AlpaPICO: Extraction of PICO frames from clinical trial documents using LLMs.

In recent years, there has been a surge in the publication of clinical trial reports, making it challenging to conduct systematic reviews. Automatically extracting Population, Intervention, Comparator, and Outcome (PICO) from clinical trial studies can alleviate the traditionally time-consuming process of manually scrutinizing systematic reviews. Existing approaches of PICO frame extraction involves supervised approach that relies on the existence of manually annotated data points in the form of BIO label tagging. Recent approaches, such as In-Context Learning (ICL), which has been shown to be effective for a number of downstream NLP tasks, require the use of labeled examples. In this work, we adopt ICL strategy by employing the pretrained knowledge of Large Language Models (LLMs), gathered during the pretraining phase of an LLM, to automatically extract the PICO-related terminologies from clinical trial documents in unsupervised set up to bypass the availability of large number of annotated data instances. Additionally, to showcase the highest effectiveness of LLM in oracle scenario where large number of annotated samples are available, we adopt the instruction tuning strategy by employing Low Rank Adaptation (LORA) to conduct the training of gigantic model in low resource environment for the PICO frame extraction task. More specifically, both of the proposed frameworks utilize AlpaCare as base LLM which employs both few-shot in-context learning and instruction tuning techniques to extract PICO-related terms from the clinical trial reports. We applied these approaches to the widely used coarse-grained datasets such as EBM-NLP, EBM-COMET and fine-grained datasets such as EBM-NLPrev and EBM-NLPh. Our empirical results show that our proposed ICL-based framework produces comparable results on all the version of EBM-NLP datasets and the proposed instruction tuned version of our framework produces state-of-the-art results on all the different EBM-NLP datasets. Our project is available at https://github.com/shrimonmuke0202/AlpaPICO.git.

Detecting context-based in-claim numerals in Financial Earnings Conference Calls.

Most investors tend to make decisions after analysing financial documents of organizations available online. These documents include financial reports, conversations, brochures, etc. While reading these documents investors need to ensure that they rely only on facts and do not get swayed away by claims which representatives of organizations make. Thus, it is essential to have an automated system for detecting whether numerals present in financial texts are in-claim. In this paper, we discuss a system for evaluating whether numerals present in financial texts are in-claim or out-of-claim. It is trained on the English version of the FinNum-3 corpus using two variants of the FinBERT model and a BERT model augmented with handcrafted features. Our best model, an ensemble of these 3 models, produces a Macro-F1 score of 0.8671 on the validation set and outperforms the existing baselines.

Quantitative structure-activity relationship study on some azidopyridinyl neonicotinoid insecticides for their selective affinity towards the drosophila nicotinic receptor over mammalian alpha4beta2 receptor using electrotopological state atom index.

Neonicotinoids are the most important class of synthetic insecticides increasingly used in agriculture and veterinary medicine. Fundamental differences between the nicotinic acetylcholine receptors (nAChRs) of insects and mammals confer remarkable selectivity of the neonicotinoids at insect nAChR over mammalian nAChR. To identify pharmacophoric requirements of azidopyridinyl neonicotinoids for their efficacy and selectivity towards the insect nAChR over the mammalian one, quantitative structure-activity relationship (QSAR) study was performed using electrotopological state atom (ETSA) indices. This study clearly showed that nitroimines, nitromethylenes, and cyanoimines are more selective to Drosophila nAChR and safe for human being, whereas N-substituted imines have affinity to mammalian receptor. Pharmacophore mapping for both the activities was done.

QSAR study on the affinity of some arylpiperazines towards the 5-HT1A/alpha1-adrenergic receptor using the E-state index.

QSAR models represent the relationship of biological activity with either physicochemical parameters or structural indices. QSAR study was performed on some arylpiperazines as 5-HT(1A)/alpha(1)-adrenergic receptor antagonists using E-state indices to identify the pharmacophoric requirements. It was found that some of the atoms played important roles to both activities and some played important role in selectivity of compound to the 5-HT(1A) antagonistic activity. The presence of COONHPr group at the ortho-position of the phenyl ring might be disadvantageous and Br at meta-position might be conducive to the activity. COOPr at the ortho-position might be disfavored the adrenergic alpha(1)-antagonistic activity, thus increase the selectivity.