to improved tactile discrimination, while the suggestion "your index finger becomes smaller" led to impaired discrimination. A hypnosis without semantic suggestions had no effect but caused a reduction of phase-locking synchronization of the beta frequency band between medial frontal cortex and the finger representation in somatosensory cortex. Late SEP components (P80-N140 complex) implicated in attentional processes were altered by the semantic contents, but processing of afferent inputs in SI remained unaltered. These data provide evidence that the psychophysically observed modifiability of tactile perception by semantic contents is not simply due to altered perception-based judgments, but instead is a consequence of modified perceptual processes which change the perceptual experience.

quEHRy: a question answering system to query electronic health records.

OBJECTIVE: We propose a system, quEHRy, to retrieve precise, interpretable answers to natural language questions from structured data in electronic health records (EHRs). MATERIALS AND METHODS: We develop/synthesize the main components of quEHRy: concept normalization (MetaMap), time frame classification (new), semantic parsing (existing), visualization with question understanding (new), and query module for FHIR mapping/processing (new). We evaluate quEHRy on 2 clinical question answering (QA) datasets. We evaluate each component separately as well as holistically to gain deeper insights. We also conduct a thorough error analysis for a crucial subcomponent, medical concept normalization. RESULTS: Using gold concepts, the precision of quEHRy is 98.33% and 90.91% for the 2 datasets, while the overall accuracy was 97.41% and 87.75%. Precision was 94.03% and 87.79% even after employing an automated medical concept extraction system (MetaMap). Most incorrectly predicted medical concepts were broader in nature than gold-annotated concepts (representative of the ones present in EHRs), eg, Diabetes versus Diabetes Mellitus, Non-Insulin-Dependent. DISCUSSION: The primary performance barrier to deployment of the system is due to errors in medical concept extraction (a component not studied in this article), which affects the downstream generation of correct logical structures. This indicates the need to build QA-specific clinical concept normalizers that understand EHR context to extract the "relevant" medical concepts from questions. CONCLUSION: We present an end-to-end QA system that allows information access from EHRs using natural language and returns an exact, verifiable answer. Our proposed system is high-precision and interpretable, checking off the requirements for clinical use.

Intermediate acoustic-to-semantic representations link behavioral and neural responses to natural sounds.

Recognizing sounds implicates the cerebral transformation of input waveforms into semantic representations. Although past research identified the superior temporal gyrus (STG) as a crucial cortical region, the computational fingerprint of these cerebral transformations remains poorly characterized. Here, we exploit a model comparison framework and contrasted the ability of acoustic, semantic (continuous and categorical) and sound-to-event deep neural network representation models to predict perceived sound dissimilarity and 7 T human auditory cortex functional magnetic resonance imaging responses. We confirm that spectrotemporal modulations predict early auditory cortex (Heschl's gyrus) responses, and that auditory dimensions (for example, loudness, periodicity) predict STG responses and perceived dissimilarity. Sound-to-event deep neural networks predict Heschl's gyrus responses similar to acoustic models but, notably, they outperform all competing models at predicting both STG responses and perceived dissimilarity. Our findings indicate that STG entails intermediate acoustic-to-semantic sound representations that neither acoustic nor semantic models can account for. These representations are compositional in nature and relevant to behavior.

Implementation of Japanese Sociocultural Values in Japanese Kotowaza: A Cognitive Linguistics Perspective.

Kotowaza were created by gaining experience and through recurring events over the years of existence of the Japanese people. The purpose of this study is to conduct a qualitative analysis of Japanese kotowaza in cognitive-linguistic discourse to divide idioms into categories and groups with specific sociocultural features. The paper focuses in detail on the semantic features of 20 kotowaza that use animal symbols as an idiomatic metaphor. In this paper, 10 proverbs with the central animal visualization, neko, were analyzed. Visionary metaphors are developed based on the comparison of cat's body parts and behavior with human qualities or characteristics of objects and phenomena. The analysis of the remaining 10 kotowaza showed that the meaning of imagery could originate from Chinese tradition and then change under the influence of Japanese style. Hence, it follows that the meanings of some kotowaza, or the animals they use, can be interpreted differently depending on context. However, the key meanings of proverbs are engrained in the national consciousness of native speakers. It was also observed that kotowaza used oxymoron. It is possible to gain a correct understanding of what kotowaza means through analyzing literal and idiomatic relations in the proverb. Each proverb has an animal symbol, the meaning of which is engrained and originates from the cultural and historical development of the Japanese nation. The practical application of the study lies in the fact that these findings can be used for further study of the special aspects of manifestation of sociocultural heritage at the linguistic level within the phraseology of the Japanese language.

Deep contrastive learning of molecular conformation for efficient property prediction.

Data-driven deep learning algorithms provide accurate prediction of high-level quantum-chemical molecular properties. However, their inputs must be constrained to the same quantum-chemical level of geometric relaxation as the training dataset, limiting their flexibility. Adopting alternative cost-effective conformation generative methods introduces domain-shift problems, deteriorating prediction accuracy. Here we propose a deep contrastive learning-based domain-adaptation method called Local Atomic environment Contrastive Learning (LACL). LACL learns to alleviate the disparities in distribution between the two geometric conformations by comparing different conformation-generation methods. We found that LACL forms a domain-agnostic latent space that encapsulates the semantics of an atom's local atomic environment. LACL achieves quantum-chemical accuracy while circumventing the geometric relaxation bottleneck and could enable future application scenarios such as inverse molecular engineering and large-scale screening. Our approach is also generalizable from small organic molecules to long chains of biological and pharmacological molecules.