Add application file

app.py

@@ -13,11 +13,10 @@ def get_completion_from_messages(messages, model="gpt-3.5-turbo", temperature=0)
 
 def get_response(text):
     messages =  [  
-        {'role':'system', 'content':'You are a document abstract information extractor, \
+        {'role':'system', 'content':'You are a paper abstract information extractor, \
         the user inputs a paper abstract, and you are responsible for extracting information. \
-        The information extracted is: Which genes or pathways are important in what state of the cancer (this state is usually a mutation in a driver gene). \
-        Do not show other information. \
-        When there is no such information, just return "No target"'},  
+        The information extracted is:  What state of the cancer (this state is usually a mutation in a driver gene) is dependent on which genes or pathways. \
+        Do not show other information. When there is no such information, just return "No dependency"'},  
         {'role':'user', 'content':'Abstract: In non–small cell lung cancer (NSCLC), \
         concurrent mutations in the oncogene KRAS and the tumor suppressor STK11 encoding the kinase LKB1 result in aggressive tumors \
         prone to metastasis but with liabilities arising from reprogrammed metabolism. \
@@ -29,23 +28,31 @@ def get_response(text):
         higher flux through the HBP pathway and elevated dependence on the HBP enzyme Glutamine-Fructose-6-Phosphate Transaminase 2 (GFPT2). \
         GFPT2 inhibition selectively reduced KL tumor cell growth in culture, xenografts and genetically-modified mice. \
         Our results define a new metabolic vulnerability in KL tumors and provide a rationale for targeting GFPT2 in this aggressive NSCLC subtype.'}, 
-        {'role':'assistant', 'content':'Hexosamine biosynthesis pathway (HBP) and GFPT2 is important in KRAS/LKB1 co-mutant non–small cell lung cancer.'},   
-        {'role':'user', 'content':'Abstract: Rationale: NRF2, a redox sensitive transcription factor, \
-        is up-regulated in head and neck squamous cell carcinoma (HNSCC), however, the associated impact and regulatory mechanisms remain unclear. \
-        Methods: The protein expression of NRF2 in HNSCC specimens was examined by IHC. The regulatory effect of c-MYC on NRF2 was validated by ChIP-qPCR, \
-        RT-qPCR and western blot. The impacts of NRF2 on malignant progression of HNSCC were determined through genetic manipulation and \
-        pharmacological inhibition in vitro and in vivo. The gene-set enrichment analysis (GSEA) on expression data of cDNA microarray combined with \
-        ChIP-qPCR, RT-qPCR, western blot, transwell migration/ invasion, cell proliferation and soft agar colony formation assays were used to \
-        investigate the regulatory mechanisms of NRF2. Results: NRF2 expression is positively correlated with malignant features of HNSCC. \
-        In addition, carcinogens, such as nicotine and arecoline, trigger c-MYC-directed NRF2 activation in HNSCC cells. \
-        NRF2 reprograms a wide range of cancer metabolic pathways and the most notable is the pentose phosphate pathway (PPP). \
-        Furthermore, glucose-6-phosphate dehydrogenase (G6PD) and transketolase (TKT) are critical downstream effectors of NRF2 that \
-        drive malignant progression of HNSCC; the coherently expressed signature NRF2/G6PD/TKT gene set is a potential prognostic \
-        biomarker for prediction of patient overall survival. Notably, G6PD- and TKT-regulated nucleotide biosynthesis is more important than \
-        redox regulation in determining malignant progression of HNSCC. Conclusions: Carcinogens trigger c-MYC-directed NRF2 activation. \
-        Over-activation of NRF2 promotes malignant progression of HNSCC through reprogramming G6PD- and TKT-mediated nucleotide biosynthesis. \
-        Targeting NRF2-directed cellular metabolism is an effective strategy for development of novel treatments for head and neck cancer.'},
-        {'role':'assistant', 'content':'NRF2, G6PD, and TKT is important in c-MYC up-regulated head and neck squamous cell carcinoma'}
+        {'role':'assistant', 'content':'KRAS/LKB1 co-mutant non–small cell lung cancer is dependent on Hexosamine biosynthesis pathway (HBP) and GFPT2.'},   
+        {'role':'user', 'content':'Abstract: Background: Thymidylate synthase (TYMS) is a successful chemotherapeutic target for anticancer therapy. \
+        Numerous TYMS inhibitors have been developed and used for treating gastrointestinal cancer now, but they have limited clinical benefits due to \
+        the prevalent unresponsiveness and toxicity. It is urgent to identify a predictive biomarker to guide the precise clinical use of TYMS inhibitors. \
+        Methods: Genome-scale CRISPR-Cas9 knockout screening was performed to identify potential therapeutic targets for treating gastrointestinal tumours \
+        as well as key regulators of raltitrexed (RTX) sensitivity. Cell-based functional assays were used to investigate how \
+        MYC regulates TYMS transcription. Cancer patient data were used to verify the correlation between drug response and MYC and/or TYMS mRNA levels. \
+        Finally, the role of NIPBL inactivation in gastrointestinal cancer was evaluated in vitro and in vivo. \
+        Findings: TYMS is essential for maintaining the viability of gastrointestinal cancer cells, and is selectively inhibited by RTX. \
+        Mechanistically, MYC presets gastrointestinal cancer sensitivity to RTX through upregulating TYMS transcription, \
+        supported by TCGA data showing that complete response cases to TYMS inhibitors had significantly higher MYC and \
+        TYMS mRNA levels than those of progressive diseases. NIPBL inactivation decreases the therapeutic responses of \
+        gastrointestinal cancer to RTX through blocking MYC. Interpretation: Our study unveils a mechanism of how TYMS is \
+        transcriptionally regulated by MYC, and provides rationales for the precise use of TYMS inhibitors in the clinic.'},
+        {'role':'assistant', 'content':'Gastrointestinal cancer with up-regulated MYC is dependent on TYMS.'},
+        {'role':'user', 'content':'Abstract: Studies have characterized the immune escape landscape across primary tumors. \
+        However, whether late-stage metastatic tumors present differences in genetic immune escape (GIE) prevalence and dynamics remains unclear. \
+        We performed a pan-cancer characterization of GIE prevalence across six immune escape pathways in 6,319 uniformly processed tumor samples. \
+        To address the complexity of the HLA-I locus in the germline and in tumors, we developed LILAC, an open-source integrative framework. \
+        One in four tumors harbors GIE alterations, with high mechanistic and frequency variability across cancer types. \
+        GIE prevalence is generally consistent between primary and metastatic tumors. We reveal that GIE alterations are selected for \
+        in tumor evolution and focal loss of heterozygosity of HLA-I tends to eliminate the HLA allele, presenting the largest neoepitope repertoire. \
+        Finally, high mutational burden tumors showed a tendency toward focal loss of heterozygosity of HLA-I as the immune evasion mechanism, \
+        whereas, in hypermutated tumors, other immune evasion strategies prevail.'},
+        {'role':'assistant', 'content':'No dependency'}
     ]
     messages.append({'role':'user', 'content':f"Abstract: {text}"})
     response = get_completion_from_messages(messages, temperature=0)
@@ -81,4 +88,4 @@ def gradio():
 
 
 if __name__ == '__main__':
-    gradio()
+    gradio()